Energy-saving method and device for base station, and computer-readable storage medium

Abstract

Provided in the embodiments of the present description are an energy-saving method and device for a base station, and a computer-readable storage medium. The method comprises: acquiring a total-power-consumption prediction model of a base station, wherein the total-power-consumption prediction model is determined on the basis of a power consumption prediction model of a main device of the base station and a power consumption prediction model of a supporting device of the base station; within an adjustable range of an adjustable operating parameter of the supporting device, optimizing the adjustable operating parameter of the supporting device at a target time, and thus the estimated total power consumption, which is predicted on the basis of the total-power-consumption prediction model, of the base station at the target time is the lowest, and taking as a target operating value the adjustable operating parameter when the estimated total power consumption is the lowest; and on the basis of the target operating value of the adjustable operating parameter, adjusting an operating value of the adjustable operating parameter of the supporting device at the target time.

Description

A base station energy-saving method, device and computer-readable storage medium

[0001] Cross-references

[0002] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on July 31, 2023, with application number 202310960471.6 and invention name “A method, device and computer-readable storage medium for energy saving of a base station”. The entire contents of the application are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the field of mobile communication technologies, and in particular to a method and device for energy saving of a base station, and a computer-readable storage medium. Background Art

[0004] In mobile communications network operations, electricity costs are one of the largest network maintenance costs for operators. For example, with the rapid development of 5G networks, 5G's high bandwidth, ultra-low latency, and massive connectivity will usher in an era of the Internet of Everything. While this will bring endless opportunities, it will also significantly increase base station power consumption, which will not only consume a large amount of electricity but also increase operators' operating costs.

[0005] Therefore, how to effectively reduce the energy consumption of base stations is a technical problem that needs to be solved urgently.

[0006] Summary of the Invention

[0007] In a first aspect, a method for saving energy of a base station is provided, comprising: obtaining a total power consumption prediction model of the base station, wherein the total power consumption prediction model is determined based on a main device power consumption prediction model and an auxiliary device power consumption prediction model of the base station; optimizing the adjustable working parameters of the auxiliary device at a target time within an adjustable range of the adjustable working parameters of the auxiliary device, so that the estimated total power consumption of the base station at the target time predicted according to the total power consumption prediction model is the lowest, and taking the adjustable working parameters when the estimated total power consumption is the lowest as the target working value; adjusting the working value of the adjustable working parameters of the auxiliary device at the target time according to the target working value of the adjustable working parameter.

[0008] In a second aspect, an energy-saving device for a base station is provided, comprising: a model acquisition module for acquiring a total power consumption prediction model of the base station, wherein the total power consumption prediction model is determined based on a main device power consumption prediction model and an auxiliary device power consumption prediction model of the base station; a parameter value optimization module for optimizing the adjustable working parameters of the auxiliary device at a target time within an adjustable range of the adjustable working parameters of the auxiliary device, so as to minimize the estimated total power consumption of the base station at the target time predicted according to the total power consumption prediction model, and taking the adjustable working parameters when the estimated total power consumption is minimized as the target working value; and a working value adjustment module for adjusting the working value of the adjustable working parameters of the auxiliary device at the target time according to the target working value of the adjustable working parameters.

[0009] According to a third aspect, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the method described in the first aspect.

[0010] In a fourth aspect, a computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0012] FIG1 is a flow chart of a method for energy saving of a base station provided in an embodiment of this specification.

[0013] FIG2 is a schematic flow chart of a base station energy saving method provided in another embodiment of this specification.

[0014] FIG3 is a schematic diagram of an implementation structure of a base station energy saving method provided in an embodiment of this specification.

[0015] FIG4 is a schematic diagram of another implementation structure of a base station energy saving method provided in an embodiment of this specification.

[0016] FIG5 is a schematic structural diagram of an electronic device according to an embodiment of the present specification.

[0017] FIG6 is a schematic structural diagram of an energy-saving device of a base station according to an embodiment of this specification.

[0018] FIG7 is a schematic structural diagram of an energy-saving device of a base station according to another embodiment of this specification. DETAILED DESCRIPTION

[0019] In order to help those skilled in the art better understand the technical solutions in the embodiments of this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0020] The terms "first," "second," and the like in this specification and claims are used to distinguish similar objects and are not intended to describe a particular order or precedence. It should be understood that such terms are interchangeable where appropriate, so that the embodiments of this specification can be implemented in orders other than those illustrated or described herein. Furthermore, the term "and / or" in this specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the connected objects are in an "or" relationship.

[0021] In order to effectively reduce the energy consumption of base stations, the embodiments of this specification propose a base station energy-saving method. This method can be executed by the base station itself (see Figure 4) or by a centralized processing unit independent of the base station (see Figure 3), such as a network management system, mobile edge computing, or multi-access edge computing (MEC). The centralized or distributed processing unit can obtain information such as user load, energy-saving strategies, air conditioning, and power supply in the jurisdiction to generate a comprehensive energy-saving strategy for the entire station.

[0022] The energy-saving method for a base station provided in an embodiment of this specification aims to coordinately adjust the working parameter values ​​of supporting equipment such as air conditioners according to the load and energy-saving strategy of the main equipment in the base station (the energy-saving strategy of the base station itself), thereby reducing the total power consumption of the base station as a whole and achieving the goal of optimizing the overall energy consumption of the entire station equipment.

[0023] The following describes in detail a base station energy saving method proposed in an embodiment of this specification.

[0024] As shown in FIG1 , an embodiment of this specification provides a base station energy saving method, including steps 101 to 105 .

[0025] In step 101, a total power consumption prediction model of a base station is obtained, wherein the total power consumption prediction model is determined based on a main device power consumption prediction model and an auxiliary device power consumption prediction model of the base station.

[0026] The main equipment of the base station includes a cabinet; the supporting equipment of the base station includes a cabinet air conditioner and / or a computer room air conditioner. Exemplarily, the supporting equipment of the base station includes power supply equipment, etc.

[0027] Among them, the main equipment power consumption prediction model and the supporting equipment power consumption prediction model of the base station are pre-built based on relevant sample data.

[0028] Some base stations have both computer room and cabinet air conditioners, while others only have cabinet air conditioners. For both scenarios, the models that need to be pre-built include: a base station load prediction model, a cabinet power consumption prediction model, a computer room air conditioner prediction model, and a cabinet air conditioner prediction model. Cabinet power consumption refers to the power consumption of the base station itself or its main equipment. Computer room air conditioners are installed outside the cabinet in the base station's computer room, while cabinet air conditioners are installed inside the base station's cabinet.

