CN113411195B - Physical layer configuration method and device for 5G slice and computing equipment - Google Patents

Abstract

The invention discloses a physical layer configuration method, a physical layer configuration device and computing equipment of a 5G slice, wherein the method comprises the following steps: responding to a slice creating request initiated by a slice user, and acquiring the requirement information of a service level protocol, scene description information of a slice service and slice air interface conditions corresponding to the slice creating request from a slice management framework; carrying out serialization preprocessing on the demand information of the service level protocol, the scene description information of the slicing service and the slicing air interface condition to generate an index sequence; inputting the index sequence into a trained slice physical layer configuration adaptive combiner to predict to obtain a physical layer configuration information combination; and carrying out physical layer configuration processing according to the physical layer configuration information combination. By the method, the corresponding physical layer configuration information combination can be obtained according to the prediction of various service scenes, and then the configuration is carried out according to the physical layer configuration information combination, so that the configuration efficiency and the configuration accuracy are improved.

Description

Physical layer configuration method, device and computing device for 5G slice

technical field

The present invention relates to the field of communication technologies, and in particular, to a physical layer configuration method, apparatus and computing device for 5G slices.

Background technique

Network Slice is an end-to-end logical function and a collection of physical or virtual resources required by it, including access network, transmission network, core network, etc. Network slice can be considered as a virtualized "private network" in 5G network ; Network slicing is based on the unified infrastructure construction of NFV (Network Functions Virtualization, referred to as Network Function Virtualization) to achieve low-cost and efficient operation. Network slicing technology can achieve logical isolation of communication networks, allowing network elements and functions to be configured and reused in each network slice to meet specific industry application requirements.

At present, the physical layer configuration of 5G slices can be configured through pre-programming, and software-defined air interfaces have been implemented, so that wireless signals can be "tailored" to service scenarios. However, this method still relies on expert experience for manual programming, and needs to be programmed separately for each business scenario; when a new business scenario appears, it still needs to be reprogrammed, which is time-consuming, labor-intensive, inefficient, and prone to human error. It can be seen that the degree of automation and flexibility of this configuration method in the existing technology cannot meet the needs of future 5G slicing multi-service scenarios.

SUMMARY OF THE INVENTION

In view of the above problems, the embodiments of the present invention are proposed to provide a physical layer configuration method, apparatus and computing device for 5G slices that overcome the above problems or at least partially solve the above problems.

According to an aspect of the embodiments of the present invention, a method for configuring a physical layer of a 5G slice is provided, including:

In response to the slice creation request initiated by the slice user, obtain the requirement information of the service level agreement corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition from the slice management framework;

Perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slicing service, and the slicing air interface conditions to generate an index sequence;

Inputting the index sequence into the trained slice physical layer configuration adaptive combiner to predict the physical layer configuration information combination;

Physical layer configuration processing is performed according to the physical layer configuration information combination.

According to another aspect of the embodiments of the present invention, a device for configuring a physical layer of a 5G slice is provided, including:

an acquisition module, adapted to acquire, from the slice management framework, in response to a slice creation request initiated by a slice user, the requirement information of the SLA corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition;

a serialization module, adapted to perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slicing service, and the slicing air interface conditions, and generate an index sequence;

a prediction module, adapted to input the index sequence into the trained slice physical layer configuration adaptive combiner to predict the physical layer configuration information combination;

The configuration module is adapted to perform physical layer configuration processing according to the physical layer configuration information combination.

According to yet another aspect of the embodiments of the present invention, a computing device is provided, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface complete each other through the communication bus communication between;

The memory is used for storing at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned physical layer configuration method for 5G slices.

According to yet another aspect of the embodiments of the present invention, a computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute the physical layer configuration method corresponding to the foregoing 5G slice. operation.

According to the physical layer configuration method, device, and computing device for 5G slices according to the embodiments of the present invention, after receiving the slice creation request, sequence the request information of the requested service level agreement, the scene description information of the slice service, and the slice air interface conditions. Then, the index sequence is input to the slice physical layer configuration adaptive combiner, and the physical layer configuration information combination can be obtained, and then the corresponding configuration processing can be performed. It can be seen that, for any new slice service scenario, the solution of this embodiment only needs to perform serialization preprocessing on the request information, and then input the slice physical layer configuration adaptive combiner to obtain the physical layer configuration combination, without the need for Manual programming for new slicing services improves the flexibility and automation of physical layer configuration, which in turn can meet the needs of future 5G slicing multi-service scenarios.

