Method for determining energy efficiency, and training method and device for energy efficiency model

Abstract

This application provides a method for determining energy efficiency, a method and apparatus for training an energy efficiency model, relating to the field of communication technology, and is used to solve the problem of being unable to determine the energy efficiency of network devices. The method includes: a server acquiring at least one energy efficiency information of a target device; the server determining a target energy efficiency factor for each piece of energy efficiency information, wherein the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold; for each piece of energy efficiency information, the server determining an energy efficiency model for the energy efficiency information based on the energy efficiency information and its target energy efficiency factor, thereby obtaining an energy efficiency model for each piece of energy efficiency information; for each piece of energy efficiency information, the server inputting a baseline value of the target energy efficiency factor of the energy efficiency information into the energy efficiency model of the energy efficiency information to determine a baseline value for the energy efficiency information, thereby obtaining a baseline value for each piece of energy efficiency information; and the server determining a baseline energy efficiency of the target device based on the baseline value for each piece of energy efficiency information.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to a method for determining energy efficiency, a method for training an energy efficiency model, and an apparatus. Background Technology

[0002] With the development of mobile communication networks, the scale of network equipment has gradually expanded, and network equipment is also being continuously updated and iterated. Due to changes in network technology and equipment capabilities, the energy consumption and service capabilities of network equipment using different technologies vary. For example, the energy consumption of 5G base stations is higher than that of 4G base stations, while the performance and service capabilities of 5G networks are also significantly improved.

[0003] However, to meet the demands of energy conservation and carbon reduction in networks, operators need to ensure network energy efficiency while maintaining network service capabilities when deploying network equipment in order to better utilize network resources. Therefore, determining the energy efficiency of network equipment has become an urgent technical problem to be solved. Summary of the Invention

[0004] This application provides a method for determining energy efficiency, a method for training an energy efficiency model, and an apparatus to solve the problem of being unable to determine the energy efficiency of network devices.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application provides a method for determining energy efficiency. In this method, at least one energy efficiency information of a target device is obtained, where each energy efficiency information corresponds to a service information of the target device, and the energy efficiency information is used to indicate the relationship between the service information and energy consumption of the target device. A target energy efficiency factor is determined for each energy efficiency information, where the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. For each energy efficiency information, an energy efficiency model is determined based on the energy efficiency information and its target energy efficiency factor to obtain the energy efficiency model for each energy efficiency information. For each energy efficiency information, a benchmark value of the target energy efficiency factor is input into the energy efficiency model to determine a benchmark value for the energy efficiency information to obtain the benchmark value for each energy efficiency information. Based on the benchmark value for each energy efficiency information, a benchmark energy efficiency of the target device is determined.

[0007] Based on the above technical solution, the server acquires at least one energy efficiency information of the target device, with each energy efficiency information corresponding to a service information of the target device. This allows for the acquisition of multi-dimensional energy efficiency information for the target device. The server then determines the target energy efficiency factor for each piece of energy efficiency information; the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. For each piece of energy efficiency information, the server determines its energy efficiency model based on the energy efficiency information and its target energy efficiency factor, thus obtaining the energy efficiency model for each piece of energy efficiency information. Then, for each piece of energy efficiency information, the server inputs the baseline value of the target energy efficiency factor into the energy efficiency model to determine the baseline value, thus obtaining the baseline value for each piece of energy efficiency information. In this way, the server can obtain the baseline values ​​for each piece of energy efficiency information for the target device when the target energy efficiency factor is the baseline value. Then, the server can determine the baseline energy efficiency of the target device based on the baseline value of each piece of energy efficiency information. Thus, the server can determine the baseline energy efficiency of the target device through multi-dimensional energy efficiency information, improving the accuracy of determining device energy efficiency. Furthermore, by using the benchmark value of the energy efficiency factor, the differences in energy efficiency factors between multiple devices can be eliminated, thereby facilitating the comparison of energy efficiency information between devices.

[0008] In one possible design, at least one energy efficiency factor is obtained, and this energy efficiency factor is associated with energy efficiency information. A set of energy efficiency correlation degrees is determined for each piece of energy efficiency information, including the correlation degree between the energy efficiency information and each energy efficiency factor. For each piece of energy efficiency information, the correlation degrees in the set of energy efficiency correlation degrees corresponding to the energy efficiency information are compared with a preset correlation degree threshold to determine the target energy efficiency factor for that energy efficiency information.

[0009] In one possible design, for each energy efficiency information, the energy efficiency level is determined based on the baseline value and the preset energy efficiency range of the energy efficiency information to obtain the energy efficiency level of each energy efficiency information. Based on the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information, the baseline energy efficiency of the target device is determined.

[0010] In one possible design, the service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

[0011] In one possible design, the energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

[0012] Secondly, this application provides a method for training an energy efficiency model, the method comprising:

[0013] Historical values ​​of energy efficiency information for each target device and historical values ​​of the target energy efficiency factor for each energy efficiency information are obtained. The target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. Each piece of energy efficiency information corresponds to the service information of one target device, and the energy efficiency information is used to indicate the relationship between the service information and energy consumption of the target device. For each piece of energy efficiency information, the historical values ​​of the energy efficiency information and the historical values ​​of the target energy efficiency factor are input into a preset prediction model to obtain the energy efficiency model for each piece of energy efficiency information.

[0014] In one possible design, historical values ​​of at least one service information and historical device energy consumption of the target device are obtained. For each service information, a historical value for each energy efficiency information is determined based on the historical value of each service information and the historical device energy consumption.

[0015] In one possible design, the service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

[0016] In one possible design, the energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

[0017] Thirdly, this application provides an energy efficiency determination device, which includes an acquisition unit and a processing unit.

[0018] The acquisition unit is used to acquire at least one energy efficiency information of the target device. Each energy efficiency information corresponds to one service information of the target device, and the energy efficiency information is used to indicate the relationship between the service information and energy consumption of the target device. The processing unit is used to determine the target energy efficiency factor for each energy efficiency information. The target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. The processing unit is also used to determine the energy efficiency model for each energy efficiency information based on the energy efficiency information and its target energy efficiency factor, thereby obtaining the energy efficiency model for each energy efficiency information. The processing unit is also used to input the benchmark value of the target energy efficiency factor of each energy efficiency information into the energy efficiency model of the energy efficiency information to determine the benchmark value for the energy efficiency information, thereby obtaining the benchmark value for each energy efficiency information. The processing unit is also used to determine the benchmark energy efficiency of the target device based on the benchmark value for each energy efficiency information.

[0019] In one possible design, the acquisition unit is further configured to acquire at least one energy efficiency factor, which is associated with energy efficiency information. The processing unit is further configured to determine an energy efficiency correlation set corresponding to each piece of energy efficiency information, the energy efficiency correlation set including the correlation degree between the energy efficiency information and each energy efficiency factor. The processing unit is further configured to, for each piece of energy efficiency information, compare the correlation degree in the energy efficiency correlation set corresponding to the energy efficiency information with a preset correlation degree threshold to determine the target energy efficiency factor for the energy efficiency information, thereby determining the target energy efficiency factor for each piece of energy efficiency information.

