WO2025118121A1

WO2025118121A1 - Methods and apparatuses for power management

Info

Publication number: WO2025118121A1
Application number: PCT/CN2023/136269
Authority: WO
Inventors: Fan Zhang; Qi Zhang; Huaisong Zhu; Haoyu LI; Jun Liang; Changqing YUAN
Original assignee: Telefonaktiebolaget LM Ericsson AB
Current assignee: Telefonaktiebolaget LM Ericsson AB
Priority date: 2023-12-04
Filing date: 2023-12-04
Publication date: 2025-06-12
Anticipated expiration: 2026-06-04
Also published as: WO2025118121A9

Abstract

Methods and apparatuses for power management are provided. According to an embodiment, data of at least one power consumption factor of a device is obtained. The at least one power consumption factor at least comprises an activation status of one or more energy saving functions of the device. Then, an estimated value of power consumption of the device is determined based on the data of the at least one power consumption factor and a power consumption calculator. The power consumption calculator is determined at least based on mapping information about an energy saving function and its corresponding atomic operations. In this way, an atomic operation-based power consumption calculation of an energy saving function can be achieved.

Description

METHODS AND APPARATUSES FOR POWER MANAGEMENT

FIELD

Embodiments of the represent disclosure relate to the field of telecommunication and in particular, to method, device, apparatus and computer readable storage medium for power management.

BACKGROUND

This section introduces aspects that may facilitate better understanding of the present disclosure. Accordingly, the statements of this section are to be read in this light and are not to be understood as admissions about what is in the prior art or what is not in the prior art.

In communication systems, a device such as a radio unit (RU) may consume power or energy to perform various functions. Currently, some procedures require the power consumption information of RU for different purpose, such as energy conservation, overtemperature handling, radio base station (RBS) system energy consumption estimation, or the like. There are several approaches to estimate the power consumption of various energy saving functions (also referred to as energy efficiency function) of RU. However, several issues associated with these approaches need to be considered.

SUMMARY

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, a method for power management is proposed. In the method, data of at least one power consumption factor of a device such as an RU is obtained. The at least one power consumption factor at least comprises an activation status of one or more energy saving functions of the device. Based on the at least one power consumption factor and a power consumption calculator, an estimated value of power consumption of the device is determined. The power consumption calculator is determined at least based on mapping information about an energy saving function and its corresponding atomic operations.

In a second aspect, an apparatus for power management is proposed. The apparatus includes a processor and a memory. The memory contains instructions executable by the processor whereby the apparatus is operative to perform a method in accordance with the first aspect of the present disclosure.

In a third aspect, a computer readable storage medium is provided. The computer readable storage medium comprises instructions, which, when executed on at least one processor, cause the at least one processor to carry out the method according to the first aspect of the present disclosure.

Other features of the present disclosure will become easily comprehensible through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

These and other objects, features and advantages of the disclosure will become apparent from the following detailed description of illustrative embodiments thereof, which are to be read in connection with the accompanying drawings.

FIG. 1 shows an environment in which embodiments of the disclosure can be implemented;

FIG. 2A and FIG. 2B illustrate PRB utilization and slot utilization, respectively;

FIG. 2C illustrates a 2-dimention (2D) description of power consumption;

FIG. 2D illustrates an example activation status of an energy saving function;

FIG. 3 illustrates a flowchart of a method for power management in accordance with an embodiment of the present disclosure;

FIG. 4A illustrates changes in the ranking of energy efficiency (EE) functions with dynamic factors in accordance with some embodiments of the present disclosure;

FIG. 4B illustrates a schematic diagram of RU hardware (HW) atomic operation in accordance with some embodiments of the present disclosure;

FIG. 4C illustrates an atomic operation of EE function mapping in accordance with some embodiments of the present disclosure;

FIG. 4D illustrates an example atomic operation-based power consumption calculator in accordance with some embodiments of the present disclosure;

FIG. 4E illustrates a relative error between atomic operation-based solution and value read by software (SW) ;

FIG. 5 illustrates an example machine learning (ML) model;

FIG. 6 illustrates a flowchart of a method for determining an estimated value of power consumption of a device in accordance with some embodiments of the present disclosure;

FIG. 7 illustrates a flowchart of a method for power consumption calculator updating in accordance with some embodiments of the present disclosure;

FIG. 8A illustrates a process for data collection, offline training and lab verification in accordance with some embodiments of the present disclosure;

FIG. 8B illustrates a 3D description of power consumption in accordance with some embodiments of the present disclosure;

FIG. 9A illustrates a schematic diagram for power consumption calculator calibration in accordance with some embodiments of the present disclosure;

FIG. 9B illustrates a schematic diagram of power consumption calculator online calibration inside RU in accordance with some embodiments of the present disclosure;

FIG. 9C illustrates a schematic diagram of power consumption calculator online calibration in digital unit (DU) in accordance with some embodiments of the present disclosure;

FIG. 9D illustrates a schematic diagram of online calibration and model running in a DU in accordance with some embodiments of the present disclosure;

FIG. 9E illustrates a flowchart of an online calibration process in accordance with some embodiments of the present disclosure;

FIG. 10 illustrates a signaling chart for communications in accordance with some embodiments of the present disclosure;

FIG. 11 illustrates a block diagram showing an apparatus suitable for use in practicing some embodiments of the present disclosure;

FIG. 12 illustrates a block diagram showing a terminal device suitable for use in practicing some embodiments of the present disclosure;

FIG. 13 illustrates an example of a communication system in accordance with some embodiments of the present disclosure;

FIG. 14 illustrates a block diagram of a host in accordance with some embodiments of the present disclosure; and

FIG. 15 illustrates a communication diagram of a host communicating via a network node with a user equipment (UE) over a partially wireless connection in accordance with some embodiments.

Throughout the drawings, the same or similar reference numerals represent the same or similar element.

DETAILED DESCRIPTION

For the purpose of explanation, details are set forth in the following description in order to provide a thorough understanding of the embodiments disclosed. It is apparent, however, to those skilled in the art that the embodiments may be implemented without these specific details or with an equivalent arrangement.

Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and/or is implied from the context in which it is used. All references to a/an/the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and/or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

Reference throughout this specification to features, advantages, or similar language does not imply that all of the features and advantages that may be realized with the present disclosure should be or are in any single embodiment of the disclosure. Rather, language referring to the features and advantages is understood to mean that a specific feature, advantage, or characteristic described in connection with an embodiment is included in at least one embodiment of the present disclosure. Furthermore, the described features, advantages, and characteristics of the disclosure may be combined in any suitable manner in one or more embodiments. One skilled in the relevant art will recognize that the disclosure may be practiced without one or more of the specific features or advantages of a particular embodiment. In other instances, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments of the disclosure.

As used herein, the terms “first” , “second” and so forth refer to different elements. The singular forms “a” and “an” are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms “comprises” , “comprising” , “has” , “having” , “includes” and/or “including” as used herein, specify the presence of stated features, elements, and/or components and the like, but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof. The term “based on” is to be read as “based at least in part on” . The term “one embodiment” and “an embodiment” are to be read as “at least one embodiment” . The term “another embodiment” is to be read as “at least one other embodiment” . Other definitions, explicit and implicit, may be included below. The term “one or more elements” used is to be read as “only one element” or “a plurality of elements” . The term “at least element” used is to be read as “only one element” or “more than one element” .

As used herein, the term “terminal device” / “communication device” may be any device intended for accessing services via an access network and configured to communicate over the access network. For instance, the terminal device/communication device may be, but is not limited to: mobile phone, smart phone, sensor device, meter, vehicle, household appliance, medical appliance, media player, camera, or any type of consumer electronic, for instance, but not limited to, television, radio, lighting arrangement, tablet computer, laptop, or PC. The terminal device/communication device may be a portable, pocket storable, hand-held, computer-comprised, or vehicle-mounted mobile device, enabled to communicate voice and/or data, via a wireless or wireline connection. The term “terminal device” may be referred to as a mobile station (MT) . Alternatively, the term “terminal device” may be referred to as a user equipment (UE) . The terms “terminal device” and “UE” can be used interchangeably hereinafter.

The term “network device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP) , for example, a node B (NodeB or NB) , an evolved NodeB (eNodeB or eNB) , an NR NB (also referred to as a gNB) , a Remote Radio Unit (RRU) , a radio header (RH) , a remote radio head (RRH) , a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology.

FIG. 1 illustrates an environment 100 in which embodiments of the disclosure can be implemented. As shown in FIG. 1, the environment 100 such as a communication environment includes a device 110 such as an RU or a network device. The environment 100 further includes a further device 120 such as a DU, a computing device or a further network element (NE) . In some embodiments, the device 110 and the device 120 may communicate with each other. Alternatively, in some embodiments, the device 120 may be deployed at the device 110. For example, the device 120 may be deployed as a component in the device 110.

In some embodiments, the device 120 may perform a power management for the device 110. For example, the device 110 may report information regarding power consumption under different statuses to the device 120. The device 120 may estimate the power consumption of the device 110 and report the estimated power consumption to the device 110. Detailes regarding the power consumption estimation will be described with respect to FIG. 3.

