TWI859051B - Energy efficiency estimation system and method for virtualized network function - Google Patents

Abstract

An energy efficiency estimation system and method for virtualized network function are used to estimate energy efficiency of virtualized infrastructure, which includes a plurality of physical devices, virtualization hypervisors, and virtual resources including each virtualized network component and a plurality of virtual machines. The method includes receiving requests from a cloud management system, collecting and storing device configuration information, device power consumption information and device performance information of physical devices, virtual resource configuration information and virtual resource performance information of virtual resources, obtaining each component power consumption of each virtual machine, virtual machine power consumption, and virtualized network component power consumption of each virtualized network component according to the above information, and obtaining an average CPU usage of each virtualized network element according to virtual machine process CPU usage corresponding to each virtualized network component.

Description

Energy efficiency estimation system and method for virtualized network elements

The present invention relates to an energy efficiency estimation system and method thereof, and in particular to an energy efficiency estimation system and method thereof for virtualized network elements.

In recent years, countries around the world have begun to pay attention to the impact of carbon emissions on the environment, and Net Zero has become the goal of governments and companies around the world. According to the Intergovernmental Panel on Climate Change (IPCC) report, if global greenhouse gas emissions are halved by 2030 and reach Net Zero by 2050, global temperature rise can be controlled within 1.5°C to cope with the impact of global warming and maintain the living environment of organisms. Therefore, global telecom operators have re-examined the ESG (Environment, Social, Governance) sustainability policy of the telecom industry in order to achieve the goal of Net Zero.

Among them, IDC cloud data centers and mobile network base stations account for a relatively high proportion of the overall carbon emissions of telecom operators. Therefore, it is imperative for enterprises to adopt renewable energy, replace old high-energy-consuming equipment, and purchase green electricity. In addition, traditional physical switching networks and computing services are also advancing under the wave of IP, virtualization, and containerization, which helps to reduce carbon emissions. Through various intelligentization, including smart cities, smart agriculture, smart grids and other fields, energy use can be made more efficient.

Currently, IDC cloud data centers are evolving towards a virtualized process, with the physical servers in the data centers carrying a large number of virtualized or containerized services, such as virtual data centers (VDCs), virtual private clouds (VPCs), virtual network functions (VNFs), virtual machines (VMs), etc. Therefore, the virtualization process helps reduce the idleness of physical equipment and thus improve the efficiency of resource use.

Traditional physical servers can obtain real-time power consumption information of equipment, such as power (W), voltage (V), current (A), etc., through tools provided by manufacturers or external measurement tools. Power consumption information helps telecom operators monitor the power usage of equipment in real time. By appropriately regulating the power of equipment, telecom operators can reduce the overall power consumption and carbon emissions of IDC cloud data centers. However, virtualized services lack corresponding power consumption measurement methods, making it difficult for telecom operators to control the power consumption information of virtual resources, and thus more difficult to control the scheduling and regulation of resources.

The present invention provides a system and method for estimating energy efficiency of virtualized network elements, which can collect virtual resource configuration information and real-time performance information, and estimate virtual resource power consumption according to the power consumption of physical equipment and its components.

The energy efficiency estimation system of a virtualized network element of the present invention is used to estimate the energy efficiency of a virtualized infrastructure, wherein the virtualized infrastructure includes a plurality of physical devices, a virtualization management program, and virtual resources generated according to the physical devices and the virtualization management program, and the virtual resources include each virtualized network element and a plurality of virtual machines corresponding to each virtualized network element, respectively. The energy efficiency estimation system includes a transceiver, a storage medium, and a processor. The processor is coupled to the storage medium and the transceiver, and the processor accesses and executes the monitoring and storage module and the power consumption estimation module stored in the storage medium. The monitoring and storage module includes a network service management database. The monitoring and storage module receives a request from the cloud management system via a transceiver to collect device configuration information, device power consumption information, and device performance information of physical devices and virtual resource configuration information and virtual resource performance information of virtual resources and store them in the network service management database. The power consumption estimation module is electrically connected to the monitoring and storage module. The power consumption estimation module obtains the power consumption of each component in each virtual machine according to the device configuration information, the device power consumption information and the device performance information of the physical device, the virtual resource configuration information and the virtual resource performance information of the virtual resource, obtains the total virtual machine power consumption of each virtual machine according to the power consumption of each component, obtains the virtual network element power consumption of each virtual network element according to the total virtual machine power consumption of each virtual machine, and obtains the average CPU usage rate of each virtual network element according to the CPU usage rate of the process of the virtual machine corresponding to each virtual network element.