[0020] In one possible design, the processing unit is further configured to determine the energy efficiency level of each energy efficiency information based on a baseline value and a preset energy efficiency range, thereby obtaining the energy efficiency level of each energy efficiency information. The processing unit is also configured to determine the baseline energy efficiency of the target device based on the energy efficiency level of each energy efficiency information and a preset weighting coefficient for each energy efficiency information.

[0021] In one possible design, the service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

[0022] In one possible design, the energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

[0023] Fourthly, this application provides a training device for an energy efficiency model, the device including an acquisition unit and a processing unit.

[0024] The acquisition unit acquires historical values ​​of each energy efficiency information item and historical values ​​of the target energy efficiency factor for each energy efficiency information item. The target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. Each energy efficiency information item corresponds to the service information of one target device, and the energy efficiency information is used to indicate the relationship between the service information and energy consumption of the target device. The processing unit, for each energy efficiency information item, inputs the historical values ​​of the energy efficiency information and the historical values ​​of the target energy efficiency factor into a preset prediction model to obtain the energy efficiency model for each energy efficiency information item.

[0025] In one possible design, the acquisition unit is further configured to acquire historical values ​​of at least one service information and historical device energy consumption of the target device. The processing unit is further configured to, for each service information, determine a historical value for each energy efficiency information based on the historical value and historical device energy consumption of each service information.

[0026] In one possible design, the service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

[0027] In one possible design, the energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

[0028] Fifthly, this application provides an energy efficiency determination apparatus, the apparatus comprising: a processor and a memory; the processor and the memory being coupled; the memory being used to store one or more programs, the one or more programs including computer-executable instructions, wherein when the energy efficiency determination apparatus is running, the processor executes the computer-executable instructions stored in the memory to implement the energy efficiency determination method as described in the first aspect and any possible implementation thereof.

[0029] In a sixth aspect, this application provides a training apparatus for an energy efficiency model, the apparatus comprising: a processor and a memory; the processor and the memory being coupled; the memory being used to store one or more programs, the one or more programs including computer-executable instructions, wherein when the energy efficiency model training apparatus is running, the processor executes the computer-executable instructions stored in the memory to implement the energy efficiency model training method as described in the second aspect and any possible implementation thereof.

[0030] In a seventh aspect, this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the energy efficiency determination method described in the first aspect, the second aspect, and any possible implementation thereof.

[0031] Eighthly, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run computer programs or instructions to implement the energy efficiency determination method described in the first aspect, the second aspect, and any possible implementation of the first aspect and the second aspect.

[0032] The technical problems that the energy efficiency determination device, computer equipment, computer storage medium or chip can solve and the technical effects that they can achieve can be found in the technical problems and effects solved in the first aspect above, and will not be repeated here. Attached Figure Description

[0033] Figure 1 A system architecture diagram of a communication system provided in this application embodiment;

[0034] Figure 2 A flowchart illustrating a method for determining energy efficiency provided in an embodiment of this application;

[0035] Figure 3 A flowchart illustrating another method for determining energy efficiency provided in this application embodiment;

[0036] Figure 4 A flowchart illustrating a training method for an energy efficiency model provided in an embodiment of this application;

[0037] Figure 5 A schematic diagram of the structure of an energy efficiency determination device provided in an embodiment of this application;

[0038] Figure 6 A schematic diagram of the structure of a training device for an energy efficiency model provided in an embodiment of this application;

[0039] Figure 7 This application provides a schematic diagram of the structure of a server according to an embodiment of the present application.

[0040] Figure 8 A conceptual partial view of a computer program product provided for an embodiment of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] In this article, the character " / " generally indicates that the objects before and after it are in an "or" relationship. For example, A / B can be understood as A or B.

[0043] The terms “first” and “second” in the specification and claims of this application are used to distinguish different objects, rather than to describe a specific order of objects.

[0044] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or device.

[0045] Furthermore, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0046] With the development of mobile communication networks, the scale of network equipment has gradually expanded, and network equipment is also being continuously updated and iterated. Due to changes in network technology and equipment capabilities, the energy consumption and service capabilities of network equipment with different technologies vary. For example, the energy consumption of 5G base stations is higher than that of 4G base stations, while the performance and service capabilities of 5G networks have also been significantly improved. The traditional single-dimensional indicator of "energy consumption" cannot objectively assess the network's effective energy conversion efficiency. Therefore, operators have proposed the "energy efficiency" indicator, which is the ratio of effective network output to energy consumption. For wireless networks such as 4G and 5G, effective output depends on the services that the network can provide, and is generally measured by indicators such as traffic, coverage area, and number of users. Compared with energy consumption indicators, energy efficiency indicators can simultaneously measure both the energy consumed by the base station and the service it can provide, reflecting the base station's energy conversion efficiency more objectively and comprehensively. For example, if the effective output of the network is traffic, then the energy efficiency indicator can be the ratio of traffic to energy consumption. Under the premise of ensuring network service capabilities, only by continuously improving network energy efficiency can network resources be better utilized, thereby reducing network energy consumption and meeting the needs of network energy conservation and carbon reduction.

[0047] Objectively and accurately assessing network energy efficiency is crucial for better utilizing energy-saving technologies and improving network energy efficiency. Currently, wireless network energy consumption assessment mainly obtains network energy consumption data through instrument measurements or base station self-statistics. Based on this, further indicators such as network traffic or number of users can be obtained. The network's energy efficiency assessment value is obtained by calculating the ratio of traffic to energy consumption or the ratio of number of users to energy consumption.

[0048] Because effective network output is related to network performance requirements and is not limited to single indicators such as service traffic or number of users, current energy efficiency assessment methods can only obtain the energy efficiency corresponding to a single indicator. They cannot comprehensively reflect effective output and energy consumption from multiple dimensions, leading to inaccurate energy efficiency assessments. Furthermore, network energy efficiency is affected by network conditions such as environment, load level, service type, and user distribution. When assessing network energy efficiency, because different networks may be in different conditions, the above methods cannot eliminate the impact of the differences in various factors affecting energy efficiency when determining energy efficiency assessment values, thus failing to accurately assess the energy efficiency levels of different networks.

[0049] Therefore, the above-mentioned energy efficiency assessment methods cannot comprehensively reflect the effective output and energy consumption of network devices from multiple dimensions, nor can they eliminate the impact of the differences in various factors affecting energy efficiency, resulting in low accuracy of energy efficiency assessment.