It can be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication system 100 may include any suitable number of devices configured to implementing embodiments of the present disclosure. Although not shown, it would be appreciated that one or more additional terminal devices may be located in the environment 100 and communicate with the device 110.

Communications in the environment 100 may be implemented according to any proper communication protocol (s) , comprising, but not limited to, cellular communication protocols of the first generation (1G) , the second generation (2G) , the third generation (3G) , the fourth generation (4G) , the fifth generation (5G) , the sixth generation (6G) , and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and/or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA) , Frequency Division Multiple Access (FDMA) , Time Division Multiple Access (TDMA) , Frequency Division Duplex (FDD) , Time Division Duplex (TDD) , Multiple-Input Multiple-Output (MIMO) , Orthogonal Frequency Division Multiple (OFDM) , Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and/or any other technologies currently known or to be developed in the future.

As mentioned, some procedures require the power consumption information of RU for different purpose, such as energy conservation, overtemperature handling, RBS system energy consumption estimation, and the like. In some approaches, there is nothing more than power consumption estimation for different physical resource block (PRB) load when these functions take effect, but they are totally 2-D concept (e.g., PRB load as X-axis, power consumption as Y-axis) .

In fact, several issues exist for such approaches. Due to only considering the utilization rate of PRB, it is difficult to reflect accurate power consumption and the test effort will be extremely large with the need to support many configurations and Radio hardware platforms for instance. In addition, when the RBS system considers multi-dimensional (multi-D) energy-saving, these existing approaches cannot be well extended and hard to describe the comprehensive energy consumption of EE function combination, because there may inevitably be conflicts between those functions. As used herein, the term “multi-D” energy saving may refer to different energy saving functions from time domain, frequency domain, amplitude domain, spatial domain, and/or the like. Furthermore, the impact of real-time state changes during the use of RU on power consumption estimation or calculation which are just static tables are not considered. Therefore, the estimated values of these approaches are currently only used for laboratory comparisons or related studies.

Conventional approaches have some disadvantages, including but not limited to huge test workload, poor scalability and accuracy, inability to support multi-D energy saving orchestration, and the complete lack of consideration of real-time status changes of RU on the real site.

Some approaches may lead to limitation of legacy energy saving function for fixed threshold. For current energy efficiency strategy, DU does not know exactly power consumption of RU under various configurations and scenarios on customer site. Therefore, in legacy approaches, experienced fixed PRB loads are often used as the thresholds (i.e., trigger condition) for energy efficiency functions (EE function will be used below) . So how to deal with it when the thresholds of two or more EE functions are met simultaneously.

Some conventional approaches use 2D description for power consumption calculation. This is not enough because resource block (RB) is a time-frequency resource block. PRB utilization just a single dimensional information, and slot utilization in time domain is another important aspect. FIG. 2A illustrates an example diagram 210 of PRB utilization and slot utilization. FIG. 2B illustrates another example diagram 220 of PRB utilization and slot utilization. In some conventional approaches, based on the PRB utilization and slot utilization, a 2D description 230 of power consumption may be obtained, as shown in FIG. 2C. However, such conventional approaches cannot obtain the energy consumption of RU from a 3D perspective, which will be more accurate.

Several conventional approaches may lead to limitation of EE functions orchestration from multi-dimension. For a single key performance indicator (KPI) , a single EE function issue will occur. For RU multi-D EE orchestration purpose, it is now becoming increasingly important as more and more EE functions introduced in RBS system. Sometime, those functions are definitely conflict (e.g., frequency domain vs. time domain, time domain vs. spatial domain) . That is to say, multi-D orchestration will replace the work of a single EE function in the near feature to capture more EE gain. So, when introducing multi-D EE orchestration, the decisions between various functions will become more complex. There may be an approach for EE decision maker. Knowing the energy consumption of each EE function (single-D) and EE functions combination (multi-D) in different scenarios is a good candidate. Unfortunately, there is no good power consumption calculation approach for multi-D EE orchestration purpose from RAN perspective now.

Several conventional approaches also lead to imitation of dynamic factors. In addition to the above limitations, if only static power consumption table for relevant EE functions is provided, it still cannot truly reflect the real situation of live network. Therefore, it is impossible to get the accurate power consumption for any of them, because dynamic changes contribute the energy consumption a lot are not considered. Furthermore, according to the running status of different sites, the convenient database updating process also needs to be considered, so it must be a future prepared solution, otherwise it will bring great costs in the future.

Some conventional approaches use lab test to measure or record power consumption of all possible configuration for each EE function. For example, in lab, all configuration combinations are tested. The tested results such as recorded power consumption values of various configurations are published and stored in a database. The RU may subscribe the stored power consumption values. However, the testing volume is large and not suitable for expansion. FIG. 2D illustrates an example activation status 200 of an energy saving function. In the illustrated activation status, half power amplifier (PA) and half transceiver (TRX) integrated circuit (IC) are turned off. The power consumption under such activation status is measured and recorded.

In some conventional approaches, the power consumption under each PRB load of this EE function is generally calculated based on the second layer. Obviously, this does not have good scalability. When a new EE function needs to turn off a different number of PA channels such as 48 PA channels, it needs to be retested and updated. In other words, a great number of lab tests are needed to measure or record power consumption under various activation statuses of the device.

To solve the above and other potential issues, embodiments of the present disclosure propose a mechanism for power management. In the mechanism, data of at least one power factor of a device such as an RU is obtained. For example, the at least one power consumption factor comprises an activation status of one or more energy saving functions of the device. As used herein, the term “energy saving function” may also be referred to as an “EE function” . A value of power consumption of the device is estimated based on the data of the at least one power consumption factor and a power consumption calculator. For example, the power consumption calculator is determined based on mapping information about an energy saving function and its corresponding atomic operations. The determined power consumption calculator determines the estimated value of power consumption of the device based on the data of the at least one power consumption factor.

With the proposed mechanism, an activation status of energy saving function (s) are considered in estimating the power consumption of the device. In addition, the calculator for estimating the power consumption is determined based on mapping information about the energy saving function and corresponding atomic operations. That is, the power consumption estimation is based on atomic operations. In this way, the power consumption of the device with energy saving functions in different activation status can be estimated accurately. For example, the energy saving functions may be from various domains such as time domain, frequency domain, amplitude domain and spatial domain. Thus, multi-dimension description of power consumption can be obtained.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

POWER CONSUMPTION ESTIMATION

FIG. 3 illustrates a flowchart of a method 300 for power management in accordance with an embodiment of the present disclosure. For the purpose of discussion, the method 300 will be described from the perspective of the device 120 in FIG. 1.

At block 310, data of at least one power consumption factor of a device such as the device 110 is obtained. For example, the device 120 obtains the data of the at least one power consumption factor. The at least one power consumption factor at least includes an activation status of one or more energy saving functions of the device 110.

In some embodiments, the activation status may indicate one or more atomic operations corresponding to at least a part of hardware of the at least one energy saving function which to be activated. In an example, the activation status may include an activation status of one of the at least one energy saving function in time domain. In another example, the activation status may include an activation status of one of the at least one energy saving function in frequency domain. In a further example, the activation status may include an activation status of the at least one energy saving function in amplitude domain. In a still further example, the activation status may include an activation status of the at least one energy saving function in spatial domain.

It is to be understood that these activation statuses can be used in any suitable combination. Any other suitable activation status can be applied. Scope of the present disclosure is not limited herein. By applying various kinds of activation statuses, multi-dimension description of power consumption of the device can be further determined.

In some embodiments, if a dynamic change associated with the device 110 occurs, the activation status of the energy saving function may change. For example, working status change may occur at any time, for instance PA failure, TRX branch failure, voltage standing wave ratio (VSWR) , etc. Such working status change may lead to activation status change. In some embodiments, the board temperature dynamically fluctuated up and down under different traffic loads and changes in ambient temperature. Such temperature change may lead to a changed activation status. In some embodiments, exactly the same HW platform but produced or calibrated are shared in different batches. In some embodiments, reliability requirement changes due to repeated power cycle, aging and other problems, which will lead to a changed activation status. In addition, new common software version upgrade or customized software function upgrade may lead to a changed activation status. Several embodiments of the activation status changing have been described without any limitation. The activation status may change in any suitable condition. Scope of the present disclosure is not limited here.

FIG. 4A illustrates changes in the ranking of EE functions with dynamic factors in accordance with some embodiments of the present disclosure. As illustrated, for a 64 TRX radio, in a first activation status 410, the ambient temperature is 25 ℃. In a second activation status 415, the ambient temperature is 40 ℃, with two PA failure and PRB load changes. The power consumption of different EE functions may be different for these two activation statuses 410 and 415. In some embodiments, the activation status of energy saving function (s) of the device 110 may indicate any suitable dynamic factors or information in the corresponding status. These dynamic factors may affect the power consumption calculation of each EE function, which may impact the scheduling of these EE functions or EE function combinations from DU perspective. While ensuring network KPI, the RBS system may invoke the most energy-efficient function or functions combination (it is called EE strategy) , and “energy-efficient” here means saving more power.

In some embodiments, the device 110 may report the activation status of the one or more energy functions of the device 110 to the device 120. In addition, in some embodiments, the at least one power consumption factor may include further information. That is, the device 110 may report further information to the device 120.

