Aggregation optimization method, device and equipment based on 5G base station energy storage participation demand response, storage medium and program product

Abstract

The invention relates to an aggregation optimization method and device based on 5G base station energy storage participation demand response, equipment, a storage medium and a program product, and relates to the technical field of power energy storage. The method can improve the resource utilization efficiency. The method comprises the following steps: cleaning and interpolating abnormal data in original base station parameters of a 5G base station to obtain target base station parameters; according to the future load curve, the future electricity price sequence and the target base station parameters, obtaining a charging and discharging strategy of the 5G base station; determining power purchase cost, frequency modulation income and loss cost according to the charging and discharging strategy, and constructing a multi-target optimization model based on the power purchase cost, the frequency modulation income and the loss cost; and determining a target problem in the multi-target optimization model, solving the target problem through an alternating direction multiplier method to obtain an optimal solution, dynamically adjusting a charging and discharging strategy according to the optimal solution and battery health degree feedback information of the 5G base station, and if the adjusted charging and discharging strategy meets an optimization termination condition, executing optimization result output.

Description

Technical Field

[0001] The present application relates to the field of power energy storage technology, and in particular to an aggregation optimization method, device, computer equipment, computer-readable storage medium, and computer program product based on 5G base station energy storage participating in demand response. Background Art

[0002] With the rapid development of 5G technology and the dramatic increase in the number of base stations, 5G base stations have become an essential component of the power system. However, the distributed nature of 5G base stations leads to geographically dispersed layouts, small individual installation capacities, diverse operators, and uncertain output times. This has resulted in idle energy storage in some areas, hindering the potential of distributed energy storage for regulation.

[0003] To address these challenges, researchers have recently begun exploring the integration of 5G base station energy storage resources into power systems, leveraging their distributed and flexible nature to participate in demand response. However, existing energy storage aggregation solutions often rely on energy storage aggregators to integrate resources and lack dynamic coordination mechanisms. This inability to fully leverage the potential of 5G base stations leads to inefficient resource utilization. Summary of the Invention

[0004] Based on this, it is necessary to provide an aggregation optimization method, device, computer equipment, computer-readable storage medium and computer program product based on 5G base station energy storage participating in demand response to address the above technical problems.

[0005] In a first aspect, the present application provides an aggregation optimization method based on 5G base station energy storage participating in demand response, including:

[0006] Collecting original base station parameters of the 5G base station, cleaning and interpolating abnormal data in the original base station parameters to obtain target base station parameters;

[0007] Predicting a future load curve using a load forecasting model based on historical load data, predicting a future electricity price sequence using an electricity price forecasting model based on historical electricity price data, and obtaining a charging and discharging strategy for the 5G base station based on the future load curve, the future electricity price sequence, and the target base station parameters;

[0008] Determining electricity purchase costs, frequency regulation benefits, and loss costs according to the charging and discharging strategy, and constructing a multi-objective optimization model based on the electricity purchase costs, the frequency regulation benefits, and the loss costs;

[0009] A target problem is determined in the multi-objective optimization model, and an optimal solution is obtained by solving the target problem using the alternating direction multiplier method. The charge and discharge strategy is dynamically adjusted based on the optimal solution and the battery health feedback information of the 5G base station. When the adjusted charge and discharge strategy meets the optimization termination condition, the optimization result is output.

[0010] In one embodiment, determining a target problem in the multi-objective optimization model and solving the target problem by an alternating direction multiplier method to obtain an optimal solution include:

[0011] The target problem is determined according to the multi-objective optimization function in the multi-objective optimization model, and the target problem is decomposed into a collaborative peak-shaving response problem, an autonomous scheduling problem and a power allocation problem; a collaborative peak-shaving response model is constructed based on the collaborative effect matrix between the 5G base stations, an autonomous scheduling model is constructed, and a power allocation model is constructed based on the power allocation matrix; through the collaborative peak-shaving response model, the autonomous scheduling model and the power allocation model, the alternating direction multiplier method is used to alternately solve the collaborative peak-shaving response problem, the autonomous scheduling problem and the power allocation problem to obtain the optimal solution.

[0012] In one embodiment, obtaining the charging and discharging strategy of the 5G base station according to the future load curve, the future electricity price sequence, and the target base station parameters includes:

[0013] The future load curve is decomposed into a base station adjustable part and a base station non-adjustable part; for the base station adjustable part, a charging and discharging plan is formulated according to the future electricity price sequence, the required frequency regulation capacity is calculated according to the charging and discharging plan, and a market bidding strategy is determined according to the frequency regulation capacity; the charging and discharging strategy is generated according to the charging and discharging plan, the market bidding strategy, and the base station non-adjustable part.

[0014] In one embodiment, before dynamically adjusting the charge and discharge strategy based on the optimal solution and the battery health feedback information of the 5G base station, the method further includes:

[0015] Obtain the battery nominal parameters and the battery historical operating parameters of the 5G base station, and construct a battery health assessment model based on the battery nominal parameters and the battery historical operating parameters; predict the available capacity sequence and the charge and discharge limit sequence of the currently used battery of the 5G base station through the battery health assessment model according to the future load curve and the future electricity price sequence; generate the battery health feedback information based on the available capacity sequence and the charge and discharge limit sequence.