The present invention provides a method for estimating the energy efficiency of a virtualized network element, which is used to estimate the energy efficiency of a virtualized infrastructure, wherein the virtualized infrastructure includes a plurality of physical devices, a virtualization management program, and virtual resources generated according to the physical devices and the virtualization management program, and the virtual resources include each virtualized network element and a plurality of virtual machines corresponding to each virtualized network element. The energy efficiency estimation method includes: receiving a request from a cloud management system, collecting and storing device configuration information, device power consumption information, and device performance information of the physical device, and virtual resources of the virtual resources; The invention relates to a method for obtaining the power consumption of each component in each virtual machine according to the device configuration information, the device power consumption information and the device performance information of the physical device, the virtual resource configuration information and the virtual resource performance information of the virtual resource, and obtaining the total power consumption of each virtual machine according to the power consumption of each component, and obtaining the virtual network element power consumption of each virtual network element according to the total power consumption of each virtual machine, and obtaining the average CPU usage rate of each virtual network element according to the CPU usage rate of the process of the virtual machine corresponding to each virtual network element.

Based on the above, the present invention provides a system and method for estimating energy efficiency of virtualized network elements, which can not only collect virtual resource configuration information and real-time performance information, but also estimate virtual resource power consumption based on the power consumption of physical equipment and its components, and provide an API interface for external system integration, and can also be used as a reference for cloud management systems, operations and business support systems to orchestrate or migrate virtual resources, thereby improving the utilization rate of physical equipment resources and achieving the goal of sustainable development of the enterprise.

In order to make the above features and advantages of the present invention more clearly understood, embodiments are specifically cited below and described in detail with reference to the accompanying drawings.

Some embodiments of the present invention will be described in detail below with reference to the accompanying drawings. When the same element symbols appear in different drawings, they will be regarded as the same or similar elements. These embodiments are only part of the present invention and do not disclose all possible implementations of the present invention.

Fig. 1 is a schematic diagram of an energy efficiency estimation system for a virtualized network element according to an embodiment of the present invention. Fig. 4 is a schematic diagram of a virtualized infrastructure according to an embodiment of the present invention.

Please refer to FIG. 1 , a virtualized network element energy efficiency estimation system 10 disclosed herein is used to estimate the energy efficiency of a virtualized infrastructure (Network Function Virtualization Infrastructure, NFVI) 15 .

1 and 4 , the virtualized infrastructure 15 may include a plurality of physical devices (e.g., a physical computing device 151, a physical network device 152, and a physical storage device 153) and a virtualization hypervisor 154 electrically connected to the physical computing device 151, the physical network device 152, and the physical storage device 153, respectively, so as to generate virtual resources according to each physical device and the virtualization hypervisor 154. The virtual resources may include each virtualized network function (VNF) 16 and a plurality of virtual machines (VM) 17 corresponding to each virtualized network function 16. In this embodiment, the virtualized network element 16 may be, for example, , , virtual machine 17 may be , , and virtualized network components The corresponding virtual machine can be … , the present invention is not limited thereto.

The energy efficiency estimation system 10 may include a transceiver 110 , a storage medium 120 , and a processor 130 .

The transceiver 110 transmits and receives signals in a wireless or wired manner. The transceiver 110 may also perform operations such as low noise amplification, impedance matching, frequency mixing, up or down frequency conversion, filtering, amplification, and the like.

The storage medium 120 is used to store various software, data and various program codes required for the operation of the energy efficiency estimation system 10. The storage medium 120 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid state drive (SSD) or similar components or a combination of the above components, and is used to store multiple modules or various applications that can be executed by the processor 130. In one embodiment, the storage medium 120 can store the monitoring and storage module 13 and the power consumption estimation module 14.

The processor 130 is, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose micro control unit (MCU), microprocessor, digital signal processor (DSP), programmable controller, application specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (FPGA), or other similar components or combinations of the above components. The processor 130 may be coupled to the storage medium 120 and the transceiver 110 , and access and execute various applications stored in the storage medium 120 and the monitoring and storage module 13 and the power consumption estimation module 14 stored in the storage medium 120 .

