Method and device for determining operation strategy of energy storage system and computer equipment

Abstract

The invention relates to an energy storage system operation strategy determination method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of obtaining energy power prediction data of an energy storage power system in a prediction total step length, determining a target energy storage system operation strategy in each prediction step length based on the energy power prediction data, a preset optimization target and a preset constraint condition, adjusting the target energy storage system operation strategy, and determining the energy storage power of the energy storage power system according to the target energy storage system operation strategy. And the change rate of the charging and discharging power of the energy storage system in the energy storage power system is in a preset change rate range. By adopting the method, the power fluctuation in the charging and discharging process of the energy storage system can be reduced, the negative influence on the battery performance is reduced, the service life of the energy storage system can be prolonged, and the stability and controllability of the system are improved.

Description

Technical Field

[0001] The present application relates to the field of energy storage control technology, and in particular to a method, device, computer equipment, storage medium and computer program product for determining an energy storage system operation strategy. Background Art

[0002] In recent years, the gap between peak and valley loads in the power grid system has continued to widen, leading to an aggravated peak load supply gap in the power grid, affecting the safe and stable operation of the power grid system.

[0003] In order to solve the problem of the widening gap between peak and valley loads in the power grid, the commonly used means include using energy storage systems to reduce peak loads and fill valley loads. The energy storage system releases electricity when the power supply of the power grid is insufficient during peak loads, and charges during low or flat loads to meet load demand.

[0004] However, the above-mentioned method of using an energy storage system to shave peak loads and fill valley loads requires the energy storage system to perform frequent charging and discharging operations, and if there are abnormal charging and discharging conditions, it will have a negative impact on the performance of the battery.

[0005] It can be seen that the above-mentioned approach of peak shaving and valley filling through energy storage systems has the problem of reducing battery performance. Summary of the invention

[0006] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining an energy storage system operation strategy that can reduce the negative impact of battery performance in response to the above technical problems.

[0007] In a first aspect, the present application provides a method for determining an energy storage system operation strategy. The method comprises:

[0008] Obtain energy power prediction data of the energy storage power system within the total prediction step length;

[0009] Determine the target energy storage system operation strategy within each prediction step based on energy power prediction data, preset optimization goals, and preset constraints;

[0010] The target energy storage system operation strategy is adjusted so that the rate of change of the charging and discharging power of the energy storage system in the energy storage power system is within a preset rate of change range.

[0011] In the technical solution of the embodiment of the present application, by obtaining the energy power prediction data of the energy storage power system within the total prediction step, basic data is provided for determining the operation strategy of the energy storage system, and the target energy storage system operation strategy within each prediction step is obtained through the energy power prediction data, the preset optimization target and the preset constraint conditions, that is, the energy storage system operation strategy after optimization calculation is obtained to improve energy utilization and system performance. Finally, by adjusting the target energy storage system operation strategy so that the charging and discharging power of the energy storage system changes smoothly, the power fluctuation during the charging and discharging process of the energy storage system can be reduced, the negative impact on battery performance can be reduced, the life of the energy storage system can be extended, and the stability and controllability of the system can be improved. In summary, the adoption of the above scheme can reduce the negative impact on battery performance and improve the stability and controllability of the system.

[0012] In some embodiments, based on the energy power forecast data, the preset optimization target, and the preset constraints, determining the target energy storage system operation strategy within each forecast step includes:

[0013] Based on energy power forecast data, a pre-built linear programming model for energy storage charging and discharging power, and preset constraints, the target energy storage system operation strategy within each forecast step is determined. The linear programming model for energy storage charging and discharging power is constructed based on preset optimization objectives.

[0014] In the technical solution of the embodiment of the present application, the operation strategy of the energy storage system is determined and converted into a linear programming problem through a linear programming model of energy storage charging and discharging power. The model is solved through energy power prediction data and preset constraints to quickly and accurately obtain the optimal target energy storage system operation strategy within each prediction step.

[0015] In some embodiments, based on energy power forecast data, a pre-built energy storage charging and discharging power linear programming model, and preset constraints, determining a target energy storage system operation strategy within each forecast step includes:

[0016] Based on energy power forecast data, a pre-built linear programming model for energy storage charging and discharging power, and preset constraints, multiple candidate energy storage system operation strategies that meet the preset constraints within each forecast step are generated with the minimum charging and discharging power adjustment step of the energy storage system as the step interval;

[0017] Determine the target value corresponding to each candidate energy storage system operation strategy;

[0018] According to the target values ​​corresponding to the candidate energy storage system operation strategies, a target energy storage system operation strategy within each prediction step is selected from a plurality of candidate energy storage system operation strategies;

[0019] The target value includes any one of electricity cost, energy storage system income and energy storage system life.

[0020] In the technical solution of the embodiment of the present application, energy power prediction data, energy storage system characteristics, and constraints are comprehensively considered to generate multiple candidate energy storage system operation strategies, and the best energy storage system operation strategy for each prediction step is screened out from the dimensions of electricity costs, energy storage system revenue, or energy storage system life, which can improve energy utilization efficiency and economic benefits.

[0021] In some embodiments, based on energy power prediction data, a pre-built linear programming model of energy storage charging and discharging power, and preset constraints, a minimum charging and discharging power adjustment step of the energy storage system is used as a step interval, and multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step are generated, including:

[0022] Based on energy power prediction data, a pre-built linear programming model for energy storage charging and discharging power, and preset constraints, the minimum charging and discharging power adjustment step of the energy storage system is used as the step interval. Multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step are generated by enumeration.

[0023] In the technical solution of the embodiment of the present application, all possible energy storage system operation strategies can be traversed by enumeration to obtain a comprehensive set of candidate strategies. Combined with the constraints, the optimal energy storage system operation strategy within each prediction step can be screened out, which can minimize electricity costs and improve economic benefits and energy utilization.