[0016] In one embodiment, the method further comprises:

[0017] When the adjusted charge and discharge strategy meets the preset termination mark, it is determined that the adjusted charge and discharge strategy meets the optimization termination condition; when the adjusted charge and discharge strategy does not meet the termination mark, return to the step of collecting the original base station parameters of the 5G base station until the optimization termination condition is met.

[0018] In one embodiment, the outputting of the optimization results includes:

[0019] According to the adjusted charging and discharging strategy, an optimization result including a day-ahead plan and real-time scheduling instructions is generated, and the optimization result is sent to each of the 5G base stations; the actual operating status of the monitoring system and the execution of the optimization result are compared; if the actual operating status is inconsistent with the execution status, the step of collecting the original base station parameters of the 5G base station is returned to perform re-optimization, and if they are consistent, the optimization process is completed.

[0020] Secondly, this application also provides an aggregation optimization device based on 5G base station energy storage participating in demand response, including:

[0021] A data acquisition module is used to collect the original base station parameters of the 5G base station, clean and interpolate the abnormal data in the original base station parameters, and obtain the target base station parameters;

[0022] a strategy formulation module, configured to predict a future load curve using a load forecasting model based on historical load data, predict a future electricity price sequence using an electricity price forecasting model based on historical electricity price data, and obtain a charging and discharging strategy for the 5G base station based on the future load curve, the future electricity price sequence, and the target base station parameters;

[0023] a model building module, configured to determine the electricity purchase cost, the frequency regulation benefit, and the loss cost according to the charging and discharging strategy, and to build a multi-objective optimization model based on the electricity purchase cost, the frequency regulation benefit, and the loss cost;

[0024] An optimization output module is used to determine a target problem in the multi-objective optimization model, solve the target problem by an alternating direction multiplier method to obtain an optimal solution, dynamically adjust the charge and discharge strategy according to the optimal solution and the battery health feedback information of the 5G base station, and execute optimization result output when the adjusted charge and discharge strategy meets the optimization termination condition.

[0025] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0026] Collect original base station parameters of the 5G base station, clean and interpolate abnormal data in the original base station parameters to obtain target base station parameters; predict the future load curve through a load forecasting model based on historical load data, predict the future electricity price series through an electricity price forecasting model based on historical electricity price data, and obtain the charging and discharging strategy of the 5G base station based on the future load curve, the future electricity price series and the target base station parameters; determine the power purchase cost, frequency regulation benefit and loss cost based on the charging and discharging strategy, and construct a multi-objective optimization model based on the power purchase cost, the frequency regulation benefit and the loss cost; determine the target problem in the multi-objective optimization model, solve the target problem through the alternating direction multiplier method to obtain an optimal solution, dynamically adjust the charging and discharging strategy based on the optimal solution and the battery health feedback information of the 5G base station, and execute the optimization result output when the adjusted charging and discharging strategy meets the optimization termination condition.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0028] Collect original base station parameters of the 5G base station, clean and interpolate abnormal data in the original base station parameters to obtain target base station parameters; predict the future load curve through a load forecasting model based on historical load data, predict the future electricity price series through an electricity price forecasting model based on historical electricity price data, and obtain the charging and discharging strategy of the 5G base station based on the future load curve, the future electricity price series and the target base station parameters; determine the power purchase cost, frequency regulation benefit and loss cost based on the charging and discharging strategy, and construct a multi-objective optimization model based on the power purchase cost, the frequency regulation benefit and the loss cost; determine the target problem in the multi-objective optimization model, solve the target problem through the alternating direction multiplier method to obtain an optimal solution, dynamically adjust the charging and discharging strategy based on the optimal solution and the battery health feedback information of the 5G base station, and execute the optimization result output when the adjusted charging and discharging strategy meets the optimization termination condition.

[0029] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0030] Collect original base station parameters of the 5G base station, clean and interpolate abnormal data in the original base station parameters to obtain target base station parameters; predict the future load curve through a load forecasting model based on historical load data, predict the future electricity price series through an electricity price forecasting model based on historical electricity price data, and obtain the charging and discharging strategy of the 5G base station based on the future load curve, the future electricity price series and the target base station parameters; determine the power purchase cost, frequency regulation benefit and loss cost based on the charging and discharging strategy, and construct a multi-objective optimization model based on the power purchase cost, the frequency regulation benefit and the loss cost; determine the target problem in the multi-objective optimization model, solve the target problem through the alternating direction multiplier method to obtain an optimal solution, dynamically adjust the charging and discharging strategy based on the optimal solution and the battery health feedback information of the 5G base station, and execute the optimization result output when the adjusted charging and discharging strategy meets the optimization termination condition.