In an example, the at least one power consumption factor may further include radio hardware information. For example, the radio hardware information may include at least one of: a type of a radio hardware, a supported antenna number of a radio hardware, a supported bandwidth of a radio hardware, or a supported maximum transmit power of a radio hardware.

In another example, the at least one power consumption factor may further include a radio runtime configuration. The radio runtime configuration may include at least one of: the number of active carriers, an active carrier center frequency, an active carrier bandwidth, an active carrier max transmission power, a carrier Radio Access Technology (RAT) mode, an active downlink path number, or an active uplink path number.

In a further example, the at least one power consumption factor may further include an environment factor. The environment factor may include at least one of: a radio internal temperature, radio installation location information, or installation location climate information.

In a still further example, the at least one power consumption factor may further include a radio runtime status. For example, the radio runtime status may include at least one of: radio fault information, hardware failure information, or radio hardware component reliability limitation.

In a yet further example, the at least one power consumption factor may further include traffic information. By way of example, the traffic information may include at least one of: resource block utilization, or time slot utilization.

Several example power consumption factors have been described. It is to be understood that these example factors are only for the purpose of illustration, without suggesting any limitation. Any suitable power consumption factor may be obtained. Scope of the present disclosure is not limited here.

Still refers to FIG. 3, at block 320, an estimated value of power consumption of the device 110 is determined based on the data of the at least one power consumption factor and a power consumption calculator. The power consumption calculator is determined at least based on mapping information about an energy saving function and its corresponding atomic operations. In some embodiments, the power consumption calculator may be deployed at the device 120. Alternatively, in some embodiments, the power consumption calculator may be deployed at an RU, a DU, or a further NE. For example, the power consumption calculator may be deployed at the device 110.

As used herein, the term “atomic operation” may refer to operation (s) on all hardware of a device or an RU, which may not be subdivided again. The energy consumption or energy capacity corresponding to the atomic operation may be referred to as a “unit energy consumption” of the operation. In some embodiments, the unit of energy consumption may use the unit of “watt” , or any other suitable unit. As used herein, the power consumption calculator determined based on the mapping information may be referred to as “an atomic operation-based power consumption calculator” .

By way of example, the device 120 may determine the power consumption calculator. The device 120 may apply the power consumption calculator to determine the estimated value of power consumption of the device 110 based on the data of the at least one power consumption factor.

In some embodiments, the power saving capability (/power consumption) of EE function are two essentially identical concepts. Which one to use in the system is actually defined on demand. If the power saving capability is needed, then compared to the “power consumption” , there will be an additional step of calculation, which is to subtract the power consumption of the EE function from the power consumption when no energy-saving function is used at this time. This delta is called the power-saving ability of the EE function. That is, the power saving capability may be determined based on the estimated power consumption value.

In the following description, embodiments regarding the power consumption estimation of the energy function will be described. It is to be understood that the power saving capability may also be determined in a similar way. As used herein, the term “power calculator” may refer to a “power consumption calculator” or a “power saving capability calculator (also referred to as power saving calculator” . Embodiments described with respect to the power consumption calculator may be applied to the power saving capability calculator in a similar way.

As mentioned, the power consumption calculator is determined based on mapping information about an energy saving function and its corresponding atomic operations. In some embodiments, hardware operations (for example, all hardware operations) on the device 110 such as an RU may be split into different kinds of atomic operations. The power consumption of each atomic operation may be tested. which is called the unit energy consumption of atomic operation (s) . Then the hardware operations corresponding to each EE function will be combined by these atomic operations. Thus, the power consumption of EE function can be obtained as well.

ATOMIC OPERATION MAPPING

In some embodiments, the device 110 may consist of many device components, including but not limited to an analog front end (AFE) (such as PA, pre-driver and PA control circuit (PACC) , etc. ) , TRXIC, digital front end (DFE) (such as crest factor reduction (CFR) , digital pre-distortion (DPD) , etc. ) , layer one (L1) beam forming (BF) and central processing unit (CPU) . Table 1 shows several hardware operations associated with different device components.

Table 1

It is to be understood that these example operations in Table 1 are only for the purpose of illustration. The device 110 may perform any other suitable operations. These hardware operations associated with device components may be divided into different atomic operations as needed. The power consumptions of atomic operations may be measured before being combined by upper-level functional modules.

FIG. 4B illustrates a schematic diagram 420 of RU hardware (HW) atomic operation in accordance with some embodiments of the present disclosure. In the description of FIG. 4B, 64 TRX is taken as an example. As illustrated, the lowest layer of FIG. 4B is called “atomic operation” . Please be aware that if TRXIC has more energy-saving methods, then this operation can still be further subdivided. For example, disabling transmitting (TX) channel or receiving (TX) channel separately etc.

By dividing the hardware operation into atomic operations, due to the good linear relationship, the energy consumption of a new function with 48 PA turned-off may be obtained by multiplying the energy consumption of the operation by 48. It is completely the same as another new EE function needs to turn off 16 PA, no more tests are needed.

FIG. 4C illustrates an atomic operation of EE function mapping in accordance with some embodiments of the present disclosure. As shown, taking a 64 TRX radio as an example, there is an EE function 432 that needs to simultaneously shut down 32 PAs. The EE function 434 needs to simultaneously shut down 16 PAs and 2 TRXIC. The EE function 436 needs to shut down 32 PAs and 1 PA VDD adjustment (-2V) . These EE functions 432, 434 and 436 may be split into atomic operations such as an one PA VDD (-0.1V) operation, an one PA turned-off operation, an one TRXIC turned-off operation. In such cases, the power consumption of these EE functions 432, 434 and 436 may be determined as:
P_total= (N·P_i +Δ1) + (M·P_j +Δ2) +… (1)

where P_total denotes the current power consumption of the device 110, P_i and P_j respectively denote power consumption of each atomic operation, N and M denote the number of each atomic operation, Δ1 and Δ2 (optional) denotes the bias introduced when combining atomic operations.

In some embodiments, the power consumption calculator may be trained by applying, to a machine learning (ML) model, reference power consumption factors and the mapping information as inputs and reference values of power consumption as an output. That is, the power consumption calculator may be a machine learning model trained based on reference power consumption factors, the mapping information and reference power consumption values. For example, with the power consumption of each EE function obtained by “atomic operation” , ML algorithm may be used for final compensation and fitting.

FIG. 4D illustrates an example atomic operation-based power consumption calculator 440 in accordance with some embodiments of the present disclosure. As illustrated, the calculator 440 is trained with ML assistance based on inputs (for example, reference power consumption factors) and output (for example, reference power consumption values) . In some embodiments, the calculator 440 may be implemented at the device 120. Alternatively, the calculator 440 may be a separate application in a further device communicatively connected with the device 120. For example, the calculator may be an application in an operation, administration and maintenance (OAM) or even a third-party platform (such as service management and orchestration (SMO) of operator) . In the following description, some embodiments will be described with the calculator being implemented at the device 120. The calculator 440 may predict (or infer) real-time power consumption for different configuration, environment, and reliability.

The calculator 440 may do offline training in live network. The installed RUs such as gNB may report their experiences to train the calculator 440. Experiences from installed RUs may be continuously collected. For example, previously measured power consumption, which is normally reported with a relatively large second level or even longer delay may be collected. For another example, power consumption related factors including but not limited to radio configuration, environment factors, reliability information and the like may be collected. The calculator 440 may be trained based on the collected information. In other words, the calculator 440 may use these “old but realistic” experiences to train itself. The mapping relation between power consumption and related factors may be determined.

In some embodiments, once the device 110 such as the gNB needs real-time power consumption estimation, the device 110 may inquire the calculator 440 about power consumption value with input parameters of related factors. The calculator 440 may use the factors to give the device 110 the real-time and accurate estimation of power consumption value.

With the trained calculator 440, atomic operations may be considered in estimating of the power consumption. Such machine learning based calculator 440 is easy combined and better expanded, and may handle various dynamic factors for power consumption of the device 110. The estimated power consumption value by the calculator 440 can be well used by DU or baseband (BB) to make the optimal decision for energy efficiency purpose.

FIG. 4E illustrates a diagram 460 of a relative error between atomic operation-based solution and value read by software (SW) . As illustrated, most of the calculated power consumption errors of the estimated power consumption values determined by the calculator are less than 2%for varies actual power consumption levels. Considering there are measurement errors in the power meter, the power consumption calculator can provide an accurate result based on the atomic operations.

ML BASED POWER CONSUMPTION CALCULATOR

Several embodiments regarding machine learning based power consumption calculator have been described. FIG. 5 illustrates an example ML model 500 such as a neural network (NN) model. The power consumption calculator such as the calculator 440 may be offline trained based on the ML model 500. Using the NN technology, varies factors (such as cell configuration &hardware information of the device 110, etc. ) are selected as input for the model 500. The output of the model 500 is power consumption of the device 110 at the input indicated conditions.

As illustrated, the model 500 may include varies hidden layers. For an input layer (for features selection) of the model 500, input of the input layer may include the following:

● Radio HW information:

Indicate the Radio HW types:

● AAS, Remote, Indoor or mmWave,

● Supported Antenna Num,

● Supported Bandwidth,

● Supported max performance.

