Energy consumption management method and device and medium
By predicting the future energy consumption of communication equipment and adjusting parameters and temperature control measures, the energy consumption and cost balance of communication equipment is solved, and the problem of energy consumption control affecting user experience in the existing technology is solved, and the accuracy of energy consumption management and energy saving are improved. Effect.
Patent Information
- Application Number
- CN202410933385.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-19
AI Technical Summary
The prior art usually relies on a single data source when controlling the energy consumption of communication equipment, and cannot consider the factors affecting energy consumption from multiple dimensions, resulting in affecting the user experience when reducing energy consumption.
By predicting the future communication energy consumption and temperature control energy consumption of communication equipment, using historical data to train models, adjust communication parameters and temperature control measures, store energy in low-energy periods, reduce temperature control energy consumption in high-energy periods, and realize energy consumption in high-energy periods, and achieve energy consumption. and balance of costs.
Without affecting the user experience, it effectively saves the energy consumption and expenses of communication equipment, reduces the energy consumption of temperature control, and improves the accuracy and efficiency of energy management.
Smart Images

Figure CN118984481A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure at least relates to the field of energy-saving technology, and in particular to an energy consumption management method, an energy consumption management device, and a computer-readable storage medium. Background Art
[0002] At present, for communication equipment such as communication rooms and communication base stations, energy consumption is controlled by only predicting energy consumption based on the tracking data and network management data of the communication equipment. The data source is single, and the factors affecting energy consumption are not considered from multiple dimensions. On the other hand, energy consumption is reduced by shutting down functions such as the 5G (fifth generation mobile communication technology) network, which results in users being able to use network services such as 4G. Although this achieves the goal of energy saving, it affects the user's service experience. Summary of the invention
[0003] The technical problem to be solved by the present disclosure is to provide an energy consumption management method, an energy consumption management device and a computer-readable storage medium in view of the above-mentioned shortcomings, so as to solve the problem of how to save the energy consumption of communication equipment without affecting the user experience.
[0004] In a first aspect, the present disclosure provides an energy consumption management method, the method comprising:
[0005] Predict the communication energy consumption and temperature control energy consumption of communication equipment in the future as well as the energy consumption costs;
[0006] According to the communication energy consumption, temperature control energy consumption and energy consumption cost, obtain the future high energy consumption and high cost time period of the communication equipment and the future low energy consumption and low cost time period before the future high energy consumption and high cost time period;
[0007] Temperature control energy storage will be controlled during future low energy consumption and low cost periods, and temperature control energy storage will be controlled during future high energy consumption and high cost periods to reduce temperature control energy consumption, so as to balance the sum of communication energy consumption and temperature control energy consumption as well as costs of communication equipment in each future period.
[0008] Furthermore, the communication energy consumption, temperature control energy consumption and energy consumption cost of the communication equipment in the future period are predicted, including:
[0009] Obtain historical and current communication data, temperature control data, and cost data of communication equipment;
[0010] Using historical time series communication data to train the communication energy consumption model of the communication equipment, using historical time series communication data and temperature control data to train the temperature control energy consumption model of the communication equipment, and using historical time series communication data, temperature control data and cost data to train the energy consumption cost model of the communication equipment;
[0011] The communication data of the current time series is input into the communication energy consumption model to predict the communication energy consumption of the communication equipment in the future time period. The communication data and temperature control data of the current time series are input into the temperature control energy consumption model to predict the temperature control energy consumption of the communication equipment in the future time period. The communication data, temperature control data and cost data of the current time series are input into the energy consumption cost model to predict the energy consumption cost of the communication equipment in the future time period.
[0012] Further, wherein:
[0013] Communication data includes user traffic data, communication parameter configuration, performance satisfaction data and communication power data; temperature control data includes equipment temperature and humidity data, weather forecast data and temperature control power data; cost data includes electricity price fluctuation data;
[0014] The communication energy consumption model includes the user business volume change model and the communication energy consumption generated by different communication parameter configurations that meet the performance requirements of different user business volumes. The temperature control energy consumption model includes the water cooling system energy consumption model, the gas liquefaction system energy consumption model, the air conditioning system energy consumption model and the fan energy consumption model.
[0015] Further, according to the communication energy consumption, the temperature control energy consumption and the energy consumption cost, the future high energy consumption and high cost period of the communication equipment and the future low energy consumption and low cost period before the future high energy consumption and high cost period are obtained, specifically including:
[0016] In response to obtaining, based on the communication energy consumption, the temperature control energy consumption, and the energy consumption cost, that the energy consumption and / or cost of the communication device in a certain period in the future exceeds a first threshold, obtaining the certain period as a future high energy consumption and high cost period;
[0017] Obtain several time periods in which energy consumption and / or costs are lower than a second threshold before a future high-energy-consumption and high-cost time period, and the sum of the differences in energy consumption and / or costs of each of the several time periods minus the second threshold is greater than or equal to the portion of the energy consumption and / or costs of the future high-energy-consumption and high-cost time period that exceeds the first threshold.
[0018] Furthermore, in the future, temperature control energy storage is controlled during low energy consumption and low cost periods, and in the future, temperature control energy storage is controlled during high energy consumption and high cost periods to reduce temperature control energy consumption, specifically including:
[0019] In future low energy consumption and low cost periods, air conditioning systems and / or fans are controlled to achieve temperature control, and water cooling systems and / or gas liquefaction systems are controlled to perform temperature control energy storage. In future high energy consumption and high cost periods, water cooling systems and / or gas liquefaction systems are controlled to perform temperature control energy storage to reduce temperature control energy consumption.
[0020] Furthermore, the method further comprises:
[0021] The user traffic volume is predicted according to the user traffic volume variation model in each future period, and the communication parameter configuration is adjusted according to the user traffic volume to control the minimum communication energy consumption that meets the performance requirements of the user traffic volume.
[0022] Further, wherein:
[0023] The communication equipment is specifically a communication room and / or a base station;
[0024] Adjusting the communication parameter configuration includes adjusting the antenna transmission power, antenna tilt angle, antenna beam configuration, and wireless signal channel configuration of the base station;
[0025] The equipment temperature and humidity data are collected in real time by sensors;
[0026] The method is implemented by controlling a cloud platform or an edge platform.
[0027] Furthermore, the method further comprises:
[0028] Continuously receive current time series communication data, temperature control data and cost data;
[0029] According to the latest communication data, temperature control data and cost data of the current time series, it is determined whether the sum of the communication energy consumption and temperature control energy consumption in each future period of the previous round of control and the cost are balanced;
[0030] In response to failure to achieve a balance, the communication energy consumption model, the temperature control energy consumption model, and the energy consumption cost model are retrained.