The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to understand the technical means of the embodiments of the present invention more clearly, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and The advantages can be more obvious and easy to understand, and the following specific implementations of the embodiments of the present invention are given.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for the purpose of illustrating the preferred embodiments, and are not considered to be limitations of the embodiments of the present invention. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

FIG. 1 shows a flowchart of a physical layer configuration method for a 5G slice provided by an embodiment of the present invention;

FIG. 2 shows a flowchart of a physical layer configuration method for a 5G slice provided by another embodiment of the present invention;

Fig. 3 shows the schematic diagram of the encoder-decoder neural network structure in a specific example of the present invention;

FIG. 4 shows a complete flow of physical layer configuration according to a slice request in a specific example of the present invention;

FIG. 5 shows a schematic structural diagram of an apparatus for configuring a physical layer of a 5G slice provided by an embodiment of the present invention;

FIG. 6 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present invention will be more thoroughly understood, and will fully convey the scope of the present invention to those skilled in the art.

Before describing the embodiments of the present invention, the following terms involved in this document are first introduced:

1. Seq2Seq (sequence-to-sequence) model: The Seq2Seq model is actually an Encoder-Decoder (encoder-decoder, also known as codec) network structure, which has been used in the field of machine translation, that is, from a source Language translation to another target language.

2. LSTM (long short-term memory, long short-term memory) neural network: a special type of recurrent neural network, the so-called recurrent neural network is that the same neural network is used repeatedly. LSTM can learn long-term dependent information. By controlling the time that the value in the cache is stored, it can remember long-term information and is suitable for long-sequence learning. Each neuron has four inputs and one output, and each neuron has a Cell to store the memory value. Each LSTM neuron contains three gates: forgetting gate, input gate and output gate. Long short-term memory neural network has a good effect on the learning of long sequences. LSTM neurons are as follows:

Y _t =σ(W'h _t ) (7)

Each LSTM neuron contains three gates: forget gate, input gate, and output gate. Formula (1) represents the forget gate, new information is added in formulas (2) and (3), formula (4) combines new information and old information, formulas (5) and (6) output the current LSTM unit Information that has been learned about the next timestamp. The long short-term memory neural network has a good effect on the learning of long-term sequences. Each connection line in the LSTM unit contains corresponding weights. Xt represents the input vector, ht represents the hidden state, and Ct represents the neuron state at time t. Yt represents the output of the neuron, W is the trainable weight matrix, and b is the bias vector.

3. Slice management architecture: The slice management architecture is mainly composed of CSMF, NSMF, and NSSMF.

Among them, CSMF (Communication Service Management Function, communication service management function): completes the demand ordering and processing of user business communication services, and is responsible for transforming the communication service requirements of operators/third-party customers into network slicing requirements, and through and NSMF The interface between them sends the requirements for network slices (such as creating, terminating, modifying network slice instance requests, etc.) to the NSMF.

Among them, NSMF (Network Slice Management Function): responsible for receiving the network slice requirements sent by CSMF, managing the life cycle, performance, fault, etc. of network slice instances, arranging the composition of network slice instances, and decomposing network slice instances. The requirement is the requirement of each network slice subnet instance or network function, and a network slice subnet instance management request is sent to each NSSMF.

Among them, NSSMF (Network Slice Subnet Management Function, Network Slice Subnet Management Function): Receive network slice subnet deployment requirements issued from NSMF, manage network slice subnet instances, arrange the composition of network slice subnet instances, and The SLA requirements of the network slicing subnet are mapped to the QoS requirements of the network service, and the deployment request of the network service is issued to the NFVO system in the ETSINFV domain.

FIG. 1 shows a flowchart of a method for configuring a physical layer of a 5G slice provided by an embodiment of the present invention. This method can be used in the NSMF (Network Slice Management Function, network slice management function) module in the slice management framework to perform physical layer configuration. The method may be performed by any computing device with data processing capabilities.