● Radio Runtime Configurations

Indicate the Radio runtime configurations:

● Active Carrier Numbers,

● Active Carrier Center Frequency,

● Active Carrier bandwidth,

● Active Carrier Max Transmission Power,

● Carrier Transmission Mode,

● Active downlink/uplink path number.

● Environment Factors

Radio Deployment information:

● Radio internal temperatures (varies location temperature inside radio) .

● Radio Installation location information (latitude and longitude information) .

● Installation location climate information (temperature, wind speed & humidity information) .

● Radio Runtime Status

Radio fault information.

Radio HW component reliability limitation.

● Traffic Information

Downlink PRB utilization in one unit time.

Downlink slot utilization in one unit time.

● EE Function Operations (Including Atomic Operation Mapping)

Time domain EE function activate status.

Frequency domain EE function activate status.

Amplitude domain EE function activate status.

Space domain EE function activate status.

Varies hidden layers of the model 500 are decided by performance and training cost. For an output layer of the model 500, power consumption of the radio at the input conditions are involved.

It is to be understood that the model 500 is only for the purpose of illustration, without suggesting any limitation. Any suitable model with any suitable structure or layers may be applied. These example inputs to the model 500 are only for the purpose of illustration. More or less inputs may be inputted to the model 500. Scope of the present disclosure is not limited in this regard.

In some embodiments, to determine the estimated value of power consumption of the device 110, the data of the at least one power consumption factor may be processed. FIG. 6 illustrates a flowchart of a method 600 for determining the estimated value of power consumption of the device 110 in accordance with some embodiments of the present disclosure. The method 600 may be an example implementation of the block 320 in the method 300. For the purpose of discussion, the method 600 will be described from the perspective of the device 120 in FIG. 1.

At block 610, the device 120 may process the data of the at least one power consumption factor by performing at least one of data cleaning or data formation. For example, the data of the at least one power consumption factor may be collected from the device 110. The collected data may be cleaned or formatted. In this way, noisy data can be removed.

In some embodiments, secondly measurements from an end-to-end lab environment with one specific advanced antenna system (AAS) RU type may be collected. The gathered information may include features that may be divided into several categories as follows.

■ Radio hardware and configuration runtime information: Information on radio hardware details and radio configuration statuses, such as antenna branch numbers, maximum supported carriers, activated carriers and carrier types.

■ Environment Factors: Radio Installation location information and internal temperature sensors.

■ Traffic statistics: Information on the traffic, such as PRB utilizations, time slot utilizations.

■ EE Function Operations (Including Atomic Operation Mapping) : Information on the activated power saving function combinations from all different domains, such as MIMO branch mute, carrier sleep and symbol based power save function.

■ Power consumption statistics: information on the power consumed by radio.

At block 620, the device 120 may apply the processed data to the power consumption calculator such as the calculator 440 to obtain the estimated value of power consumption. The power consumption calculator may be offline trained.

In some embodiments, the available dataset from data collection procedure may be divided into two parts: a training dataset and a testing dataset. For example, the training dataset may include 80%or other percentage of total which has pre-randomization, the testing dataset may include the rest of total dataset. The power consumption calculator may be trained by adopting the Adam version of the stochastic gradient descent algorithm or any other suitable algorithm.

In some embodiments, an offline training criteria selection may depend on the detail ML model selection and the target result. For example, regression may usually select the MAE &MSE, etc. Binary classification may usually select the Binary Cross-Entropy, etc. Multi-class classification may select multi-class cross-entropy, etc. The offline trained power consumption calculator may determine the estimated power consumption value based on the processed data.

By using the trained ML based power consumption model, efficiency, accuracy and better scalability (supporting more configurations and hardware platforms) of the power consumption estimation can be achieved. Such power consumption estimation has unique advantage than conventional approaches, since radio knows best about poet consumption for different snapshot and BB is good at in-phase and quadrature (I&Q) scheduling and KPI assurance.

In addition, on the premise of ensuring the accuracy of calculating hardware power consumption, splitting of atomic operations in RU HW according to each EE function can makes subsequent maintenance easier even new EE function introduced just with different combinations, which will greatly reduce update costs.

Furthermore, with the online trained power calculator, DU/BB can get an estimation of power consumption directly. This true and real time estimation contributes a lot to generate an optimal energy saving command. Of course, the premise of power saving is to ensure network KPI.

Real time situation may change the ranking of power consumption of different EE functions, such as HW fault, temperature, reliability requirement and so on. This will inevitably change the selection of EE function or EE functions combination on the peer end.

Compared with conventional approaches, the present solution can well cover the complex and dynamic field environment and diverse configurations, and truly reflect dynamicity of threshold for each EE function on realistic network. This greatly reduces misjudgment of decision maker and makes poor energy-saving strategy.

POWER CONSUMPTION CALCULATOR CALIBRATION

Several embodiments regarding the atomic operation-based power consumption estimation have been described. In some embodiments, the power consumption calculator may be calibrated. FIG. 7 illustrates a flowchart of another method 700 for power consumption calculator updating in accordance with some embodiments of the present disclosure. For the purpose of discussion, the method 700 will be described from the perspective of the device 120 in FIG. 1.

At block 710, the device 120 may obtain further data of the at least one power consumption factor of the device 110. As discussed, in some embodiments, the available dataset from data collection procedure may be divided into the training dataset and the testing dataset. The further data of the at least one power consumption factor may be from the testing dataset. Alternatively, in some embodiments, the further data of the at least one power consumption factor may be from another data collection from the lab environment.

At block 720, the device 120 may process the further data by performing data cleaning. Alternatively, or in addition, in some embodiments, the device 120 may process the further data by performing data formation.

At block 730, the device 120 may obtain an updated power consumption calculator by applying the processed further data to a calculator calibrator. As used herein, the term “calculator calibrator” may also be referred to as a “calculator calibration module” , “power consumption calculator calibrator” , “power consumption calculator calibration module” . For an ML-based power consumption calculator, the term “calculator calibrator” may also be referred to as a “model calibrator” or “model calibration module” . The calculator calibrator may be deployed at an RU, a DU or a network element. In some embodiments, the calculator calibrator may be deployed at the device 110 or the device 120. Further embodiments of the calculator calibration will be described with respect to FIG. 9A to FIG. 9E.

At block 740, the device 120 may determine whether the updated power consumption calculator meets a deploying criterion. For example, a difference such as mean square error (MSE) between a predicted (or estimated) power consumption value of the updated power consumption calculator and the measurement data may be determined. If the error is less than or equal to a threshold error, the updated power consumption calculator meets the deployment criterion. It is to be understood that any suitable deployment criterion except for the threshold error may be applied. Scope of the present disclosure is not limited here.

If the device 120 determines that updated power consumption calculator meets the deploying criterion, at block 750, the device 120 may replace the power consumption calculator with the updated power consumption calculator. Otherwise, the device 120 may keep the power consumption calculator or proceed back to the block 710.

In this way, the power consumption calculator can be calibrated and updated. With the updated power consumption calculator, the power consumption estimation can be more accurate. With such online monitoring, measurement and updating, efficiency, accuracy and better scalability of the power consumption estimation can be ensured.

In some embodiments, the method 300, the method 600 and the method 700 can be combined. That is, data collection, offline training and calibration (also referred to as model lab verification) can be jointly applied.

FIG. 8A illustrates a process for data collection, offline training and model lab verification in accordance with some embodiments of the present disclosure. As shown in the diagram 810 in FIG. 8A, data is collected from different monitor function blocks with atomic operation mapping results. All the data may be labeled in a data collection/formation block. In the diagram 820 in FIG. 8A, based on the retrieved data, the machine learning algorithm is used to train the power consumption calculator (i.e., the model) . In the diagram 830, the calculator calibration or the model lab verification may be done with new collected data or the data not in the training set.

In the diagram 820 and 830, the surface represents full range power consumption of a certain EE function. In some embodiments, different EE functions may have different surfaces. As used herein, “full-range” means the PRB load from 0%to 100%, slot utilization from 0%to 100%. In some embodiments, since the device 110 such as the RU is not aware of the traffic model, the full power consumption (or the energy saving capability as needed) for use is provided by the peer end. The KPI assurance is secured by baseband or upper layer of DU.

With the power consumption calculator, different power consumption surfaces may be determined for different EE functions. With these surfaces, a 3D description of power consumption may be obtained. FIG. 8B illustrates a 3D description 840 of power consumption in accordance with some embodiments of the present disclosure. Compared with the 2D description 230 of power consumption as shown in FIG. 2C, the 3D description may be more accurate. When increasing in computational complexity, 3D description may be much more accurate than the 2D description. The fact also proves that on this, the calculation time only increased by 0.0028ms.