[0031] In a second aspect, the present disclosure provides an energy consumption management device, the device comprising:
[0032] A prediction module, used to predict the communication energy consumption and temperature control energy consumption of communication equipment in the future period and the energy consumption cost;
[0033] The time period selection module is connected to the prediction module and is used to obtain the future high energy consumption and high cost time period of the communication equipment and the future low energy consumption and low cost time period before the future high energy consumption and high cost time period according to the communication energy consumption, the temperature control energy consumption and the energy consumption cost;
[0034] The control module is connected to the time period selection module and is used to control temperature control energy storage in future low-energy consumption and low-cost time periods, and to control the use of temperature control energy storage to reduce temperature control energy consumption in future high-energy consumption and high-cost time periods, so as to balance the sum of communication energy consumption and temperature control energy consumption and costs of communication equipment in each future time period.
[0035] In a third aspect, the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the energy consumption management method as described above is implemented.
[0036] The present disclosure provides an energy consumption management method, an energy consumption management device and a computer-readable storage medium. According to the characteristics of communication equipment, by predicting the future communication energy consumption, temperature control energy consumption and energy consumption cost of the communication equipment, energy storage means are used to reduce the temperature control energy consumption in future high energy consumption and high cost periods, so as to achieve balanced control of energy consumption and cost, and save the energy consumption and cost of the communication equipment without affecting the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 is a flow chart of an energy consumption management method according to an embodiment of the present disclosure;
[0038] Figure 2 is a schematic diagram of the structure of an energy consumption management system according to an embodiment of the present disclosure;
[0039] Figure 3 It is a structural diagram of an energy consumption management device according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0040] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.
[0041] It should be understood that the specific embodiments and drawings described herein are only used to explain the present disclosure rather than to limit the present disclosure.
[0042] It can be understood that, in the absence of conflict, the various embodiments of the present disclosure and the various features in the embodiments can be combined with each other.
[0043] It can be understood that, for the convenience of description, the drawings of the present disclosure only show parts related to the present disclosure, while parts irrelevant to the present disclosure are not shown in the drawings.
[0044] It can be understood that each unit and module involved in the embodiments of the present disclosure may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.
[0045] It will be understood that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present disclosure may occur in an order different from that marked in the drawings.
[0046] It is understood that the flowcharts and block diagrams of the present disclosure illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present disclosure. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.
[0047] It can be understood that the units and modules involved in the embodiments of the present disclosure can be implemented by software or hardware, for example, the units and modules can be located in a processor.
[0048] Embodiment 1:
[0049] like Figure 1 As shown, the present disclosure provides an energy consumption management method, the method comprising:
[0050] S1. Predict the communication energy consumption and temperature control energy consumption and energy consumption cost of communication equipment in the future period;
[0051] S2. According to the communication energy consumption, temperature control energy consumption and energy consumption cost, obtain the future high energy consumption and high cost time period of the communication equipment and the future low energy consumption and low cost time period before the future high energy consumption and high cost time period;
[0052] S3. Control temperature control energy storage during future low energy consumption and low cost periods, and control the use of temperature control energy storage to reduce temperature control energy consumption during future high energy consumption and high cost periods, so as to balance the sum of communication energy consumption and temperature control energy consumption and costs of communication equipment in each future period.
[0053] In this embodiment, based on the characteristics of the communication equipment, by predicting the future communication energy consumption, temperature control energy consumption and energy consumption costs of the communication equipment, energy storage methods are used to reduce the temperature control energy consumption during future high energy consumption and high cost periods, thereby achieving balanced control of energy consumption and costs, and saving the energy consumption and costs of the communication equipment without affecting the user experience.
[0054] Specifically, since communication equipment needs to provide communication services to users, communication energy consumption changes according to user business needs. Communication equipment needs to be temperature-controlled to avoid excessively high or low temperatures. The temperature of communication equipment is affected by weather, environmental conditions, and communication energy consumption. When managing energy consumption, the energy consumption of communication needs and temperature control needs is comprehensively considered. According to the changes in communication energy consumption and factors such as temperature, the temperature control adjustment plan is changed to achieve energy saving while considering reducing costs. By reducing the temperature control energy consumption during high-energy consumption and high-cost periods, there is no need to take energy-reducing measures for communications during this period, and the network quality will not be sacrificed, and the service perception of network users will not be affected. At the same time, the reduction in temperature control energy consumption is achieved through pre-storage of energy, and the cooling effect is still guaranteed when the communication energy consumption increases. It can not only adapt to the current coexistence of 2, 3, 4, and 5G networks, but also support subsequent 6G networks, satellite communications, integrated space-ground collaborative networks, and other future networks.
[0055] In one implementation, S1, predicting the communication energy consumption and temperature control energy consumption and energy consumption cost of the communication device in a future period, specifically includes:
[0056] Obtain historical and current communication data, temperature control data, and cost data of communication equipment;
[0057] Using historical time series communication data to train the communication energy consumption model of the communication equipment, using historical time series communication data and temperature control data to train the temperature control energy consumption model of the communication equipment, and using historical time series communication data, temperature control data and cost data to train the energy consumption cost model of the communication equipment;
[0058] The communication data of the current time series is input into the communication energy consumption model to predict the communication energy consumption of the communication equipment in the future time period. The communication data and temperature control data of the current time series are input into the temperature control energy consumption model to predict the temperature control energy consumption of the communication equipment in the future time period. The communication data, temperature control data and cost data of the current time series are input into the energy consumption cost model to predict the energy consumption cost of the communication equipment in the future time period.
[0059] In this embodiment, in order to solve the energy consumption problems of operator computer rooms, data centers and base stations, various relevant information that affects the power consumption of communication operator computer rooms and base stations is digitized through artificial intelligence algorithms and model construction, and intelligent, automated and precise scenario analysis, energy-saving strategy configuration and automatic control are realized to achieve the purpose of saving energy and reducing carbon emissions.
[0060] Specifically, the data used include historical data, current real-time system status, real-time weather conditions, temperature and humidity, electricity prices, real-time business load, related subsystem parameters and operation performance information and other multi-dimensional data. Based on the multi-dimensional data, complex models of communication energy consumption model, temperature control energy consumption model and energy consumption cost model are established, and all information is connected in real time using high-speed and low-latency network connections, such as low-latency performance of at least 5G urllc (Ultra-reliable and Low Latency Communications) or above. The model is updated and iterated in real time through artificial intelligence algorithms, and the optimal solution with the lowest energy consumption is output to make autonomous decisions through artificial intelligence.