As shown in Figure 1, the method includes the following steps:

Step S110: In response to the slice creation request initiated by the slice user, acquire the requirement information of the SLA corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition from the slice management framework.

Specifically, a slice user initiates a slice creation request to the slice management framework, and a new slice business scenario exists at this time. The request information of the request, including the SLA (Service level Agreement) requirement information, is obtained from the slice management framework. , which reflects the scene description information required for coverage, capacity, reliability, etc., as well as the slice air interface conditions that reflect the support for frame structure, waveform, etc.

Step S120: Perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slice service, and the slice air interface conditions to generate an index sequence.

Among them, serialization preprocessing refers to a process in which words contained in a piece of text are indexed and finally converted into a piece of index numbers (ie, an index sequence). Correspondingly, in this embodiment of the present invention, each word in the text segment formed by the requirement information of the service level agreement, the scene description information of the slice service, and the slice air interface condition is indexed to generate an index sequence.

Step S130: Input the index sequence into the trained slice physical layer configuration adaptive combiner to predict and obtain the physical layer configuration information combination.

Wherein, the slice physical layer configuration adaptive combiner can predict another sequence according to the input arbitrary sequence. The adaptive combiner is obtained by training the request information of a large number of historical slice requests and the manually annotated physical layer configuration information.

In the embodiment of the present invention, the problem of determining the physical layer configuration of a slice is regarded as a sequence-to-sequence (seq2seq) problem, that is, from the sequence corresponding to the request information to the sequence corresponding to the physical layer configuration information. By inputting the index sequence into the adaptive combiner, a sequence can be output, and the sequence is an index combination composed of indexes of multiple physical layer configurations, that is, a physical layer configuration information combination.

Step S140: Perform physical layer configuration processing according to the physical layer configuration information combination.

After the physical layer configuration information combination is obtained, through deserialization processing, the physical layer configuration combination represented by the physical layer configuration information combination can be obtained, and accordingly, configuration processing can be performed to meet the requirements of the new slice service scenario.

According to the physical layer configuration method for 5G slices provided in this embodiment, after receiving a slice creation request, by performing serialization preprocessing on the demand information of the requested service level agreement, the scene description information of the slice service, and the slice air interface conditions, the generated slice is generated. index sequence; and then input the index sequence to the slice physical layer configuration adaptive combiner, the physical layer configuration information combination can be obtained, and then the corresponding configuration processing can be performed. It can be seen that, for any new slice service scenario, the solution of this embodiment only needs to perform serialization preprocessing on the request information, and then input the slice physical layer configuration adaptive combiner to obtain the physical layer configuration combination, without the need for Manual programming for new slicing services improves the flexibility and automation of physical layer configuration, which in turn can meet the needs of future 5G slicing multi-service scenarios.

FIG. 2 shows a flowchart of a method for configuring a physical layer of a 5G slice provided by another embodiment of the present invention. As shown in Figure 2, the method includes the following steps:

Step S210 : the adaptive combiner of the slice physical layer configuration is obtained by training.

In the embodiment of the present invention, the physical layer configuration of the slice service is regarded as a sequence-to-sequence (seq2seq) problem, and an encoder-decoder neural network, that is, an encoder-decoder structure, is used for prediction. The codec model is used in the scenario of slicing physical layer configuration and combination. The encoder is used to encode the SLA requirements of the slice application, the description of the slice service scenario, and the slice air interface condition text into a fixed-length context vector. In the latter context vector, the corresponding optimal combination of six slice physical layer configurations of frame structure, waveform, multiple access, modulation and coding, duplex mode and/or multi-antenna is generated. Among them, neurons all use long short-term memory (long short-term memory, referred to as LSTM).