[0031] The above-mentioned aggregate optimization method, device, computer equipment, computer-readable storage medium and computer program product based on 5G base station energy storage participating in demand response obtain the charging and discharging strategy of the 5G base station according to the future load curve, the future electricity price sequence and the target base station parameters; then, according to the charging and discharging strategy, the power purchase cost, frequency regulation income and loss cost are determined, and a multi-objective optimization model is constructed based on the power purchase cost, frequency regulation income and loss cost; then, the target problem is determined in the multi-objective optimization model, and the target problem is solved by the alternating direction multiplier method to obtain the optimal solution. According to the optimal solution and the battery health feedback information of the 5G base station, the charging and discharging strategy is dynamically adjusted, and when the adjusted charging and discharging strategy meets the optimization termination condition, the optimization result output is executed. This application introduces a multi-time-scale optimization framework, combines the load forecast and electricity price forecast in the day-ahead stage, and generates a charging and discharging strategy for 5G base stations, effectively solving the problems of resource dispersion and single-target optimization in traditional solutions, and improving the overall system efficiency. At the same time, the alternating direction multiplier method is used to solve the target problem to obtain the optimal solution, realizing the functions of efficient solution and dynamic coordination, meeting the real-time optimization needs, thereby giving full play to the potential value of 5G base stations and improving resource utilization efficiency. By introducing rolling time domain prediction and dynamic correction strategy for battery health, the service life of energy storage is effectively extended, maintenance costs are reduced, and system reliability is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 This is an application environment diagram of an aggregated optimization method based on 5G base station energy storage participating in demand response in one embodiment;

[0034] Figure 2 1. A flowchart of an aggregation optimization method for 5G base station energy storage participating in demand response in one embodiment;

[0035] Figure 3 A flowchart of steps for solving a target problem in one embodiment is shown;

[0036] Figure 4 A flow chart of an aggregation optimization method for 5G base station energy storage participating in demand response in an application embodiment;

[0037] Figure 5 This is a structural block diagram of an aggregated optimization method and apparatus for participating in demand response based on 5G base station energy storage in one embodiment;

[0038] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0040] The aggregation optimization method based on 5G base station energy storage participating in demand response provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown in FIG. , the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server or placed on the cloud or other network servers. Figure 1 In the application environment shown, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0041] In one embodiment, Figure 2 As shown in the figure, an aggregation optimization method based on 5G base station energy storage participating in demand response is provided. Figure 1 The following steps are used as an example to illustrate the terminal in the figure:

[0042] Step S201: collect the original base station parameters of the 5G base station, clean and interpolate the abnormal data in the original base station parameters, and obtain the target base station parameters.

[0043] Specifically, the data interaction and collection in this embodiment may include the following steps:

[0044] Step 1: Establish a communication connection:

[0045] A data channel is established between the base station and the aggregator via a 5G / fiber network. The communication protocol meets the following requirements:

[0046]

[0047] In the above formula, : Communication delay, : Bit error rate.

[0048] Step 2: Collect data:

[0049] Real-time collection of base station parameters:

[0050] In the above formula, : The remaining power of the i-th base station at time t, : Maximum energy storage capacity, : Battery charging status of the i-th base station at time t.

[0051] Step 3: Data preprocessing:

[0052] Clean and interpolate abnormal data:

[0053] In the above formula, : the mean value of the parameter x of the i-th base station, : standard deviation.

[0054] For example, the terminal establishes a data communication connection with the aggregator through the 5G communication network; collects the load power, energy storage SOC (State of Charge) status and electricity price signals of each base station; among them, the load power is collected in real time by the smart meter, the energy storage SOC status is directly obtained through the energy storage management system, and the electricity price signal is obtained through the data collection system provided by the power grid company; the collected raw base station parameters are preprocessed and stored in the database. The preprocessing includes data cleaning, missing value processing, and outlier detection to ensure the accuracy and consistency of the data, and ultimately obtain the target base station parameters.

[0055] Step S202: The future load curve is predicted by the load forecasting model based on the historical load data, and the future electricity price sequence is predicted by the electricity price forecasting model based on the historical electricity price data. The charging and discharging strategy of the 5G base station is obtained based on the future load curve, the future electricity price sequence and the target base station parameters.

[0056] Specifically, the process of formulating the charge and discharge strategy in this embodiment may include the following steps:

[0057] Step 1: Load forecasting model prediction:

[0058] The load forecasting model can be an LSTM (Long Short-Term Memory) neural network, which is used to predict base station loads:

[0059]

[0060] In the above formula, : LSTM weight matrix, H: prediction time domain (such as 24 hours).

[0061] Step 2: Electricity price prediction model prediction:

[0062] The electricity price prediction model can be a hybrid model that combines ARIMA (AutoRegressive Integrated Moving Average) and XGBoost (Extreme Gradient Boosting):

[0063]

[0064] In the above formula, ∈[0,1]: model fusion weight coefficient.

[0065] Step 3: Generate charging and discharging strategy:

[0066] Formulate charging and discharging strategies based on prediction results:

[0067]

[0068] In the above formula, : Charging efficiency, : Low threshold of electricity price (such as 0.3 yuan / kWh).