[0024] In some embodiments, the energy power prediction data includes a renewable energy power prediction value and a load total power prediction value;

[0025] Based on the energy power forecast data, the pre-built energy storage charging and discharging power linear programming model, and the preset constraints, before determining the target energy storage system operation strategy within each forecast step, it also includes:

[0026] Get the latest demand electricity prices, rate adjustment charges, and time-of-use electricity prices;

[0027] Based on energy power forecast data, demand electricity price, interest rate adjustment fee, time-of-use electricity price, and preset constraints, combined with the minimum charging and discharging power adjustment step of the energy storage system, and with the goal of maximizing the rate of return of the energy storage power system, a linear programming model for energy storage charging and discharging power is constructed;

[0028] Among them, the preset constraints include: when it is monitored that the predicted power value of renewable energy exceeds the predicted power value of the total load, the remaining power is directed to the energy storage system to charge the energy storage system, and the remaining power is determined based on the predicted power value of renewable energy and the predicted power value of the total load.

[0029] In the technical solution of the embodiment of the present application, by comprehensively considering energy power forecast data, demand electricity price, interest rate adjustment fee and time-of-use electricity price, etc., a linear programming model of energy storage system charging and discharging power is constructed, which can comprehensively analyze the operation strategy of the energy storage system and maximize the systematic rate of return. By setting the constraints of renewable energy power and overall load power, the local consumption capacity of renewable energy power generation can be improved. In addition, since the on-grid electricity price of renewable energy is lower than the price of electricity obtained by the energy storage park from the power grid, the overall benefit of the system is also improved.

[0030] In some embodiments, adjusting the charging strategy in the target energy storage system operation strategy includes:

[0031] Locate the charging strategy in the target energy storage system operation strategy, and identify the continuous charging strategy in the target energy storage system operation strategy;

[0032] In the case where the charging power in the continuous charging strategy is unbalanced, the charging power in the continuous charging strategy is adjusted according to a preset power change rate so that the change rate of the charging power is within a preset change rate range.

[0033] In the technical solution of the embodiment of the present application, by adjusting the charging power in the continuous charging strategy, the charging power in the continuous charging strategy can be balanced, which is beneficial to maximize the charging capacity of the energy storage system, improve the efficiency and stability of the system, and reduce the imbalance in the charging process, thereby extending the service life of the energy storage system.

[0034] In some embodiments, adjusting the charging strategy in the target energy storage system operation strategy includes:

[0035] When the charging strategy in the target energy storage system operation strategy has abnormal charging power, smoothing or interpolating the abnormal charging power;

[0036] The abnormal charging power includes a charging power whose change rate is greater than a preset change rate threshold.

[0037] In the technical solution of the embodiment of the present application, by smoothing or interpolating the abnormal charging power, the fluctuation of the charging power can be eliminated, so that the charging power changes more gradually, which is conducive to making full use of the charging time of the energy storage system, reducing the charging power, and extending the life of the energy storage system.

[0038] In some embodiments, obtaining energy power prediction data of the energy storage power system within the total prediction step length includes:

[0039] Obtain real-time energy power data and historical energy power data of energy storage power system;

[0040] Based on the real-time energy power data and the historical energy power data, the energy power within the total prediction step is predicted to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0041] In the technical solution of the embodiment of the present application, energy power is predicted based on real-time energy power data and historical energy power data, and energy power prediction data within the total prediction step is provided to the energy storage power system, which can facilitate the system operator to formulate and make decisions on operation strategies to achieve effective management and optimal utilization of energy.

[0042] In some embodiments, based on the real-time energy power data and the historical energy power data, the energy power within the predicted total step length is predicted, and the energy power prediction data of the energy storage power system within the predicted total step length is obtained, including:

[0043] Perform data preprocessing on real-time energy power data and historical energy power data;

[0044] Based on the preprocessed real-time energy power data and historical energy power data, the energy power within the total prediction step is predicted through a preset multi-dimensional time series prediction algorithm to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0045] In the technical solution of the embodiment of the present application, data quality can be improved through data preprocessing, and energy power can be predicted for real-time energy power data and historical energy power data through a preset multi-dimensional time series prediction algorithm, so as to obtain more accurate energy power prediction data.

[0046] In a second aspect, the present application also provides a device for determining an energy storage system operation strategy. The device comprises:

[0047] A data prediction module is used to obtain energy power prediction data of the energy storage power system within the total prediction step length;

[0048] An operation strategy generation module is used to determine the target energy storage system operation strategy within each prediction step based on energy power prediction data, preset optimization goals, and preset constraints;

[0049] The strategy adjustment module is used to adjust the target energy storage system operation strategy so that the change rate of the charging and discharging power of the energy storage system in the energy storage power system is within a preset change rate range.

[0050] In a third aspect, the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps in the above-mentioned energy storage system operation strategy determination method embodiments are implemented.

[0051] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-mentioned energy storage system operation strategy determination method embodiments.

[0052] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned energy storage system operation strategy determination method embodiments are implemented.

[0053] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0055] Figure 1 This is an application environment diagram of the method for determining the operation strategy of the energy storage system in some embodiments of the present application;

[0056] Figure 2 A schematic diagram of a flow chart of a method for determining an energy storage system operation strategy in some embodiments of the present application;

[0057] Figure 3 A schematic diagram of a flow chart of a method for determining an energy storage system operation strategy in other embodiments of the present application;

[0058] Figure 4 A schematic flow chart of the steps of screening the target energy storage system operation strategy in some embodiments of the present application;

[0059] Figure 5 A schematic diagram of a flow chart of a method for determining an energy storage system operation strategy in other embodiments of the present application;

[0060] Figure 6 A schematic diagram of a flow chart of a method for determining an energy storage system operation strategy in some other embodiments of the present application;

[0061] Figure 7 A detailed flowchart of a method for determining an energy storage system operation strategy in some embodiments of the present application;

[0062] Figure 8This is a schematic diagram of the effect of executing the target energy storage system operation strategy obtained by this method in some embodiments of the present application;

[0063] Fig. 9 This is a structural block diagram of a device for determining an energy storage system operation strategy in some embodiments of the present application;

[0064] Fig.10 A structural block diagram of a device for determining an energy storage system operation strategy in some other embodiments of the present application;

[0065] Fig.11 This is a diagram of the internal structure of a computer device in some embodiments of the present application. DETAILED DESCRIPTION

[0066] The following embodiments of the technical solution of the present application will be described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0068] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0070] In recent years, the energy-saving and environmentally friendly characteristics of electric vehicles, renewable energy generation and energy storage systems have become a hot topic in the research of smart grid systems. As the gap between peak and valley loads in the power grid system continues to widen, the peak load supply gap in the power grid has intensified, affecting the safe and stable operation of the power grid system.