FIG. 2 is a schematic diagram of a monitoring and storage module according to an embodiment of the present invention.

2 , the monitoring and storage module 13 includes a device configuration collection unit 131, a device performance collection unit 132, a device power consumption measurement unit 133, a component power consumption measurement unit 134, a virtual resource configuration collection unit 135, a virtual resource performance collection unit 136, and a network service management database 137 electrically connected to the device performance collection unit 132, the device power consumption measurement unit 133, the component power consumption measurement unit 134, the virtual resource configuration collection unit 135, and the virtual resource performance collection unit 136, respectively.

The monitoring and storage module 13 receives the request command issued by the user 11 through the cloud management system 12 via the transceiver 110 to collect the device configuration information, device power consumption information and device performance information of the physical device and the virtual resource configuration information and virtual resource performance information of the virtual resource and store them in the network service management database 137.

In one embodiment, a physical device can obtain device configuration information, device power consumption information, and device performance information through a device API or software suite and tool (e.g., IPMI, Redfish, SNMP, Intel RAPL, ICMP, etc.). Device configuration information may include, for example, manufacturer, model, number of CPU cores and clock, memory size, hard disk size, maximum speed of network card, number of fans, power supply, motherboard, and other hardware specification information. Device power consumption information may include, for example, total device power consumption (unit: watt), CPU and memory combined power consumption (unit: watt), and other information. The device performance information may include, for example, CPU usage, memory usage, hard disk read/write times and read/write rates, and read/write times per second (IOPS), network card read/write times and read/write rates, fan speed, device temperature, etc. The present invention is not limited thereto.

The device configuration collection unit 131 is used to collect device configuration information of the physical device and store it in the network service management database 137. The device performance collection unit 132 is used to collect device performance information of the physical device and store it in the network service management database 137. The device power consumption measurement unit 133 and the component power consumption measurement unit 134 are used to collect device power consumption information of the physical device and store it in the network service management database 137.

In one embodiment, the virtual resource can obtain virtual resource configuration information and virtual resource performance information through the virtualization hypervisor 154. The virtual resource configuration information can be, for example, specification information such as the number and clock of virtual CPU cores, virtual memory size, virtual hard disk size, and virtual network card maximum speed. The virtual resource performance information can be, for example, information such as virtual CPU usage, virtual memory usage, virtual hard disk read and write times and read and write rate and IOPS, virtual network card read and write times and read and write rate. The present invention is not limited to this.

The virtual resource configuration collection unit 135 is used to collect virtual resource configuration information of virtual resources and store it in the network service management database 137. The virtual resource performance collection unit 136 is used to collect virtual resource performance information of virtual resources and store it in the network service management database 137.

FIG3 is a schematic diagram of a power consumption estimation module according to an embodiment of the present invention.

Referring to FIG. 3 , the power consumption estimation module 14 is electrically connected to the monitoring and storage module 13. The power consumption of each component in each virtual machine 17 is obtained according to the device configuration information, device power consumption information and device performance information of the physical device, the virtual resource configuration information and virtual resource performance information of the virtual resource stored in the network service management database 137. The total virtual machine power consumption of each virtual machine 17 is obtained according to the power consumption of each component. The power consumption of each virtual network element 16 is obtained according to the total power consumption of each virtual machine 17, and the average CPU usage of each virtual network element 16 is obtained according to the CPU usage of the process of the virtual machine 17 corresponding to each virtual network element 16, so as to estimate the power consumption of the virtual resources by statistically analyzing the power consumption of the physical device and its components.

In one embodiment, the power consumption of each component in each virtual machine 17 may include the total power consumption of the virtual machine CPU and memory, the power consumption of the virtual machine hard disk, the power consumption of the virtual machine network card, the power consumption of other virtual machine components, the power consumption of the virtual machine storage, and the power consumption of the virtual machine network. The present invention is not limited thereto.

In one embodiment, the power consumption estimation module 14 may include a device configuration and performance statistics unit 141, a virtual resource configuration and performance statistics unit 142, a device and component power consumption statistics unit 143, a virtual machine power consumption estimation unit 144 and a virtual network component power consumption estimation unit 145.