[0029] The following is a brief introduction to the construction process of the above model.

[0030] First, collect relevant information for modeling.

[0031] The relevant information includes but is not limited to at least one of the following information.

[0032] 1) Base station information, including but not limited to:

[0033] a. User load information, including but not limited to the number of users, uplink and downlink physical resource blocks (PRBs), PRB utilization, uplink and downlink throughput, uplink and downlink user rates, etc.

[0034] b. Energy consumption information.

[0035] c. Cabinet board temperature information.

[0036] d. Cabinet fan speed information.

[0037] 2) Air conditioning information, including but not limited to: ambient temperature and air conditioning temperature information.

[0038] 3) Public network weather and meteorological information.

[0039] When there is an interface with the external public network, weather and forecast information of the area can be crawled, including temperature, weather, humidity, etc.

[0040] 4) Power consumption information, etc.

[0041] Secondly, modeling is performed based on the collected relevant information.

[0042] 1) Modeling of load forecasting model.

[0043] A load forecasting model is constructed based on the historical load time series of the base station.

[0044] Specifically, a load forecasting model is constructed based on the user load information of each cell under a base station using a specific time series modeling method. This model can predict the user load of the base station at a specific time or time period in the future. The load forecasting model can be constructed using time series-based predictive modeling methods such as long short-term memory (LSTM) and autoregressive integrated moving average (ARIMA).

[0045] 2) Construction of cabinet power consumption prediction model.

[0046] The examples in this specification have found that the cabinet's power consumption is related to factors such as the actual base station load (number of users, etc.), the base station's energy-saving strategy, and the cabinet temperature. The higher the actual base station load, the more baseband resources the base station uses, the higher the cabinet temperature, and the corresponding cabinet power consumption. Furthermore, the cabinet's power consumption is also affected by the base station's own energy-saving strategy. When a cell in the base station implements an energy-saving strategy such as sleep, the cabinet's power consumption will decrease.

[0047] Therefore, as an example, a cabinet power consumption prediction model is trained based on first sample data, wherein the first sample data may include but is not limited to the historical load of the base station, the historical temperature of the cabinet of the base station, the historical energy-saving strategy of the cabinet, and the historical power consumption of the cabinet.

[0048] Among them, the historical load of the base station is determined based on the user load information collected above; the historical energy-saving strategy of the cabinet refers to the historical energy-saving strategy of the base station itself, specifically refers to the carrier shutdown, deep sleep and other strategies executed by the base station based on the actual load; the historical power consumption of the cabinet refers to the power consumption of the main equipment of the base station, and this data can also be obtained from the relevant information collected above.

[0049] The constructed cabinet power consumption prediction model can be expressed as: nbPower(load, esDuration, temp), where load represents the load of the base station, esDuration represents the energy-saving strategy of the base station, and temp represents the temperature of the cabinet (specifically, the temperature of the cabinet board).

[0050] Exemplarily, the basic model for constructing the cabinet power consumption prediction model includes a neural network or a general regression model.

[0051] Because cabinet power consumption varies between base station models, the base station model can be incorporated into the first sample data, taking the base station model into account in modeling to improve the accuracy of the prediction results provided by the constructed model. Alternatively, different cabinet power consumption prediction models can be constructed for different base station models, which can also improve the accuracy of the prediction results provided by the constructed model.

[0052] 3) Construction of cabinet air conditioner power consumption prediction model.

[0053] Air conditioner power consumption is primarily affected by indoor and outdoor temperatures and the air conditioner's cooling temperature (return air temperature). Higher indoor temperatures and / or lower return air temperature settings increase air conditioner power consumption. Therefore, air conditioner power consumption can be modeled based on these factors.

[0054] As an example, a cabinet air conditioner power consumption prediction model may be trained based on second sample data, wherein the second sample data includes but is not limited to historical operating values ​​of adjustable operating parameters of the cabinet air conditioner, ambient temperature, and historical power consumption.

[0055] Exemplarily, the basic model for constructing the cabinet air conditioner power consumption prediction model includes a neural network or a general regression model.

[0056] Since the air conditioning cooling conditions are also related to factors such as humidity, cabinet size and cabinet material, these factors can also be introduced into the above second sample data to improve the accuracy of the prediction results given by the constructed cabinet power consumption prediction model.

[0057] 4) Construction of computer room air conditioning power consumption prediction model.

[0058] Like cabinet air conditioners, the power consumption of computer room air conditioners is primarily affected by the indoor and outdoor temperatures and the air conditioner's cooling temperature (return air temperature). Higher indoor temperatures and / or lower return air temperature settings increase the air conditioner's power consumption. Therefore, air conditioner power consumption can be modeled based on these factors.

[0059] As an example, a computer room air conditioner power consumption prediction model may be trained based on third sample data, wherein the third sample data includes historical operating values ​​of adjustable operating parameters of the computer room air conditioner, ambient temperature, and historical power consumption.

[0060] Exemplarily, the basic model for constructing the computer room air conditioner power consumption prediction model includes a neural network or a general regression model.

[0061] Since the air conditioning cooling conditions are also related to factors such as humidity, cabinet size, and cabinet material (the material of the computer room's exterior wall affects the heat conduction of outdoor temperature), these factors can also be introduced into the above-mentioned third sample data to improve the accuracy of the prediction results given by the constructed cabinet power consumption prediction model.

[0062] 5) Construction of cabinet temperature prediction model.

[0063] The cabinet temperature refers to the temperature of the cabinet itself, such as the temperature of a cabinet board. The cabinet temperature is related to the temperature of the cabinet air conditioner and / or the computer room air conditioner. Therefore, as an example, a cabinet temperature prediction model for the base station can be trained based on fourth sample data, where the fourth sample data includes historical set temperatures of the cabinet air conditioner and / or the computer room air conditioner of the base station, as well as historical cabinet temperatures.

[0064] After building the power consumption prediction models for the base station's main equipment and supporting equipment, you can use these models to determine the base station's total power consumption model. Specifically, depending on whether the base station's supporting equipment includes the computer room air conditioner (CRA), there are two scenarios:

[0065] Case 1: The supporting equipment of the base station includes cabinet air conditioners and computer room air conditioners.