[0050] To address the aforementioned issues, this application provides a method for determining energy efficiency. A server acquires at least one energy efficiency information item for a target device, where each energy efficiency information item corresponds to one service information item for the target device. The server determines a target energy efficiency factor for each energy efficiency information item, where the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. For each energy efficiency information item, the server determines an energy efficiency model based on the energy efficiency information and its target energy efficiency factor, thereby obtaining an energy efficiency model for each item. For each energy efficiency information item, the server inputs the baseline value of the target energy efficiency factor into the energy efficiency model to determine a baseline value, thereby obtaining a baseline value for each item. The server determines the baseline energy efficiency of the target device based on the baseline value for each energy efficiency information item.

[0051] Understandably, the server acquires at least one energy efficiency information piece from the target device, with each energy efficiency information piece corresponding to a service information piece from the target device. This allows the server to obtain energy efficiency information from multiple dimensions of the target device. Next, the server can determine the target energy efficiency factor for each piece of energy efficiency information. The target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. For each piece of energy efficiency information, the server can determine its energy efficiency model based on the energy efficiency information and its target energy efficiency factor, thus obtaining the energy efficiency model for each piece of energy efficiency information. Then, for each piece of energy efficiency information, the server inputs the baseline value of the target energy efficiency factor into the energy efficiency model to determine the baseline value for the energy efficiency information, thus obtaining the baseline value for each piece of energy efficiency information. In this way, the server can obtain the baseline values ​​for each piece of energy efficiency information for the target device when the target energy efficiency factor is the baseline value. Then, the server can determine the baseline energy efficiency of the target device based on the baseline value for each piece of energy efficiency information. Thus, the server can determine the baseline energy efficiency of the target device through energy efficiency information from multiple dimensions, improving the accuracy of determining the device's energy efficiency. Furthermore, by using the benchmark value of the energy efficiency factor, the differences in energy efficiency factors between multiple devices can be eliminated, thereby facilitating the comparison of energy efficiency information between devices.

[0052] The implementation environment of the embodiments of this application is described below.

[0053] like Figure 1 As shown, a communication system provided in an embodiment of this application is provided. The communication system includes network devices (e.g., base station 101 and base station 102), terminal 103 and server 104.

[0054] Base stations (such as base station 101) can include various forms of base stations, supporting the same or different network standards and equipment types. Examples include macro base stations, micro base stations (also known as small stations), relay stations, and access points. Specifically, they can be: access points (APs) in Wireless Local Area Networks (WLANs), base stations (BTSs) in Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), base stations (NodeBs, NBs) in Wideband Code Division Multiple Access (WCDMA), evolved Node Bs (eNBs or eNodeBs) in LTE, relay stations or access points, or base stations in vehicle-mounted equipment, wearable devices, and future 5G networks (Next Generation Node Bs, gNBs) or future Public Land Mobile Networks (PLMNs).

[0055] In this application embodiment, the target device may include one or more network devices.

[0056] Terminal 103 can be a device with transceiver capabilities. The terminal can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on water (such as on ships); and it can be deployed in the air (e.g., on airplanes, balloons, and satellites). Terminals include handheld devices, vehicle-mounted devices, wearable devices, or computing devices with wireless communication capabilities. For example, the terminal can be a mobile phone, tablet computer, or computer with wireless transceiver capabilities. The terminal device can also be a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in autonomous driving, a wireless terminal in telemedicine, a wireless terminal in a smart grid, a wireless terminal in a smart city, a wireless terminal in a smart home, etc.

[0057] It should be noted that server 104 can be a single physical server, or a server cluster consisting of multiple servers. Alternatively, the server cluster can be a distributed cluster. Alternatively, server 104 can be a cloud server. Alternatively, server 104 can be an energy efficiency determination module, which can be located in a network device or in a separate physical entity. This application embodiment does not limit the specific implementation of the server.

[0058] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0059] like Figure 2 As shown, this application provides a method for determining energy efficiency, the method comprising:

[0060] S201. The server obtains at least one energy efficiency information of the target device.

[0061] One energy efficiency information corresponds to one target device's service information. The energy efficiency information is used to indicate the relationship between the target device's service information and energy consumption.

[0062] In this embodiment, service information is used to reflect the effective output of the target device. Service information may include at least one of the following: service traffic, number of access users, service perceived quality, coverage, etc.

[0063] The service traffic is the sum of uplink and downlink service traffic transmitted by the target device within a preset period. The number of access users is the sum of the number of users accessing the target device within a preset period. The perceived service quality is the average perceived service quality of all users accessing the target device within a preset period. The perceived service quality of each user can be determined by the terminal and reported to the network device, or it can be determined by the network device based on parameters such as the user's service rate and service latency. The coverage rate is the probability that the signal strength received at any location within the coverage area of ​​the target device is greater than a preset signal strength threshold within a preset period. It can be determined based on the measurement reports reported by users within the target device. Specifically, the measurement reports reported by all users accessing the target device within a preset period are obtained. Each measurement report carries the signal strength value measured by the user. The ratio of the number of measurement reports with signal strength values ​​greater than the signal strength threshold to the total number of measurement reports is determined as the coverage rate of the target device.

[0064] It should be noted that the embodiments of this application do not limit the preset period. For example, the preset period can be 15 minutes, 60 minutes, 1200 minutes, etc.

[0065] In one possible implementation, the server can obtain at least one service information. Then, the server can determine each energy efficiency information based on each service information and its energy consumption.

[0066] For example, if the service information consists of business traffic and the number of connected users, then the energy efficiency information consists of the energy efficiency information of business traffic and the energy efficiency information of the number of connected users. The energy efficiency information of business traffic is determined as the ratio of business traffic to energy consumption, and the energy efficiency information of the number of connected users is determined as the ratio of the number of connected users to energy consumption.

[0067] It is understandable that by determining one energy efficiency information through one service information, the effective output of the target device can be reflected from multiple different dimensions, thereby determining multiple different energy efficiency information and realizing a comprehensive reflection of the energy conversion efficiency of the target device from multiple dimensions.

[0068] In another possible implementation, the server can send a service request message to the target device, requesting service information from the target device. The target device then sends its service information to the server and determines its energy efficiency information.

[0069] For example, 5G enhanced mobile broadband services have high requirements for perceived quality of service, such as traffic and speed. Service information includes service traffic and perceived quality of service, while energy efficiency information includes energy efficiency information for both service traffic and perceived quality of service. For 5G IoT services, the focus is more on the number of connections and coverage performance. Service information includes the number of connected users and coverage rate, while energy efficiency information includes energy efficiency information for both the number of connected users and coverage rate.

[0070] Understandably, different services have different network requirements. By determining the service information of the target device from multiple dimensions, the effective energy efficiency information of the target device can be determined more accurately.

[0071] S202. The server determines the target energy efficiency factor for each energy efficiency information.

[0072] The target energy efficiency factor is an energy efficiency factor whose correlation with energy efficiency information is greater than a preset correlation threshold.

[0073] In one possible implementation, the server stores the correlation between each energy efficiency information and different energy efficiency factors. The server can compare multiple correlations corresponding to each energy efficiency information with preset correlation thresholds to determine the target energy efficiency factor for each energy efficiency information.