The monitoring and storage module 13 and the power consumption estimation module 14 can be implemented by software, firmware, hardware circuits or any combination thereof, and the present disclosure does not limit the implementation method of the monitoring and storage module 13 and the power consumption estimation module 14.

In the following, virtual machines For example, calculate the power consumption of each component in virtual machine VM1. On a physical computing device, it is still a process of an operating system.

The virtual machine power consumption estimation unit 144 uses the virtual machine power consumption according to Formula 1. The CPU usage of the processes and the virtual machines (e.g. virtual machines …virtual machines ) is allocated to the total power consumption of the CPU and memory of the physical computing device in proportion to the total CPU usage of the processes, thereby obtaining The total power consumption of the virtual machine CPU and memory. Formula 1 is as follows:

Right now

Where i and n are positive integers, is the CPU and memory power consumption of VM ₁ , is the sum of CPU usage of all VM processes (e.g. VM _1… VM _n ). is the CPU usage of the VM ₁ process. It is the total power consumption of the CPU and memory of a physical computing device.

The device configuration and performance statistics unit 141 obtains the total power consumption of the components of the physical computing device, such as hard disk, network card, motherboard, fan, etc., except the CPU and memory, according to Formula 2. Formula 2 is as follows:

Right now

It is the total power consumption of the physical computing device excluding the CPU and memory. is the total power consumption of the physical computing device, It is the total power consumption of the CPU and memory of a physical computing device.

Generally speaking, the power consumption of the hard disk accounts for about 5%-15% of the physical computing device. In this embodiment, 10% is used as the power consumption ratio of the hard disk of the physical computing device. The virtual machine power consumption estimation unit 144 uses Formula 3 to calculate the power consumption of the virtual machine. The virtual hard disk input/output operations per second (IOPS) and each virtual machine (such as virtual machine _… virtual machines ) is allocated to the hard disk power consumption of the physical computing device in proportion to the total IOPS of The virtual machine hard disk power consumption is as follows:

Right now

Where i and n are positive integers, is the hard disk power consumption of VM ₁ , for Virtual hard disk IOPS, For all VMs (such as virtual machines _… virtual machines ) of the virtual hard disk IOPS, It is the total power consumption of physical computing equipment excluding CPU and memory.

Generally speaking, the power consumption of the network card accounts for about 5%-10% of the physical computing device. In this embodiment, 10% is used as the power consumption ratio of the network card of the physical computing device. The virtual machine power consumption estimation unit 144 uses formula 4 to calculate the virtual machine power consumption. The read and write times of the virtual network card and each virtual machine (for example, virtual machine _… virtual machines ) is used to allocate the network card power consumption of the physical computing device in proportion to the total number of read and write times, thereby obtaining The power consumption of the virtual machine network card is as follows:

Right now

Where i and n are positive integers, for Network card power consumption, for The number of read and write times of the virtual network card. For all VMs (such as virtual machines _… virtual machines )’s total number of read and write times of the virtual network card. It is the total power consumption of physical computing equipment excluding CPU and memory.

The virtual machine power consumption estimation unit 144 uses the virtual machine power consumption according to Formula 5. The CPU usage of the processes and the virtual machines (e.g. virtual machines _… virtual machines The power consumption of the remaining components of the physical computing device except the CPU, memory, hard disk and network card is allocated by the ratio of the total CPU usage of the processes in the physical computing device to obtain The power consumption of the remaining components of the virtual machine is calculated as follows:

Right now

Where i and n are positive integers, is the power consumption of the remaining components of VM ₁ , for CPU usage of the process, For all VMs (such as virtual machines _… virtual machines ) The total CPU usage of the process, It is the total power consumption of physical computing equipment excluding CPU and memory.

The virtual machine power consumption estimation unit 144 uses the virtual machine power consumption according to Formula 6. The virtual hard disk read/write times per second (IOPS) and each virtual machine (such as virtual machine _… virtual machines ) is allocated to the total power consumption of the physical storage device in proportion to the total IOPS of the virtual hard disks, thereby obtaining The virtual machine storage power consumption is . Formula 6 is as follows:

Right now

Where i and n are positive integers, for Virtual machine storage power consumption, for Virtual hard disk IOPS, For all VMs (such as virtual machines _… virtual machines ) of the virtual hard disk IOPS, Total power consumption of physical storage devices.