Specifically, the requirement information of the historical service level agreement, the scene description information of the slice service, and the air interface conditions of the slice are obtained to form a data set; wherein, the historical request information can be obtained from the slice management framework. For any piece of data, perform serialization preprocessing on the demand information of the service level agreement of the piece of data, the scene description information of the slice service, and the slice air interface conditions, and generate an index sequence sample corresponding to the piece of data, including removing all punctuation marks, If the text is in Chinese, the text is divided into words, if the text is in English, the letters are unified into lowercase, and each word is tokenized, so that each piece of text is converted into an index number, and the maximum text length is not reached. In addition, the longest length of the SLA requirement information, slice service scenario description information, and slice air interface conditions in the data set is taken as the index sequence length, and the number of all words contained in the data set is taken as the size of the dictionary. And, mark the physical layer configuration combination for the piece of data, and perform serialization preprocessing on the marked physical layer configuration combination to obtain a physical layer configuration information combination sample, which is the demand information of each service level agreement-slice business scenario Descriptive information-slice air interface condition data is manually marked with the corresponding physical layer configuration combination, and the longest length of the physical layer configuration combination corresponding to the data set is taken as the index sequence length of the physical layer configuration information combination sample, and the physical layer corresponding to the data set is taken. The number of all words included in the configuration combination is the size of the dictionary; the index sequence samples corresponding to multiple pieces of data in the dataset are used as the training input data of the encoder-decoder neural network, and the combination samples of physical layer configuration information corresponding to the multiple pieces of data are used as the training output. data; use the training input data and training output data to train the encoder-decoder neural network, specifically compare the results of each iteration with the training output data to calculate the objective function, and use gradient descent to gradually find the weight value that minimizes the objective function to The network weights after training convergence constitute the slice physical layer configuration adaptive combiner. In practice, the total data set can be divided into training set and test set, 90% of the total data set is divided into training set, and 10% of the total data set is divided into test set. The training set is used to train the model and the test set is used to test the model.

Among them, the SLA of slicing application usually includes but is not limited to one or more of the following: security, privacy, visibility, manageability, reliability, availability, specific service characteristics (service type, air interface requirements, customized network function, etc.) and corresponding performance indicators (delay, throughput rate, packet loss rate, call drop rate, etc.); correspondingly, the SLA requirements of slicing applications include but are not limited to one or more of the following: Delay (for example, less than 5ms) ), bandwidth, throughput rate, packet loss rate, call drop rate, number of connections, reliability (e.g. 99.999%), service range, user scale, isolation (e.g. strong, medium, weak), security (e.g. strong, medium , weak), access method, and max TP/site (eg 5Gbps).

Among them, the scenarios of slicing services include but are not limited to one or more of the following: wide-area coverage, high-capacity hotspots, low-latency, high reliability, and low-power consumption and large connections.

The slice air interface conditions include, but are not limited to, the physical layer's support for frame structure, waveform, multiple access, modulation and coding, duplex mode and/or multiple antennas.

The slice physical layer configuration includes six configurations of frame structure, waveform, multiple access, modulation and coding, duplex mode, and multi-antenna technology, and the physical layer configuration combination is a combination composed of one or more of the above six configurations. In addition, the configuration information of each physical layer configuration is as follows: the waveform information can be OFDM, non-orthogonal waveform, single carrier, multi-carrier and/or filter bank multi-carrier; the multiple access information can be orthogonal frequency division multiple access (Orthogonal Frequency Division Multiple Access (OFDMA)) OFDMA), Single-Carrier Frequency Division Multiple Access (SC-FDMA), Multi-User Shared Access (MUSA), Non-Orthogonal Multiple Access (NOMA), Pattern Division Multiple Access (PDMA), and/or Sparse Code Division Multiple Access (SCMA) ); modulation coding information can be Turbo coding, Polar coding, multivariate domain low density parity check (LDPC) and/or quadrature amplitude modulation (QAM); duplex mode information can be TDD, FDD, XDD, full duplex and / or flexible duplex; multi-antenna information can be centralized, distributed, massive antenna and/or digital-analog hybrid mMIMO; frame structure information can be dynamic TTI, dynamic uplink and downlink configuration, semi-static uplink and downlink configuration long TTI And/or semi-static uplink and downlink matching short TTI.