[0069] For example, the terminal first stabilizes historical load data to extract seasonal and trend factors; then constructs an LSTM neural network to estimate network parameters; and finally, uses the LSTM neural network to predict future load curves. The time series characteristics of historical electricity price data are analyzed to extract daily, weekly, and monthly periodic factors. Then, an electricity price prediction model is constructed to fit the relationship between electricity price and load. Finally, the model is used to generate a future electricity price series. Based on the future load curve, future electricity price series, and target base station parameters, a charging and discharging strategy for the 5G base station is formulated.

[0070] Step S203: Determine the electricity purchase cost, frequency regulation benefit, and loss cost according to the charge and discharge strategy, and build a multi-objective optimization model based on the electricity purchase cost, frequency regulation benefit, and loss cost.

[0071] The multi-objective optimization function (weighted minimization) included in the multi-objective optimization model can be minF = electricity purchase cost - frequency regulation benefit + loss cost:

[0072]

[0073] In the above formula, : The amount of electricity purchased from the power grid, : FM gain, : Loss weight coefficient.

[0074] Specifically, the terminal first calculates the electricity purchase cost according to the charging and discharging strategy, and optimizes the electricity purchase period and amount based on the predicted future load curve and future electricity price series; then calculates the frequency regulation revenue based on the predicted future load curve and frequency regulation price coefficient; then calculates the loss cost, including charging and discharging efficiency loss, inverter loss and line loss; finally, a multi-objective optimization model is constructed based on the electricity purchase cost, frequency regulation revenue and loss cost.

[0075] In step S204, the target problem is determined in the multi-objective optimization model, and the target problem is solved by the alternating direction multiplier method to obtain the optimal solution. The charge and discharge strategy is dynamically adjusted based on the optimal solution and the battery health feedback information of the 5G base station. When the adjusted charge and discharge strategy meets the optimization termination condition, the optimization result is output.

[0076] Specifically, the terminal decomposes the target problem into a coordinated peak-shaving response problem, an autonomous scheduling problem, and a power allocation problem. It then constructs a coordinated peak-shaving response model to optimize the peak-shaving synergy between base stations, an autonomous scheduling model to optimize the charge and discharge strategies of individual base stations, and a power allocation model to achieve balanced energy distribution and minimize losses. The optimal solution is obtained by alternately solving these three sub-problems using the alternating direction multiplier method. Based on the optimal solution and combined with battery health feedback, the charge and discharge strategy is dynamically adjusted through the cloud platform to ensure that the battery SOC remains within a reasonable range. Once the adjusted charge and discharge strategy meets the optimization termination conditions, the optimization results are output.

[0077] The above-mentioned aggregate optimization method based on 5G base station energy storage participating in demand response obtains the charging and discharging strategy of the 5G base station based on the future load curve, future electricity price series and target base station parameters. Then, based on the charging and discharging strategy, the power purchase cost, frequency regulation revenue and loss cost are determined. Based on the power purchase cost, frequency regulation revenue and loss cost, a multi-objective optimization model is constructed. Then, the target problem is determined in the multi-objective optimization model, and the target problem is solved to obtain the optimal solution through the alternating direction multiplication method. According to the optimal solution and the battery health feedback information of the 5G base station, the charging and discharging strategy is dynamically adjusted. When the adjusted charging and discharging strategy meets the optimization termination conditions, the optimization result output is executed. This application introduces a multi-time-scale optimization framework, combines the load forecast and electricity price forecast in the day-ahead stage, and generates a charging and discharging strategy for 5G base stations, effectively solving the problems of resource dispersion and single-target optimization in traditional solutions, and improving the overall system efficiency. At the same time, the alternating direction multiplier method is used to solve the target problem to obtain the optimal solution, realizing the functions of efficient solution and dynamic coordination, meeting the real-time optimization needs, thereby giving full play to the potential value of 5G base stations and improving resource utilization efficiency. By introducing rolling time domain prediction and dynamic correction strategy for battery health, the service life of energy storage is effectively extended, maintenance costs are reduced, and system reliability is improved.

[0078] In one embodiment, Figure 3 As shown, in the above step S204, the target problem is determined in the multi-objective optimization model, and the target problem is solved by the alternating direction multiplier method to obtain the optimal solution, which specifically includes the following steps:

[0079] Step S301 : determining a target problem according to a multi-objective optimization function in a multi-objective optimization model, and decomposing the target problem into a coordinated peak-shaving response problem, an autonomous scheduling problem, and a power allocation problem.

[0080] Step S302: construct a collaborative peak-shaving response model based on the synergy effect matrix between 5G base stations, construct an autonomous scheduling model, and construct a power allocation model based on the power allocation matrix.

[0081] Step S303: Through the coordinated peak-shaving response model, the autonomous scheduling model and the power allocation model, the alternating direction multiplier method is used to alternately solve the coordinated peak-shaving response problem, the autonomous scheduling problem and the power allocation problem to obtain the optimal solution.