The virtual machine power consumption estimation unit 144 uses the formula 7 to estimate the virtual machine power consumption. The read and write times of the virtual network card and each virtual machine (for example, virtual machine _… virtual machines ) is used to allocate the total power consumption of the physical network device in proportion to the total number of read and write times, thereby obtaining The virtual machine network power consumption is calculated as follows:

Right now

Where i and n are positive integers, is the network power consumption of VM ₁ , for The number of read and write times of the virtual network card. For all VMs (such as virtual machines _… virtual machines )’s total number of read and write operations. It is the total power consumption of physical network devices.

The equipment configuration and performance statistics unit 141 and the virtual resource configuration and performance statistics unit 142 calculate the virtual machine according to the above formula 1, formula 3 to formula 7 according to formula 8. The virtual machine CPU and memory power consumption, virtual machine hard disk power consumption, virtual machine network card power consumption, virtual machine other components power consumption, virtual machine storage power consumption and virtual machine network power consumption are used to obtain the virtual machine The total power consumption of the virtual machine. Formula 8 is as follows:

Right now

in for Total power consumption of the virtual machine, for The total power consumption of the virtual machine CPU and memory, for Virtual machine hard drive power consumption, for Virtual machine network card power consumption, for The power consumption of other components of the virtual machine, for Virtual machine storage power consumption, for Virtual machine network power consumption.

Taking the virtual network element VNF ₁ as an example, the virtual network element power consumption estimation unit 145 calculates the power consumption of the virtual network element according to Formula 9. Each virtual machine (for example, virtual machine …virtual machines ) are summed up to obtain The power consumption of the virtual network components is given by Equation 9:

Right now

Where i and n are positive integers, for Of Power consumption, To correspond to All virtual machines (for example, virtual machines …virtual machines ) is the sum of the total power consumption of the virtual machines.

The virtual network element power consumption estimation unit 145 calculates the power consumption of the virtual network element according to formula 10. Each virtual machine (for example, virtual machine …virtual machines ) to obtain the average CPU usage of The average CPU usage. Formula 10 is as follows:

Right now

Where i and n are positive integers, is the total CPU usage of VNF ₁ , To correspond to All virtual machines (for example, virtual machines …virtual machines ) is the sum of the CPU usage of all virtual machine processes.

Right now

Where i and n are positive integers, is the average CPU usage of VNF ₁ , , To correspond to All virtual machines (for example, virtual machines …virtual machines )'s average CPU usage by the virtual machine processes.

The above statistical and estimated data can be stored in the software-based network service management database 137.

In one embodiment, the monitoring and storage module 13 may include an application programming interface (API) (not shown) for interfacing with other systems and querying information such as configuration, performance, and power consumption of related physical devices and virtual resources.

Hereinafter, the method described in the embodiment of the present invention will be described with reference to the devices, components and modules in FIG1. The various processes of the method can be adjusted according to the implementation situation, and are not limited thereto.

FIG. 5 is a flow chart of a method for estimating energy efficiency of a virtualized network element according to an embodiment of the present invention.

5 , in step S501 , the monitoring and storage module 13 receives a request from the cloud management system 12 , collects and stores device configuration information, device power consumption information and device performance information of physical devices, and virtual resource configuration information and virtual resource performance information of virtual resources.

In step S502, the power consumption estimation module 14 obtains the power consumption of each component in each virtual machine 17 according to the device configuration information, the device power consumption information and the device performance information of the physical device, the virtual resource configuration information and the virtual resource performance information of the virtual resource, obtains the total virtual machine power consumption of each virtual machine 17 according to the power consumption of each component, obtains the virtual network element power consumption of each virtual network element 16 according to the total virtual machine power consumption of each virtual machine 17, and obtains the average CPU usage of each virtual network element 16 according to the CPU usage of the process of the virtual machine corresponding to each virtual network element 16.

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technical personnel in this field without making creative differences are within the scope of protection of the present invention.

FIG6 is a schematic diagram of an energy efficiency estimation system for virtualized network elements according to a first embodiment of the present invention.