[0066] In the case where the base station is equipped with a computer room air conditioner and a cabinet air conditioner, the main equipment power consumption prediction model includes a cabinet power consumption prediction model, the supporting equipment power consumption prediction model includes a computer room air conditioner power consumption prediction model and a cabinet air conditioner power consumption prediction model, and the total power consumption prediction model is determined based on the cabinet power consumption prediction model, the computer room air conditioner power consumption prediction model and the cabinet air conditioner power consumption prediction model.

[0067] Specifically, the pre-built cabinet power consumption prediction model, the computer room air conditioner power consumption prediction model and the cabinet air conditioner power consumption prediction model are obtained; the cabinet power consumption prediction model, the computer room air conditioner power consumption prediction model and the cabinet air conditioner power consumption prediction model are added together to obtain the total power consumption prediction model.

[0068] At this time, illustratively, the total power consumption prediction model can be expressed as:

[0069] in, Indicates the total power consumption, represents the operating value (set temperature) of the i-th cabinet air conditioner at time t, where i ranges from 0 to N, and N is the number of cabinet air conditioners; Indicates the operating value (set temperature) of the jth computer room air conditioner at time t. The value of j ranges from 0 to M, where M is the number of computer room air conditioners.

[0070] in, represents the cabinet power consumption prediction model, represents the load of the base station corresponding to the i-th cabinet at time t, represents the energy-saving duration of the base station corresponding to the i-th cabinet at time t, represents the temperature of the i-th cabinet at time t.

[0071] As an example, if t is a time in the future, then: It can be the load of the base station corresponding to the i-th cabinet at time t predicted by the above load prediction model, that is, the energy-saving strategy of the base station at the target time is determined based on the predicted load of the base station at time t, Can be based on predictions And the energy-saving duration corresponding to the i-th cabinet obtained by the energy-saving strategy of the base station itself, It can represent the temperature of the i-th cabinet at time t predicted by the above cabinet temperature prediction model.

[0072] As another example, if t is a time in the future near the current time, then: It can be the load of the i-th cabinet at the current moment measured in real time, It can be the energy-saving duration used by the base station at the current moment measured in real time, The temperature of the i-th cabinet at the current moment can be measured in real time.

[0073] in, represents the cabinet air conditioner power consumption prediction model, Indicates the temperature in the equipment room (indoor temperature) at time t, which can be calculated based on the statistics of the most recent measurement results of historical measurements.

[0074] in, represents the power consumption prediction model of the computer room air conditioner, Indicates the temperature outside the computer room at time t (outdoor temperature). If a web interface exists, it can be obtained based on the crawled weather forecast information. If there is no web interface, the weather data of the same period in history and the weather data of the recent days can be combined and calculated by weight.

[0075] Case 2: The supporting equipment of the base station includes cabinet air conditioners but does not include computer room air conditioners.

[0076] In the case that the base station is only equipped with a cabinet air conditioner, the main equipment power consumption prediction model includes a cabinet power consumption prediction model, the supporting equipment power consumption prediction model includes a cabinet air conditioner power consumption prediction model, and the total power consumption prediction model is determined based on the cabinet power consumption prediction model and the cabinet air conditioner power consumption prediction model.

[0077] Specifically, the pre-built cabinet power consumption prediction model and the cabinet air conditioner power consumption prediction model are obtained; and the cabinet power consumption prediction model and the cabinet air conditioner power consumption prediction model are added together to obtain the total power consumption prediction model.

[0078] At this time, illustratively, the total power consumption prediction model can be expressed as:

[0079] in, Indicates the total power consumption, represents the operating value (set temperature) of the i-th cabinet air conditioner at time t, where i ranges from 0 to N, and N is the number of cabinet air conditioners; Indicates the operating value (set temperature) of the jth computer room air conditioner at time t. The value of j ranges from 0 to M, where M is the number of computer room air conditioners.

[0080] in, represents the cabinet power consumption prediction model, represents the load of the base station corresponding to the i-th cabinet at time t, represents the energy-saving duration of the base station corresponding to the i-th cabinet at time t, represents the temperature of the i-th cabinet at time t.

[0081] As an example, if t is a time in the future, then: It can be the load of the base station corresponding to the i-th cabinet at time t predicted by the above load prediction model, Can be based on predictions and the energy-saving duration corresponding to the i-th cabinet obtained by the energy-saving strategy of the base station itself, that is, the energy-saving strategy of the base station at the target time is determined based on the predicted load of the base station at time t, It can represent the temperature of the i-th cabinet at time t predicted by the above cabinet temperature prediction model.

[0082] As another example, if t is the current time, then: It can be the load of the i-th cabinet at the current moment measured in real time, It can be the energy-saving duration used by the base station at the current moment measured in real time, The temperature of the i-th cabinet at the current moment can be measured in real time.

[0083] in, represents the cabinet air conditioner power consumption prediction model, Indicates the temperature in the equipment room (indoor temperature) at time t, which can be calculated based on the statistics of the most recent measurement results of historical measurements.

[0084] In step 102, within the adjustable range of the adjustable working parameters of the supporting equipment, the adjustable working parameters of the supporting equipment at the target time are optimized so that the estimated total power consumption of the base station at the target time predicted by the total power consumption prediction model is the lowest, and the adjustable working parameters when the estimated total power consumption is the lowest are used as the target working values.

[0085] The target time can be one or more moments or a time period. The target time can be a time in the future that is far from the current moment, or a time that is close to the current moment. The time granularity and time period of the target time can be determined based on actual application requirements.

[0086] Exemplarily, for the above-described situation 1, predicting the estimated total power consumption of the base station at the target time according to the total power consumption prediction model includes:

[0087] Predicting a first predicted power consumption of the cabinet at the target time according to the load of the base station at the target time, the temperature of the cabinet of the base station at the target time, the energy-saving strategy of the base station at the target time, and the cabinet power consumption prediction model;

[0088] Predicting a second predicted power consumption of the cabinet air conditioner at the target time based on the indoor temperature of the computer room where the base station is located at the target time, the operating temperature of the cabinet air conditioner at the target time, and the cabinet air conditioner power consumption prediction model;

[0089] Predicting a third predicted power consumption of the computer room air conditioner at the target time based on the outdoor temperature of the computer room where the base station is located at the target time, the operating temperature of the computer room air conditioner at the target time, and the computer room air conditioner power consumption prediction model;

[0090] The first predicted power consumption, the second predicted power consumption and the third predicted power consumption are added together to obtain the estimated total power consumption of the base station at the target time.