[0071] In order to solve the problem of the widening gap between peak and valley loads in the power grid, currently commonly used methods include using energy storage systems to reduce peak loads and fill valley loads. The energy storage system releases electricity when the power supply of the power grid is insufficient during peak loads, and charges during low or flat loads to meet load demand. Among them, the energy storage system can be a distributed energy storage system.

[0072] However, the above-mentioned method of using an energy storage system to shave peak loads and fill valley loads requires the energy storage system to perform frequent charging and discharging operations, which will affect the performance of the battery and shorten the battery life. In addition, if the depth of discharge is too great during the discharge process, it will affect the safety performance of the battery.

[0073] In order to alleviate the impact of the above-mentioned peak shaving and valley filling on battery life and safety performance, research has found that a dynamic power adjustment mechanism can be introduced to balance the supply and demand relationship, reduce the impact of discharge depth on battery safety, and optimize the charging and discharging strategy during the charging and discharging process of the energy storage system to achieve optimal control of the energy storage system and reduce the impact of frequent charging and discharging on battery life.

[0074] Based on the above considerations, the present application provides a solution for determining the operation strategy of an energy storage system. Specifically, the determination of the operation strategy of the energy storage system can be converted into an optimization problem, the optimization target can be determined, and several constraints can be set. Then, by predicting the energy power of the energy storage park, such as photovoltaic power generation power and the overall load power of the park, the energy power prediction data within the total prediction step can be obtained. Then, the optimization target is optimized in combination with the energy prediction data and the preset constraints to obtain the optimal solution, that is, the optimal target energy storage system operation strategy is obtained. In order to further reduce the negative impact of charging and discharging on battery performance, the charging strategy and discharging strategy in the target energy storage system operation strategy can be optimized and adjusted to smooth the changes in charging and discharging power and reduce the adverse effects of abnormal charging and discharging on battery performance.

[0075] The above scheme, on the one hand, can better match energy supply and demand and avoid energy waste by predicting the energy power of the energy storage park; on the other hand, by converting the operation strategy of the energy storage system into a target optimization problem, the target energy storage system operation strategy within each prediction step is obtained through energy power prediction data and preset constraints, that is, the energy storage system operation strategy after optimized calculation is obtained, which can improve energy utilization and system performance; on the third hand, by adjusting the charging strategy and discharging strategy in the target energy storage system operation strategy so that the charging and discharging power of the energy storage system changes smoothly, the power fluctuation during the charging and discharging process of the energy storage system can be reduced, the negative impact on battery performance can be reduced, the life of the energy storage system can be extended, and the stability and controllability of the system can be improved. In addition, the above scheme can also reduce the operating cost of energy and improve the economic benefits of energy.

[0076] The energy storage system operation strategy determination method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the power measurement device 102 of the energy storage power system communicates with the control terminal 104 of the energy storage power system through the incoming line of the energy storage power system. The data storage system can store the data that the control terminal 104 needs to process. The data storage system can be integrated on the server, or it can be placed on the cloud or other network servers.

[0077] Specifically, the optimization target and several constraints may be pre-set on the control end 104. In practical applications, the power measurement equipment 102 installed in the energy storage park distribution network incoming line, each feeder, and the energy storage power system transmits the collected current and voltage data to the control end 104 in real time. The control end 104 obtains the energy power prediction data of the energy storage power system within the total prediction step by monitoring the current and voltage data, as well as the historical energy power data, and then determines the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the preset optimization conditions, and the preset constraints, that is, the optimal energy storage system operation strategy, and then adjusts the target energy storage system operation strategy so that the change rate of the charging and discharging power of the energy storage system in the energy storage power system is within the preset change rate range, reducing the negative impact of too low or too high charging power on battery performance.

[0078] The power measuring device 102 may include but is not limited to a power meter, a current sensor, a voltage sensor, etc. The control terminal 104 may be but is not limited to various personal computers, laptops, smart phones, tablet computers, IoT devices and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The control terminal 104 may also be implemented using an independent server or a server cluster consisting of multiple servers.

[0079] In some embodiments, Figure 2 As shown, a method for determining an energy storage system operation strategy is provided, and the method is applied to Figure 1 The control end in the example is used to illustrate, including the following steps:

[0080] S200, obtaining energy power prediction data of the energy storage power system within the total prediction step.

[0081] The energy storage power system refers to a power system that includes an energy storage system. In this embodiment, the energy storage power system may include an energy storage system, a wind power generation system, a photovoltaic power generation system, and other renewable energy power generation systems. The energy storage system may also be a distributed energy storage system. It is understandable that the wind power generation system and the photovoltaic system are non-essential systems. In other embodiments, the energy storage power system may not include the wind power generation system and the photovoltaic system. The total prediction step refers to the time interval or time step used when making a prediction or simulation. In the operation strategy of the energy storage system, the total prediction step is used to determine the time resolution of the simulation or prediction, which can be adjusted according to the actual system computing power. Energy power prediction data includes power grid load prediction data, energy storage system charging and discharging power prediction data, and renewable energy generation power prediction data.

[0082] In the specific implementation, taking the total prediction step of 24 hours as an example, when the control end receives the current, voltage and other data transmitted in real time by the power measurement equipment, it can obtain the energy power prediction data of the energy storage power system in the next 24 hours by monitoring the current and voltage.

[0083] S400, based on energy power prediction data, preset optimization objectives, and preset constraints, determine a target energy storage system operation strategy within each prediction step.