Please refer to Figure 6. In this embodiment, the virtualized infrastructure 15 may include physical computing devices, physical storage devices and physical network devices. The monitoring and storage module 13 obtains the power consumption of the physical computing device as 250 watts through software packages and tools such as device API and virtualization management program. Among its components, the total power consumption of CPU and memory is 150 watts, the power consumption of physical storage device is 150 watts, and the power consumption of physical network device is 100 watts.

The monitoring and storage module 13 generates two virtual network elements 16, namely VNF_1 and VNF_2, through the hypervisor. VNF_1 consists of three virtual machines 17, namely VM_11, VM_12, and VM_13, with CPU process utilization rates of 15%, 30%, and 25%, virtual hard disk IOPS of 100, 200, and 150, and virtual network card read and write times of 50, 100, and 80, respectively. VNF_2 is composed of two virtual machines 17, namely VM_21 and VM_22, whose CPU process utilization rates are 25% and 10% respectively, virtual hard disk IOPS are 80 and 60 respectively, and virtual network card read and write times are 100 and 90 respectively. The above monitoring data is stored in the software-based network service management database 137.

The power consumption estimation module 14 accesses the software-based network service management database 137 to obtain the above-mentioned monitoring data, and obtains the power consumption information of the virtual machine 17 and the virtual network element 16 through the power consumption estimation algorithm of the above-mentioned formulas 1-10. The unit of the following power consumption information is watt.

Specifically, the power consumption estimation module 14 uses formula 1 and obtains the total power consumption of the virtual machine CPU and memory of the virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22 according to the above monitoring data:

The power consumption estimation module 14 uses Formula 2 to obtain the total power consumption of the physical computing device excluding the CPU and memory:

The power consumption estimation module 14 uses formula 3 to obtain the virtual machine hard disk power consumption of virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22:

The power consumption estimation module 14 uses formula 4 to obtain the virtual machine network card power consumption of virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22:

The power consumption estimation module 14 uses formula 5 to obtain the power consumption of the remaining components of the virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22:

The power consumption estimation module 14 uses formula 6 to obtain the virtual machine storage power consumption of virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22:

The power consumption estimation module 14 uses formula 7 to obtain the virtual machine network power consumption of virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22:

The power consumption estimation module 14 uses formula 8 to obtain the total power consumption of the virtual machines VM_11, VM_12, VM_13, VM_21, and VM_22:

The power consumption estimation module 14 uses formula 9 to obtain the virtual network element power consumption of the virtual network elements VNF_1 and VNF_2:

The power consumption estimation module 14 uses formula 10 to obtain the average CPU usage of the virtual network elements VNF_1 and VNF_2:

The above statistical and estimated data are stored in the software-based network service management database 137, and an API interface is provided for external system integration.

Based on the above, the present invention provides a system and method for estimating energy efficiency of virtualized network elements, which can not only collect virtual resource configuration information and real-time performance information, but also estimate virtual resource power consumption based on the power consumption of physical equipment and its components, and provide an API interface for external system integration, and can also be used as a reference for cloud management systems, operations and business support systems to orchestrate or migrate virtual resources, thereby improving the utilization rate of physical equipment resources and achieving the goal of sustainable development of the enterprise.

Although the present invention has been disclosed as above by the embodiments, they are not intended to limit the present invention. Any person with ordinary knowledge in the relevant technical field can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be defined by the scope of the attached patent application.