[0074] It should be noted that the embodiments of this application do not limit the energy efficiency factor. For example, the energy efficiency factor may include at least one of the following: climate factor, load factor, business factor, user factor, etc.

[0075] For example, the climate factor is the average temperature of the area where the target device is located within a preset period. The load factor is the average load of the target device within the preset period. Alternatively, the load factor is at least one of the percentage of high load time, medium load time, and low load time within the preset period. The percentages of high, medium, and low load time are the proportions of high, medium, and low load periods within the preset period, respectively. If the service load of the target device within a unit time period is greater than a preset high load threshold, the server determines that unit time period as a high load period. If the service load of the target device within a unit time period is less than or equal to the preset high load threshold, but greater than a preset medium load threshold, the server determines that unit time period as a medium load period. If the service load of the target device within a unit time period is less than or equal to the preset medium load threshold, the server determines that unit time period as a low load period.

[0076] The service factor is the proportion of high-performance, medium-performance, and low-performance services transmitted by the target device within a preset period. The proportion of high, medium, and low-performance services is the ratio of the traffic of high, medium, and low-performance services transmitted by the target device within the preset period to the total traffic. High-performance services are those with a expected rate greater than a preset high-rate threshold or a expected latency less than a preset low-latency threshold. Medium-performance services are those with an expected rate less than or equal to a preset high-rate threshold but greater than a preset medium-rate threshold, or an expected latency greater than or equal to a preset low-latency threshold but greater than a preset medium-latency threshold. Low-performance services are those with an expected rate less than or equal to a preset medium-rate threshold or an expected latency greater than or equal to a preset medium-latency threshold. The expected rate and expected latency can be determined based on the service quality parameters, which are carried in the service request message sent by the terminal and reported to the network device, or determined by the network device based on the terminal's subscription data. Alternatively, the service factor can be at least one of the proportions of large packet traffic, medium packet traffic, and small packet traffic transmitted by the target device within the preset period. The proportion of large, medium, and small packet traffic is the ratio of the traffic of large, medium, and small packets transmitted by the target device within a preset period to the total traffic. Large packets are those with a data packet length greater than a preset first packet length. Medium packets are those with a data packet length less than or equal to the preset first packet length but greater than a preset second packet length. Small packets are those with a data packet length less than or equal to the preset second packet length.

[0077] The user factor is defined as the percentage of far-point users, mid-point users, and near-point users connected to the target device within a preset period. The percentages of far-point, mid-point, and near-point users are the ratios of the total number of far-point, mid-point, and near-point users connected to the target device within the preset period to the total number of users accessing the target device. Far-point users receive a signal strength less than a preset first signal strength threshold. Mid-point users receive a signal strength greater than or equal to the preset first signal strength threshold, but less than a preset second signal strength threshold. Near-point users receive a signal strength greater than or equal to the preset second signal strength threshold. The signal strength received by each user can be reported by the terminal to the network device.

[0078] It should be noted that when the target device consists of multiple network devices, the energy efficiency factor can be the average of the energy efficiency factors of the multiple network devices. For example, the load factor of the target device is the average of the load factors of each network device in the target device.

[0079] In one possible design, the target energy efficiency factor for energy efficiency information may include one or more energy efficiency factors.

[0080] For example, as shown in Table 1, it illustrates the correlation between energy efficiency information and energy efficiency factors.

[0081] Table 1

[0082] Energy efficiency information a Energy Efficiency Factor a 0.8 Energy efficiency information a Energy Efficiency Factor b 0.6 Energy efficiency information a Energy Efficiency Factor c 0.4 Energy efficiency information a Energy Efficiency Factor d 0.3

[0083] In other words, the correlation between energy efficiency information 'a' and energy efficiency factors 'a', 'b', 'c', and 'd' is 0.8, 0.6, 0.4, and 0.3, respectively. If the preset correlation threshold is 0.5, then the target energy efficiency factors are energy efficiency factors 'a' and 'b'.

[0084] This embodiment defines multiple energy efficiency factors to reflect various factors affecting the energy efficiency level of target equipment; climate factors to reflect environmental factors affecting network energy efficiency; load factors to reflect network-related factors affecting energy efficiency; and service factors and user factors to reflect user-related factors affecting network energy efficiency. By defining multiple energy efficiency factors, multiple factors affecting network energy efficiency can be quantified, and the degree of influence of different factors on energy efficiency can be further analyzed to screen out target energy efficiency factors that play a key role in affecting energy efficiency.

[0085] S203. The server determines the energy efficiency model of the energy efficiency information based on the energy efficiency information and the target energy efficiency factor of the energy efficiency information.

[0086] Among them, the energy efficiency model is used to determine the value of energy efficiency information based on the value of the target energy efficiency factor.

[0087] In other words, an energy efficiency model can reflect the value of energy efficiency information when the target energy efficiency factor is a certain value. That is, the energy efficiency model can reflect the energy efficiency of the target equipment under a specific environment.

[0088] In this embodiment of the application, at least one energy efficiency model is determined in the server, and different energy efficiency information and target energy efficiency factors of energy efficiency information correspond to different energy efficiency models.

[0089] For example, Table 2 shows the relationship between energy efficiency information, target energy efficiency factor and energy efficiency model.

[0090] Table 2

[0091] Energy efficiency information a Energy Efficiency Factor a Model a Energy efficiency information a Energy Efficiency Factor b Model b Energy efficiency information a Energy Efficiency Factor c Model c

[0092] In other words, when the energy efficiency information is energy efficiency information 'a' and the target energy efficiency factor is energy efficiency factor 'a', the energy efficiency model is model a. When the energy efficiency information is energy efficiency information 'a' and the target energy efficiency factor is energy efficiency factor 'b', the energy efficiency model is model b. When the energy efficiency information is energy efficiency information 'a' and the target energy efficiency factor is energy efficiency factor 'c', the energy efficiency model is model c.

[0093] In this embodiment, for each piece of energy efficiency information, the server can determine the energy efficiency model of the energy efficiency information based on the energy efficiency information and the target energy efficiency factor of the energy efficiency information, so as to obtain the energy efficiency model of each piece of energy efficiency information. That is, for each piece of energy efficiency information, the server needs to execute S203 to obtain the energy efficiency model of that energy efficiency information.

[0094] S204. The server inputs the baseline value of the target energy efficiency factor of the energy efficiency information into the energy efficiency model of the energy efficiency information to determine the baseline value of the energy efficiency information.

[0095] It should be noted that the reference value for the target energy efficiency factor is not limited in this application embodiment. For example, when the target energy efficiency factor is a climate factor, the reference value can be 0 degrees, 10 degrees, 20 degrees, etc. The reference value for the load factor is 10% of the average load or the proportions of high, medium, and low load durations of 33%, 42%, and 25%, respectively. The reference value for the business factor is the proportions of high, medium, and low performance business volume or the proportions of large, medium, and small package business volume of 25%, 25%, and 50%, respectively. The reference value for the user factor is the proportions of users at distant, medium, and nearby locations of 10%, 50%, and 40%, respectively.