[0084] The target energy storage system operation strategy is the optimal target energy storage system operation strategy, which specifically includes the energy storage system charging and discharging power corresponding to each moment in each prediction step and the reactive content of the energy storage system discharge power. The optimization target can be determined based on the characteristics of the energy storage park and the load demand, including but not limited to minimizing energy costs, maximizing energy utilization, minimizing peak-to-valley differences, etc. Constraints include but are not limited to energy balance constraints, charging and discharging power constraints, and energy storage system state (such as SOC (State of Charge)) constraints.

[0085] In specific implementation, it can be based on the characteristics of the energy storage park, optimization goals and constraints, using optimization methods such as linear programming, integer programming or nonlinear programming, to establish an optimization model for the energy storage system operation strategy, determine the decision variables that need to be optimized, namely the energy storage operation strategy, use the energy power prediction data as the input of the optimization model, combine the constraints, and continuously optimize the optimization model through the optimization algorithm to obtain the optimal energy storage system operation strategy.

[0086] In the specific implementation, the total prediction step is 24 hours, and the energy storage system operation strategy is generated every 5 minutes. When the control end obtains the energy power prediction data, it can be based on the energy power prediction data, taking into account the constraints and optimization goals, to determine the optimal charging and discharging power plan within each prediction step, and obtain the target energy storage system operation strategy within each prediction step, including the corresponding energy storage system charging and discharging power within every 5 minutes within 24 hours and the reactive content of the energy storage system discharge power.

[0087] S600, adjusting the target energy storage system operation strategy so that the rate of change of the charging and discharging power of the energy storage system in the energy storage power system is within a preset rate of change range.

[0088] The rate of change of charge and discharge power refers to the amount of change in the charging power or discharging power of the energy storage system per unit time, which indicates the speed of charging or discharging of the energy storage system per unit time. For example, if the charging power of the energy storage system at time t1 is P1, and the charging power at time t2 is P2, then the rate of change of charging power can be expressed as (P2-P1) / (t2-t1). The charge and discharge strategy in the target energy storage system operation strategy refers to the decision on how the energy storage system performs charge and discharge operations within the total predicted step length, specifically including the charge and discharge power, charge and discharge time, and corresponding strategy data within each predicted step length.

[0089] In practical applications, since the charging power may fluctuate greatly or change suddenly in the target energy storage system operation strategy, and the above situation may have an adverse effect on the performance of the battery of the energy storage system and affect the life of the energy storage system, therefore, in this embodiment, the range of the rate of change of the charging and discharging power can be pre-set so that the rate of change of the charging and discharging power changes smoothly within the rate of change range.

[0090] Specifically, after obtaining the target energy storage system operation strategy, the charge and discharge strategy in the target energy storage system operation strategy may be adjusted to smooth the charge and discharge power changes of the energy storage system. Specifically, the charge and discharge strategy may be adjusted as follows: the measure of smooth charge and discharge power may be to set the upper limit of the charge and discharge power of the energy storage system to limit the charge and discharge rate. By limiting the change speed of the charge and discharge power, the charge and discharge power can be smoothly changed. It may also be to distribute the charge and discharge time to a longer time period so that the charge and discharge power is low and changes smoothly. For example, charging and discharging at night or during periods with low load can reduce the peak value of the charge and discharge power and achieve a smooth change. It may also be to adjust the capacity of the energy storage system according to the system requirements and the requirements for smooth changes in charge and discharge power. Increasing the capacity of the energy storage system can provide a larger space for smooth changes in charge and discharge power, making the charge and discharge process smoother. Further, after adjusting the charge and discharge strategy, the adjusted energy storage system operation strategy may be applied to the actual energy storage system. According to the preset adjustment step interval, actual operation is performed according to the charge and discharge power value in the strategy, the feedback information of the monitoring system is monitored, and adjustments and optimizations are made according to actual conditions.

[0091] In the above-mentioned method for determining the operation strategy of the energy storage system, by obtaining the energy power prediction data of the energy storage power system within the total prediction step, basic data is provided for determining the operation strategy of the energy storage system. Through the energy power prediction data, the preset optimization target and the preset constraint conditions, the target energy storage system operation strategy within each prediction step is obtained, that is, the energy storage system operation strategy after optimization calculation is obtained to improve energy utilization and system performance. Finally, by adjusting the target energy storage system operation strategy so that the charging and discharging power of the energy storage system changes smoothly, the power fluctuation during the charging and discharging process of the energy storage system can be reduced, the negative impact on battery performance can be reduced, the life of the energy storage system can be extended, and the stability and controllability of the system can be improved. In summary, the above-mentioned scheme can reduce the negative impact on battery performance and improve the stability and controllability of the system.

[0092] like Figure 3 As shown, in some embodiments, S400 includes: S402, determining the target energy storage system operation strategy within each prediction step based on energy power prediction data, a pre-built energy storage charging and discharging power linear programming model, and preset constraints, and the energy storage charging and discharging power linear programming model is constructed based on a preset optimization goal.

[0093] In this embodiment, the energy storage charging and discharging power linear programming model is a model for optimizing the charging and discharging power configuration of the energy storage system. The model transforms the operation strategy problem of the energy storage system into a linear programming problem, and can solve the optimal charging and discharging power solution through mathematical methods.

[0094] In practical applications, the operator can pre-build a linear programming model for energy storage charge and discharge power based on the characteristics of the energy storage system and actual needs, and set several constraints and reward and punishment conditions. In the above linear programming model, the decision variable of the model is the charge and discharge power of the energy storage system within each prediction step, and the goal is to minimize or maximize a certain objective function, such as cost, energy utilization efficiency or system performance. At the same time, the model must also meet a series of constraints, including energy balance constraints, charge and discharge power constraints, and energy storage system status (such as SOC (State of Charge)) constraints. After the energy storage charge and discharge power linear programming model is constructed, the above model and several constraints are deployed to the control end. It can be understood that in other embodiments, an integer linear programming model for energy storage charge and discharge power or a mixed integer linear programming model for energy storage charge and discharge power can also be constructed to determine the optimal energy storage system operation strategy.