10: Energy efficiency estimation system

110: Transceiver

120: Storage Media

130:Processor

11: User

12: Cloud Management System

13: Monitoring and storage module

14: Power consumption estimation module

15: Virtualized Infrastructure

16: Virtualized Network Components

17: Virtual Machine

131: Equipment configuration collection unit

132: Equipment performance collection unit

133: Equipment power consumption measurement unit

134: Component power consumption measurement unit

135: Virtual resource configuration collection unit

136: Virtual Resource Performance Collection Unit

137: Network Service Management Database

141: Equipment Configuration and Performance Statistics Unit

142: Virtual Resource Configuration and Performance Statistics Unit

143: Equipment and component power consumption statistics unit

144: Virtual machine power consumption estimation unit

145: Virtual network element power consumption estimation unit

151: Physical computing equipment

152: Physical network equipment

153: Physical storage device

154:Virtualization Hypervisor

S501, S502: Steps

FIG. 1 is a schematic diagram of a system for estimating energy efficiency of a virtualized network element according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a monitoring and storage module according to an embodiment of the present invention. FIG. 3 is a schematic diagram of a power consumption estimation module according to an embodiment of the present invention. FIG. 4 is a schematic diagram of a virtualized infrastructure according to an embodiment of the present invention. FIG. 5 is a flow chart of a method for estimating energy efficiency of a virtualized network element according to an embodiment of the present invention. FIG. 6 is a schematic diagram of a system for estimating energy efficiency of a virtualized network element according to a first embodiment of the present invention.

10: Energy efficiency estimation system

110: Transceiver

120: Storage media

130: Processor

11: User

12: Cloud management system

13: Monitoring and storage module

14: Power consumption estimation module

15: Virtualized infrastructure

16: Virtualized network components

17: Virtual Machine

Claims (13)