[0091] Exemplarily, for the above-described situation 2, predicting the estimated total power consumption of the base station at the target time according to the total power consumption prediction model includes:

[0092] Based on the load of the base station at the target time, the temperature of the cabinet of the base station at the target time, the energy-saving strategy of the base station at the target time, and the cabinet power consumption prediction model, the first predicted power consumption of the cabinet at the target time is predicted; based on the indoor temperature of the computer room where the base station is located at the target time, the operating temperature of the cabinet air conditioner at the target time, and the cabinet air conditioner power consumption prediction model, the second predicted power consumption of the cabinet air conditioner at the target time is predicted; the first predicted power consumption and the second predicted power consumption are added to obtain the estimated total power consumption of the base station at the target time.

[0093] In the above two situations, as an example, if the target time is a future moment far away from the current moment, then: the load of the base station at the target time is predicted by the load prediction model, and the energy-saving strategy of the base station at the target time is determined based on the predicted load of the base station at the target time, and the temperature of the cabinet of the base station at the target time is predicted by the above cabinet temperature prediction model.

[0094] In the above two cases, as another example, if the target time is a future moment close to the current moment, then: the load of the base station at the target time can be the load of the base station at the current moment measured in real time, the energy-saving strategy of the base station at the target time can be the energy-saving duration adopted by the base station at the current moment measured in real time, and the temperature of the cabinet of the base station at the target time can be the temperature of the cabinet at the current moment measured in real time.

[0095] From the above description, it can be found that the estimated total power consumption of the base station is the sum of the cabinet power consumption and the power consumption of the supporting equipment. It can be understood that for the supporting equipment of the base station - the cabinet air conditioner and / or the computer room air conditioner, when the air conditioner operating temperature is set high, the air conditioner power consumption decreases, but the cabinet power consumption increases; conversely, when the air conditioner operating temperature is set low, the air conditioner power consumption increases and the cabinet power consumption decreases. Therefore, the operating value of the cabinet air conditioner and / or the computer room air conditioner that makes the estimated total power consumption the lowest at the target time can be found through optimization, that is, the operating value of the cabinet air conditioner and / or the computer room air conditioner that makes the estimated total power consumption the lowest at the target time can be found. and value.

[0096] For supporting equipment such as computer room air conditioners and cabinet air conditioners, since their adjustable working parameters often include multiple items, the adjustable range of each adjustable working parameter includes several optional values. For example, if the cabinet air conditioner is an air-cooled air conditioner, the adjustable working parameters of the cabinet air conditioner include at least one of temperature and wind speed; if the cabinet air conditioner is a liquid-cooled air conditioner, the adjustable working parameters of the cabinet air conditioner include at least one of temperature and liquid flow rate; similarly, if the computer room air conditioner is an air-cooled air conditioner, the adjustable working parameters of the computer room air conditioner include at least one of temperature and wind speed; if the computer room air conditioner is a liquid-cooled air conditioner, the adjustable working parameters of the computer room air conditioner include at least one of temperature and liquid flow rate. Therefore, if the optimal solution is found by enumeration, the amount of calculation is huge and not very realistic. Therefore, the embodiment of this specification proposes solving the target working value of the adjustable working parameter corresponding to the lowest estimated total power consumption based on a preset optimization algorithm.

[0097] Specifically, step 102 may include optimizing the adjustable operating parameters of the accessory device at the target time within the adjustable range of the adjustable operating parameters of the accessory device according to a preset optimization algorithm. More specifically, within the adjustable range of the adjustable operating parameters of the accessory device, the preset optimization algorithm is used to continuously adjust the operating values ​​of the adjustable operating parameters and input them into the total power consumption prediction model to find the target operating value of the adjustable operating parameter that minimizes the estimated total power consumption output by the total power consumption prediction model.

[0098] The preset optimization algorithm includes but is not limited to one of a genetic algorithm, an ant colony algorithm, a simulated annealing algorithm, a particle swarm optimization algorithm and a differential evolution algorithm.

[0099] Taking the genetic algorithm as an example, the following briefly describes the process of continuously adjusting the working value of the adjustable working parameter within the adjustable range of the adjustable working parameter of the supporting equipment and inputting it into the total power consumption prediction model to find the target working value of the adjustable working parameter that makes the estimated total power consumption output by the total power consumption prediction model the lowest, as shown in the following details.

[0100] (1) Initialize A Xs, where X represents a value of an adjustable operating parameter of the supporting equipment (cabinet air conditioner and / or cabinet air conditioner and computer room air conditioner), and A is an integer greater than 1.

[0101] (2) A Xs are input into the total power consumption prediction model respectively, and A estimated total power consumptions are output. The A Xs are evaluated and sorted according to the A estimated total power consumptions, and the top B better Xs (Xs with lower estimated total power consumptions) are selected as the candidate set.

[0102] (3) Within the adjustable range of the adjustable working parameters of the supporting equipment, the genes of X in the candidate set are exchanged to generate some new X.

[0103] (4) Within the adjustable range of the adjustable working parameters of the supporting equipment, the genes of X in the candidate set are changed to generate some new X.

[0104] (5) Return to (2), taking one round as a generation, and taking N generations as the termination condition, and output the best X.

[0105] It is understood that the best X is the estimated operating value of the cabinet air conditioner and / or computer room air conditioner with the lowest total power consumption.

[0106] In step 103, the operating value of the adjustable operating parameter of the supporting equipment at the target time is adjusted according to the target operating value of the adjustable operating parameter.

[0107] Wherein, adjusting the operating value of the adjustable operating parameter of the supporting equipment at the target time according to the target operating value of the adjustable operating parameter may include:

[0108] Based on the target operating value of the adjustable operating parameter, an energy-saving strategy is generated to adjust the operating value of the adjustable operating parameter of the supporting equipment at the target time; before the target time, the energy-saving strategy is sent to the air-conditioning adjustment module, so that the air-conditioning adjustment module reduces the actual total power consumption of the base station at the target time by executing the energy-saving strategy.

[0109] The air conditioning adjustment module may be a functional module of the base station, such as the air conditioning temperature adjustment module 4014 located in the base station / cabinet 400, as shown in FIG4 . The air conditioning adjustment module may also be a functional module independent of the base station, such as the air conditioning temperature adjustment module 3032 located in the air conditioning environment unit 303, as shown in FIG3 .

[0110] Specifically, the energy-saving strategy is sent to the air conditioning adjustment module before the target time so that the air conditioning adjustment strategy can be adjusted according to the strategy when the target time is reached, rather than obtaining the strategy only when the target time is reached.