[0096] For each energy efficiency information, the server inputs the baseline value of the target energy efficiency factor into the energy efficiency model of the energy efficiency information to determine the baseline value of the energy efficiency information, thereby obtaining the baseline value for each energy efficiency information. In other words, the server can execute S204 for each energy efficiency information to obtain the baseline value for each energy efficiency information.

[0097] Understandably, by inputting the baseline value of the target energy efficiency factor into the energy efficiency model, the server can obtain the energy efficiency value under the condition that the target energy efficiency factor is the baseline value. In this way, the differences in energy efficiency factors among multiple devices can be unified, thereby facilitating the comparison of energy efficiency information between devices.

[0098] S205. The server determines the baseline energy efficiency of the target device based on the baseline value of each energy efficiency information.

[0099] The benchmark energy efficiency is used to indicate the energy efficiency of the target device when all target energy efficiency factors are benchmark values.

[0100] In one possible implementation, the server can determine the energy efficiency level of each piece of energy efficiency information based on a baseline value and a preset energy efficiency range. Then, the server can determine the baseline energy efficiency of the target device based on the energy efficiency level of each piece of energy efficiency information. The baseline energy efficiency of the target device is the sum of the energy efficiency levels of the energy efficiency information.

[0101] It should be noted that the embodiments of this application do not limit the energy efficiency level. For example, the energy efficiency level can be any one of N+1 integers from 0 to N. The larger the baseline value of the energy efficiency information, the higher the corresponding energy efficiency level.

[0102] For example, the preset energy efficiency range corresponding to the energy efficiency information of service traffic is: [0,10), [10,20), [20,30), [30,40), [40,50), [50,60), [60,100). The preset values ​​corresponding to each preset range are 1, 2, 3, 4, 5, 6, and 7, respectively. If the energy efficiency baseline value of the service traffic of the target device is 30GB / kWh, then the corresponding energy efficiency level is 4. The preset energy efficiency range corresponding to the energy efficiency information of the number of access users is: [0,100), [100,200), [200,300), [300,400), [400,500), [500,600), [600,1000]. The preset values ​​corresponding to each preset range are 1, 2, 3, 4, 5, 6, and 7, respectively. If the number of access users of the target device is 550, then the corresponding energy efficiency level is 6. Then the baseline energy efficiency of the target device is 10.

[0103] In another possible implementation, the server can determine the energy efficiency level of each energy efficiency information based on the baseline value and the preset energy efficiency range of the energy efficiency information. Then, the server determines the baseline energy efficiency of the target device based on the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information.

[0104] For example, if the energy efficiency information of the target device includes: energy efficiency information a and energy efficiency information b, the energy efficiency level of energy efficiency information a is 5, the energy efficiency level of energy efficiency information b is 6, the preset weighting coefficient of energy efficiency information a is 0.3, and the preset weighting coefficient of energy efficiency information b is 0.7, then the benchmark energy efficiency of the target device is 5.7.

[0105] Understandably, by determining the benchmark energy efficiency of the target equipment based on the benchmark values ​​and preset weighting coefficients of different energy efficiency information, the obtained benchmark energy efficiency is determined under the condition that the energy efficiency influencing factors are exactly the same, thereby improving the accuracy of the energy efficiency level assessment of different target equipment.

[0106] Based on the above technical solution, the server acquires at least one energy efficiency information of the target device, with each energy efficiency information corresponding to a service information of the target device. This allows for the acquisition of multi-dimensional energy efficiency information for the target device. The server then determines the target energy efficiency factor for each piece of energy efficiency information; the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. For each piece of energy efficiency information, the server determines its energy efficiency model based on the energy efficiency information and its target energy efficiency factor, thus obtaining the energy efficiency model for each piece of energy efficiency information. Then, for each piece of energy efficiency information, the server inputs the baseline value of the target energy efficiency factor into the energy efficiency model to determine the baseline value, thus obtaining the baseline value for each piece of energy efficiency information. In this way, the server can obtain the baseline values ​​for each piece of energy efficiency information for the target device when the target energy efficiency factor is the baseline value. Then, the server can determine the baseline energy efficiency of the target device based on the baseline value of each piece of energy efficiency information. Thus, the server can determine the baseline energy efficiency of the target device through multi-dimensional energy efficiency information, improving the accuracy of determining device energy efficiency. Furthermore, by using the benchmark value of the energy efficiency factor, the differences in energy efficiency factors between multiple devices can be eliminated, thereby facilitating the comparison of energy efficiency information between devices.

[0107] like Figure 3 As shown, another method for determining device energy efficiency provided in this application embodiment is described. In this method, step S202 may include:

[0108] S301, The server obtains at least one energy efficiency factor.

[0109] Among them, the energy efficiency factor is associated with energy efficiency information.

[0110] S302. The server determines the set of energy efficiency correlation degrees corresponding to each energy efficiency information.

[0111] The energy efficiency correlation set includes the correlation between energy efficiency information and each energy efficiency factor. This correlation reflects the closeness of the relationship between energy efficiency information and energy efficiency factors.

[0112] In one possible implementation, the server stores a set of energy efficiency correlations corresponding to each energy efficiency information.

[0113] In another possible implementation, for each piece of energy efficiency information, the server determines the energy efficiency correlation set corresponding to each piece of energy efficiency information according to a first operation. The first operation includes: the server obtaining the historical value of the first energy efficiency information and the historical value of each energy efficiency factor. Then, the service determines the energy efficiency correlation set of the first energy efficiency information based on the historical value of the first energy efficiency information, the historical value of each energy efficiency factor, and a preset correlation coefficient algorithm. The first energy efficiency information is any one of at least one piece of energy efficiency information.

[0114] It should be noted that the embodiments of this application do not limit the preset correlation coefficient algorithm. For example, the preset correlation coefficient algorithm can be the Pearson algorithm, the Spearman correlation coefficient method, or the Kendall algorithm, etc.

[0115] For example, the energy efficiency correlation set of the first energy efficiency information can satisfy the following formula.

[0116]

[0117] Among them, A j Let Ei be the correlation degree between the first energy efficiency information and the j-th energy efficiency factor in the energy efficiency correlation degree set of the first energy efficiency information, and Ri be the i-th historical value of the first energy efficiency information and the j-th energy efficiency factor. Both i and j are positive integers.

[0118] In one possible design, the correlation coefficient ranges from 1 to -1. A correlation coefficient greater than 0 indicates a positive correlation between energy efficiency information and the energy efficiency factor; a correlation coefficient less than 0 indicates a negative correlation; and a correlation coefficient of 0 indicates no correlation between energy efficiency information and the energy efficiency factor.