[0061] More specifically, the method is applied to Figure 2 The energy consumption management system shown in the figure connects the base station or data center of the communication operator with antennas, various sensors, air conditioners, gas liquid compression, water cooling and other systems, a data platform using a database on the cloud, and an edge computing data platform. Through artificial intelligence algorithms and model construction, various relevant information that affects the power consumption of the communication operator's computer room and base station is digitized, and real-time intercommunication between data and the cloud platform is achieved through 5G, 6G, satellite communications or future networks. The computing power and storage of the cloud platform are used for data integration and predictive modeling analysis based on artificial intelligence, and intelligent, automated, and precise scenario analysis, energy-saving strategy configuration and intelligent decision-making are realized, and real-time AI (Artificial Intelligence) autonomous decision-making automatic control is performed on base station equipment, air cooling, water cooling, gas liquefaction compression systems, etc., to achieve the purpose of saving energy consumption and reducing carbon emissions. The implementation steps of this method may include:
[0062] 1) Establish a data platform: Build a data collection and integration platform deployed on the cloud to ensure real-time data collection and accuracy. Obtain various types of information and data from operator equipment, computer rooms, data centers, various sensors, etc., and aggregate them into the database of the data platform.
[0063] 2) Data preprocessing: Integrate the above data into a data platform with a database deployed on the cloud, which can clean, classify, convert, normalize and extract the data, realize statistics, analysis and calculation of the data, complete various data mining tasks and artificial intelligence algorithm calculations, and ensure the accuracy and consistency of the data. Prepare for subsequent analysis.
[0064] 3) Establish energy consumption model: Based on the processed data and combined with historical data, an energy consumption model is established through multiple regression analysis, time series prediction, genetic algorithm, deep learning and other artificial intelligence algorithms.
[0065] 4) Predictive modeling: Use time series forecasting methods to predict power consumption and weather changes.
[0066] 5) Decision optimization: Genetic algorithms, generative adversarial networks and other methods are used to generate optimal energy consumption strategies, while taking into account factors such as electricity prices, temperature, weather, and business volume.
[0067] 6) Reinforcement Learning: Apply deep reinforcement learning and neural network algorithms to enable the system to adaptively optimize energy consumption adjustment strategies.
[0068] 7) Real-time automatic control: Apply the optimized strategy to actual equipment control to achieve real-time energy consumption adjustment.
[0069] In one embodiment, wherein:
[0070] Communication data includes user traffic data, communication parameter configuration, performance satisfaction data and communication power data; temperature control data includes equipment temperature and humidity data, weather forecast data and temperature control power data; cost data includes electricity price fluctuation data;
[0071] The communication energy consumption model includes the user business volume change model and the communication energy consumption generated by different communication parameter configurations that meet the performance requirements of different user business volumes. The temperature control energy consumption model includes the water cooling system energy consumption model, the gas liquefaction system energy consumption model, the air conditioning system energy consumption model and the fan energy consumption model.
[0072] In this embodiment, in order to solve the problem that the existing communication equipment energy consumption analysis control data source is single and cannot adapt to changes in power grids, networks, weather, ambient temperature, humidity, buildings, user services, equipment loads, etc., and cannot solve the independent selectivity of energy-saving strategies of each base station in different environments, this method extracts key information from huge data to achieve accurate energy consumption analysis, and can more accurately understand the energy consumption characteristics of each base station, thereby better optimizing energy management strategies.
[0073] Specifically, the following Figure 2 The system shown is explained by taking base station energy saving as an example:
[0074] First, data collection and integration are carried out, including:
[0075] 1) Data source collection: obtain data such as base station operation status, performance data, base station basic configuration data, real-time user service usage, antenna transmission status, user reported information, etc. from base station equipment; collect data such as base station equipment surface temperature, internal chip temperature of the equipment, air temperature in the computer room, temperature outside the computer room, humidity, etc. through various sensors; obtain weather forecasts through information provided by the meteorological department; obtain data such as electricity price fluctuations, peak and valley time nodes and corresponding electricity prices through information provided by the power department; obtain users' network usage habits, user behavior portraits, usage time, business volume and other data through the operator's core network.
[0076] 2) Data integration: The above data are integrated into a data platform with a database deployed on the cloud, which can perform operations such as cleaning, classification, conversion, normalization and extraction on the data, and further realize statistics, analysis and calculation of the data, complete various data mining tasks and calculation of artificial intelligence algorithms, while ensuring the accuracy and consistency of the data, in preparation for subsequent model construction and artificial intelligence algorithm analysis.
[0077] Next, perform predictive modeling and analysis, including:
[0078] 1) User behavior and business model: Based on the user behavior portrait, usage habits, business volume, historical data of usage time obtained in "data collection and integration", as well as the current business development and real-time data, a user behavior and business prediction model is established to predict the user's future business usage, usage time, etc., and further predict the network equipment load, power consumption and temperature, etc.
[0079] 2) Weather and environment prediction model: Using the weather forecast data, equipment operation status, historical temperature data of the room and equipment, historical weather data, etc. obtained in "data collection and integration", a weather and temperature prediction model is established to predict future indoor and outdoor temperatures, sunshine conditions, equipment and chip temperatures, etc., to provide a reference for intelligent energy consumption decisions. The time series prediction method can be used to predict future weather changes and power consumption fluctuations and trends. In the scenario of power consumption prediction of communication room equipment, by analyzing historical data, such as electricity price fluctuation cycles, seasonal fluctuations, and weather changes, future trend predictions and periodic predictions can be generated to guide energy consumption strategies.
[0080] 3) Establish energy consumption model: Based on the real-time and historical energy consumption data of base station equipment, air conditioners, fans, antennas, etc., an energy consumption model is established through multiple regression analysis, time series prediction, genetic algorithms, deep learning and other artificial intelligence algorithms. The data used in the construction of the model include but are not limited to equipment load, indoor and outdoor temperature, ground temperature, water cooling system operation status, base station operation and performance data, base station basic configuration data, equipment surface temperature collected by sensors, board temperature, CPU (Central Processing Unit) and other chip power consumption, weather forecasts from meteorological departments, time, season, electricity price, user business volume and other variables. Based on the established accurate energy consumption model, the energy consumption of air conditioners, fans, base station equipment, boards and antennas can be predicted. By establishing an energy consumption model, we can predict the energy consumption changes and trends of each device under different conditions and obtain the overall estimated power consumption.
[0081] 4) Energy consumption cost model: Based on the historical energy consumption data and electricity price data obtained in "data collection and integration", including tiered electricity prices, peak and valley electricity prices, etc., by analyzing historical electricity price data and weather forecasts, an energy consumption-cost binary prediction model is established, and reliable input data is provided for the subsequent dynamic adjustment of energy consumption strategies based on the prediction results. The energy consumption cost model is constructed using the multivariate regression analysis method, and the energy consumption costs of air conditioners, fans, antennas, etc. are predicted by considering multiple factors (such as temperature, business volume, usage time, etc.).
[0082] The above model can provide predictions of future energy consumption based on multiple variables, thereby guiding energy consumption adjustment decisions.