[0111] An energy-saving method for a base station provided in an embodiment of this specification, on the one hand, in addition to the power consumption of the main device, the power consumption of the supporting equipment is also included in the consideration of reducing the total power consumption of the base station; on the other hand, after obtaining the total power consumption prediction model of the base station, the estimated total power consumption of the base station at the target time is predicted according to the total power consumption prediction model within the adjustable range of the adjustable working parameters of the supporting equipment, and optimization is performed to find the target working value of the adjustable working parameter that makes the estimated total power consumption lowest; and according to the target working value of the adjustable working parameter, the working value of the adjustable working parameter of the supporting equipment at the target time is dynamically adjusted, so that the total power consumption of the base station is minimized, thereby effectively reducing the energy consumption of the base station.

[0112] As shown in FIG2 , in another embodiment, if the target time includes a future time adjacent to the current time, the energy saving method for a base station provided in this specification may further include steps 104 and 105 before step 103 .

[0113] In step 104, the actual total power consumption of the base station at the current moment is obtained.

[0114] In step 105 , it is determined whether the minimum estimated total power consumption is less than the actual total power consumption. If so, step 103 is executed; otherwise, the process returns to step 102 or ends the process.

[0115] That is, when the minimum estimated total power consumption is less than the actual total power consumption, the operating value of the adjustable operating parameter of the accessory device at the target time is adjusted according to the target operating value of the adjustable operating parameter. It can be understood that if the actual total power consumption at the current moment is already lower than the minimum estimated total power consumption, then it may not be necessary to adjust the operating value of the adjustable operating parameter of the accessory device for the time in the future adjacent to the current moment; if the actual total power consumption at the current moment is not lower than or is much higher than the minimum estimated total power consumption, then it is necessary to adjust the operating value of the adjustable operating parameter of the accessory device for the time in the future adjacent to the current moment to reduce the actual total power consumption.

[0116] In an optional implementation, the supporting equipment of the base station further includes a power supply device, and the supporting equipment power consumption prediction model further includes a power supply device power consumption prediction model. Before step 102, the energy-saving method of the base station provided in the embodiment of this specification may further include:

[0117] The power supply device power consumption prediction model is added as a sum item to the total power consumption prediction model.

[0118] Accordingly, in step 102, the estimated total power consumption of the base station at the target time also includes a fourth predicted power consumption predicted by the power supply device power consumption prediction model. Furthermore, through optimization, a target operating value of an adjustable operating parameter of the power supply device is obtained that minimizes the estimated total power consumption of the base station at the target time.

[0119] Correspondingly, in step 103 , the operating value of the adjustable operating parameter of the power supply device at the target time may also be adjusted according to the target operating value of the adjustable operating parameter of the power supply device.

[0120] The adjustable operating parameters of the power supply device include at least one of the number of power supplies, the voltage of the power supply device, and the current of the power supply device.

[0121] It can be understood that in addition to considering the impact of cabinet air conditioners and / or computer room air conditioners on the total power consumption of the base station, incorporating power supply equipment into the scope of base station energy conservation considerations can more comprehensively and effectively reduce the total power consumption of the base station and achieve the goal of optimizing the overall energy consumption of the entire station equipment.

[0122] In addition, as mentioned above, a base station energy-saving method provided in an embodiment of this specification can be executed by the base station itself or by a centralized processing unit independent of the base station, such as a network management, mobile edge computing, or multi-access edge computing (Mobile Edge Computing / Muti-access Edge Computing, MEC), which is briefly described below in conjunction with Figures 3 and 4.

[0123] In one embodiment, several processing units independent of the base station can be used as the execution entities of a base station energy-saving method provided in the embodiments of this specification. As shown in Figure 3, a centralized processing unit 301 and an air conditioning environment unit 303 can be set up outside the base station 302. The base station 302 and the air conditioning environment unit 303 are respectively connected to the centralized processing unit 301 via interfaces.

[0124] The centralized processing unit 301 may include: an information collection and modeling module 3011 for collecting and modeling relevant information, for example, receiving information reported by the air conditioning environment unit 303 and the base station 302; an energy-saving strategy generation module 3012 for generating an energy-saving strategy for the base station itself and delivering it to the base station 302; and an air conditioning strategy generation module 3012 for generating an air conditioning energy-saving strategy and delivering it to the air conditioning environment unit 303.

[0125] The base station 302 may include: a base station load monitoring module 3021 for detecting information such as the base station load and reporting it to the central processing unit 301; and an energy-saving strategy execution module 3022 for executing the energy-saving strategy issued by the central processing unit.

[0126] The air conditioning environment unit 303 may include: an ambient temperature monitoring module 3031 for monitoring ambient temperature information and its own operating value and reporting it to the central processing unit 301; an air conditioning temperature adjustment module 3032 for adjusting the air conditioning operating value according to the air conditioning energy saving strategy issued by the central processing unit 301.

[0127] In another embodiment, the base station may be used as the executing entity of a base station energy-saving method provided in an embodiment of this specification. As shown in Figure 4, the following functional modules may be set in the base station 400: an information collection and modeling module 4011, which is used to collect relevant information and model it. For details, please refer to the description of step 101 in Figure 1 above. An energy-saving strategy generation module 4012, which is used to generate an energy-saving strategy for the base station itself. An air-conditioning strategy generation module 4013, which is used to generate an air-conditioning energy-saving strategy. For details, please refer to the description of steps 102 and 103 in Figure 1 above. An air-conditioning temperature adjustment module 4014, which is used to adjust the working value of the air-conditioning according to the air-conditioning energy-saving strategy generated by the air-conditioning strategy generation module 4013.

[0128] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] FIG5 is a schematic diagram of the structure of an electronic device according to an embodiment of the present specification. Referring to FIG5 , at the hardware level, the electronic device includes a processor; in an optional embodiment, the electronic device also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include hardware required for other services.

[0130] The processor, network interface, and memory can be interconnected via an internal bus, such as an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. These buses can be categorized as address buses, data buses, and control buses. For ease of illustration, FIG5 shows only one bidirectional arrow, but this does not imply that there is only one bus or only one type of bus.

[0131] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0132] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming the energy-saving device of the base station at the logical level. The processor executes the program stored in the memory and is specifically responsible for performing the following operations.

[0133] Obtain a total power consumption prediction model of the base station, wherein the total power consumption prediction model is determined based on a main device power consumption prediction model and an auxiliary device power consumption prediction model of the base station; within an adjustable range of the adjustable working parameters of the auxiliary device, optimize the adjustable working parameters of the auxiliary device at the target time so that the estimated total power consumption of the base station at the target time predicted according to the total power consumption prediction model is the lowest, and use the adjustable working parameters when the estimated total power consumption is the lowest as the target working value; according to the target working value of the adjustable working parameter, adjust the working value of the adjustable working parameter of the auxiliary device at the target time.