FIG. 3 shows a schematic diagram of the structure of the encoder-decoder neural network in a specific example of the present invention. The encoding and decoding neural network is composed of an embedding layer, a long short-term memory network encoding layer, a long short-term memory network decoding layer and a fully connected (Dense) layer in turn; wherein, the embedding layer converts each word in the index sequence sample into is a vector. As shown in Figure 3: The first layer is the input layer: input the indexed slice application SLA requirements, slice business scenario description, slice air interface conditions, and the length of each index sequence is SLA&scene&condition_length, so the shape of the output data of this layer is (None ,SLA&scene&condition_length); the second layer is the embedding layer: use word embedding to convert each word into a vector, the input data dimension is SLA&scene&conditio_vocab_size, the output is set to need to convert the word into a 128-dimensional space vector, input The sequence length is SLA&scene&condition_length, so the shape of the output data of this layer is (None, SLA&scene&condition_length, 128). The function of this layer is to perform vector mapping on the input words, and convert the index of each word into a 128-dimensional fixed shape vector; The third and fourth layers are LSTM encoding layers: containing 256 LSTM neurons, the activation function is set to "relu", and the shape of the output data of this layer is (None, SLA&scene&condition_length, 128); the fifth and sixth layers are LSTM decoding layers: containing 256 LSTM neurons, the activation function is set to "relu", the shape of the output data of this layer is (None, SLA&scene&condition_length, 128); the seventh layer is the fully connected (Dense) layer (output layer): Contains Dense fully connected neurons The number is portfolio_vocab_size, the activation function is set to "softmax", and the softmax output is sent to the multi-class cross-entropy loss function. The shape of the output data of this layer is (None, portfolio_vocab_size). When using the neural network structure built in Figure 3 for training, set the number of training rounds to 1000 (epochs=1000), set the batch size to 100 (batch_size=100), and select categorical crossentropy as the loss function, that is, the target Function (loss='categorical_crossentropy'): n is the number of samples, m is the number of categories.

The gradient descent optimization algorithm selects the adam optimizer to improve the learning speed of traditional gradient descent (optimizer='adam'). Through gradient descent, the optimal weight value that minimizes the objective function can be found, and the neural network will learn the weight value autonomously through training. , and derive the weights for that model after the model has converged.

Step S220: In response to the slice creation request initiated by the slice user, acquire the requirement information of the SLA corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition from the slice management framework.

Specifically, the slice user initiates a slice creation request to the CSMF (communication service management function) module in the slice management architecture, and the CSMF transmits the relevant request information to the NSMF. Obtain the slice application SLA requirements, slice service scenario description, and slice air interface conditions from the module; or, obtain the SLA requirements and slice service scenarios corresponding to the slice creation request from the communication service management function module in the slice management architecture description information; and, acquiring the slice air interface condition corresponding to the slice creation request from the network slice management function module in the slice management architecture.

Step S230: Perform serialization preprocessing on the requirement information of the service level agreement, the scene description information of the slicing service, and the slicing air interface condition to generate an index sequence.

Specifically, the index sequence is generated according to the requirement information of the dictionary for the service level agreement, the scene description information of the slice service, and the indexing of words contained in the text corresponding to the slice air interface condition.

Step S240: Input the index sequence into the trained slice physical layer configuration adaptive combiner to predict and obtain the physical layer configuration information combination.

Wherein, the physical layer configuration includes frame structure, waveform, multiple access, modulation and coding, duplex mode and/or multi-antenna technology.

Step S250: Feedback the physical layer configuration information combination to the network slice management function module in the slice management architecture, so that the network slice management function module can perform physical layer configuration processing according to the physical layer configuration information combination.

FIG. 4 shows a complete flow of physical layer configuration according to a slice request in a specific example of the present invention. As shown in Figure 4:

1. The slice user initiates a slice creation request to CSMF, and CSMF transmits the relevant request information to NSMF;

2. Obtain slice application SLA requirements, slice service scenario description, and slice air interface conditions from NSMF;

3. Convert the acquired text information into sequences through the data preprocessing module;

4. Input the preprocessed slice application SLA requirements, slice service scenario description, slice air interface conditions into the pre-trained slice physical layer configuration adaptive combiner;

5. The optimal combination of the optimal physical layer configuration predicted by the output of the slice physical layer configuration adaptive combiner;

6. The NSMF performs slice physical layer configuration according to the best combination of the predicted best physical layer configurations.