[0119] Understandably, determining the target energy efficiency factor allows us to identify the relevant factors that have a significant impact on the energy efficiency of the target equipment from among the various factors that affect the energy efficiency of the target equipment, and remove irrelevant factors, thus making the energy efficiency assessment more accurate.

[0120] S303. The server compares the correlation degree in the energy efficiency correlation degree set corresponding to the energy efficiency information with the preset correlation degree threshold to determine the target energy efficiency factor of the energy efficiency information.

[0121] In one possible design, the target energy efficiency factor is an energy efficiency factor whose correlation with energy efficiency information is greater than a preset correlation threshold. The server compares the correlation scores in the energy efficiency correlation set corresponding to the energy efficiency information with the preset correlation threshold, and selects the energy efficiency factors with a correlation score greater than the preset correlation threshold as the target energy efficiency factors for the energy efficiency information.

[0122] Optionally, the target energy efficiency factor includes: energy efficiency factors whose correlation with energy efficiency information is greater than a preset correlation threshold.

[0123] In this embodiment of the application, for each energy efficiency information, the server compares the correlation degree in the energy efficiency correlation degree set corresponding to the energy efficiency information with a preset correlation degree threshold to determine the target energy efficiency factor of the energy efficiency information, so as to determine the target energy efficiency factor of each energy efficiency information.

[0124] like Figure 4 As shown, this application provides a method for training an energy efficiency model, which includes:

[0125] S401. The server obtains the historical values ​​of each energy efficiency information of the target device and the historical values ​​of the target energy efficiency factor for each energy efficiency information.

[0126] Among them, the target energy efficiency factor is the energy efficiency factor whose correlation with energy efficiency information is greater than a preset correlation threshold, and one energy efficiency information corresponds to the service information of one target device.

[0127] In one possible implementation, the server can obtain historical values ​​of at least one service information and historical device energy consumption of the target device. Then, for each service information, the server determines the historical value of each energy efficiency information based on the historical value of each service information and the historical device energy consumption.

[0128] For example, when the service information includes business traffic, the corresponding energy efficiency information is the energy efficiency of the business traffic, defined as the ratio of business traffic to energy consumption. When the service information includes the number of connected users, the corresponding energy efficiency information is the energy efficiency of the number of connected users, defined as the ratio of the number of connected users to energy consumption.

[0129] In another possible implementation, the target device includes multiple network devices. The server sends a parameter request message to each network device in the target device to obtain the historical values ​​of each energy efficiency information and each energy efficiency factor for each network device within a preset historical period. The message carries information such as the preset historical period, energy efficiency information type, and energy efficiency factor type. Each network device in the target device sends a parameter indication message to the server, which includes the historical values ​​of each energy efficiency information and each energy efficiency factor for each network device within the preset historical period. Then, the server determines the historical energy efficiency factor value of the target device based on the historical energy efficiency factor values ​​of each network device, where the historical energy efficiency factor value of the target device is the average of the historical energy efficiency factor values ​​of each network device.

[0130] S402. The server inputs the historical values ​​of energy efficiency information and the historical values ​​of the target energy efficiency factor of energy efficiency information into the preset prediction model to obtain the energy efficiency model of energy efficiency information.

[0131] In one possible implementation, the server can input historical values ​​of energy efficiency information and historical values ​​of the target energy efficiency factor of energy efficiency information into a preset prediction model for training, thereby obtaining an energy efficiency model of energy efficiency information.

[0132] It should be noted that the embodiments of this application do not limit the preset prediction model. For example, the preset prediction model can be a regression model in artificial intelligence algorithms; regression analysis is a prediction model technique in the field of artificial intelligence that studies the relationship between independent and dependent variables. The relationship between variables is obtained by training an initial regression model with sample data; the initial regression model can be a linear regression, multinomial regression, or other models.

[0133] In this embodiment of the application, for each energy efficiency information, the server inputs the historical value of the energy efficiency information and the historical value of the target energy efficiency factor of the energy efficiency information into a preset prediction model to obtain the energy efficiency model of the energy efficiency information, so as to obtain the energy efficiency model of each energy efficiency information.

[0134] Understandably, the server acquires historical values ​​of each energy efficiency information and the historical value of the target energy efficiency factor for each energy efficiency information of the target device. Then, the server can train a prediction model based on these historical values, obtaining the energy efficiency model for the energy efficiency information. In this way, the relationship between the target energy efficiency factor and the energy efficiency information can be determined through the energy efficiency model, allowing for the acquisition of energy efficiency information corresponding to different values ​​of the energy efficiency factor as needed, thus improving the efficiency of energy efficiency assessment.

[0135] The foregoing mainly describes the solutions provided in the embodiments of this application from a methodological perspective. It is understood that the energy efficiency determination device, energy efficiency model training device, or server, in order to achieve the above functions, includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the energy efficiency determination method steps described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0136] This application also provides an energy efficiency determination device. This energy efficiency determination device can be a computer device, a central processing unit (CPU) within the aforementioned computer device, a determination module for determining energy efficiency within the aforementioned computer device, or a client application for determining energy efficiency within the aforementioned computer device.

[0137] This application also provides a training device for an energy efficiency model. This training device can be a computer device, a CPU within the aforementioned computer device, a training module within the aforementioned computer device for training the energy efficiency model, or a client within the aforementioned computer device for training the energy efficiency model.

[0138] This application embodiment can divide the energy efficiency determination device and the energy efficiency model training device into functional modules or functional units according to the above method examples. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0139] like Figure 5 The diagram shown is a structural schematic of an energy efficiency determination device provided in an embodiment of this application. The energy efficiency determination device is used to perform... Figure 2 or Figure 3 The method for determining energy efficiency is shown. The energy efficiency determination apparatus may include an acquisition unit 501 and a processing unit 502.

[0140] The acquisition unit 501 is used to acquire at least one energy efficiency information of the target device, where each energy efficiency information corresponds to one service information of the target device. The processing unit 502 is used to determine the target energy efficiency factor for each energy efficiency information, where the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. The processing unit 502 is also used to, for each energy efficiency information, determine the energy efficiency model of the energy efficiency information based on the energy efficiency information and its target energy efficiency factor, thereby obtaining the energy efficiency model for each energy efficiency information. The processing unit 502 is also used to, for each energy efficiency information, input the benchmark value of the target energy efficiency factor into the energy efficiency model of the energy efficiency information to determine the benchmark value of the energy efficiency information, thereby obtaining the benchmark value for each energy efficiency information. The processing unit 502 is also used to determine the benchmark energy efficiency of the target device based on the benchmark value of each energy efficiency information.

[0141] In one possible design, the acquisition unit 501 is further configured to acquire at least one energy efficiency factor, which is associated with energy efficiency information. The processing unit 502 is further configured to determine an energy efficiency correlation set corresponding to each piece of energy efficiency information, the energy efficiency correlation set including the correlation degree between the energy efficiency information and each energy efficiency factor. The processing unit 502 is further configured to, for each piece of energy efficiency information, compare the correlation degree in the energy efficiency correlation set corresponding to the energy efficiency information with a preset correlation degree threshold to determine the target energy efficiency factor for the energy efficiency information, thereby determining the target energy efficiency factor for each piece of energy efficiency information.