[0134] The method performed by the energy-saving device of the base station disclosed in the embodiment shown in Figure 5 of this specification can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by the hardware integrated logic circuit in the processor or by software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The processor can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of this specification. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this specification can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0135] The electronic device can also execute the method of Figure 1 or Figure 2, and realize the functions of the energy-saving device of the base station in the embodiment shown in Figure 1 or Figure 2, and the embodiments of this specification will not be repeated here.

[0136] Of course, in addition to software implementation, the electronic device in this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc. That is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0137] The embodiments of this specification also propose a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by a portable electronic device including multiple applications, the portable electronic device can execute the method of the embodiment shown in Figure 1 or Figure 2, and is specifically used to perform the following operations.

[0138] Obtaining a total power consumption prediction model of the base station, wherein the total power consumption prediction model is determined based on a main device power consumption prediction model and an auxiliary device power consumption prediction model of the base station;

[0139] Optimizing the adjustable operating parameters of the supporting equipment at a target time within an adjustable range of the adjustable operating parameters of the supporting equipment so that the estimated total power consumption of the base station at the target time predicted by the total power consumption prediction model is minimized, and using the adjustable operating parameters at the time of the lowest estimated total power consumption as target operating values;

[0140] According to the target operating value of the adjustable operating parameter, the operating value of the adjustable operating parameter of the supporting equipment at the target time is adjusted.

[0141] FIG6 is a schematic diagram of the structure of a base station energy-saving device 600 provided in one embodiment of this specification. Referring to FIG6 , in a software implementation, the base station energy-saving device 600 may include: a model acquisition module 601, a parameter value optimization module 602, and a working value adjustment module 603, wherein: the model acquisition module 601 is configured to acquire a total power consumption prediction model of the base station, wherein the total power consumption prediction model is determined based on the power consumption prediction model of the base station's main equipment and the power consumption prediction model of the supporting equipment.

[0142] The main equipment of the base station includes a cabinet, and the supporting equipment of the base station includes a cabinet air conditioner and / or a computer room air conditioner. Exemplarily, the supporting equipment of the base station may also include a power supply device.

[0143] Among them, the main equipment power consumption prediction model and the supporting equipment power consumption prediction model of the base station are pre-built based on relevant sample data.

[0144] Some base stations have both computer room and cabinet air conditioners, while others only have cabinet air conditioners. For both scenarios, the models that need to be pre-built include: a base station load prediction model, a cabinet power consumption prediction model, a computer room air conditioner prediction model, and a cabinet air conditioner prediction model. Cabinet power consumption refers to the power consumption of the base station itself or its main equipment. Computer room air conditioners are located outside the cabinet in the base station's computer room, while cabinet air conditioners are located inside the base station's cabinet.

[0145] Regarding the construction process of the above model, please refer to the description of the method embodiment above and will not be repeated here.

[0146] The parameter value optimization module 602 is used to optimize the adjustable working parameters of the supporting equipment at the target time within the adjustable range of the adjustable working parameters of the supporting equipment, so that the estimated total power consumption of the base station at the target time predicted by the total power consumption prediction model is the lowest, and the adjustable working parameters when the estimated total power consumption is the lowest are used as the target working values.

[0147] The target time can be one or more moments or a time period. The target time can be a time in the future that is far from the current moment, or a time that is close to the current moment. The time granularity and time period of the target time can be determined based on actual application requirements.

[0148] Exemplarily, for the situation 1 described above, the parameter value optimization module 602 can be used to: predict the first predicted power consumption of the cabinet at the target time based on the load of the base station at the target time, the temperature of the cabinet of the base station at the target time, the energy-saving strategy of the base station at the target time, and the cabinet power consumption prediction model; predict the second predicted power consumption of the cabinet air conditioner at the target time based on the indoor temperature of the computer room where the base station is located at the target time, the operating temperature of the cabinet air conditioner at the target time, and the cabinet air conditioner power consumption prediction model; predict the third predicted power consumption of the computer room air conditioner at the target time based on the outdoor temperature of the computer room where the base station is located at the target time, the operating temperature of the computer room air conditioner at the target time, and the computer room air conditioner power consumption prediction model; add the first predicted power consumption, the second predicted power consumption, and the third predicted power consumption to obtain the estimated total power consumption of the base station at the target time.

[0149] For example, for the above-mentioned situation 2, the parameter value optimization module 602 may be used to:

[0150] Based on the load of the base station at the target time, the temperature of the cabinet of the base station at the target time, the energy-saving strategy of the base station at the target time, and the cabinet power consumption prediction model, the first predicted power consumption of the cabinet at the target time is predicted; based on the indoor temperature of the computer room where the base station is located at the target time, the operating temperature of the cabinet air conditioner at the target time, and the cabinet air conditioner power consumption prediction model, the second predicted power consumption of the cabinet air conditioner at the target time is predicted; the first predicted power consumption and the second predicted power consumption are combined to obtain the estimated total power consumption of the base station at the target time.

[0151] In the above two situations, as an example, if the target time is a future moment far away from the current moment, then: the load of the base station at the target time is predicted by the load prediction model, and the energy-saving strategy of the base station at the target time is determined based on the predicted load of the base station at the target time, and the temperature of the cabinet of the base station at the target time is predicted by the above cabinet temperature prediction model.

[0152] In the above two cases, as another example, if the target time is a future moment close to the current moment, then: the load of the base station at the target time can be the load of the base station at the current moment measured in real time, the energy-saving strategy of the base station at the target time can be the energy-saving duration adopted by the base station at the current moment measured in real time, and the temperature of the cabinet of the base station at the target time can be the temperature of the cabinet at the current moment measured in real time.

[0153] From the above description, we can see that the estimated total power consumption of a base station is the sum of the cabinet power consumption and the power consumption of supporting equipment. It can be understood that for the base station's supporting equipment—the cabinet air conditioner and / or computer room air conditioner—when the air conditioner operating temperature is set high, the air conditioner power consumption decreases, but the cabinet power consumption increases; conversely, when the air conditioner operating temperature is set low, the air conditioner power consumption increases, but the cabinet power consumption decreases. Therefore, through optimization, the operating values ​​of the cabinet air conditioner and / or computer room air conditioner that minimize the estimated total power consumption at the target time can be found.