According to the physical layer configuration method for 5G slices provided in this embodiment, in order to solve the current situation that the physical layer configuration of slices still relies on expert experience, the SLA requirements of historical slice applications, the description of slice service scenarios, and the formation data of slice air interface conditions are obtained from the CSMF. Set, manually mark the best slice physical layer configuration combination scheme for each piece of data in the data set, and convert the text of the data set into sequences. Build an encoder-decoder neural network through a deep learning framework. The encoder is used to encode the SLA requirements of the slice application, the slice business scenario description, and the slice air interface condition text sequence into a fixed-length context vector, and the decoder is used to extract the encoded context vector from the encoded context vector. The optimal combination of six slice physical layer configurations of corresponding frame structure, waveform, multiple access, modulation and coding, duplex mode and multi-antenna is generated. Then compare and calculate the objective function with the correct configuration combination, and use gradient descent to gradually find the weight value that minimizes the objective function. Configure the combiner with the model weights after training converged as a slice physical layer. The final wireless sub-slice manager NSSMF implements physical layer configuration composition according to this composition scheme. Thus, the flexibility of the air interface is improved, so that the air interface can generate different physical layer configurations according to different slicing service scenarios to best match the service requirements.

FIG. 5 shows a schematic structural diagram of an apparatus for configuring a physical layer of a 5G slice provided by an embodiment of the present invention. As shown in Figure 5, the device includes:

The obtaining module 510 is adapted to, in response to a slice creation request initiated by a slice user, obtain from the slice management framework the requirement information of the service level agreement corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition;

The serialization module 520 is adapted to perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slicing service, and the slicing air interface conditions, and generate an index sequence;

The prediction module 530 is adapted to input the index sequence into the trained slice physical layer configuration adaptive combiner to predict the physical layer configuration information combination;

The configuration module 540 is adapted to perform physical layer configuration processing according to the physical layer configuration information combination.

In an optional manner, the physical layer configuration includes frame structure, waveform, multiple access, modulation and coding, duplex mode and/or multi-antenna technology.

In an optional manner, the device further includes:

The training module is suitable for obtaining the demand information of the historical service level agreement, the scene description information of the slice service, and the slice air interface condition to form a data set;

For any piece of data, perform serialization preprocessing on the demand information of the service level agreement of the piece of data, the scene description information of the slice service, and the conditions of the slice air interface, and generate an index sequence sample corresponding to the piece of data; and label the piece of data. physical layer configuration combination, and perform serialization preprocessing on the marked physical layer configuration combination to obtain a physical layer configuration information combination sample;

The index sequence samples corresponding to the multiple pieces of data in the dataset are used as the training input data of the encoding and decoding neural network, and the combined samples of the physical layer configuration information corresponding to the multiple pieces of data are used as the training output data;

The encoding/decoding neural network is trained by using the training input data and the training output data, and an adaptive combiner is configured to form a slice physical layer with the network weights after training convergence.

In an optional manner, the encoding-decoding neural network is sequentially composed of an embedding layer, a long-short-term memory network encoding layer, a long-short-term memory network decoding layer, and a fully connected layer;

The training module is further adapted: the embedding layer converts each word in the index sequence sample into a vector.

In an optional manner, the serialization module is further adapted to:

The index sequence is generated according to the requirement information of the dictionary for the service level agreement, the scene description information of the slice service, and the indexing of the words contained in the text corresponding to the slice air interface condition.

In an optional manner, the configuration module is further adapted to:

The physical layer configuration information combination is fed back to the network slice management function module in the slice management architecture, so that the network slice management function module can perform physical layer configuration processing according to the physical layer configuration information combination.

In an optional manner, the obtaining module is further adapted to:

Obtain the requirement information of the SLA corresponding to the slice creation request and the scene description information of the slice service from the communication service management function module in the slice management framework; and,

Obtain the slice air interface condition corresponding to the slice creation request from the network slice management function module in the slice management architecture.

An embodiment of the present invention provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer-executable instruction can execute the physical layer configuration method for 5G slices in any of the foregoing method embodiments .

FIG. 6 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

As shown in FIG. 6 , the computing device may include: a processor (processor) 602 , a communications interface (Communications Interface) 604 , a memory (memory) 606 , and a communication bus 608 .