In some conventional approaches, little even no consideration was given to online calibration before, however, dynamic factors have a big impact on the energy consumption of various EE functions. As more and more EE functions are introduced in RBS system, the ranking of each function must be changed when one of these dynamic factors changes. For example, the power consumption calculator may calculate the power consumption under different conditions (traffic, EE functions, etc. ) based on the atomic operations. The power consumption may be impacted by traffic, PRB distribution, component usage, and the hardware operations etc. These factors may get in the lab or simulation. However, the actual environment factors, such as fault, HW working status and reliability status cannot be simulated in the lab. This information may only be retrieved from the live network running. With this information retrieved from the feedback loop, an online calibration process will be triggered to retrain the current running power consumption calculator model. Once the newly online trained model fits the preset criteria, this new model will be set to running state and provide the new power consumption calculator results with a high precision for this RU. With the newly trained model, RU power consumption calculator can have the recalibration function to provide more accurate output to suit the individual RU differences.

With the power consumption calculator calibration, the power consumption calculator may adapt to various dynamic factors and changing statuses. Embodiments of the power consumption calculator calibration will now be described with respect to FIG. 9A, which illustrates a schematic diagram 900 for power consumption calculator calibration.

As illustrated in FIG. 9A, an RU 901 may include an online data collection /formation module 902. The online data collection /formation module 902 may collect data of the at least one power consumption factor and report the collected data to the model calibration device 911 (also referred to as a calculator calibrator) . For example, the at least one power consumption factor may include but not limited to environment factors, RU temperature factors, HW operation monitoring, alarm monitoring, reliability monitoring, and atomic operation mapping. In some embodiments, the online data collection /formation module 902 may perform data cleaning and/or data formation before reporting the collected data to the model calibration device 911.

The model calibration device 911 may have a model calibration module 912, configured to perform the power consumption calculator (or power saving calculator) calibration. That is, the model calibration module 912 may determine whether the power consumption calculator model or the power saving calculator model meets a criterion. If the power consumption calculator model or the power saving calculator model meets the criteria, the consumption calculator model or the power saving calculator model may be deployed. For example, the power consumption calculator model or the power saving calculator model may be deployed at the RU 901.

In some embodiments, the RU 901 may include an atomic operation mapping module 903, configured to map the current EE function into atomic operations (HW operations cannot sub-divided) . The online calibration module 912 will use this output to label the data.

The RU 901 may include an environment factors monitoring module 904 configured to collect the RU location, time zone, humidity, climate, air pressure, fan information, air temperature, etc.

The RU 901 may include an RU temperature factors monitoring module 905 configured to collect the RU temperature internal sensors results. Including digital components and analog devices running status.

The RU 901 may include a hardware operation monitoring module 907 configured to collect the current HW operation states, including but not limited to HW power saving time, recovery time, operation frequency, operation counter, etc.

The RU 901 may include an alarm monitoring module 908 configured to collect the RU internal alarms and all external alarms.

The RU 901 may include a reliability monitoring module 909 configured to collect the RU reliability status. Include HW manufacture information, RU running ages, RU HW operation status (voltage, current) , etc.

The RU 901 may include a further monitoring module 906 configured to monitor all the other factors that can impact the radio power consumption, including traffic model info, actual RU power consumption info etc.

After monitoring the different factors from these modules, the online data collection/formation module 902 may retrieve all these data, then run the data clean &format. The output of the online data collection/formation module 902 is the same format as the input when the Power Consumption Calculator was initially trained.

The online data collection/formation module 902 may transmit the data to the model calibration module 912. The model calibration module 912 may perform the power consumption calculator (or power saving calculator) calibration. If the power consumption calculator model or the power saving calculator model meets the criteria, the consumption calculator model or the power saving calculator model may be deployed. For example, the power consumption calculator model or the power saving calculator model may be deployed at the RU 901.

FIG. 9B illustrates a schematic diagram 910 of power consumption calculator online calibration inside RU in accordance with some embodiments of the present disclosure. Similar to FIG. 9A, the RU 901 may include the online data collection /formation module 902, the atomic operation mapping module 903, the environment factors monitoring module 904, the RU temperature factors monitoring module 905, the hardware operation monitoring module 907, the alarm monitoring module 908, the reliability monitoring module 909 and the further monitoring module 906. These modules may be similar to those in FIG. 9A, and will not be repeated here.

In FIG. 9B, the RU monitored data are collected inside the RU 901. The RU monitored data are cleaned and formatted by the online data collection/formation module 902. The RU 901 in FIG. 9B may further include an online calibration module 915. The data may be transmitted to the online calibration module 915. The online calibration module 915 may execute the online calibration algorithm to generate new power calculator model. The RU 901 may use the new power calculator model to run the inference to generate new power consumption results. That is, the calculator model may be deployed at the RU 901. The RU 901 may transmit the power consumption result to a DU (not shown) .

FIG. 9C illustrates a schematic diagram 920 of power consumption calculator online calibration in a DU 921 in accordance with some embodiments of the present disclosure. Similar to FIG. 9A, the RU 901 may include the online data collection /formation module 902, the atomic operation mapping module 903, the environment factors monitoring module 904, the RU temperature factors monitoring module 905, the hardware operation monitoring module 907, the alarm monitoring module 908, the reliability monitoring module 909 and the further monitoring module 906. These modules may be similar to those in FIG. 9A, and will not be repeated here.

In FIG. 9C, the RU monitored data are collected inside the RU 901. The RU monitored data are cleaned and formatted by the online data collection/formation module 902. An online model calibration module 922 may be deployed at a DU 921 or a further network element (not shown) . For example, the online data collection /formation module 902 may transmit the collected/processed data to the online model calibration module 922 in the DU 921.

The online model calibration module 922 may execute the online calibration algorithm, then send the new power calculator model back to RU 901. The RU 901 may use the new power calculator model to run the inference.

FIG. 9D illustrates a schematic diagram 930 of online calibration and model running in DU in accordance with some embodiments of the present disclosure. Similar to FIG. 9A, the RU 901 may include the online data collection/formation module 902, the atomic operation mapping module 903, the environment factors monitoring module 904, the RU temperature factors monitoring module 905, the hardware operation monitoring module 907, the alarm monitoring module 908, the reliability monitoring module 909 and the further monitoring module 906. These modules may be similar to those in FIG. 9A, and will not be repeated here.

In FIG. 9D, the RU monitored data are collected inside the RU 901. The RU monitored data are cleaned and formatted by the online data collection/formation module 902. An online model calibration module 922 may be deployed at the DU 921 or a further network element (not shown) . For example, the online data collection /formation module 902 may transmit the collected/processed data to the online model calibration module 922 in the DU 921.

The online model calibration module 922 may execute the online calibration algorithm. The DU 921 may implement the new power calculator model. For example, the DU 921 may use the new power calculator model to run the interface. In some embodiments, the DU 921 may transmit the power consumption estimation result by the new power calculator model to the RU 901.

FIG. 9E illustrates a flowchart of an online calibration process 950 in accordance with some embodiments of the present disclosure. At block 960, the atomic operation mapping module 903, the environment factors monitoring module 904, the RU temperature factors monitoring module 905, the hardware operation monitoring module 907, the alarm monitoring module 908, the reliability monitoring module 909 and the further monitoring module 906 may monitor or measure data of the at least one power consumption factor. The online data collection/formation module 902 may collect and process the data of the at least one power consumption factor. In some embodiments, since the power calculation is a non-linear issue impacted by multiple factors, large number of the tests are needed to provide the non-linear characteristic. Automation tests may be used to provide such big data. That is, the above modules may use automation tests to collect data.

At block 970, a model calibration may be performed on the power consumption calculator based on the processed data of the at least one power consumption factor output by the online data collection/formation module 902. For example, the model calibration may be performed by the model calibration module 911 in the model calibration device 911, or the online model calibration module 915 deployed at the RU 901, or the online model calibration module 922 deployed at the DU 921, or a further model calibration module deployed at a further network element.

In some embodiments, at block 970, a model validation is performed on the power consumption calculator. For example, the collected data may be formatted into training dataset. A training algorithm same with that in the offline training phase may be used to determine an updated power consumption calculator. The updated power consumption calculator is the newly updated model trained with the new data collected by the online data collection/formation module 902. In addition, a difference such as MSE between the power consumption estimation and the measured power consumption may be determined.

In some embodiments, the power consumption calculator is an ML model such as NN model. Using ML can provide strong non-linear computing capabilities to support complicate calculations. In addition, ML are designed to process and analyze these complicated data. Finding out the hidden pattern and trend of these test data may further provide the accurate calculation methods. ML has the capability of inference. Not all the factors can be tested before deployment. ML may use it inference capability to provide the untested results. With ML, the power consumption calculator can support the online data retrieve and online calibration process.

At block 980, whether the updated power consumption calculator meets a criterion is determined. For example, if the difference is less than or equal to a threshold difference, the power consumption calculator meets the criterion. In some embodiments, the criteria selection may depend on the detail ML model selection and the target result. For regression, the MAE and/or MSE may be selected. For binary classification, the binary cross-entropy may be selected. For multi-class classification, multi-class cross-entropy may be selected. It is to be understood that any other criterion may be applied. Scope of the present disclosure is not limited here.

If the updated power consumption calculator meets the criterion, at block 990, the updated power consumption calculator may be deployed. That is, the updated power consumption calculator may replace the current running power consumption calculator. For example, the updated power consumption calculator may be deployed at the RU 901, the DU 921, or a further network element. With ML, it is easy to transfer the power consumption calculator between different RU HW platform based on tiny incremental data collection and training process. In some embodiments, the data of the at least one power consumption factor may be collected again at block 960. The updated power consumption calculator may be updated again, as well.