[0082] Among them, the collaborative peak-shaving model (global constraint):

[0083]

[0084] Autonomous scheduling model (individual optimization):

[0085]

[0086] Power distribution model (loss leveling):

[0087]

[0088] Specifically, the terminal determines the target problem based on the multi-objective optimization function in the multi-objective optimization model and decomposes the target problem into a coordinated peak-shaving response problem, an autonomous scheduling problem, and a power allocation problem. First, a coordinated effect matrix between base stations is constructed. Then, a peak-shaving response model is established, taking into account the regulation capability and response speed of each base station. Finally, a game theory algorithm is used to optimize the coordinated strategy. First, a battery charging and discharging model is established, taking into account the battery's efficiency and lifespan. Then, day-ahead and real-time scheduling models are constructed to optimize the charging and discharging periods and power allocation. Finally, a dynamic programming algorithm is used to solve the optimal strategy. First, a power allocation matrix is ​​constructed, taking into account the load and regulation capability of each base station. Then, energy balance constraints are established. Finally, a linear programming algorithm is used to optimize power allocation. The ADMM (Alternating Direction Method of Multipliers) algorithm is used to alternately solve the coordinated peak-shaving response problem, the autonomous scheduling problem, and the power allocation problem. The variables are initialized, the maximum number of iterations and the convergence accuracy are set, and the iterative calculation is performed until convergence, ultimately outputting the optimal solution.

[0089] In one embodiment, in the above step S202, the charging and discharging strategy of the 5G base station is obtained according to the future load curve, the future electricity price sequence, and the target base station parameters, which specifically includes the following steps:

[0090] Decompose the future load curve into the adjustable part of the base station and the non-adjustable part of the base station; for the adjustable part of the base station, formulate a charging and discharging plan based on the future electricity price sequence, calculate the required frequency regulation capacity based on the charging and discharging plan, and determine the market bidding strategy based on the frequency regulation capacity; generate a charging and discharging strategy based on the charging and discharging plan, the market bidding strategy, and the non-adjustable part of the base station.

[0091] Specifically, the terminal first decomposes the predicted future load curve into the adjustable part and the non-adjustable part of the base station; then, for the adjustable part of the base station, it formulates a charging and discharging plan based on the predicted future electricity price sequence, calculates the required frequency regulation capacity according to the charging and discharging plan, and determines the market bidding strategy according to the frequency regulation capacity; generates a charging and discharging strategy based on the charging and discharging plan, the market bidding strategy and the non-adjustable part of the base station.

[0092] In one embodiment, before dynamically adjusting the charge and discharge strategy based on the optimal solution and the battery health feedback information of the 5G base station, the method of the present application further includes the following steps:

[0093] Obtain the nominal battery parameters and historical operating parameters of the 5G base station, and build a battery health assessment model based on the nominal battery parameters and historical operating parameters. Use the battery health assessment model to predict the available capacity sequence and charge and discharge limit sequence of the currently used battery of the 5G base station based on the future load curve and future electricity price sequence. Generate battery health feedback information based on the available capacity sequence and charge and discharge limit sequence.

[0094] Specifically, the terminal first calculates the nominal battery parameters and historical operating parameters of the 5G base station. Based on these parameters and historical operating parameters, the terminal constructs a battery health assessment model, taking into account the battery's service life and cycle efficiency. A capacity decay model is also established to describe how battery capacity changes over time. Future load curves and future electricity price series are analyzed to extract short-term and medium-term trends. An ARIMA model is then constructed to describe the time series characteristics of load and electricity prices. The battery health assessment model is used to predict the available capacity series and charge and discharge limit series of the 5G base station's currently used battery. Based on the available capacity series and charge and discharge limit series, battery health feedback information is generated.

[0095] In one embodiment, the method of the present application further includes the following steps:

[0096] When the adjusted charge and discharge strategy meets the preset termination mark, it is determined that the adjusted charge and discharge strategy meets the optimization termination condition; when the adjusted charge and discharge strategy does not meet the termination mark, return to the step of collecting the original base station parameters of the 5G base station until the optimization termination condition is met.

[0097] The preset termination flag can be set as:

[0098]

[0099] In the above formula, : Convergence threshold, execution deviation = .

[0100] Specifically, the terminal determines whether the adjusted charge and discharge strategy meets the preset termination mark. When it is identified that the adjusted charge and discharge strategy meets the preset termination mark, it determines that the adjusted charge and discharge strategy meets the optimization termination condition. When it is identified that the adjusted charge and discharge strategy does not meet the termination mark, it returns to the step of collecting the original base station parameters of the 5G base station until the optimization termination condition is met.

[0101] In one embodiment, in step S204, performing the optimization result output specifically includes the following steps:

[0102] Based on the adjusted charging and discharging strategy, an optimization result including the day-ahead plan and real-time scheduling instructions is generated and distributed to each 5G base station. The actual operating status of the system and the execution of the optimization result are monitored. If the actual operating status is inconsistent with the execution status, the system returns to the step of collecting the original base station parameters of the 5G base station and re-optimizes. If they are consistent, the optimization process is completed.