[0095] In the specific implementation, the total prediction step is 24 hours, and the energy storage system operation strategy is generated every 5 minutes. When the control end obtains the energy power prediction data, the energy power prediction data can be input into the energy storage charging and discharging power linear programming model. Then, considering the constraints and the objective function, the model is solved to determine the charging and discharging power scheme that makes the objective function obtain the optimal solution within each prediction step, and the target energy storage system operation strategy within each prediction step is obtained, including the corresponding energy storage system charging and discharging power within every 5 minutes within 24 hours and the reactive content of the energy storage system discharge power.

[0096] In the technical solution of the embodiment of the present application, the operation strategy of the energy storage system is determined and converted into a linear programming problem through a linear programming model of energy storage charging and discharging power. The model is solved through energy power prediction data and preset constraints to quickly and accurately obtain the optimal target energy storage system operation strategy within each prediction step.

[0097] Optionally, in some embodiments of the present application, based on the energy power prediction data, the preset optimization target, and the preset constraints, the target energy storage system operation strategy within each prediction step is determined. It can also be: based on the optimization target and the constraints, an initial neural network is constructed using a machine learning algorithm, and then historical energy power data is obtained. Based on the preset optimization target and the historical energy power data, the initial neural network is trained so that the initial neural network learns the operation strategy of the energy storage system from the historical energy power until the energy storage system operation strategy predicted by the initial neural network can achieve the optimal solution for the optimization target and complete the training. In practical applications, the energy power prediction data can be used as the input of the trained neural network so that the neural network can predict the optimal energy storage system operation strategy within each prediction step according to the current energy power prediction data and the optimization target.

[0098] In the application scheme of this embodiment, the optimal energy storage system operation strategy is obtained by means of a machine learning method. Since the machine learning algorithm can adapt to complex nonlinear relationships and dynamically changing environments, it can determine the optimal energy storage system operation strategy more flexibly and accurately.

[0099] Optionally, in some embodiments of the present application, based on the energy power prediction data, the preset optimization target, and the preset constraints, the target energy storage system operation strategy within each prediction step is determined. It can also be: based on the energy power prediction data, the preset optimization target, and the preset constraints, a heuristic algorithm is used to search for an approximate optimal solution for the energy storage system operation strategy. The heuristic algorithms that can be used include but are not limited to genetic algorithms and particle swarm optimization algorithms. The above algorithm gradually improves the operation strategy of the energy storage system through iterative search and optimization, so that it approaches the optimal solution and obtains the optimal energy storage system operation strategy.

[0100] In the application scheme of this embodiment, the optimal energy storage system operation strategy is obtained by means of a heuristic algorithm, which can cope with complex optimization problems and nonlinear constraints and improve applicability and flexibility.

[0101] like Figure 4 As shown, in some embodiments, S402 includes:

[0102] S420, based on the energy power prediction data, the pre-built energy storage charging and discharging power linear programming model, and the preset constraints, with the minimum charging and discharging power adjustment step of the energy storage system as the step interval, generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step.

[0103] S440, determining target values ​​corresponding to each candidate energy storage system operation strategy.

[0104] S460 , based on the target values ​​corresponding to the candidate energy storage system operation strategies, a target energy storage system operation strategy within each prediction step is screened out from a plurality of candidate energy storage system operation strategies.

[0105] The minimum charge and discharge power adjustment step of the energy storage system refers to the smallest unit of charge and discharge power adjustment each time the energy storage system is performing charge and discharge operations. This step is usually determined by the hardware and control system of the energy storage system.

[0106] In this embodiment, the energy storage charging and discharging power linear programming model can be an energy storage charging and discharging power integer linear programming model. The target value refers to the value of the preset optimization target obtained by calculation, including any one of the electricity fee, the energy storage system income and the energy storage system life. Among them, the electricity fee includes the demand electricity fee, the energy consumption electricity fee, etc.

[0107] Taking the target value of demand electricity charge as an example, the sliding window period for calculating the demand electricity charge for industrial and commercial users is 15 minutes. In this embodiment, the prediction step interval can be 5 minutes, that is, from the predicted energy power forecast data for the next 24 hours, the energy power forecast data is collected at an interval of 5 minutes. The process of screening out the target energy storage system operation strategy within each prediction step can be: inputting the collected energy power forecast data into a pre-built energy storage charging and discharging power integer linear programming model, with the goal of minimizing electricity expenditure and the minimum charging and discharging power adjustment step of the energy storage system as the step interval, and using an integer linear programming solution algorithm such as a Monte Carlo search algorithm to generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step of 5 minutes. Each candidate energy storage system operation strategy includes the charging and discharging power value of the energy storage system within the prediction step and the reactive content of the discharge power.

[0108] Then, the operation strategies of each candidate energy storage system are evaluated, and the charging and discharging power values ​​of the energy storage system and the reactive content of the discharge power in each candidate energy storage operation strategy are substituted into the integer linear programming model of the energy storage charging and discharging power. Combined with the billing rules and billing rates of the power grid electricity charges, the power grid electricity charges corresponding to each candidate energy storage system operation strategy are calculated. Then, for each prediction step, the candidate energy storage system operation strategy with the smallest power grid electricity charge is determined as the target energy storage system operation strategy within each prediction step.

[0109] Optionally, in some embodiments, if the target value is energy storage benefit, then the optimization goal of the energy storage charging and discharging power integer linear programming model is to maximize the energy storage benefit. Similarly, based on inputting the energy power prediction data into the energy storage charging and discharging power linear programming model, preset constraints are considered. The constraints may include the capacity limitation of the energy storage system, the charging and discharging rate limitation, the charging and discharging efficiency, etc., and the minimum charging and discharging power adjustment step of the energy storage system is used as the step interval to generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step. Then, according to factors such as electricity cost savings, peak-valley balance, and grid support, the benefit of each candidate energy storage operation strategy is evaluated. Then, for each prediction step, the candidate energy storage system operation strategy with the largest energy storage benefit is determined as the target energy storage system operation strategy within each prediction step.