[0154] For supporting equipment such as computer room air conditioners and cabinet air conditioners, since their adjustable working parameters often include multiple items, the adjustable range of each adjustable working parameter includes several optional values. For example, if the cabinet air conditioner is an air-cooled air conditioner, the adjustable working parameters of the cabinet air conditioner include at least one of temperature and wind speed; if the cabinet air conditioner is a liquid-cooled air conditioner, the adjustable working parameters of the cabinet air conditioner include at least one of temperature and liquid flow rate; similarly, if the computer room air conditioner is an air-cooled air conditioner, the adjustable working parameters of the computer room air conditioner include at least one of temperature and wind speed; if the computer room air conditioner is a liquid-cooled air conditioner, the adjustable working parameters of the computer room air conditioner include at least one of temperature and liquid flow rate. Therefore, if the optimal solution is found by enumeration, the amount of calculation is huge and not very realistic. Therefore, the embodiment of this specification proposes solving the target working value of the adjustable working parameter corresponding to the lowest estimated total power consumption based on a preset optimization algorithm.

[0155] Specifically, the parameter value optimization module 602 may be configured to optimize the adjustable operating parameters of the accessory device at the target time within the adjustable range of the adjustable operating parameters of the accessory device according to a preset optimization algorithm. Specifically, according to the preset optimization algorithm, within the adjustable range of the adjustable operating parameters of the accessory device, the operating values ​​of the adjustable operating parameters are continuously adjusted and input into the total power consumption prediction model to find the target operating value of the adjustable operating parameter that minimizes the estimated total power consumption output by the total power consumption prediction model.

[0156] The preset optimization algorithm includes but is not limited to one of a genetic algorithm, an ant colony algorithm, a simulated annealing algorithm, a particle swarm optimization algorithm and a differential evolution algorithm.

[0157] The working value adjustment module 603 is used to adjust the working value of the adjustable working parameter of the supporting equipment at the target time according to the target working value of the adjustable working parameter.

[0158] Specifically, the working value adjustment module 603 can be used to: generate an energy-saving strategy for adjusting the working value of the adjustable working parameter of the supporting equipment at the target time based on the target working value of the adjustable working parameter; before the target time, send the energy-saving strategy to the air-conditioning adjustment module, so that the air-conditioning adjustment module reduces the actual total power consumption of the base station at the target time by executing the energy-saving strategy.

[0159] An energy-saving device 600 for a base station provided in an embodiment of this specification, on the one hand, in addition to the power consumption of the main device, also includes the power consumption of the supporting equipment in the scope of consideration for reducing the total power consumption of the base station; on the other hand, after obtaining the total power consumption prediction model of the base station, the estimated total power consumption of the base station at the target time is predicted according to the total power consumption prediction model within the adjustable range of the adjustable working parameters of the supporting equipment, and optimization is performed to find the target working value of the adjustable working parameter that makes the estimated total power consumption lowest; and according to the target working value of the adjustable working parameter, the working value of the adjustable working parameter of the supporting equipment is dynamically adjusted at the target time, so that the total power consumption of the base station is minimized, thereby effectively reducing the energy consumption of the base station.

[0160] As shown in FIG. 7 , in another embodiment, a base station energy-saving device 600 provided in this specification may further include: a power consumption acquisition module 604 and a judgment module 605 .

[0161] The power consumption acquisition module 604 is configured to acquire the actual total power consumption of the base station at the current moment before triggering the working value adjustment module 603 if the target moment includes a future time adjacent to the current moment.

[0162] The judgment module 605 is used to judge whether the minimum estimated total power consumption is less than the actual total power consumption. If so, the working value adjustment module 603 is triggered; otherwise, the process returns to trigger the parameter value optimization module 602.

[0163] That is, when the minimum estimated total power consumption is less than the actual total power consumption, the operating value of the adjustable operating parameter of the accessory device at the target time is adjusted according to the target operating value of the adjustable operating parameter. It can be understood that if the actual total power consumption at the current moment is already lower than the minimum estimated total power consumption, then it may not be necessary to adjust the operating value of the adjustable operating parameter of the accessory device for the time in the future adjacent to the current moment; if the actual total power consumption at the current moment is not lower than or is much higher than the minimum estimated total power consumption, then it is necessary to adjust the operating value of the adjustable operating parameter of the accessory device for the time in the future adjacent to the current moment to reduce the actual total power consumption.

[0164] In an optional embodiment, the supporting equipment of the base station also includes a power supply equipment, and the supporting equipment power consumption prediction model also includes a power supply equipment power consumption prediction model. In a base station energy-saving device 600 provided in an embodiment of this specification, the model acquisition module 601 can also be used to: add the power supply equipment power consumption prediction model as a sum item to the total power consumption prediction model.

[0165] Accordingly, in parameter value optimization module 602, the estimated total power consumption of the base station at the target time also includes a fourth predicted power consumption predicted by the power supply device power consumption prediction model. Furthermore, through optimization, a target operating value of the adjustable operating parameter of the power supply device is obtained that minimizes the estimated total power consumption of the base station at the target time.

[0166] Correspondingly, in the working value adjustment module 603, the working value of the adjustable working parameter of the power supply device at the target time may be adjusted according to the target working value of the adjustable working parameter of the power supply device.

[0167] The adjustable operating parameters of the power supply device include at least one of the number of power supplies, the voltage of the power supply device, and the current of the power supply device.

[0168] It can be understood that in addition to considering the impact of cabinet air conditioners and / or computer room air conditioners on the total power consumption of the base station, incorporating power supply equipment into the scope of base station energy conservation considerations can more comprehensively and effectively reduce the total power consumption of the base station and achieve the goal of optimizing the overall energy consumption of the entire station equipment.

[0169] The energy-saving device 600 of a base station provided in an embodiment of this specification can also execute the method of Figure 1 or Figure 2, and realize the functions of the energy-saving device 600 of a base station in the embodiment shown in Figure 1 or Figure 2, which will not be repeated in this embodiment of this specification.

[0170] In short, the above description is only part of the embodiments of this specification and is not intended to limit the scope of protection of this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this specification shall be included in the scope of protection of this specification.