[0103] Specifically, the terminal generates an optimization result including the day-ahead plan and real-time scheduling instructions based on the adjusted charging and discharging strategy, and sends the optimization result to each 5G base station through the 5G communication network or optical fiber network; monitors the actual operating status of the system and the execution of the optimization result; if the actual operating status is inconsistent with the execution status, it returns to the step of collecting the original base station parameters of the 5G base station for re-optimization; if they are consistent, the optimization process is completed.

[0104] In order to more clearly illustrate the aggregation optimization method based on 5G base station energy storage participating in demand response provided by the embodiment of this application, the following is a specific embodiment of the aggregation optimization method based on 5G base station energy storage participating in demand response. As an application embodiment, Figure 4 As shown, another aggregation optimization method based on 5G base station energy storage participating in demand response is provided, which specifically includes the following steps:

[0105] Step 1: Data interaction and collection:

[0106] Step 101: Establish a communication connection:

[0107] A data channel is established between the base station and the aggregator via a 5G / fiber network. The communication protocol meets the following requirements:

[0108]

[0109] In the above formula, : Communication delay, : Bit error rate.

[0110] Step 102: Collect data:

[0111] Real-time collection of base station parameters:

[0112] In the above formula, : The remaining power of the i-th base station at time t, : Maximum energy storage capacity, : Battery charging status of the i-th base station at time t.

[0113] Step 103: Data preprocessing:

[0114] Clean and interpolate abnormal data:

[0115] In the above formula, : the mean value of the parameter x of the i-th base station, : standard deviation.

[0116] Step 2: Build a multi-objective optimization model:

[0117] Step 201: Load forecasting model:

[0118] Using LSTM neural network to predict base station load:

[0119] In the above formula, : LSTM weight matrix, H: prediction time domain (such as 24 hours).

[0120] Step 202: Electricity price prediction model:

[0121] Combining ARIMA and XGBoost hybrid models:

[0122] In the above formula, ∈[0,1]: model fusion weight coefficient.

[0123] Step 203: Generate a charge and discharge plan:

[0124] Formulate charging and discharging strategies based on prediction results:

[0125] In the above formula, : Charging efficiency, : Low threshold of electricity price (such as 0.3 yuan / kWh).

[0126] Step 204: Objective function definition:

[0127] Multi-objective optimization function (weighted minimization): minF = electricity purchase cost - frequency regulation benefit + loss cost, which is specifically expressed as follows:

[0128]

[0129] In the above formula, : The amount of electricity purchased from the power grid, : FM gain, : Loss weight coefficient.

[0130] Step 3: Improve the ADMM algorithm to solve:

[0131] Steps 301-304, problem decomposition and sub-model construction:

[0132] Collaborative peak-shaving model (global constraints):

[0133]

[0134] Autonomous scheduling model (individual optimization):

[0135]

[0136] Power distribution model (loss leveling):

[0137]

[0138] Step 305: ADMM alternately iterates to solve:

[0139] Improved ADMM iterative formula (introducing adaptive inertia weight ):

[0140]

[0141] In the above formula, : augmented Lagrangian function, : penalty factor, : Maximum number of iterations.

[0142] Step 4: Dynamic policy modification:

[0143] Step 401: Battery health model:

[0144] Based on the exponential model of capacity fading:

[0145] In the above formula, : initial capacity, : Cumulative charge and discharge times, : Battery activation energy.

[0146] Step 402: Rolling time domain prediction:

[0147] Update the forecast window every 15 minutes:

[0148] In the above formula, .

[0149] Steps 403-404, strategy adjustment and feedback:

[0150] Dynamically correct SOC constraint range (example):

[0151]

[0152] Steps 5-6: Termination judgment and result execution:

[0153] Termination condition formulation:

[0154]

[0155] In the above formula, : Convergence threshold, execution deviation = .

[0156] The beneficial effects brought about by the above embodiment are as follows:

[0157] 1) By introducing a multi-timescale optimization framework and combining day-ahead load forecasting with electricity price signal analysis, this approach enables intelligent charging and discharging planning and market bidding strategies for base station energy storage. This effectively addresses the resource fragmentation and single-objective optimization issues of traditional solutions, improving overall system efficiency.

[0158] 2) A dynamic zoning and priority scheduling mechanism is adopted to divide the energy storage SOC into emergency frequency regulation zone, economic response zone and prohibited discharge zone, responding to different demand scenarios according to priority, achieving multi-objective collaborative optimization, and fully considering the synergistic benefits of the energy market and ancillary service market.

[0159] 3) Based on the Minkowski sum method, dynamic aggregation of heterogeneous resources is achieved, an adjustable domain model is constructed, and the distributed 5G base station energy storage resources are effectively integrated to improve resource utilization efficiency.

[0160] 4) By introducing a graph convolutional neural network, multimodal fusion of the base station load time series knowledge graph and battery parameters is performed to achieve high-precision SOC estimation, overcoming the problems of slow solution speed and poor convergence of traditional algorithms when dealing with large-scale heterogeneous variables.