[0083] In one embodiment, S2, according to the communication energy consumption, the temperature control energy consumption and the energy consumption cost, obtain the future high energy consumption and high cost period of the communication device and the future low energy consumption and low cost period before the future high energy consumption and high cost period, specifically including:
[0084] In response to obtaining, based on the communication energy consumption, the temperature control energy consumption, and the energy consumption cost, that the energy consumption and / or cost of the communication device in a certain period in the future exceeds a first threshold, obtaining the certain period as a future high energy consumption and high cost period;
[0085] Obtain several time periods in which energy consumption and / or costs are lower than a second threshold before a future high-energy-consumption and high-cost time period, and the sum of the differences in energy consumption and / or costs of each of the several time periods minus the second threshold is greater than or equal to the portion of the energy consumption and / or costs of the future high-energy-consumption and high-cost time period that exceeds the first threshold.
[0086] In this embodiment, the second threshold is less than the first threshold, and the first threshold and the second threshold may include an energy consumption threshold and a cost threshold, respectively. The energy consumption is the sum of the communication energy consumption and the temperature control energy consumption, and the cost is the total cost of the communication energy consumption and the temperature control energy consumption. In order to achieve the goal of balancing the total energy consumption and the total cost of each time period in the future, when it is predicted that there will be a high energy consumption and high cost period in the future, several time periods before this period are selected for temperature control energy storage. The stored energy should meet the temperature control energy demand exceeded in the future high energy consumption and high cost period, and the saved energy can be used to meet the communication demand of this period.
[0087] In one embodiment, in S3, temperature control energy storage is controlled during future low energy consumption and low cost periods, and temperature control energy storage is controlled to reduce temperature control energy consumption during future high energy consumption and high cost periods, specifically including:
[0088] In future low energy consumption and low cost periods, air conditioning systems and / or fans are controlled to achieve temperature control, and water cooling systems and / or gas liquefaction systems are controlled to perform temperature control energy storage. In future high energy consumption and high cost periods, water cooling systems and / or gas liquefaction systems are controlled to perform temperature control energy storage to reduce temperature control energy consumption.
[0089] In this embodiment, the equipment that affects the power consumption of the communication operator's computer room and base station is automatically controlled through artificial intelligence algorithms to balance energy consumption, such as air conditioners, fans, water cooling, and antenna transmission power, and corresponding automation strategies are implemented, such as peak and valley electricity price optimization, ambient temperature intelligent strategy, load identification strategy, etc.; the adjustment of temperature control energy consumption is mainly achieved by setting up a variety of temperature control schemes such as water cooling systems, gas liquefaction systems, air conditioning systems and fans, that is, the communication equipment is equipped with a variety of temperature control devices, at least some of which are energy storage temperature control devices. During the predicted high energy consumption period, the energy stored by these energy storage temperature control devices reduces the demand for electricity on the power grid, and during the predicted low energy consumption period, these devices store energy from the power grid.
[0090] In one embodiment, the method further comprises:
[0091] The user traffic volume is predicted according to the user traffic volume variation model in each future period, and the communication parameter configuration is adjusted according to the user traffic volume to control the minimum communication energy consumption that meets the performance requirements of the user traffic volume.
[0092] In this embodiment, not only the power consumption of the operator's base station can be reduced, but also the power consumption of the machine room, the antenna, and the carrier power consumption, channel power consumption and symbol power consumption at the air interface level can be reduced.
[0093] Specifically, combined Figure 2The system shown, taking base station energy saving as an example, the method also includes the cloud platform generating an intelligent energy consumption strategy. The prediction model and data analysis results obtained according to the aforementioned "predictive modeling and analysis" will serve as the basis for the formulation of the intelligent energy consumption strategy. The prediction model and data analysis results are combined with the optimization algorithm to generate the best intelligent energy consumption strategy. The intelligent energy consumption strategy will comprehensively consider multiple factors such as equipment operating status, indoor and outdoor temperature, date, time, electricity price, weather, user business volume, etc., and generate the best parameters and operation strategies for base station equipment, antennas, air conditioners, fans and water cooling systems under different circumstances based on artificial intelligence algorithms, so as to achieve better energy efficiency and energy saving effects. Specifically including:
[0094] 1) Temperature and weather perception strategy: Combine indoor and outdoor temperatures and weather forecasts to adjust the use of air conditioners and fans to reduce energy consumption. According to the difference in indoor and outdoor temperatures, lower the indoor temperature in advance before hot weather to reduce the working intensity of air conditioners during high temperatures and improve energy efficiency; in low temperature weather, ventilate and dissipate heat through fans, and suspend air conditioning refrigeration. Maintain the computer room at a constant temperature. Synchronize the real-time collected data to a data platform with computing power through transmission technologies such as 5G, 6G, satellite communications, or future networks. The data platform refers to an edge computing data platform or a data platform deployed on the cloud. Input the data into the energy consumption model on the data platform, and obtain a new multi-dimensional energy consumption model through artificial intelligence algorithms and combined with other data through iterative calculations. The generated results are sent to the intelligent strategy system, automated control system, and intelligent monitoring system in real time, and participate in continuous optimization.
[0095] 2) Smart utilization strategy of water cooling system: In areas where the peak-valley electricity price policy is implemented, the water cooling system is started to make ice during the electricity valley period when the electricity price is low. Ice is made in the ice-making pool by ice-making equipment to accumulate cold capacity. There is a circulating liquid pipeline that serves as a heat exchange function in the pool. During the peak period when the electricity price is high, the ice maker or central air conditioner does not work. The circulating liquid in the circulating liquid pipeline is driven by the water-cooling circulation pump. The low-temperature circulating liquid flows through the fan coil unit. After heat exchange through the fan coil unit, the temperature rises and the temperature of the equipment in the computer room is reduced. The heated circulating liquid is then returned to the ice-making pool through the loop for heat exchange and re-circulation. Heat exchange is performed between the water cooling system and the equipment in the computer room, etc., reducing the use of air conditioning compressors. Based on artificial intelligence algorithms, combined with peak and valley electricity prices, the startup time and power consumption of each electrical equipment, the final electricity price in the future is estimated, and the current optimal electricity consumption strategy is reversely calculated to achieve load sharing and power consumption balance between the water cooling system and the air-conditioning fan system, reasonably allocate energy consumption, and maintain the target value of the final electricity price at the lowest value estimated by the system.
[0096] 3) Intelligent utilization strategy of gas liquefaction system: In areas where the peak-valley electricity price policy is implemented, during the electricity valley period when the electricity price is low, the gas liquefaction system is started to compress the specific gas into liquid. The compressed gas into liquid is then stored in the liquid storage tank to accumulate energy. During the peak period when the electricity price is high, the liquefaction compression function does not work. The liquefied gas in the storage tank is driven to flow by the liquid pump, evaporates and absorbs heat in the heat exchanger, and the temperature rises, and it quickly gasifies and expands. The high-temperature gas after heating and expansion can be returned to the gas liquefaction system through the loop to re-participate in the circulation. Through the utilization of the gas liquefaction system, combined with the peak-valley electricity price, the startup time and power consumption of each electrical equipment, and modeling and analysis based on artificial intelligence algorithms, the final electricity price in the future can be estimated, and the current optimal electricity consumption strategy can be reversely calculated to achieve load sharing and power consumption balance between the gas liquefaction system and other systems, reasonably allocate energy consumption, and maintain the target value of the final electricity price at the lowest value estimated by the system in real time.