The processor 602 , the communication interface 604 , and the memory 606 communicate with each other through the communication bus 608 . The communication interface 604 is used to communicate with network elements of other devices such as clients or other servers. The processor 602 is configured to execute the program 610, and specifically may execute the relevant steps in the foregoing embodiments of the physical layer configuration method for a 5G slice of a computing device.

Specifically, the program 610 may include program code including computer operation instructions.

The processor 602 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the computing device may be the same type of processors, such as one or more CPUs; or may be different types of processors, such as one or more CPUs and one or more ASICs.

The memory 606 is used to store the program 610 . Memory 606 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

The program 610 can specifically be used to cause the processor 602 to perform the following operations:

In response to the slice creation request initiated by the slice user, obtain the requirement information of the service level agreement corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition from the slice management framework;

Perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slicing service, and the slicing air interface conditions to generate an index sequence;

Inputting the index sequence into the trained slice physical layer configuration adaptive combiner to predict the physical layer configuration information combination;

Physical layer configuration processing is performed according to the physical layer configuration information combination.

In an optional manner, the physical layer configuration includes frame structure, waveform, multiple access, modulation and coding, duplex mode and/or multi-antenna technology.

In an optional manner, the program 610 causes the processor 602 to perform the following operations:

Obtain the demand information of the historical service level agreement, the scene description information of the slice service, and the slice air interface conditions to form a data set;

For any piece of data, perform serialization preprocessing on the service level agreement requirement information of the piece of data, the scene description information of the slice service, and the slice air interface conditions, and generate an index sequence sample corresponding to the piece of data; and, label the piece of data physical layer configuration combination, and perform serialization preprocessing on the marked physical layer configuration combination to obtain a physical layer configuration information combination sample;

The index sequence samples corresponding to the multiple pieces of data in the dataset are used as the training input data of the encoding and decoding neural network, and the combined samples of the physical layer configuration information corresponding to the multiple pieces of data are used as the training output data;

The encoding/decoding neural network is trained by using the training input data and the training output data, and an adaptive combiner is configured to form a slice physical layer with the network weights after training convergence.

In an optional manner, the encoding-decoding neural network is sequentially composed of an embedding layer, a long-short-term memory network encoding layer, a long-short-term memory network decoding layer, and a fully connected layer;

Among them, the embedding layer converts each word in the index sequence sample into a vector.

In an optional manner, the program 610 causes the processor 602 to perform the following operations:

The index sequence is generated according to the requirement information of the dictionary for the service level agreement, the scene description information of the slice service, and the indexing of the words contained in the text corresponding to the slice air interface condition.

In an optional manner, the program 610 causes the processor 602 to perform the following operations:

The physical layer configuration information combination is fed back to the network slice management function module in the slice management architecture, so that the network slice management function module can perform physical layer configuration processing according to the physical layer configuration information combination.

In an optional manner, the program 610 causes the processor 602 to perform the following operations:

Obtain the requirement information of the SLA corresponding to the slice creation request and the scene description information of the slice service from the communication service management function module in the slice management framework; and,

Obtain the slice air interface condition corresponding to the slice creation request from the network slice management function module in the slice management architecture.

The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with teaching based on this. The structure required to construct such a system is apparent from the above description. Furthermore, embodiments of the present invention are not directed to any particular programming language. It is to be understood that various programming languages can be used to implement the contents of the embodiments of the invention described herein and that the above descriptions of specific languages are intended to disclose the best mode of carrying out the embodiments of the invention.

In the description provided herein, numerous specific details are set forth. It will be understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it is to be understood that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in order to simplify the embodiments of the invention and to aid in the understanding of one or more of the various aspects of the invention. in a single embodiment, figure, or description thereof. However, this disclosed approach should not be construed to reflect an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and further they may be divided into multiple sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method so disclosed may be employed in any combination unless at least some of such features and/or procedures or elements are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, it will be understood by those skilled in the art that although some of the embodiments herein include certain features, but not others, included in other embodiments, that combinations of features of the different embodiments are intended to be within the scope of the present invention And form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

Various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. Embodiments of the present invention can also be implemented as apparatus or apparatus programs (eg, computer programs and computer program products) for performing part or all of the methods described herein. Such a program implementing embodiments of the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from Internet sites, or provided on carrier signals, or in any other form.