In some embodiments, if the updated power consumption calculator does not meet the criterion, the current running power consumption calculator may not be replaced. The process 950 from the block 960 will be repeated.

Several embodiments regarding calibration of the power consumption calculator have been described with respect to FIG. 9A to FIG. 9D. With the calculator calibration, various dynamic factors can be handled to estimate an accurate power consumption value. The present solution has unique advantage than legacy solution, since radio knows best about power consumption for different snapshot and BB is good at IQ scheduling and KPI assurance.

Furthermore, on the premise of ensuring the accuracy of calculating hardware power consumption, splitting of atomic operations in RU HW according to each EE function can makes subsequent maintenance easier even new EE function introduced just with different combinations, which will greatly reduce update costs.

In addition, when increasing in computational complexity is not significant, 3D description is much more accurate than 2D description. The fact also proves that on this, the calculation time only increased by 0.0028ms.

With the online trained power calculator, DU/BB can get an estimation of power consumption directly. This true and real time estimation contributes a lot to generate an optimal energy saving command. Of course, the premise of power saving is to ensure network KPI.

On top of that, real time situation may change the ranking of power consumption of different EE functions, such as HW fault, temperature, reliability requirement and so on. This will inevitably change the selection of EE function or EE functions combination on the peer end.

Compared with conventional approaches, the solution in the present disclosure can well cover the complex and dynamic field environment and diverse configurations, and truly reflect dynamicity of threshold for each EE function on realistic network. This greatly reduces misjudgment of decision maker and makes poor energy-saving strategy.

FIG. 10 illustrates a signaling chart 1000 for communications in accordance with some embodiments of the present disclosure. The signaling chart 1000 involves a dynamic factor monitor 1010 (also referred to as a dynamic factor monitoring module) , a data collection/formation module 1020 and a model training and calibration module 1030. For example, the dynamic factor monitor 1010 may include at least one of: the atomic operation mapping module 903, the environment factors monitoring module 904, the RU temperature factors monitoring module 905, the hardware operation monitoring module 907, the alarm monitoring module 908, the reliability monitoring module 909 and the further monitoring module 906 in the RU 901. The data collection/formation module may be the online data collection /formation module 902 in the RU 901. The model training and calibration 1030 may be performed by the model calibration module 911 in the model calibration device 911, or the online model calibration module 915 deployed at the RU 901, or the online model calibration module 922 deployed at the DU 921, or a further model calibration module deployed at a further network element.

As illustrated, a loop 1040 may be repeated. In the loop, the dynamic factor monitor 1010 may collect data or information. The dynamic factor monitor may transmit (1042) the collected data or information to the data collection/formation module 1020. The data collection/formation module 1020 may receive (1044) the data or information. In some embodiments, the data collection/formation module 1020 may perform (1046) data cleaning and data formatting to the received data. The data collection/formation module 1020 may transmit (1048) the processed data to the model training and calibration module 1030. The data training and calibration module 1030 may receive (1050) the processed data. The online calibration may thus be triggered. The model training and calibration module 1030 may perform (1052) the ML training and calibration process based on the received data.

In some embodiments, the model training and calibration module 1030 may determine (1054) whether the new trained and calibrated power consumption calculator (also referred to as the new trained and calibrated model) meet a criterion. If the new trained and calibrated model meets the criterion, the new trained and calibrated model may be deployed to network.

The loop 1040 may be repeated for a number of times, or for a predetermined time duration, or repeated all the time. With the loop 1040, the power consumption calculator may be updated on the fly. In this way, the power consumption estimation can be improved.

It would be appreciated that some example specifications and embodiments are provided above, and the detailed description may be varied. It would be also appreciated that the example parameters, example factors and example criteria in some embodiments are only for the purpose of illustration, without suggesting any limitation. These parameters, factors and criteria may be varied.

FIG. 11 is a block diagram showing an apparatus 1100 suitable for use in practicing some embodiments of the disclosure. For example, any one of the devices described above, including the device 110 and the device 120 in FIG. 1, may be implemented through the apparatus 1100. As shown, the apparatus 1100 may include a processor 1110, a memory 1120 that stores a program, and optionally a communication interface 1130 for communicating data with other external devices through wired and/or wireless communication.

The program includes program instructions that, when executed by the processor 1110, enable the apparatus 1100 to operate in accordance with the embodiments of the present disclosure, as discussed above. That is, the embodiments of the present disclosure may be implemented at least in part by computer software executable by the processor 1110, or by hardware, or by a combination of software and hardware.

The memory 1120 may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as semiconductor-based memory devices, flash memories, magnetic memory devices and systems, optical memory devices and systems, fixed memories and removable memories. The processor 1110 may be of any type suitable to the local technical environment, and may include one or more of general-purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multi-core processor architectures, as non-limiting examples.

FIG. 12 shows a block diagram showing an apparatus 1200 suitable for use in practicing some embodiments of the present disclosure. For example, the apparatus 1200 may be the device 110 shown in FIG. 1. As shown in FIG. 12, the apparatus 1200 may include a transceiver module 1210 and a processing module 1220. The transceiver module 1210 and the processing module 1220 may be configured to perform the method described with reference to any of FIGS. 3 and 6-7.

FIG. 13 shows an example of a communication system 3100 in accordance with some embodiments.

In the example, the communication system 3100 includes a telecommunication network 3102 that includes an access network 3104, such as a radio access network (RAN) , and a core network 3106, which includes one or more core network nodes 3108. The access network 3104 includes one or more access network nodes, such as network nodes 3110a and 3110b (one or more of which may be generally referred to as network nodes 3110) , or any other similar 3rd Generation Partnership Project (3GPP) access node or non-3GPP access point. The network nodes 3110 facilitate direct or indirect connection of user equipment (UE) , such as by connecting UEs 3112a, 3112b, 3112c, and 3112d (one or more of which may be generally referred to as UEs 3112) to the core network 3106 over one or more wireless connections.

Example wireless communications over a wireless connection include transmitting and/or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and/or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 3100 may include any number of wired or wireless networks, network nodes, UEs, and/or any other components or systems that may facilitate or participate in the communication of data and/or signals whether via wired or wireless connections. The communication system 3100 may include and/or interface with any type of communication, telecommunication, data, cellular, radio network, and/or other similar type of system.

The UEs 3112 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and/or operable to communicate wirelessly with the network nodes 3110 and other communication devices. Similarly, the network nodes 3110 are arranged, capable, configured, and/or operable to communicate directly or indirectly with the UEs 3112 and/or with other network nodes or equipment in the telecommunication network 3102 to enable and/or provide network access, such as wireless network access, and/or to perform other functions, such as administration in the telecommunication network 3102.

In the depicted example, the core network 3106 connects the network nodes 3110 to one or more hosts, such as host 3116. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 3106 includes one more core network node (e.g., core network node 3108) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and/or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 3108. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC) , Mobility Management Entity (MME) , Home Subscriber Server (HSS) , Access and Mobility Management Function (AMF) , Session Management Function (SMF) , Authentication Server Function (AUSF) , Subscription Identifier De-concealing function (SIDF) , Unified Data Management (UDM) , Security Edge Protection Proxy (SEPP) , Network Exposure Function (NEF) , and/or a User Plane Function (UPF) .

The host 3116 may be under the ownership or control of a service provider other than an operator or provider of the access network 3104 and/or the telecommunication network 3102 and may be operated by the service provider or on behalf of the service provider. The host 3116 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio/video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

As a whole, the communication system 3100 of FIG. 13 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM) ; Universal Mobile Telecommunications System (UMTS) ; Long Term Evolution (LTE) , and/or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G) ; wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi) ; and/or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax) , Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and/or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

In some examples, the telecommunication network 3102 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 3102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 3102. For example, the telecommunications network 3102 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and/or Massive Machine Type Communication (mMTC) /Massive IoT services to yet further UEs.

In some examples, the UEs 3112 are configured to transmit and/or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 3104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 3104. Additionally, a UE may be configured for operating in single-or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e., being configured for multi-radio dual connectivity (MR-DC) , such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio –Dual Connectivity (EN-DC) .

In the example, the hub 3114 communicates with the access network 3104 to facilitate indirect communication between one or more UEs (e.g., UE 3112c and/or 3112d) and network nodes (e.g., network node 3110b) . In some examples, the hub 3114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 3114 may be a broadband router enabling access to the core network 3106 for the UEs. As another example, the hub 3114 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 3110, or by executable code, script, process, or other instructions in the hub 3114. As another example, the hub 3114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 3114 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 3114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 3114 then provides to the UE either directly, after performing local processing, and/or after adding additional local content. In still another example, the hub 3114 acts as a proxy server or orchestrator for the UEs, in particular in if one or more of the UEs are low energy IoT devices.