[0171] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0172] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0173] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0174] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

Claims

1. A base station energy saving method, comprising: Obtaining a total power consumption prediction model of the base station, wherein the total power consumption prediction model is determined according to a main device power consumption prediction model and an auxiliary device power consumption prediction model of the base station; Within the adjustable range of the adjustable working parameters of the supporting equipment, optimizing the adjustable working parameters of the supporting equipment at the target time, so that the estimated total power consumption of the base station at the target time predicted by the total power consumption prediction model is the lowest, and taking the adjustable working parameters when the estimated total power consumption is the lowest as the target working value; According to the target operating value of the adjustable operating parameter, the operating value of the adjustable operating parameter of the supporting equipment at the target time is adjusted.

2. The method according to claim 1, wherein: In the case where the base station is equipped with a computer room air conditioner and a cabinet air conditioner, the main equipment power consumption prediction model includes a cabinet power consumption prediction model, the supporting equipment power consumption prediction model includes a computer room air conditioner power consumption prediction model and a cabinet air conditioner power consumption prediction model, and the total power consumption prediction model is determined based on the cabinet power consumption prediction model, the computer room air conditioner power consumption prediction model and the cabinet air conditioner power consumption prediction model.

3. The method according to claim 2, wherein obtaining the total power consumption prediction model of the base station comprises: Obtaining the cabinet power consumption prediction model, the computer room air conditioner power consumption prediction model and the cabinet air conditioner power consumption prediction model; The cabinet power consumption prediction model, the computer room air conditioner power consumption prediction model and the cabinet air conditioner power consumption prediction model are added together to obtain the total power consumption prediction model.

4. The method according to claim 3, wherein: Predicting the estimated total power consumption of the base station at the target time according to the total power consumption prediction model includes: Predicting a first predicted power consumption of the cabinet at the target time according to the load of the base station at the target time, the temperature of the cabinet of the base station at the target time, the energy-saving strategy of the base station at the target time, and the cabinet power consumption prediction model; Predicting a second predicted power consumption of the cabinet air conditioner at the target time according to the indoor temperature of the computer room where the base station is located at the target time, the operating temperature of the cabinet air conditioner at the target time, and the cabinet air conditioner power consumption prediction model; Predicting a third predicted power consumption of the computer room air conditioner at the target time according to the outdoor temperature of the computer room where the base station is located at the target time, the operating temperature of the computer room air conditioner at the target time, and the power consumption prediction model of the computer room air conditioner; The first predicted power consumption, the second predicted power consumption and the third predicted power consumption are added together to obtain the estimated total power consumption of the base station at the target time.

5. The method according to claim 1, wherein: In the case where the base station is equipped with a cabinet air conditioner, the main equipment power consumption prediction model includes a cabinet power consumption prediction model, the supporting equipment power consumption prediction model includes a cabinet air conditioner power consumption prediction model, and the total power consumption prediction model is determined based on the cabinet power consumption prediction model and the cabinet air conditioner power consumption prediction model.

6. The method according to claim 5, wherein obtaining the total power consumption prediction model of the base station comprises: Obtaining the cabinet power consumption prediction model and the cabinet air conditioner power consumption prediction model; The cabinet power consumption prediction model and the cabinet air conditioner power consumption prediction model are added together to obtain the total power consumption prediction model.

7. The method according to claim 6, wherein: Predicting the estimated total power consumption of the base station at the target time according to the total power consumption prediction model includes: Predicting a first predicted power consumption of the cabinet at the target time according to the load of the base station at the target time, the temperature of the cabinet of the base station at the target time, the energy-saving strategy of the base station at the target time, and the cabinet power consumption prediction model; Predicting a second predicted power consumption of the cabinet air conditioner at the target time according to the indoor temperature of the computer room where the base station is located at the target time, the operating temperature of the cabinet air conditioner at the target time, and the cabinet air conditioner power consumption prediction model; The first predicted power consumption and the second predicted power consumption are combined to obtain the power consumption of the base station at the target time. Estimate total power consumption.

8. The method according to claim 4 or 7, wherein the target time comprises a specified time in the future, and the load of the base station at the target time is predicted by a load prediction model, and the method further comprises: The load prediction model is constructed according to the historical load time series of the base station.

9. The method according to claim 8, The energy saving strategy of the base station at the target time is determined based on the predicted load of the base station at the target time.

10. The method according to any one of claims 2 to 7, before acquiring the total power consumption prediction model of the base station, further comprising: A cabinet power consumption prediction model is trained based on first sample data, wherein the first sample data includes a historical load of the base station, a historical temperature of a cabinet of the base station, a historical energy-saving strategy of the cabinet, and a historical power consumption of the cabinet.

11. The method according to any one of claims 2 to 7, before acquiring the total power consumption prediction model of the base station, further comprising: The cabinet air conditioner power consumption prediction model is trained according to the second sample data, wherein the second sample data includes historical operating values ​​of adjustable operating parameters of the cabinet air conditioner, ambient temperature, and historical power consumption.

12. The method according to any one of claims 2 to 4, before acquiring the total power consumption prediction model of the base station, further comprising: The computer room air conditioner power consumption prediction model is trained according to the third sample data, wherein the third sample data includes historical operating values ​​of adjustable operating parameters of the computer room air conditioner, ambient temperature, and historical power consumption.

13. The method according to any one of claims 1 to 7, wherein the target time comprises a future time adjacent to the current time, and before adjusting the adjustable operating parameter of the supporting equipment to the operating value of the target time according to the target operating value of the adjustable operating parameter, the method further comprises: Obtaining the actual total power consumption of the base station at the current moment; When the minimum estimated total power consumption is less than the actual total power consumption, according to the adjustable The target working value of the working parameter is used to adjust the working value of the adjustable working parameter of the supporting equipment at the target time.

14. The method according to claim 1, wherein optimizing the adjustable working parameters of the supporting equipment at the target time within the adjustable range of the adjustable working parameters of the supporting equipment comprises: Within the adjustable range of the adjustable working parameters of the supporting equipment, the adjustable working parameters of the supporting equipment at the target time are optimized according to a preset optimization algorithm, wherein the preset optimization algorithm includes one of a genetic algorithm, an ant colony algorithm, a simulated annealing algorithm, a particle swarm optimization algorithm and a differential evolution algorithm.

15. The method according to any one of claims 2 to 7, wherein the supporting equipment power consumption prediction model further comprises a power supply equipment power consumption prediction model, and the method further comprises: The power supply device power consumption prediction model is added as a sum item to the total power consumption prediction model.

16. The method according to claim 15, The estimated total power consumption of the base station at the target time also includes a fourth predicted power consumption predicted according to the power consumption prediction model of the power supply device.

17. An electronic device comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 16.

18. A computer-readable storage medium, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 16.

Images