[0097] 4) User service adaptation strategy: Based on the relevant historical data of user services, including but not limited to user service usage time, service duration, user location, user identity, service type and scenario, service busy hours and other data. Use the above relevant historical data of user services to make user usage predictions, and adjust the antenna transmission power, number of wireless signal channels and other parameters in combination with the power consumption, service load and power consumption of the base station equipment at the corresponding time and geographical location. During peak traffic, increase the antenna transmission power and optimize channel allocation to ensure stable communication quality; during low traffic, reduce equipment power consumption, reduce unnecessary operations, and reduce energy consumption.
[0098] 5) Time-aware intelligent scheduling strategy: Combined with season, date and time information, analyze the energy consumption patterns of different seasons, dates and time periods, consider seasonal changes and the impact of special events (such as holidays and activities), establish a time energy consumption model based on historical data, and associate historical data with the time dimension. The model includes seasonal trends, weekly and daily energy consumption change patterns, and the impact of special events on energy consumption. The model uses machine learning models including but not limited to recurrent neural networks (RNN) or long short-term memory networks (LSTM), superimposes intelligent weight strategies, and evaluates the best energy consumption strategy at a specific time. Intelligent weight strategy: The perception of temperature, equipment status, electricity price, user business, weather, water cooling system status, etc. in the above-listed strategies is input as a data source into the intelligent weight strategy model. Each strategy may have different weights in different time periods. Use artificial intelligence-based algorithms, such as reinforcement learning or evolutionary algorithms, to automatically learn and adjust the weights of each strategy at different time points through learning and simulating decisions on historical data.
[0099] 6) Dynamic selection strategy: The generated strategy is not fixed. In actual operation, the system selects the optimal energy consumption strategy or combination strategy based on the current time, date, season and other information, combined with real-time data, through feedback loops, using intelligent weight algorithms to ensure that the system can flexibly and adaptively adjust the operating status of the equipment at different times. Based on real-time temperature, weather forecast, electricity price and other data, the use of air conditioners, fans, and antennas is continuously monitored and dynamically adjusted to optimize energy consumption. For example, in the dynamic adjustment strategy for the use of air conditioners and fans, because the compressor needs to compress the refrigerant to release heat and then exchange heat with water or air, a medium will be added to the heat exchange process of the entire system, which also adds a layer of loss. Relying on temperature and weather perception strategies, if the real-time strategy evaluation believes that the combination of fan heat dissipation and water-cooled circulating pumps under low temperature conditions should be adopted under current conditions, then switch to this solution. The fan and circulating pump directly exchange heat between the heat exchange medium and the wind, water, and ground, without the need for an intermediate medium. Compared with the air conditioning cooling method, it reduces losses, thereby reducing power consumption and electricity costs.
[0100] 7) Intelligent strategy optimization: Using deep learning algorithms, such as generative adversarial networks (GAN), the mutual game learning between generative models and discriminative models produces better output results, namely energy consumption strategies, and continuously optimizes strategies so that the system can learn from interactions and gradually improve strategies. Autonomously adjust energy consumption control strategies to maximize long-term benefits. This method performs well in environments with high uncertainty and complexity, and can adapt to the changing conditions of different base station equipment, time periods, weather and user behavior. Using strategy optimization algorithms such as genetic algorithms, simulated annealing algorithms and other random optimization algorithms based on iterative solution methods, using multiple factors such as historical experience data, real-time information and current strategies as parameters, find the energy consumption strategy corresponding to the global optimal solution. These algorithms can explore different decisions and decision combinations, make trade-offs between multiple factors, and find the best balance between energy efficiency and performance through iterative search and simulation of survival of the fittest. At the same time, intelligent strategy optimization can continuously optimize strategies as the environment and business changes to ensure the continuity and adaptability of energy consumption management.
[0101] The above-mentioned strategies and their combinations can not only reduce the energy consumption of the communication operator's computer room, but also improve operational efficiency and user experience. Through intelligent energy consumption strategies, communication operators can make more accurate and wise decisions under different weather, temperature, business needs and electricity price fluctuations, reduce power consumption while ensuring service quality, and achieve accurate and adaptive energy consumption management and business optimization. The strategy provided by this method, which comprehensively considers multiple factors, can minimize the power consumption of base station equipment and improve energy utilization efficiency in different environments and usage scenarios.
[0102] In one embodiment, wherein:
[0103] The communication equipment is specifically a communication room and / or a base station;
[0104] Adjusting the communication parameter configuration includes adjusting the antenna transmission power, antenna tilt angle, antenna beam configuration, and wireless signal channel configuration of the base station;
[0105] The equipment temperature and humidity data are collected in real time by sensors;
[0106] The method is implemented by controlling a cloud platform or an edge platform.
[0107] In this embodiment, the implementation of the strategy of this method requires an intelligent decision-making system, which will monitor various parameters in real time, execute optimization algorithms and apply the best strategy to the base station equipment. An automated control system is required to convert the specific decisions generated by the intelligent decision-making system into automated control signals for execution and implementation on the actual equipment.
[0108] Specifically, combined Figure 2 The system shown takes base station energy saving as an example, and the method also includes intelligent decision-making, automated implementation and monitoring, specifically including:
[0109] 1) Intelligent decision-making system: Based on the prediction models and energy consumption strategies in the aforementioned "predictive modeling and analysis" and "generating intelligent energy consumption strategies", real-time data monitoring and energy consumption optimization decisions are generated. The content of the decision includes but is not limited to when to start or shut down the air conditioner, fan, and water cooling system, the operating time, operation strategy, and power of each system, the antenna's transmission power, antenna tilt, antenna beam configuration, wireless signal channel configuration, and various parameters of the base station. Through artificial intelligence algorithms, the effects of different optimization strategies are predicted and evaluated to select the decision path that can best reduce energy consumption.
[0110] 2) Automated control system: The specific decisions generated by the intelligent decision-making system need to be executed and implemented on the actual equipment. The automated control system connects the intelligent decision-making system with the actual equipment, and converts the specific decisions generated by the intelligent decision-making system into automated control signals and sends them to each controllable device to achieve energy consumption optimization based on automated control. This energy consumption optimization based on automated control is based on the real-time status of the equipment and the real-time status of the environment. It is a normalized, dynamic real-time optimization. In "data collection and integration", the data of the equipment and the data collected by various sensors are transmitted in real time to the data platform using a database deployed on the cloud through a low-latency high-speed network. The data that is more sensitive to latency is transmitted to the edge computing data platform to reduce latency and ensure the real-time and accuracy of energy consumption strategies and automated control. The automated control system automatically adjusts the operating status, configuration and parameters of each device. In addition, the automated control system also has the following characteristics:
[0111] The automation control system supports the interfaces of various devices: enabling the automation control system to establish connections with various devices in the computer room (air conditioners, fans, antennas, water cooling systems, etc.) to achieve real-time remote control.