The hub 3114 may have a constant/persistent or intermittent connection to the network node 3110b. The hub 3114 may also allow for a different communication scheme and/or schedule between the hub 3114 and UEs (e.g., UE 3112c and/or 3112d) , and between the hub 3114 and the core network 3106. In other examples, the hub 3114 is connected to the core network 3106 and/or one or more UEs via a wired connection. Moreover, the hub 3114 may be configured to connect to an M2M service provider over the access network 3104 and/or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 3110 while still connected via the hub 3114 via a wired or wireless connection. In some embodiments, the hub 3114 may be a dedicated hub –that is, a hub whose primary function is to route communications to/from the UEs from/to the network node 3110b. In other embodiments, the hub 3114 may be a non-dedicated hub –that is, a device which is capable of operating to route communications between the UEs and network node 3110b, but which is additionally capable of operating as a communication start and/or end point for certain data channels.

FIG. 14 is a block diagram of a host 3200, which may be an embodiment of the host 3116 of FIG. 13, in accordance with various aspects described herein. As used herein, the host 3200 may be or comprise various combinations hardware and/or software, including a standalone server, a blade server, a cloud-implemented server, a distributed server, a virtual machine, container, or processing resources in a server farm. The host 3200 may provide one or more services to one or more UEs.

The host 3200 includes processing circuitry 3202 that is operatively coupled via a bus 3204 to an input/output interface 3206, a network interface 3208, a power source 3210, and a memory 3212. Other components may be included in other embodiments. Features of these components may be substantially similar to those described with respect to the devices of previous figures such that the descriptions thereof are generally applicable to the corresponding components of host 3200.

The memory 3212 may include one or more computer programs including one or more host application programs 3214 and data 3216, which may include user data, e.g., data generated by a UE for the host 3200 or data generated by the host 3200 for a UE. Embodiments of the host 3200 may utilize only a subset or all of the components shown. The host application programs 3214 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Versatile Video Coding (VVC) , High Efficiency Video Coding (HEVC) , Advanced Video Coding (AVC) , MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC) , MPEG, G. 711) , including transcoding for multiple different classes, types, or implementations of UEs (e.g., handsets, desktop computers, wearable display systems, heads-up display systems) . The host application programs 3214 may also provide for user authentication and licensing checks and may periodically report health, routes, and content availability to a central node, such as a device in or on the edge of a core network. Accordingly, the host 3200 may select and/or indicate a different host for over-the-top services for a UE. The host application programs 3214 may support various protocols, such as the HTTP Live Streaming (HLS) protocol, Real-Time Messaging Protocol (RTMP) , Real-Time Streaming Protocol (RTSP) , Dynamic Adaptive Streaming over HTTP (MPEG-DASH) , etc.

FIG. 15 shows a communication diagram of a host 3302 communicating via a network node 3304 with a UE 3306 over a partially wireless connection in accordance with some embodiments. Example implementations, in accordance with various embodiments, of the UE (such as a UE 3112a of FIG. 13) , network node (such as network node 3110a of FIG. 13) , and host (such as host 3116 of FIG. 13 and/or host 3200 of FIG. 14) discussed in the preceding paragraphs will now be described with reference to FIG. 15.

Like host 3200, embodiments of host 3302 include hardware, such as a communication interface, processing circuitry, and memory. The host 3302 also includes software, which is stored in or accessible by the host 3302 and executable by the processing circuitry. The software includes a host application that may be operable to provide a service to a remote user, such as the UE 3306 connecting via an over-the-top (OTT) connection 3350 extending between the UE 3306 and host 3302. In providing the service to the remote user, a host application may provide user data which is transmitted using the OTT connection 3350.

The network node 3304 includes hardware enabling it to communicate with the host 3302 and UE 3306. The connection 3360 may be direct or pass through a core network (like core network 3106 of FIG. 13) and/or one or more other intermediate networks, such as one or more public, private, or hosted networks. For example, an intermediate network may be a backbone network or the Internet.

The UE 3306 includes hardware and software, which is stored in or accessible by UE 3306 and executable by the UE’s processing circuitry. The software includes a client application, such as a web browser or operator-specific “app” that may be operable to provide a service to a human or non-human user via UE 3306 with the support of the host 3302. In the host 3302, an executing host application may communicate with the executing client application via the OTT connection 3350 terminating at the UE 3306 and host 3302. In providing the service to the user, the UE's client application may receive request data from the host's host application and provide user data in response to the request data. The OTT connection 3350 may transfer both the request data and the user data. The UE's client application may interact with the user to generate the user data that it provides to the host application through the OTT connection 3350.

The OTT connection 3350 may extend via a connection 3360 between the host 3302 and the network node 3304 and via a wireless connection 3370 between the network node 3304 and the UE 3306 to provide the connection between the host 3302 and the UE 3306. The connection 3360 and wireless connection 3370, over which the OTT connection 3350 may be provided, have been drawn abstractly to illustrate the communication between the host 3302 and the UE 3306 via the network node 3304, without explicit reference to any intermediary devices and the precise routing of messages via these devices.

As an example of transmitting data via the OTT connection 3350, in step 3308, the host 3302 provides user data, which may be performed by executing a host application. In some embodiments, the user data is associated with a particular human user interacting with the UE 3306. In other embodiments, the user data is associated with a UE 3306 that shares data with the host 3302 without explicit human interaction. In step 3310, the host 3302 initiates a transmission carrying the user data towards the UE 3306. The host 3302 may initiate the transmission responsive to a request transmitted by the UE 3306. The request may be caused by human interaction with the UE 3306 or by operation of the client application executing on the UE 3306. The transmission may pass via the network node 3304, in accordance with the teachings of the embodiments described throughout this disclosure. Accordingly, in step 3312, the network node 3304 transmits to the UE 3306 the user data that was carried in the transmission that the host 3302 initiated, in accordance with the teachings of the embodiments described throughout this disclosure. In step 3314, the UE 3306 receives the user data carried in the transmission, which may be performed by a client application executed on the UE 3306 associated with the host application executed by the host 3302.

In some examples, the UE 3306 executes a client application which provides user data to the host 3302. The user data may be provided in reaction or response to the data received from the host 3302. Accordingly, in step 3316, the UE 3306 may provide user data, which may be performed by executing the client application. In providing the user data, the client application may further consider user input received from the user via an input/output interface of the UE 3306. Regardless of the specific manner in which the user data was provided, the UE 3306 initiates, in step 3318, transmission of the user data towards the host 3302 via the network node 3304. In step 3320, in accordance with the teachings of the embodiments described throughout this disclosure, the network node 3304 receives user data from the UE 3306 and initiates transmission of the received user data towards the host 3302. In step 3322, the host 3302 receives the user data carried in the transmission initiated by the UE 3306.

One or more of the various embodiments improve the performance of OTT services provided to the UE 3306 using the OTT connection 3350, in which the wireless connection 3370 forms the last segment. More precisely, the teachings of these embodiments may improve the data rate and thereby provide benefits such as relaxed restriction on file size, improved content resolution, and better responsiveness.

In an example scenario, factory status information may be collected and analyzed by the host 3302. As another example, the host 3302 may process audio and video data which may have been retrieved from a UE for use in creating maps. As another example, the host 3302 may collect and analyze real-time data to assist in controlling vehicle congestion (e.g., controlling traffic lights) . As another example, the host 3302 may store surveillance video uploaded by a UE. As another example, the host 3302 may store or control access to media content such as video, audio, VR or AR which it can broadcast, multicast or unicast to UEs. As other examples, the host 3302 may be used for energy pricing, remote control of non-time critical electrical load to balance power generation needs, location services, presentation services (such as compiling diagrams etc. from data collected from remote devices) , or any other function of collecting, retrieving, storing, analyzing and/or transmitting data.

In some examples, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve. There may further be an optional network functionality for reconfiguring the OTT connection 3350 between the host 3302 and UE 3306, in response to variations in the measurement results. The measurement procedure and/or the network functionality for reconfiguring the OTT connection may be implemented in software and hardware of the host 3302 and/or UE 3306. In some embodiments, sensors (not shown) may be deployed in or in association with other devices through which the OTT connection 3350 passes; the sensors may participate in the measurement procedure by supplying values of the monitored quantities exemplified above, or supplying values of other physical quantities from which software may compute or estimate the monitored quantities. The reconfiguring of the OTT connection 3350 may include message format, retransmission settings, preferred routing etc.; the reconfiguring need not directly alter the operation of the network node 3304. Such procedures and functionalities may be known and practiced in the art. In certain embodiments, measurements may involve proprietary UE signaling that facilitates measurements of throughput, propagation times, latency and the like, by the host 3302. The measurements may be implemented in that software causes messages to be transmitted, in particular empty or ‘dummy’ messages, using the OTT connection 3350 while monitoring propagation times, errors, etc.

In an aspect of the disclosure, there is provided a method implemented in a host configured to operate in a communication system that further includes a network node and a user equipment (UE) . The method may comprise providing user data for the UE. The method may further comprise initiating a transmission carrying the user data to the UE via a cellular network comprising the network node. The network node may perform the following operations to transmit the user data from the host to the UE. The network node may schedule, for a first terminal device whose capability of whether supporting FDM of a first physical channel for transmitting traffic data and a second physical channel for transmitting control information is unknown to the network node, one or more transmissions each using the first physical channel that is multiplexed with the second physical channel in an FDM manner. The network node may perform the one or more transmissions to the first terminal device, based on the scheduling. The network node may receive, from the first terminal device, one or more reception feedbacks on the one or more transmissions. The network node may determine whether the first terminal device supports FDM of the first and second physical channels, based on the one or more reception feedbacks.