It should be noted that the above-described embodiments illustrate rather than limit embodiments of the invention, and that alternative embodiments may be devised by those skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention may be implemented by means of hardware comprising several different elements and by means of suitably programmed computers. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. do not denote any order. These words can be interpreted as names. The steps in the above embodiments should not be construed as limitations on the execution order unless otherwise specified.

Claims (10)

1. A physical layer configuration method for 5G slices, comprising: In response to the slice creation request initiated by the slice user, obtain the requirement information of the service level agreement corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition from the slice management framework; Perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slicing service, and the slicing air interface conditions to generate an index sequence; Inputting the index sequence into the trained slice physical layer configuration adaptive combiner to predict the physical layer configuration information combination; Physical layer configuration processing is performed according to the physical layer configuration information combination. 2. The method of claim 1, wherein the physical layer configuration includes frame structure, waveform, multiple access, modulation coding, duplex mode, and/or multiple antenna techniques. 3. The method according to claim 1 or 2, wherein the slice physical layer configuration adaptive combiner is obtained by training through the following steps: Obtain the demand information of the historical service level agreement, the scene description information of the slice service, and the slice air interface conditions to form a data set; For any piece of data, perform serialization preprocessing on the service level agreement requirement information of the piece of data, the scene description information of the slice service, and the slice air interface conditions, and generate an index sequence sample corresponding to the piece of data; and, label the piece of data physical layer configuration combination, and perform serialization preprocessing on the marked physical layer configuration combination to obtain a physical layer configuration information combination sample; The index sequence samples corresponding to the multiple pieces of data in the dataset are used as the training input data of the encoding and decoding neural network, and the combined samples of the physical layer configuration information corresponding to the multiple pieces of data are used as the training output data; The encoding/decoding neural network is trained by using the training input data and the training output data, and an adaptive combiner is configured to form a slice physical layer with the network weights after training convergence. 4. The method according to claim 3, wherein the encoding and decoding neural network is sequentially composed of an embedding layer, a long short-term memory network encoding layer, a long short-term memory network decoding layer and a fully connected layer; Among them, the embedding layer converts each word in the index sequence sample into a vector. 5. The method according to claim 1 or 2, wherein the serialization preprocessing further comprises: The index sequence is generated according to the requirement information of the dictionary for the service level agreement, the scene description information of the slice service, and the indexing of the words contained in the text corresponding to the slice air interface condition. 6. The method according to claim 1 or 2, wherein the performing physical layer configuration processing according to the physical layer configuration information combination further comprises: The physical layer configuration information combination is fed back to the network slice management function module in the slice management architecture, so that the network slice management function module can perform physical layer configuration processing according to the physical layer configuration information combination. 7. The method according to claim 1 or 2, wherein the obtaining, from the slice management framework, the requirement information of the service level agreement corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition further comprise: : Obtain the requirement information of the SLA corresponding to the slice creation request and the scene description information of the slice service from the communication service management function module in the slice management framework; and, Obtain the slice air interface condition corresponding to the slice creation request from the network slice management function module in the slice management architecture. 8. A physical layer configuration device for 5G slices, comprising: an acquisition module, adapted to acquire, in response to a slice creation request initiated by a slice user, the requirement information of the service level agreement corresponding to the slice creation request, the scene description information of the slice service, and the slice air interface condition from the slice management framework; a serialization module, adapted to perform serialization preprocessing on the demand information of the service level agreement, the scene description information of the slicing service, and the slicing air interface conditions, and generate an index sequence; a prediction module, adapted to input the index sequence into the trained slice physical layer configuration adaptive combiner to predict the physical layer configuration information combination; The configuration module is adapted to perform physical layer configuration processing according to the physical layer configuration information combination. 9. A computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; The memory is used for storing at least one executable instruction, and the executable instruction causes the processor to perform an operation corresponding to the physical layer configuration method for a 5G slice according to any one of claims 1-7. 10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, the executable instruction enables a processor to execute the physical layer configuration method for 5G slices according to any one of claims 1-7 corresponding operation.

Images