[0112] Real-time response: The automated control system can respond to instructions from the intelligent decision-making system in real time and quickly perform corresponding operations.
[0113] Abnormality handling: The automated control system can identify faults and emergencies such as abnormal equipment status, abnormal environment, abnormal temperature, and take appropriate measures, such as automatically restarting the equipment, automatically alarming, notifying maintenance personnel, or switching to backup equipment.
[0114] Energy-saving mode switching: Based on the energy-saving mode decision made by the intelligent decision-making system, the system can intelligently and adaptively switch the working mode of the equipment. The intelligent decision-making system uses the acquired data to identify the network load and user business volume in real time, and combines the network load, user business volume, different regions, non-call time periods, peak and valley and tiered electricity prices to generate a dynamic mode borrowing and returning strategy. Through the automated control system, the equipment is controlled to adaptively switch between several modes such as high-performance and high-power consumption mode, normal mode, and energy-saving mode, saving energy while ensuring user business perception.
[0115] In one embodiment, the method further comprises:
[0116] Continuously receive current time series communication data, temperature control data and cost data;
[0117] According to the latest communication data, temperature control data and cost data of the current time series, it is determined whether the sum of the communication energy consumption and temperature control energy consumption in each future period of the previous round of control and the cost are balanced;
[0118] In response to failure to achieve a balance, the communication energy consumption model, the temperature control energy consumption model, and the energy consumption cost model are retrained.
[0119] In this embodiment, specifically, combined with Figure 2 The system shown takes base station energy saving as an example, and the method also includes intelligent decision-making, automated implementation and monitoring, and specifically includes:
[0120] 3) Real-time monitoring system: Real-time monitoring of the status of each system and module, the operating status of equipment and boards, various sensors, user business conditions, electricity prices, etc., so as to detect abnormal situations in time and take measures. Through sensors and monitoring equipment, the system monitors the status of each device in the computer room in real time to ensure that they are working properly, and sends operating data and status information to the intelligent decision-making system. Use machine learning algorithms to detect anomalies, such as equipment failures, unusual energy consumption fluctuations, etc. Monitor real-time data streams, such as meteorological data, user business data, electricity price changes, etc., to respond to emergencies, such as sudden temperature increases, concentrated and concurrent user business, or electricity price increases. Monitor changes in equipment status, such as air conditioning or fan performance degradation, water cooling system liquid cooling pipe or ice maker failure, and take corresponding measures.
[0121] 4) Continuous optimization: Use regular, event-triggered, and multiple strategies to evaluate system performance, including energy consumption reduction effects, real-time electricity bills, energy usage trends, decision accuracy, etc., and send the evaluation results to the intelligent decision-making system. Through deep learning, the intelligent decision-making system can gain insights from performance evaluations and propose real-time optimization decisions to compare with the benchmarks of the prediction model to discover changes or trends that deviate from expectations. Adjust the prediction model and optimization strategy based on the deviation to continuously improve the energy consumption optimization effect. Then feed the results of the previous actual optimization decision back to the intelligent decision-making system to improve the accuracy of each energy consumption model and form a feedback loop. Through deep learning algorithms, the energy consumption model is continuously retrained based on new data to ensure that it can adapt to changing conditions. It is also possible to adjust the performance and energy consumption target values according to the specific needs of communication operators, and then change the energy consumption strategy to better meet the customized energy efficiency and cost control needs of communication operators.
[0122] The intelligent decision-making system integrates the aforementioned intelligent energy consumption strategy with actual equipment control to realize real-time monitoring and feedback control mechanism to ensure the rapid response and accuracy of energy consumption decisions. Through the above methods, the overall system continuously monitors, evaluates, optimizes and improves during operation to achieve more efficient energy utilization, reduce operating costs, and ensure that the computer room can maintain the best performance and energy consumption balance under different conditions. This intelligent energy consumption management method can effectively adapt to complex and changing environments and bring greater benefits to communication operators. Artificial intelligence technology can be used to realize intelligent management and optimization of the energy consumption of communication operators' computer rooms, thereby minimizing the power consumption of air conditioners, fans and antennas, improving energy efficiency, reducing costs, and providing the best decision-making plan under different temperature, electricity prices and business volume conditions.
[0123] Compared with the prior art, this embodiment has at least the following advantages:
[0124] 1) Obtain information from multi-dimensional data sources, including: obtaining base station operation status, performance data, base station basic configuration data, real-time user service usage, antenna transmission status, user reporting information and other data from base station equipment; collecting base station equipment surface temperature, internal chip temperature, air temperature in the equipment room, external temperature and humidity through various sensors; obtaining weather forecasts through information provided by the meteorological department; obtaining electricity price fluctuations, peak and valley time nodes and corresponding electricity prices through information provided by the power department; obtaining users' network usage habits, user behavior portraits, usage time, business volume and other data through the operator's core network, etc. Use more comprehensive data and information as the data source of artificial intelligence algorithms to build a more comprehensive and accurate power-saving model, taking into account the influence of external factors, to more accurately predict the energy consumption changes of base stations and provide more reasonable energy-saving strategies.
[0125] 2) Use dynamic model building technology, not only to build a fixed model based on historical information, but also to build a multi-dimensional complex model based on the current real-time system status, real-time weather conditions, temperature and humidity, electricity prices, real-time business load, related subsystem parameters and operating performance, and all information is connected in real time using a high-speed, low-latency network. The model is updated and iterated in real time through artificial intelligence algorithms, and the optimal solution with the lowest energy consumption is output to make autonomous decisions through artificial intelligence. Since the base station operation status and external factors change in real time in actual operation, the system can identify the base station operation status and environmental changes in real time, and combine various sensors, equipment self-collection, user business usage and real-time dynamic data provided by the power department. Through feedback loops, the model parameters are dynamically adjusted, and the weights of different influencing factors are updated. Various models are continuously updated and improved to maintain the accuracy and real-time performance of the model.
[0126] 3) Use artificial intelligence decision-making algorithms to automatically analyze large amounts of data through computers, discover electricity consumption trends and power-saving models hidden in big data, and provide more accurate decision-making basis. Use multiple regression analysis algorithms to build energy consumption models and predict energy consumption correlations of air conditioners, fans, antennas, etc. Use time series prediction algorithms to predict future power consumption and weather changes. Use genetic algorithms to find the optimal energy consumption strategy among a large number of factors provided by multidimensional data sources. Deep reinforcement learning is used for adaptive learning and deep learning modeling to analyze multiple variables such as equipment load, indoor and outdoor temperature, ground temperature, base station operation and performance data, base station basic configuration data, equipment surface temperature collected by sensors, board temperature, CPU and other chip power consumption, weather forecasts from meteorological departments, time, season, electricity price, user business volume, etc., and predict the energy consumption of air conditioners, fans, base station equipment, boards and antennas based on the established accurate energy consumption model. Artificial intelligence-based methods can achieve automated energy consumption management without frequent manual intervention, thus improving efficiency. Using artificial intelligence algorithms and model building methods, various relevant information that affects the power consumption of communication operators' computer rooms, equipment, and base stations are digitized to achieve intelligent, automated, and precise scenario analysis, energy-saving strategy configuration, and automatic control, thereby saving base station energy consumption and reducing carbon emissions.