[0110] Optionally, in some embodiments, if the target value is the energy storage life, the optimization goal of the energy storage charging and discharging power integer linear programming model is to maximize the life of the energy storage system. Similarly, based on inputting the energy power prediction data into the energy storage charging and discharging power linear programming model, the preset constraints are considered. The constraints may include the capacity limit of the energy storage system, the charging and discharging rate limit, the charging and discharging efficiency, etc., and the minimum charging and discharging power adjustment step of the energy storage system is used as the step interval to generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step. Then, according to factors such as the number of charging and discharging cycles and the degree of deep charging and discharging, the energy storage system life corresponding to each candidate energy storage operation strategy is evaluated. Then, for each prediction step, the candidate energy storage system operation strategy with the longest energy storage system life is determined as the target energy storage system operation strategy within each prediction step.

[0111] In the technical solution of the embodiment of the present application, energy power prediction data, energy storage system characteristics and constraints are comprehensively considered to generate multiple candidate energy storage system operation strategies, and the best energy storage system operation strategy for each prediction step is screened out from the dimensions of electricity costs, energy storage income and energy storage system, which can improve the energy utilization efficiency and economic benefits of the energy storage power system.

[0112] Furthermore, since the energy storage charging and discharging power will affect the incoming line power, by controlling the energy storage system charging and discharging power within any continuous 5 minutes, the system incoming line power can be effectively controlled during the window period, thereby achieving the purpose of reducing demand electricity charges.

[0113] According to some embodiments of the present application, optionally, S420 includes: based on energy power prediction data, a pre-built energy storage charging and discharging power linear programming model, and preset constraints, with the minimum charging and discharging power adjustment step of the energy storage system as the step interval, generating multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step by enumeration.

[0114] Continuing from the previous embodiment, in this embodiment, the process of generating multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step may be: using the minimum charge and discharge power adjustment step of the energy storage system as the variable adjustment unit in the enumeration process to ensure the smooth change of the charge and discharge power. Starting from the start time of the prediction data, enumeration is performed according to the minimum charge and discharge power adjustment step. For each prediction step, based on the energy power prediction data, the pre-built energy storage charge and discharge power linear programming model, and the preset constraints, all candidate energy storage system operation strategies that meet the constraints within each prediction step are enumerated. Specifically, all possible candidate energy storage system operation strategies can be enumerated in a loop structure. Then, for each candidate energy storage system operation strategy, the corresponding electricity fee is calculated according to the charge and discharge power value of the energy storage system, the reactive content of the discharge power, and the electricity billing rules and billing rates of the power grid, and the candidate energy storage system operation strategy with the smallest electricity fee is determined as the optimal energy storage system operation strategy within each prediction step.

[0115] It is understandable that in some other embodiments, methods other than enumeration may be used, such as heuristic algorithms including genetic algorithms, simulated annealing algorithms, and machine learning algorithms or other optimization algorithms, to generate the optimal energy storage system operation strategy within each prediction step.

[0116] In the technical solution of the embodiment of the present application, all possible energy storage system operation strategies can be traversed by enumeration to obtain a comprehensive set of candidate strategies. Combined with the constraints, the optimal energy storage system operation strategy within each prediction step can be screened out, which can minimize electricity costs and improve economic benefits and energy utilization.

[0117] In some embodiments, before S400, it also includes: obtaining the latest demand electricity price, interest rate adjustment fee and time-of-use electricity price, based on the energy power forecast data, demand electricity price, interest rate adjustment fee, time-of-use electricity price, and preset constraints, combined with the minimum charge and discharge power adjustment step of the energy storage system, with the goal of maximizing the rate of return of the energy storage power system, constructing an energy storage charge and discharge power linear programming model;

[0118] Among them, the preset constraints include: when it is monitored that the predicted power value of renewable energy exceeds the predicted power value of the total load, the remaining power is directed to the energy storage system to charge the energy storage system, and the remaining power is determined based on the predicted power value of renewable energy and the predicted power value of the total load.

[0119] In this embodiment, the energy power forecast data includes the power forecast value of renewable energy, the total load power forecast value, the energy storage charging and discharging power forecast value, and the incoming line power forecast value. Among them, the renewable energy power forecast value includes the photovoltaic power forecast value and the wind power power forecast value, the incoming line power forecast value includes the incoming line active power forecast value, the incoming line active power forecast value of the current month, and the incoming line reactive power forecast value of the current month, and the total load power forecast value includes the load active power forecast value and the total reactive power of the load of the current month. The demand price is calculated based on the user's maximum demand (i.e., peak power demand) in a specific time period. For example, when electricity is used during a period with low peak demand, the demand price is usually low; and when electricity is used during a period with high peak demand, the demand price is high. The time-of-use electricity price includes a two-part time-of-use electricity price, specifically including a basic electricity price and a price calculated according to electricity consumption. The interest rate adjustment fee is determined by adjusting the electricity bill for a period of time in the future based on the user's maximum demand or electricity consumption in a certain period of time in the past. Demand electricity prices, interest rate adjustment fees and time-of-use electricity prices can all change dynamically, and their corresponding prices may be different at different times.

[0120] In this embodiment, after obtaining the power forecast data of the energy storage power system in the next 24 hours, the latest demand electricity price, interest rate adjustment fee and time-of-use electricity price may be obtained. Then, based on the energy power forecast data, demand electricity price, interest rate adjustment fee, time-of-use electricity price, and preset constraints, combined with the minimum charge and discharge power adjustment step of the energy storage system, with the goal of maximizing the rate of return of the energy storage power system, an energy storage charge and discharge power linear programming model is constructed. Specifically, taking the energy storage charge and discharge power linear programming model as an energy storage charge and discharge power integer linear programming model as an example, the expression of the model may be as follows:

[0121]

[0122] Where T represents the total prediction step length (24 hours), t n+1 -t n =5 means the interval is 5 minutes, represents the load power during period t, represents the photovoltaic power generation power during period t, represents the wind turbine power generation during period t, represents the charging and discharging power of the energy storage system at time t ( Charge; Shutdown, discharge), p t represents the time-of-use electricity price at time t, Indicates the maximum incoming line demand, p need Indicates the demand price, Pay cos Represents interest rate adjustment fee.