[0142] In one possible design, the processing unit 502 is further configured to determine the energy efficiency level of each energy efficiency information based on the baseline value of the energy efficiency information and the preset energy efficiency range of the energy efficiency information, thereby obtaining the energy efficiency level of each energy efficiency information. The processing unit 502 is also configured to determine the baseline energy efficiency of the target device based on the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information.

[0143] In one possible design, the service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

[0144] In one possible design, the energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

[0145] like Figure 6 The diagram shown is a structural schematic of a training device for an energy efficiency model provided in an embodiment of this application. The energy efficiency model training device is used to execute... Figure 4 The method for determining energy efficiency is shown. The training device for the energy efficiency model may include an acquisition unit 601 and a processing unit 602.

[0146] The acquisition unit 601 is used to acquire the historical values ​​of each energy efficiency information of the target device and the historical values ​​of the target energy efficiency factor of each energy efficiency information. The target energy efficiency factor is the energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. One energy efficiency information corresponds to the service information of one target device. The processing unit 602 is used to input the historical values ​​of the energy efficiency information and the historical values ​​of the target energy efficiency factor of the energy efficiency information into a preset prediction model for each energy efficiency information to obtain the energy efficiency model of the energy efficiency information.

[0147] In one possible design, the acquisition unit 601 is further configured to acquire historical values ​​of at least one service information and historical device energy consumption of the target device. The processing unit 602 is further configured to, for each service information, determine the historical value of each energy efficiency information based on the historical value of each service information and the historical device energy consumption.

[0148] In one possible design, the service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

[0149] In one possible design, the energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

[0150] Figure 7 This is a schematic diagram of the hardware structure of an energy efficiency determination apparatus (or energy efficiency training model) (which may also be a server) according to an exemplary embodiment. The server may include a processor 702, which is used to execute application code to implement the energy efficiency determination method or energy efficiency model training apparatus of this application.

[0151] The processor 702 may be a CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0152] like Figure 7 As shown, the server may further include a memory 703. The memory 703 stores the application code that executes the scheme of this application, and its execution is controlled by the processor 702.

[0153] Memory 703 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 703 may exist independently and be connected to processor 702 via bus 704. Memory 703 may also be integrated with processor 702.

[0154] like Figure 7 As shown, the server may also include a communication interface 701, wherein the communication interface 701, processor 702, and memory 703 may be coupled to each other, for example, through a bus 704. The communication interface 701 is used for information interaction with other devices, for example, supporting information interaction between the server and other devices.

[0155] It should be pointed out that, Figure 7 The device structure shown does not constitute a limitation on the server, except... Figure 7 In addition to the components shown, the server may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0156] In actual implementation, the functions implemented by the processing unit 602 can be derived from... Figure 7 The processor 702 shown calls the program code in memory 703 to implement this.

[0157] This application also provides a computer-readable storage medium storing instructions that, when executed by a processor of a computer device, enable the computer to perform the energy efficiency determination method provided in the embodiments described above. For example, the computer-readable storage medium may be a memory 703 including instructions, which may be executed by a processor 702 of a computer device to complete the method. Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0158] Figure 8 A conceptual partial view of a computer program product provided in an embodiment of this application is shown schematically. The computer program product includes a computer program for executing computer processes on a computing device.

[0159] In one embodiment, the computer program product is provided using a signal bearer medium 800. The signal bearer medium 800 may include one or more program instructions that, when executed by one or more processors, can provide the above-mentioned... Figure 2 , Figure 3 , Figure 4 The described function or part of the function. Therefore, for example, refer to... Figure 2 In the embodiment shown, one or more features of S201 to S205 can be fulfilled by one or more instructions associated with the signal carrying medium 800. Furthermore, Figure 8 The program instructions in the document also describe example instructions.

[0160] In some examples, the signal carrying medium 800 may include a computer-readable medium 801, such as, but not limited to, a hard disk drive, a compact disc (CD), a digital video disc (DVD), a digital magnetic tape, a memory, a read-only memory (ROM), or a random access memory (RAM), etc.

[0161] In some implementations, the signal carrying medium 800 may include a computer recordable medium 802, such as, but not limited to, a memory, a read / write (R / W) CD, a R / W DVD, and so on.

[0162] In some implementations, the signal carrying medium 800 may include a communication medium 803, such as, but not limited to, digital and / or analog communication media (e.g., fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0163] The signal-bearing medium 800 can be transmitted by a wireless communication medium 803. One or more program instructions can be, for example, computer-executable instructions or logical implementation instructions.

[0164] In some examples, such as targeting Figure 7 The described server can be configured to provide various operations, functions, or actions in response to one or more program instructions transmitted through a computer-readable medium 801, a computer-recordable medium 802, and / or a communication medium 803.

[0165] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0167] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the constituent units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0168] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0169] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0170] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of determining energy efficiency, characterized by, The method includes: Acquire at least one energy efficiency information of the target device, wherein each energy efficiency information corresponds to a service information of the target device; the energy efficiency information is used to indicate the relationship between the service information of the target device and energy consumption. Determine the target energy efficiency factor for each of the energy efficiency information, wherein the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold; For each piece of energy efficiency information, an energy efficiency model is determined based on the energy efficiency information and the target energy efficiency factor of the energy efficiency information, so as to obtain an energy efficiency model for each piece of energy efficiency information; For each energy efficiency information, the baseline value of the target energy efficiency factor of the energy efficiency information is input into the energy efficiency model of the energy efficiency information to determine the baseline value of the energy efficiency information, so as to obtain the baseline value of each energy efficiency information; wherein, the baseline value of each target energy efficiency factor is predefined; For each piece of energy efficiency information, the energy efficiency level of the energy efficiency information is determined based on the baseline value of the energy efficiency information and the preset energy efficiency range of the energy efficiency information, so as to obtain the energy efficiency level of each piece of energy efficiency information; Based on the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information, the benchmark energy efficiency of the target device is determined. The benchmark energy efficiency is used to eliminate the evaluation bias caused by the actual difference in energy efficiency factors between different target devices, so as to realize the energy efficiency comparison between different target devices.

2. The method of claim 1, wherein, Determining the target energy efficiency factor for each of the energy efficiency information includes: Obtain at least one energy efficiency factor, which is associated with the energy efficiency information; Determine the energy efficiency correlation set corresponding to each of the energy efficiency information, wherein the energy efficiency correlation set includes: the correlation between the energy efficiency information and each of the energy efficiency factors; For each energy efficiency information, the correlation degree in the energy efficiency correlation degree set corresponding to the energy efficiency information is compared with the preset correlation degree threshold to determine the target energy efficiency factor of the energy efficiency information, thereby determining the target energy efficiency factor of each energy efficiency information.