A virtualized network element energy efficiency estimation system is used to estimate the energy efficiency of a virtualized infrastructure, wherein the virtualized infrastructure includes a plurality of physical devices, a virtualization management program, and virtual resources generated according to the physical devices and the virtualization management program. The virtual resources include each virtualized network element and a plurality of virtual machines corresponding to each virtualized network element. The energy efficiency estimation system includes: a transceiver; a storage medium for storing a plurality of modules; and a processor. The processor accesses and executes the modules stored in the storage medium, wherein the modules include: a monitoring and storage module, including a network service management database, wherein the monitoring and storage module receives a request from the cloud management system via the transceiver to collect the device configuration information, device power consumption information and device performance information of the physical devices and the virtual resource configuration information and virtual resource performance information of the virtual resource and stores the information in the network service management database. a power consumption estimation module electrically connected to the monitoring and storage module, the power consumption estimation module respectively obtaining the power consumption of each component in each virtual machine according to the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resources, obtaining the total virtual machine power consumption of each virtual machine according to the power consumption of each component, and obtaining the virtual network element power consumption of each virtual network element according to the total virtual machine power consumption of each virtual machine. , and according to the CPU usage of the processes of the virtual machines corresponding to the virtual network elements, the average CPU usage of each virtual network element is obtained, wherein the power consumption of each element in each virtual machine includes the power consumption of the virtual machine hard disk and the power consumption of the virtual machine network card, wherein the physical devices include physical computing devices, physical storage devices and physical network devices, wherein the power consumption estimation module is further based on the number of reads and writes per second (Input/Output The hard disk power consumption of the physical computing device is allocated according to the ratio of the number of operations per second (IOPS) to the total number of IOPS of the virtual machines to obtain the virtual hard disk power consumption of each virtual machine, wherein the power consumption estimation module further allocates the network card power consumption of the physical computing device according to the ratio of the number of read and write times of the virtual network card of each virtual machine to the total number of read and write times of the virtual machines to obtain the virtual network card power consumption of each virtual machine. The energy efficiency estimation system as described in claim 1, wherein the monitoring and storage module includes an application programming interface, and the application programming interface is used to provide an interface and query the device configuration information, the device power consumption information, the device performance information, the virtual resource configuration information and the virtual resource performance information. The energy efficiency estimation system as described in claim 1, wherein the power consumption of each component in each virtual machine includes the total power consumption of the virtual machine CPU and memory, the power consumption of other components of the virtual machine, the virtual machine storage power consumption and the virtual machine network power consumption. The energy efficiency estimation system as described in claim 3, wherein the power consumption estimation module further allocates the total power consumption of the CPU and memory of the physical computing device according to the ratio of the CPU usage of each virtual machine process to the sum of the CPU usage of the processes of the virtual machines, so as to obtain the total power consumption of the virtual machine CPU and memory of each virtual machine. The energy efficiency estimation system as described in claim 3, wherein the power consumption estimation module further allocates the power consumption of the remaining components of the physical computing device according to the ratio of the CPU usage of the processes of each virtual machine to the sum of the CPU usage of the processes of the virtual machines, so as to obtain the power consumption of the remaining components of the virtual machine of each virtual machine. The energy efficiency estimation system as described in claim 3, wherein the power consumption estimation module further allocates the total power consumption of the physical storage device according to the ratio of the input/output operations per second (IOPS) of the virtual hard disk of each virtual machine and the total IOPS of the virtual hard disks of the virtual machines to obtain the virtual machine storage power consumption of each virtual machine. The energy efficiency estimation system as described in claim 3, wherein the power consumption estimation module further allocates the total power consumption of the physical network device according to the ratio of the read and write times of the virtual network card of each virtual machine to the total read and write times of the virtual machines, so as to obtain the virtual machine network power consumption of each virtual machine. A method for estimating energy efficiency of virtualized network elements is used to estimate energy efficiency of virtualized infrastructure, wherein the virtualized infrastructure includes multiple physical devices, a virtualization management program, and virtual resources generated according to the physical devices and the virtualization management program. The virtual resources include each virtualized network element and multiple virtual machines corresponding to each virtualized network element. The energy efficiency estimation method includes: Receiving cloud management The system collects and stores the device configuration information, device power consumption information and device performance information of the physical devices and the virtual resource configuration information and virtual resource performance information of the virtual resource; and obtains the power consumption of each component in each virtual machine according to the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resource, and obtains the power consumption of each component in each virtual machine according to the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resource. The total power consumption of each virtual machine is obtained according to the power consumption of each virtual machine, and the power consumption of each virtual network element is obtained according to the total power consumption of each virtual machine, and the average CPU usage rate of each virtual network element is obtained according to the CPU usage rates of the processes of the virtual machines respectively corresponding to each virtual network element, wherein the power consumption of each element in each virtual machine includes the power consumption of the virtual machine hard disk and the power consumption of the virtual machine network card, wherein The physical devices include physical computing devices, physical storage devices, and physical network devices, wherein the step of obtaining the power consumption of each component in each virtual machine based on the device configuration information, the device power consumption information, and the device performance information of the physical devices, and the virtual resource configuration information and the virtual resource performance information of the virtual resource further includes: obtaining the power consumption of each component in each virtual machine based on the input/output times per second of the virtual hard disk of each virtual machine; Operations Per Second (IOPS) and the total IOPS of the virtual machines to obtain the virtual machine hard disk power consumption of each virtual machine; and The network card power consumption of the physical computing device is allocated according to the ratio of the read and write times of the virtual network card of each virtual machine to the total read and write times of the virtual machines to obtain the virtual machine network card power consumption of each virtual machine. The energy efficiency estimation method as described in claim 8, wherein the power consumption of each component in each virtual machine includes the total power consumption of the virtual machine CPU and memory, the power consumption of other components of the virtual machine, the virtual machine storage power consumption and the virtual machine network power consumption. The energy efficiency estimation method as described in claim 9, wherein the step of obtaining the power consumption of each component in each virtual machine based on the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resource further includes: allocating the total power consumption of the CPU and memory of the physical computing device based on the ratio of the CPU usage rate of the process of each virtual machine to the total CPU usage rate of the processes of the virtual machines to obtain the total power consumption of the virtual machine CPU and memory of each virtual machine. The energy efficiency estimation method as described in claim 9, wherein the step of obtaining the power consumption of each component in each virtual machine based on the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resources respectively further includes: allocating the power consumption of the remaining components of the physical computing device based on the ratio of the CPU usage of the process of each virtual machine to the sum of the CPU usage of the processes of the virtual machines to obtain the power consumption of the remaining components of each virtual machine. The energy efficiency estimation method as described in claim 9, wherein the step of obtaining the power consumption of each component in each virtual machine based on the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resource further includes: allocating the total power consumption of the physical storage device based on the ratio of the input/output operations per second (IOPS) of the virtual hard disk of each virtual machine to the total IOPS of the virtual hard disks of the virtual machines to obtain the virtual machine storage power consumption of each virtual machine. The energy efficiency estimation method as described in claim 9, wherein the step of obtaining the power consumption of each component in each virtual machine based on the device configuration information, the device power consumption information and the device performance information of the physical devices, the virtual resource configuration information and the virtual resource performance information of the virtual resource further includes: allocating the total power consumption of the physical network device based on the ratio of the read and write times of the virtual network card of each virtual machine to the total read and write times of the virtual machines to obtain the virtual machine network power consumption of each virtual machine.

Images