[0161] 5) An improved distributed optimization algorithm (ADMM) is used to decompose the large-scale optimization problem into coordinated peak-shaving response, autonomous scheduling, and power allocation sub-problems, achieving efficient solution and meeting real-time optimization requirements.

[0162] 6) By introducing rolling time-domain prediction and dynamic battery health correction strategies, the service life of energy storage is effectively extended, maintenance costs are reduced, and system reliability is improved. The voltage fluctuation is reduced by 29.6%, the SOC estimation error is less than 2%, and the algorithm solution speed is increased by 40%.

[0163] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0164] Based on the same inventive concept, an embodiment of the present application further provides an aggregate optimization device based on 5G base station energy storage participating in demand response, which is used to implement the above-mentioned aggregate optimization method based on 5G base station energy storage participating in demand response. The implementation solution provided by this device is similar to the implementation solution described in the above-mentioned method. Therefore, the specific limitations of one or more embodiments of the aggregate optimization device based on 5G base station energy storage participating in demand response provided below can be found in the above-mentioned limitations of the aggregate optimization method based on 5G base station energy storage participating in demand response, and will not be repeated here.

[0165] In an exemplary embodiment, Figure 5 As shown, an aggregation optimization device based on 5G base station energy storage participating in demand response is provided, including:

[0166] The data acquisition module 501 is used to collect the original base station parameters of the 5G base station, clean and interpolate the abnormal data in the original base station parameters, and obtain the target base station parameters;

[0167] Strategy formulation module 502, configured to predict a future load curve using a load forecasting model based on historical load data, predict a future electricity price sequence using an electricity price forecasting model based on historical electricity price data, and determine a charging and discharging strategy for the 5G base station based on the future load curve, the future electricity price sequence, and target base station parameters;

[0168] The model building module 503 is used to determine the power purchase cost, frequency regulation benefit and loss cost according to the charging and discharging strategy, and to build a multi-objective optimization model based on the power purchase cost, frequency regulation benefit and loss cost;

[0169] The optimization output module 504 is used to determine the target problem in the multi-objective optimization model, solve the target problem by the alternating direction multiplier method to obtain the optimal solution, dynamically adjust the charge and discharge strategy based on the optimal solution and the battery health feedback information of the 5G base station, and execute the optimization result output when the adjusted charge and discharge strategy meets the optimization termination condition.

[0170] In one embodiment, the optimization output module 504 is also used to determine the target problem based on the multi-objective optimization function in the multi-objective optimization model, and decompose the target problem into a collaborative peak-shaving response problem, an autonomous scheduling problem, and a power allocation problem; construct a collaborative peak-shaving response model based on the collaborative effect matrix between 5G base stations, construct an autonomous scheduling model, and construct a power allocation model based on the power allocation matrix; through the collaborative peak-shaving response model, the autonomous scheduling model, and the power allocation model, the alternating direction multiplier method is used to alternately solve the collaborative peak-shaving response problem, the autonomous scheduling problem, and the power allocation problem to obtain the optimal solution.

[0171] In one embodiment, the strategy formulation module 502 is further used to decompose the future load curve into an adjustable part of the base station and an unadjustable part of the base station; for the adjustable part of the base station, a charging and discharging plan is formulated according to the future electricity price sequence, the required frequency regulation capacity is calculated according to the charging and discharging plan, and the market bidding strategy is determined according to the frequency regulation capacity; and a charging and discharging strategy is generated according to the charging and discharging plan, the market bidding strategy, and the unadjustable part of the base station.

[0172] In one embodiment, the aggregation optimization device based on 5G base station energy storage participating in demand response also includes a battery feedback module, which is used to obtain the battery nominal parameters and battery historical operating parameters of the 5G base station, and construct a battery health assessment model based on the battery nominal parameters and battery historical operating parameters; predict the available capacity sequence and charge and discharge limit sequence of the currently used battery of the 5G base station through the battery health assessment model based on the future load curve and the future electricity price sequence; and generate battery health feedback information based on the available capacity sequence and the charge and discharge limit sequence.

[0173] In one embodiment, the aggregation optimization device based on 5G base station energy storage participating in demand response also includes a condition judgment module, which is used to determine that the adjusted charging and discharging strategy meets the optimization termination condition when the adjusted charging and discharging strategy meets the preset termination mark; when the adjusted charging and discharging strategy does not meet the termination mark, return to the step of collecting the original base station parameters of the 5G base station until the optimization termination condition is met.

[0174] In one embodiment, the optimization output module 504 is further used to generate an optimization result including a day-ahead plan and real-time scheduling instructions based on the adjusted charging and discharging strategy, and send the optimization result to each 5G base station; monitor the actual operating status of the system and the execution of the optimization result; if the actual operating status is inconsistent with the execution status, return to the step of collecting the original base station parameters of the 5G base station for re-optimization, and if they are consistent, complete the optimization process.