In an embodiment of the disclosure, the method may further comprise, at the network node, transmitting the user data provided by the host for the UE.

In an embodiment of the disclosure, the user data may be provided at the host by executing a host application that interacts with a client application executing on the UE. The client application may be associated with the host application.

In another aspect of the disclosure, there is provided a host configured to operate in a communication system to provide an over-the-top (OTT) service. The host may comprise processing circuitry configured to provide user data; and a network interface configured to initiate transmission of the user data to a network node in a cellular network for transmission to a user equipment (UE) . The network node may have a communication interface and processing circuitry. The processing circuitry of the network node may be configured to perform the following operations to transmit the user data from the host to the UE. The processing circuitry of the network node may be configured to schedule, for a first terminal device whose capability of whether supporting FDM of a first physical channel for transmitting traffic data and a second physical channel for transmitting control information is unknown to the network node, one or more transmissions each using the first physical channel that is multiplexed with the second physical channel in an FDM manner. The processing circuitry of the network node may be configured to perform the one or more transmissions to the first terminal device, based on the scheduling. The processing circuitry of the network node may be configured to receive, from the first terminal device, one or more reception feedbacks on the one or more transmissions. The processing circuitry of the network node may be configured to determine whether the first terminal device supports FDM of the first and second physical channels, based on the one or more reception feedbacks.

In an embodiment of the disclosure, the processing circuitry of the host may be configured to execute a host application that provides the user data. The UE may comprise processing circuitry configured to execute a client application associated with the host application to receive the transmission of user data from the host.

In yet another aspect of the disclosure, there is provided a communication system configured to provide an over-the-top service. The communication system may comprise a host. The host may comprise processing circuitry configured to provide user data for a user equipment (UE) . The user data may be associated with the over-the-top service. The host may further comprise a network interface configured to initiate transmission of the user data toward a cellular network node for transmission to the UE. The network node may have a communication interface and processing circuitry. The processing circuitry of the network node may be configured to perform the following operations to transmit the user data from the host to the UE. The processing circuitry of the network node may be configured to schedule, for a first terminal device whose capability of whether supporting FDM of a first physical channel for transmitting traffic data and a second physical channel for transmitting control information is unknown to the network node, one or more transmissions each using the first physical channel that is multiplexed with the second physical channel in an FDM manner. The processing circuitry of the network node may be configured to perform the one or more transmissions to the first terminal device, based on the scheduling. The processing circuitry of the network node may be configured to receive, from the first terminal device, one or more reception feedbacks on the one or more transmissions. The processing circuitry of the network node may be configured to determine whether the first terminal device supports FDM of the first and second physical channels, based on the one or more reception feedbacks.

In an embodiment of the disclosure, the communication system may further comprise the network node; and/or the user equipment.

In an embodiment of the disclosure, the processing circuitry of the host may be configured to execute a host application, thereby providing the user data. The host application may be configured to interact with a client application executing on the UE. The client application may be associated with the host application.

In general, the various exemplary embodiments may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device, although the disclosure is not limited thereto. While various aspects of the exemplary embodiments of this disclosure may be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

As such, it should be appreciated that at least some aspects of the exemplary embodiments of the disclosure may be practiced in various components such as integrated circuit chips and modules. It should thus be appreciated that the exemplary embodiments of this disclosure may be realized in an apparatus that is embodied as an integrated circuit, where the integrated circuit may comprise circuitry (as well as possibly firmware) for embodying at least one or more of a data processor, a digital signal processor, baseband circuitry and radio frequency circuitry that are configurable so as to operate in accordance with the exemplary embodiments of this disclosure.

It should be appreciated that at least some aspects of the exemplary embodiments of the disclosure may be embodied in computer-executable instructions, such as in one or more program modules, executed by one or more computers or other devices. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types when executed by a processor in a computer or other device. The computer executable instructions may be stored on a computer readable medium such as a hard disk, optical disk, removable storage media, solid state memory, RAM, etc. As will be appreciated by one skilled in the art, the function of the program modules may be combined or distributed as desired in various embodiments. In addition, the function may be embodied in whole or in part in firmware or hardware equivalents such as integrated circuits, field programmable gate arrays (FPGA) , and the like.

References in the present disclosure to “one embodiment” , “an embodiment” and so on, indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to implement such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

It should be understood that, although the terms “first” , “second” and so on may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of the disclosure. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed terms.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the present disclosure. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” , “comprising” , “has” , “having” , “includes” and/or “including” , when used herein, specify the presence of stated features, elements, and/or components, but do not preclude the presence or addition of one or more other features, elements, components and/or combinations thereof. The terms “connect” , “connects” , “connecting” and/or “connected” used herein cover the direct and/or indirect connection between two elements. It should be noted that two blocks shown in succession in the above figures may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

The present disclosure includes any novel feature or combination of features disclosed herein either explicitly or any generalization thereof. Various modifications and adaptations to the foregoing exemplary embodiments of this disclosure may become apparent to those skilled in the relevant arts in view of the foregoing description, when read in conjunction with the accompanying drawings. However, any and all modifications will still fall within the scope of the non-Limiting and exemplary embodiments of this disclosure.

Abbreviation
DU                      Digital unit
RU                      Radio unit
BB                      Base band
RIC                     RAN intelligent controller
NE                      Network Element
KPI                     Key performance indicator
DFE                     Digital front end
AFE                     Analog front end
TRX                     Transceiver
PA                      Power amplifier
CFR                     Crest Factor Reduction
DPD                     Digital Pre-Distortion

Claims

A method (300) for power management, comprising:

obtaining (310) data of at least one power consumption factor of a device, the at least one power consumption factor at least comprising an activation status of one or more energy saving functions of the device; and

determining (320) an estimated value of power consumption of the device based on the data of the at least one power consumption factor and a power consumption calculator, the power consumption calculator being determined at least based on mapping information about an energy saving function and its corresponding atomic operations.
The method (300) of claim 1, wherein the activation status indicates one or more atomic operations corresponding to at least a part of hardware of the at least one energy saving function which to be activated.
The method (300) of claim 1 or 2, wherein the activation status comprises at least one of:

an activation status of one of the at least one energy saving function in time domain,

an activation status of one of the at least one energy saving function in frequency domain,

an activation status of the at least one energy saving function in amplitude domain, or

an activation status of the at least one energy saving function in spatial domain.
The method (300) of claim 1, wherein the power consumption calculator is trained by applying, to a machine learning model, reference power consumption factors and the mapping information as inputs and reference values of power consumption as an output.
The method (300) of claim 1, wherein determining (320) the estimated value of power consumption of the device comprises:

processing (610) the data of the at least one power consumption factor by performing at least one of data cleaning or data formation; and

applying (620) the processed data to the power consumption calculator to obtain the estimated value of power consumption.
The method (300) of claim 1, further comprising:

obtaining (710) further data of the at least one power consumption factor of the device;

processing (720) the further data by performing at least one of data cleaning or data formation; and

obtaining (730) an updated power consumption calculator by applying the processed further data to a calculator calibrator.
The (300) method of claim 6, wherein the calculator calibrator is deployed at a radio unit, a digital unit, or a network element.
The (300) method of claim 6, further comprising:

determining (740) whether the updated power consumption calculator meets a deploying criterion; and

in accordance with a determination that updated power consumption calculator meets the deploying criterion, replacing (750) the power consumption calculator with the updated power consumption calculator.
The method (300) of any of claims 1 to 8, wherein the at least one power consumption factor further comprises at least one of the following:

radio hardware information,

a radio runtime configuration,

an environment factor,

a radio runtime status, or

traffic information.
The method (300) of claim 9, wherein the radio hardware information comprises at least one of:

a type of a radio hardware,

a supported antenna number of a radio hardware,

a supported bandwidth of a radio hardware, or

a supported maximum transmit power of a radio hardware.
The method (300) of claim 9, wherein the radio runtime configuration comprises at least one of:

the number of active carriers,

an active carrier center frequency,

an active carrier bandwidth,

an active carrier max transmission power,

a carrier Radio Access Technology (RAT) mode,

an active downlink path number, or

an active uplink path number.
The method (300) of claim 9, wherein the environment factor comprises at least one of:

a radio internal temperature,

radio installation location information, or

installation location climate information.
The method (300) of claim 9, wherein the radio runtime status comprises at least one of:

radio fault information, hardware failure information, or

radio hardware component reliability limitation.
The method (300) of claim 9, wherein the traffic information indicates at least one of:

resource block utilization, or

time slot utilization.
An apparatus (1100) for power management, comprising:

a processor (1110) and a memory (1120) , the memory (1120) containing instructions executable by the processor (1110) whereby the apparatus (1100) is operative to perform a method (300) according to any of claims 1 to 14.
A computer readable medium having instructions stored thereon, the instructions, when executed on at least one processor, causing the at least one processor to perform a method (300) according to any of claims 1 to 14.