3. The method according to claim 1 or 2, characterized in that, The service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

4. The method of claim 2, wherein, The energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

5. A method for training an energy efficiency model, the method comprising: The method includes: The historical values ​​of each energy efficiency information of the target device and the historical values ​​of the target energy efficiency factor of each energy efficiency information are obtained. The target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. One energy efficiency information corresponds to one service information of the target device. The energy efficiency information is used to indicate the relationship between the service information of the target device and energy consumption. For each energy efficiency information, the historical value of the energy efficiency information and the historical value of the target energy efficiency factor of the energy efficiency information are input into a preset prediction model to obtain the energy efficiency model of the energy efficiency information. Each energy efficiency information corresponds to a preset energy efficiency range and a preset weighting coefficient. The energy efficiency model is used to determine the benchmark value of the energy efficiency information based on the benchmark value of the target energy efficiency factor, wherein the benchmark value of each target energy efficiency factor is predefined. The benchmark value of the energy efficiency information and the preset weighting coefficient of the energy efficiency information are used to determine the energy efficiency level of the energy efficiency information, and the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information are used to determine the benchmark energy efficiency of the target device. The benchmark energy efficiency is used to eliminate the evaluation deviation caused by the actual difference of energy efficiency factors between different target devices, so as to realize the energy efficiency comparison between different target devices.

6. The method according to claim 5, characterized in that, Obtaining historical values ​​for each of the energy efficiency information items, including: Obtain historical values ​​of at least one of the service information and historical device energy consumption of the target device; For each of the service information, the historical value of each energy efficiency information is determined based on the historical value of each service information and the historical energy consumption of the device.

7. The method according to claim 5 or 6, characterized in that, The service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

8. The method according to claim 5 or 6, characterized in that, The energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

9. An energy efficiency determination device, characterized in that, The device includes: An acquisition unit is configured to acquire at least one energy efficiency information of a target device, wherein one piece of energy efficiency information corresponds to one piece of service information of the target device, and the energy efficiency information is used to indicate the relationship between the service information of the target device and energy consumption. The processing unit is configured to determine a target energy efficiency factor for each of the energy efficiency information, wherein the target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. The processing unit is further configured to, for each energy efficiency information, determine the energy efficiency model of the energy efficiency information based on the energy efficiency information and the target energy efficiency factor of the energy efficiency information, so as to obtain the energy efficiency model of each energy efficiency information; The processing unit is further configured to, for each energy efficiency information, input the benchmark value of the target energy efficiency factor of the energy efficiency information into the energy efficiency model of the energy efficiency information, determine the benchmark value of the energy efficiency information, and obtain the benchmark value of each energy efficiency information; wherein, the benchmark value of each target energy efficiency factor is predefined; The processing unit is further configured to determine the energy efficiency level of each energy efficiency information based on the baseline value of the energy efficiency information and the preset energy efficiency range of the energy efficiency information, so as to obtain the energy efficiency level of each energy efficiency information; The processing unit is further configured to determine the benchmark energy efficiency of the target device based on the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information, wherein the benchmark energy efficiency is used to eliminate the evaluation deviation caused by the actual difference in energy efficiency factors between different target devices, so as to realize the energy efficiency comparison between different target devices.

10. The apparatus according to claim 9, characterized in that, The acquisition unit is further configured to acquire at least one energy efficiency factor, which is associated with the energy efficiency information; The processing unit is further configured to determine an energy efficiency correlation set corresponding to each energy efficiency information, wherein the energy efficiency correlation set includes: the correlation between the energy efficiency information and each energy efficiency factor; The processing unit is further configured to, for each energy efficiency information, compare the correlation degree in the energy efficiency correlation degree set corresponding to the energy efficiency information with the preset correlation degree threshold, and determine the target energy efficiency factor of the energy efficiency information, so as to determine the target energy efficiency factor of each energy efficiency information.

11. The apparatus according to claim 9 or 10, characterized in that, The service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

12. The apparatus according to claim 9, characterized in that, The energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

13. A training device for an energy efficiency model, characterized in that, The device includes: The acquisition unit is used to acquire the historical value of each energy efficiency information of the target device and the historical value of the target energy efficiency factor of each energy efficiency information. The target energy efficiency factor is an energy efficiency factor whose correlation with the energy efficiency information is greater than a preset correlation threshold. One energy efficiency information corresponds to one service information of the target device. The energy efficiency information is used to indicate the relationship between the service information of the target device and energy consumption. The processing unit is configured to input the historical value of the energy efficiency information and the historical value of the target energy efficiency factor of the energy efficiency information into a preset prediction model for each energy efficiency information to obtain the energy efficiency model of the energy efficiency information. Each energy efficiency information corresponds to a preset energy efficiency range and a preset weighting coefficient. The energy efficiency model is used to determine the benchmark value of the energy efficiency information based on the benchmark value of the target energy efficiency factor, wherein the benchmark value of each target energy efficiency factor is predefined. The benchmark value of the energy efficiency information and the preset weighting coefficient of the energy efficiency information are used to determine the energy efficiency level of the energy efficiency information, and the energy efficiency level of each energy efficiency information and the preset weighting coefficient of each energy efficiency information are used to determine the benchmark energy efficiency of the target device. The benchmark energy efficiency is used to eliminate the evaluation deviation caused by the actual difference of energy efficiency factors between different target devices, so as to realize the energy efficiency comparison between different target devices.

14. The apparatus according to claim 13, characterized in that, The acquisition unit is also used to acquire at least one historical value of the service information and historical device energy consumption of the target device; The processing unit is further configured to determine the historical value of each energy efficiency information based on the historical value of each service information and the historical device energy consumption for each service information.

15. The apparatus according to claim 13 or 14, characterized in that, The service information includes at least one of the following: service traffic, number of connected users, service perceived quality, and coverage.

16. The apparatus according to claim 13, characterized in that, The energy efficiency factors include at least one of the following: climate factor, load factor, business factor, and user factor.

17. An energy efficiency determination device, characterized in that, include: Processor and memory; The processor and the memory are coupled; The memory is used to store one or more programs, the one or more programs including computer-executable instructions, which, when the energy efficiency determining device is running, are executed by the processor to execute the computer-executable instructions stored in the memory to cause the energy efficiency determining device to perform the method as described in any one of claims 1-4.

18. A training device for an energy efficiency model, characterized in that, include: Processor and memory; The processor and the memory are coupled; The memory is used to store one or more programs, the one or more programs including computer-executable instructions, which, when the training of the energy efficiency model is running, are executed by the processor to execute the computer-executable instructions stored in the memory to cause the training device of the energy efficiency model to perform the method as described in any one of claims 5-8.

19. A computer-readable storage medium storing instructions, characterized in that, When the computer executes the instruction, the computer performs the method as described in any one of claims 1-8.

Images