[0175] Each module in the aforementioned aggregated optimization device for participating in demand response using 5G base station energy storage can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0176] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, mobile cellular networks, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements an aggregated optimization method based on 5G base station energy storage participating in demand response. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0177] Those skilled in the art will understand that Figure 6The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0178] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0179] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0180] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0181] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0182] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0183] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0184] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An aggregation optimization method based on 5G base station energy storage participating in demand response, characterized in that: The method comprises: Collecting original base station parameters of the 5G base station, cleaning and interpolating abnormal data in the original base station parameters to obtain target base station parameters; Predicting a future load curve using a load forecasting model based on historical load data, predicting a future electricity price sequence using an electricity price forecasting model based on historical electricity price data, and obtaining a charging and discharging strategy for the 5G base station based on the future load curve, the future electricity price sequence, and the target base station parameters; Determining electricity purchase costs, frequency regulation benefits, and loss costs according to the charging and discharging strategy, and constructing a multi-objective optimization model based on the electricity purchase costs, the frequency regulation benefits, and the loss costs; A target problem is determined in the multi-objective optimization model, and an optimal solution is obtained by solving the target problem using the alternating direction multiplier method. The charge and discharge strategy is dynamically adjusted based on the optimal solution and the battery health feedback information of the 5G base station. When the adjusted charge and discharge strategy meets the optimization termination condition, the optimization result is output.

2. The method according to claim 1, characterized in that Determining a target problem in the multi-objective optimization model and solving the target problem by an alternating direction multiplier method to obtain an optimal solution include: Determining the target problem according to the multi-objective optimization function in the multi-objective optimization model, and decomposing the target problem into a coordinated peak-shaving response problem, an autonomous scheduling problem, and a power allocation problem; Building a coordinated peak-shaving response model based on the synergy effect matrix between the 5G base stations, building an autonomous scheduling model, and building a power allocation model based on the power allocation matrix; Through the collaborative peak-shaving response model, the autonomous scheduling model and the power allocation model, the alternating direction multiplier method is used to alternately solve the collaborative peak-shaving response problem, the autonomous scheduling problem and the power allocation problem to obtain the optimal solution.

3. The method according to claim 1, characterized in that The obtaining, according to the future load curve, the future electricity price sequence, and the target base station parameters, a charging and discharging strategy of the 5G base station includes: Decomposing the future load curve into a base station adjustable portion and a base station non-adjustable portion; Formulate a charging and discharging plan for the adjustable portion of the base station according to the future electricity price sequence, calculate the required frequency regulation capacity according to the charging and discharging plan, and determine a market bidding strategy based on the frequency regulation capacity; The charging and discharging strategy is generated according to the charging and discharging plan, the market bidding strategy and the unadjustable part of the base station.

4. The method according to claim 1, wherein Before dynamically adjusting the charge and discharge strategy according to the optimal solution and the battery health feedback information of the 5G base station, the method further includes: Obtaining nominal battery parameters and historical battery operating parameters of the 5G base station, and building a battery health assessment model based on the nominal battery parameters and the historical battery operating parameters; Predicting the available capacity sequence and the charge and discharge limit sequence of the currently used battery of the 5G base station by using the battery health assessment model according to the future load curve and the future electricity price sequence; The battery health feedback information is generated according to the available capacity sequence and the charge and discharge limit sequence.

5. The method according to claim 1, characterized in that The method further comprises: When the adjusted charge-discharge strategy meets a preset termination flag, determining that the adjusted charge-discharge strategy meets the optimization termination condition; In the case that the adjusted charge and discharge strategy does not meet the termination flag, return to the step of collecting the original base station parameters of the 5G base station until the optimization termination condition is met.

6. The method according to any one of claims 1 to 5, characterized in that The execution optimization result output includes: According to the adjusted charging and discharging strategy, an optimization result including a day-ahead plan and a real-time scheduling instruction is generated, and the optimization result is sent to each of the 5G base stations; Monitoring the actual operating status of the system and the execution of the optimization results; If the actual operating status is inconsistent with the execution status, return to the step of collecting the original base station parameters of the 5G base station for re-optimization. If they are consistent, the optimization process is completed.

7. An aggregation optimization device based on 5G base station energy storage participating in demand response, characterized in that: The device comprises: A data acquisition module is used to collect the original base station parameters of the 5G base station, clean and interpolate the abnormal data in the original base station parameters, and obtain the target base station parameters; a strategy formulation module, configured to predict a future load curve using a load forecasting model based on historical load data, predict a future electricity price sequence using an electricity price forecasting model based on historical electricity price data, and obtain a charging and discharging strategy for the 5G base station based on the future load curve, the future electricity price sequence, and the target base station parameters; a model building module, configured to determine the electricity purchase cost, the frequency regulation benefit, and the loss cost according to the charging and discharging strategy, and to build a multi-objective optimization model based on the electricity purchase cost, the frequency regulation benefit, and the loss cost; An optimization output module is used to determine a target problem in the multi-objective optimization model, solve the target problem by an alternating direction multiplier method to obtain an optimal solution, dynamically adjust the charge and discharge strategy according to the optimal solution and the battery health feedback information of the 5G base station, and execute optimization result output when the adjusted charge and discharge strategy meets the optimization termination condition.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images