[0127] 4) A management and control platform integrating monitoring, analysis, decision-making, automatic control and self-optimization has been built. The platform integrates a real-time monitoring system to monitor the status of each system and module, the operating status of equipment and boards, various sensors, user business conditions, electricity prices, etc., so as to detect abnormal situations in time and take measures; at the same time, the data analysis system is integrated to import data such as base station operation status, performance data, base station basic configuration data, real-time user business usage, antenna transmission status, user reporting information, etc.; through various sensors, the surface temperature of base station equipment, the temperature of the chip inside the equipment, the air temperature in the computer room, the temperature outside the computer room, humidity, etc. are collected. The system will automatically establish a prediction model to analyze the data; then an intelligent decision-making system is also integrated, and through the analysis results given by the data analysis system, In the case of fully balancing the influence of various aspects, the decision path that can best reduce energy consumption is selected; then the automation control system is also integrated. The specific decisions generated by the intelligent decision-making system need to be executed and implemented on the actual equipment. The automation control system connects the intelligent decision-making system with the actual equipment, and converts the specific decisions generated by the intelligent decision-making system into automated control signals and sends them to each controllable device to achieve energy consumption optimization based on automated control; finally, the self-optimization system is also integrated, and the system performance is evaluated by periodic, event-triggered, and multiple strategies, including energy consumption reduction effects, real-time electricity expenses, energy usage trends, decision accuracy, etc., and the evaluation results are sent to the intelligent decision-making system. Through deep learning, the intelligent decision-making system can gain insights from performance evaluation, propose real-time optimization decisions and compare them with the benchmark of the prediction model to find changes or trends that deviate from expectations. Adjust the prediction model and optimization strategy according to the deviation to continuously improve the energy consumption optimization effect.
[0128] Embodiment 2:
[0129] like Figure 3 As shown, the present disclosure provides an energy consumption management device, the device comprising:
[0130] Prediction module 1, used to predict the communication energy consumption and temperature control energy consumption and energy consumption cost of the communication equipment in the future period;
[0131] The time period selection module 2 is connected to the prediction module 1 and is used to obtain the future high energy consumption and high cost time period of the communication equipment and the future low energy consumption and low cost time period before the future high energy consumption and high cost time period according to the communication energy consumption, the temperature control energy consumption and the energy consumption cost;
[0132] The control module 3 is connected to the time period selection module 2, and is used to control the temperature control energy storage in the future low energy consumption and low cost time period, and to control the use of temperature control energy storage to reduce temperature control energy consumption in the future high energy consumption and high cost time period, so as to balance the communication energy consumption and temperature control energy consumption of the communication equipment in each future time period and the cost.
[0133] In one embodiment, the prediction module 1 specifically includes:
[0134] A data acquisition unit, used to acquire communication data, temperature control data and cost data of the communication device at the historical and current time series;
[0135] A model training unit, connected to the data acquisition unit, is used to train a communication energy consumption model of a communication device using historical time-series communication data, train a temperature control energy consumption model of a communication device using historical time-series communication data and temperature control data, and train an energy consumption cost model of a communication device using historical time-series communication data, temperature control data, and cost data;
[0136] The model prediction unit is connected to the model training unit, and is used to input the communication data of the current time series into the communication energy consumption model to predict the communication energy consumption of the communication equipment in the future time period, input the communication data and temperature control data of the current time series into the temperature control energy consumption model to predict the temperature control energy consumption of the communication equipment in the future time period, and input the communication data, temperature control data and cost data of the current time series into the energy consumption cost model to predict the energy consumption cost of the communication equipment in the future time period.
[0137] In one embodiment, wherein:
[0138] Communication data includes user traffic data, communication parameter configuration, performance satisfaction data and communication power data; temperature control data includes equipment temperature and humidity data, weather forecast data and temperature control power data; cost data includes electricity price fluctuation data;
[0139] The communication energy consumption model includes the user business volume change model and the communication energy consumption generated by different communication parameter configurations that meet the performance requirements of different user business volumes. The temperature control energy consumption model includes the water cooling system energy consumption model, the gas liquefaction system energy consumption model, the air conditioning system energy consumption model and the fan energy consumption model.
[0140] In one embodiment, the time period selection module 2 specifically includes:
[0141] A first time period selection unit is used for obtaining, in response to obtaining that the energy consumption and / or cost of the communication device in a certain time period in the future exceeds a first threshold according to the communication energy consumption, the temperature control energy consumption and the energy consumption cost, the certain time period is a future high energy consumption and high cost time period;
[0142] The second time period selection unit is connected to the first time period selection unit, and is used to obtain several time periods before the future high-energy consumption and high-cost time period in which energy consumption and / or costs are lower than a second threshold value, and the second threshold value minus the sum of the differences in energy consumption and / or costs of each of the several time periods is greater than or equal to the part of the energy consumption and / or costs of the future high-energy consumption and high-cost time period that exceeds the first threshold value.
[0143] In one embodiment, the control module 3 specifically includes:
[0144] The temperature control energy consumption control unit is used to control the use of air conditioning systems and / or fans to achieve temperature control during future low energy consumption and low cost periods, and to control the water cooling system and / or gas liquefaction system for temperature control energy storage, as well as to control the use of water cooling systems and / or gas liquefaction systems for temperature control energy storage to reduce temperature control energy consumption during future high energy consumption and high cost periods.
[0145] In one embodiment, the control module 3 further includes:
[0146] The communication energy consumption control unit is used to predict the user traffic volume in the future according to the user traffic volume change model, and adjust the communication parameter configuration according to the user traffic volume to control the minimum communication energy consumption that meets the performance requirements of the user traffic volume.
[0147] In one embodiment, wherein:
[0148] The communication equipment is specifically a communication room and / or a base station;
[0149] Adjusting the communication parameter configuration includes adjusting the antenna transmission power, antenna tilt angle, antenna beam configuration, and wireless signal channel configuration of the base station;
[0150] The equipment temperature and humidity data are collected in real time by sensors;
[0151] The device is a cloud platform or an edge platform.
[0152] In this embodiment, the device may be as follows Figure 2 The data platform using a database on the cloud and / or the edge computing data platform shown, or Figure 2 The overall energy management system shown.