[0123]

[0124]

[0125] In the formula, Represents the reactive power output by the energy storage system at time t.

[0126] The constraint expressions are as follows:

[0127]

[0128] Among them, condition ① indicates that at time t The possible values ​​of the energy storage system charging and discharging power are: from the maximum discharge power to the maximum charging power, with the minimum adjustable step size of the energy storage control system as the interval A finite, enumerable value.

[0129] Condition ② means that after the predicted electric energy generated by the renewable energy power system (including photovoltaic power generation system and wind power generation system) at time t (i.e., the predicted value of renewable energy power) exceeds the predicted value of the total load power required by the park where the energy storage power system is located, the excess power is used to charge the energy storage system instead of supplying power to the grid. The excess power is the difference between the predicted value of renewable energy power and the predicted value of total load power.

[0130] Condition ③ constrains the range of SOC of the energy storage system at time t, where SOC low Indicates the minimum SOC value set manually, SOC high Indicates the set maximum SOC value, SOC init represents the initial SOC, It represents the absolute value of SOC change after the strategy is executed, which can effectively reduce the adverse effects of over-charging and discharging.

[0131] Condition ④ means that the interest rate adjustment factor for the current month must be higher than the reward and punishment benchmark COS set by the power supply company. set .

[0132] Condition ⑤ indicates the constraint of the reactive power content in the output power of the energy storage system on the overall active power, that is, when the energy storage system is required to output reactive power, the active power output of the energy storage system will be reduced. Indicates the rated apparent output power of the energy storage system, represents the output active power of the energy storage system at time t, Represents the output reactive power of the energy storage system at time t.

[0133] By setting the above constraints, the generated candidate energy storage system operation strategy can meet the restrictions of the energy storage system's charging and discharging capacity, SOC variation range, energy cost, etc. After constructing the above energy storage system charging and discharging power integer linear programming model, the above model can be solved to obtain the optimal energy storage system operation strategy in each prediction step within the total prediction step, including energy storage charging and discharging power and energy storage discharge power reactive content.

[0134] In the technical solution of the embodiment of the present application, by comprehensively considering energy power forecast data, demand electricity price, interest rate adjustment fee and time-of-use electricity price, etc., a linear programming model of energy storage system charging and discharging power is constructed, which can comprehensively analyze the operation strategy of the energy storage system and maximize the systematic rate of return. By setting the constraints of renewable energy power and overall load power, the local consumption capacity of renewable energy power generation can be improved. In addition, since the on-grid electricity price of renewable energy is lower than the price of electricity obtained by the energy storage park from the power grid, the overall benefit of the system is also improved.

[0135] like Figure 5 As shown, in some embodiments, S200 includes:

[0136] S220, obtaining real-time energy power data and historical energy power data of the energy storage power system, predicting the energy power within the total prediction step based on the real-time energy power data and the historical energy power data, and obtaining energy power prediction data of the energy storage power system within the total prediction step.

[0137] In actual applications, current sensors, voltage sensors, power meters and other equipment in energy storage power systems transmit the collected electrical signals such as current and voltage to the control end in real time. The control end obtains real-time energy power data by monitoring current and voltage, including renewable energy power, total load power, energy storage charging and discharging power, and incoming line power. Similarly, renewable energy power includes photovoltaic power generation and wind power generation, incoming line power includes incoming line active power, incoming line active power of the month, and incoming line reactive power of the month, and total load power includes load active power and total load reactive power of the month.

[0138] During specific implementation, after obtaining the above-mentioned real-time energy power data, the stored historical energy power data can be obtained. Then, based on the real-time energy power data and the historical energy power data, the energy power within the total prediction step is predicted, and the energy power prediction data of the energy storage power system within the total prediction step is obtained. Specifically, a machine learning method or a statistical model can be used to predict the real-time energy power data and the historical energy power data, and the energy power prediction data of the energy storage power system within the total prediction step, such as 24 hours, is predicted. For example, linear regression, support vector regression, time series model or deep learning model is used to perform energy power prediction on real-time energy power data and historical energy power data.

[0139] Optionally, in other embodiments of the present application, the acquisition of energy power prediction data can also be: acquiring historical energy power data, analyzing the historical energy power data of the energy storage power system through statistical analysis or time series analysis, obtaining patterns and trends in the historical energy power prediction data, and then obtaining the energy power prediction data.

[0140] Optionally, in other embodiments, the acquisition of energy power prediction data can also be: acquiring historical energy power data of the energy storage power system in the past, using a machine learning algorithm to construct an initial energy power prediction model for learning the energy power prediction mode of the energy storage power system, and then using a supervised learning algorithm to train the energy power prediction model through historical energy power data. Then, the currently acquired energy power data is input into the energy power prediction model to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0141] Similarly, energy power prediction data can also be obtained by: obtaining real-time energy power data and historical energy power data of the energy storage power system, and at the same time, obtaining enterprise production plan data, load demand data and / or weather data, etc. Based on the real-time energy power data, historical energy power data, enterprise production plan data, load demand data and / or weather data, etc., machine learning or deep learning methods are used to train an energy power prediction model, and then energy power prediction is performed through the model prediction to obtain more accurate energy power prediction data within the total prediction step.

[0142] In the technical solution of the embodiment of the present application, energy power is predicted based on real-time energy power data and historical energy power data, and energy power prediction data within the total prediction step is provided to the energy storage power system. Compared with the method of using historical energy power data for prediction, the obtained energy power prediction data is more accurate, which can facilitate the system operator to formulate and make decisions on operating strategies, so as to achieve effective management and optimal utilization of energy.