[0153] In one embodiment, wherein:
[0154] The data acquisition unit is also used to continuously receive the communication data, temperature control data and cost data of the current time sequence;
[0155] The device also includes a judgment unit connected to the data acquisition unit, which is used to judge whether the sum of communication energy consumption and temperature control energy consumption in each future time period of the previous round of control and the cost are balanced according to the latest communication data, temperature control data and cost data of the current time sequence;
[0156] The model training unit is also connected to the judgment unit and is used to retrain the communication energy consumption model, the temperature control energy consumption model and the energy consumption cost model in response to failure to achieve balance.
[0157] Embodiment 3:
[0158] Embodiment 3 of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the energy consumption management method as described in Embodiment 1 or the energy consumption management device as described in Embodiment 2 is implemented.
[0159] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.
[0160] In addition, the present disclosure may also provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the energy consumption management method as described in Example 1. The computer device may be an energy consumption management device as described in Example 2.
[0161] The memory is connected to the processor, the memory may be a flash memory or a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.
[0162] Embodiments 1-3 of the present disclosure provide an energy consumption management method, an energy consumption management device, and a computer-readable storage medium. Based on the characteristics of communication equipment, by predicting the future communication energy consumption, temperature control energy consumption, and energy consumption costs of the communication equipment, energy storage methods are used to reduce the temperature control energy consumption during future high-energy consumption and high-cost periods, thereby achieving balanced control of energy consumption and costs, and saving the energy consumption and costs of the communication equipment without affecting the user experience.
[0163] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.
Claims
1. An energy consumption management method, characterized in that: The method comprises: Predict the communication energy consumption and temperature control energy consumption of communication equipment in the future as well as the energy consumption costs; According to the communication energy consumption, temperature control energy consumption and energy consumption cost, obtain the future high energy consumption and high cost time period of the communication equipment and the future low energy consumption and low cost time period before the future high energy consumption and high cost time period; Temperature control energy storage will be controlled during future low energy consumption and low cost periods, and temperature control energy storage will be controlled during future high energy consumption and high cost periods to reduce temperature control energy consumption, so as to balance the sum of communication energy consumption and temperature control energy consumption as well as costs of communication equipment in each future period.
2. The method according to claim 1, characterized in that Predict the communication energy consumption, temperature control energy consumption and energy consumption costs of communication equipment in the future, including: Obtain historical and current communication data, temperature control data, and cost data of communication equipment; Using historical time series communication data to train the communication energy consumption model of the communication equipment, using historical time series communication data and temperature control data to train the temperature control energy consumption model of the communication equipment, and using historical time series communication data, temperature control data and cost data to train the energy consumption cost model of the communication equipment; The communication data of the current time series is input into the communication energy consumption model to predict the communication energy consumption of the communication equipment in the future time period. The communication data and temperature control data of the current time series are input into the temperature control energy consumption model to predict the temperature control energy consumption of the communication equipment in the future time period. The communication data, temperature control data and cost data of the current time series are input into the energy consumption cost model to predict the energy consumption cost of the communication equipment in the future time period.
3. The method according to claim 2, characterized in that in: Communication data includes user traffic data, communication parameter configuration, performance satisfaction data and communication power data; temperature control data includes equipment temperature and humidity data, weather forecast data and temperature control power data; cost data includes electricity price fluctuation data; The communication energy consumption model includes the user business volume change model and the communication energy consumption generated by different communication parameter configurations that meet the performance requirements of different user business volumes. The temperature control energy consumption model includes the water cooling system energy consumption model, the gas liquefaction system energy consumption model, the air conditioning system energy consumption model and the fan energy consumption model.
4. The method according to any one of claims 1 to 3, characterized in that: According to the communication energy consumption, temperature control energy consumption and energy consumption cost, the future high energy consumption and high cost period of the communication equipment and the future low energy consumption and low cost period before the future high energy consumption and high cost period are obtained, specifically including: In response to obtaining, based on the communication energy consumption, the temperature control energy consumption, and the energy consumption cost, that the energy consumption and / or cost of the communication device in a certain period in the future exceeds a first threshold, obtaining the certain period as a future high energy consumption and high cost period; Obtain several time periods in which energy consumption and / or costs are lower than a second threshold before a future high-energy-consumption and high-cost time period, and the sum of the differences in energy consumption and / or costs of each of the several time periods minus the second threshold is greater than or equal to the portion of the energy consumption and / or costs of the future high-energy-consumption and high-cost time period that exceeds the first threshold.
5. The method according to any one of claims 1 to 3, characterized in that: In the future, temperature control energy storage will be carried out during low energy consumption and low cost periods, and temperature control energy storage will be used to reduce temperature control energy consumption during high energy consumption and high cost periods. Specifically, it includes: In future low energy consumption and low cost periods, air conditioning systems and / or fans are controlled to achieve temperature control, and water cooling systems and / or gas liquefaction systems are controlled to perform temperature control energy storage. In future high energy consumption and high cost periods, water cooling systems and / or gas liquefaction systems are controlled to perform temperature control energy storage to reduce temperature control energy consumption.
6. The method according to claim 5, characterized in that The method further comprises: The user traffic volume is predicted according to the user traffic volume variation model in each future period, and the communication parameter configuration is adjusted according to the user traffic volume to control the minimum communication energy consumption that meets the performance requirements of the user traffic volume.
7. The method according to claim 6, characterized in that in: The communication equipment is specifically a communication room and / or a base station; Adjusting the communication parameter configuration includes adjusting the antenna transmission power, antenna tilt angle, antenna beam configuration, and wireless signal channel configuration of the base station; The equipment temperature and humidity data are collected in real time by sensors; The method is implemented by controlling a cloud platform or an edge platform.
8. The method according to any one of claims 2 to 3, characterized in that: The method further comprises: Continuously receive current time series communication data, temperature control data and cost data; According to the latest communication data, temperature control data and cost data of the current time series, determine whether the sum of communication energy consumption and temperature control energy consumption in each future period of the previous round of control and the cost are balanced; In response to failure to achieve a balance, the communication energy consumption model, the temperature control energy consumption model, and the energy consumption cost model are retrained.
9. An energy consumption management device, characterized in that: The device comprises: A prediction module, used to predict the communication energy consumption and temperature control energy consumption of communication equipment in the future period and the energy consumption cost; The time period selection module is connected to the prediction module and is used to obtain the future high energy consumption and high cost time period of the communication equipment and the future low energy consumption and low cost time period before the future high energy consumption and high cost time period according to the communication energy consumption, the temperature control energy consumption and the energy consumption cost; The control module is connected to the time period selection module and is used to control temperature control energy storage in future low-energy consumption and low-cost time periods, and to control the use of temperature control energy storage to reduce temperature control energy consumption in future high-energy consumption and high-cost time periods, so as to balance the sum of communication energy consumption and temperature control energy consumption and costs of communication equipment in each future time period.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the energy consumption management method according to any one of claims 1 to 8 is implemented.