[0143] In some embodiments, based on real-time energy power data and historical energy power data, the energy power within the total prediction step is predicted to obtain the energy power prediction data of the energy storage power system within the total prediction step, including: preprocessing the real-time energy power data and the historical energy power data, and based on the preprocessed real-time energy power data and the historical energy power data, predicting the energy power within the total prediction step through a preset multi-dimensional time series prediction algorithm to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0144] Continuing from the previous embodiment, in this embodiment, predicting the energy power data of the energy storage power system can be: after acquiring the real-time energy power data and the historical energy power data, first preprocessing the real-time energy power data and the historical energy power data, including data cleaning, denoising and normalization operations, then extracting the features of the real-time energy power data and the historical energy power data after data preprocessing, and based on the extracted features, using a multi-dimensional time series prediction algorithm to predict the energy power within the total prediction step, to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0145] Optionally, in other embodiments, an energy power prediction model based on a time series can also be established, and then the historical energy power data can be used to train and verify the model. The data is divided into a training set and a verification set, and the performance of the model is optimized by adjusting the model parameters and evaluation indicators (such as root mean square error, mean absolute error) to obtain a trained energy power prediction model. Then, multi-dimensional features for predicting energy power, such as time features, seasonal features, statistical features of historical power data, etc., are extracted from real-time energy power data and historical energy power data, and the extracted features are input into the trained energy power prediction model to obtain energy power prediction data of the energy storage power system within a total prediction step of 24 hours. Furthermore, the energy power prediction data output by the model can be evaluated later, compared with the actual energy power data, and the prediction error index is calculated. According to the evaluation results, the model is adjusted and optimized to improve the accuracy and stability of the prediction.

[0146] Optionally, in other embodiments of the present application, data preprocessing may be performed on the real-time energy power data and the historical energy power data. Based on the preprocessed real-time energy power data and the historical energy power data, the energy power within the total prediction step length is predicted through statistical methods such as the moving average method, machine learning methods such as support vector regression and random forest, or deep learning methods such as recurrent neural networks, to obtain the energy power prediction data of the energy storage power system within the total prediction step length. The specific prediction method can be selected according to the needs of the application scenario.

[0147] In the technical solution of the embodiment of the present application, data quality can be improved through data preprocessing, and energy power can be predicted for real-time energy power data and historical energy power data through a preset multi-dimensional time series prediction algorithm, so as to obtain more accurate energy power prediction data.

[0148] like Figure 5 As shown, according to some embodiments of the present application, optionally, S600 includes: S620, locating the charging strategy in the target energy storage system operation strategy, identifying the continuous charging strategy in the target energy storage system operation strategy, and in the case of an unbalanced charging power in the continuous charging strategy, adjusting the charging power in the continuous charging strategy according to a preset power change rate so that the change rate of the charging power is within a preset change rate range.

[0149] In this embodiment, the continuous charging strategy in the energy storage system operation strategy can be adjusted to reduce the adverse effects of long-term overcharging. In specific implementation, taking the total prediction step length of 24 hours and each prediction step length of 5 minutes as an example, the target energy storage system operation strategy obtained includes 288 items. The control end can be a comprehensive analysis of all target energy storage system operation strategies, and locate the charging strategy according to the preset charging power threshold. If it is detected that the strategies within multiple consecutive prediction steps are all charging strategies, the charging strategy within the continuous prediction step range is determined to be a continuous charging strategy.

[0150] Since the charging power in each charging strategy in the continuous charging strategy may fluctuate or be unbalanced, in this embodiment, the charging power in the continuous charging strategy may be smoothed to reduce the adverse effects of high-power charging on battery performance. Specifically, the charging power change rate may be pre-set, and the charging power in the continuous charging strategy may be adjusted according to the preset power change rate so that the charging power change rate is within the preset change rate range. For example, if the charging powers in three consecutive charging strategies are 150W, 30W, and 150W, respectively, the charging power may be balanced, and the processed charging powers are 110W, 110W, and 110W, respectively. It is understood that in other embodiments, a continuous discharge strategy may also be identified. If the discharge power in the continuous discharge strategy is unbalanced, the discharge power may be adjusted according to the preset discharge power change rate to balance the discharge power, and the discharge order, discharge duration, and discharge power of each battery may be adjusted again to balance the discharge power.

[0151] In the technical solution of the embodiment of the present application, by adjusting the charging power in the continuous charging strategy, the charging power in the continuous charging strategy can be balanced, which is beneficial to maximize the charging capacity of the energy storage system, improve the efficiency and stability of the system, and reduce the imbalance in the charging process, thereby extending the service life of the energy storage system.

[0152] like Figure 6 As shown, in some embodiments, S600 includes: S640, when there is abnormal charging power in the charging strategy in the target energy storage system operation strategy, the abnormal charging power is smoothed or interpolated, wherein the abnormal charging power includes a charging power whose change rate is greater than a preset change rate threshold.

[0153] Continuing from the previous embodiment, in actual applications, the target energy storage system operation strategy may have a charging power with a change rate greater than a preset change rate threshold, that is, an abnormal charging power with a large fluctuation or mutation. For this abnormal charging power, the abnormal charging power may be smoothed. Specifically, the abnormal charging power may be averaged or filtered to reduce the sudden change and fluctuation of power.

[0154] In other embodiments, it is also possible to interpolate missing or discrete abnormal charging powers, that is, to infer and fill in the values ​​between abnormal charging power data points based on known normal charging power data. For example, the two normal charging power values ​​before and after the abnormal charging power can be taken respectively, and then the average of the two normal charging powers before and after can be calculated, and the abnormal charging power can be replaced with the charging power average value. In other embodiments, it is also possible to calculate the reasonable value of the abnormal data point based on the existing charging power data points through mathematical models or curve fitting methods.

[0155] In the technical solution of the embodiment of the present application, by smoothing or interpolating the abnormal charging power, the fluctuation of the charging power can be eliminated, so that the charging power changes more gradually, which is conducive to making full use of the charging time of the energy storage system, reducing the charging power, and extending the life of the energy storage system.

[0156] In order to make a clearer description of the method for determining the operation strategy of the energy storage system provided in the present application, the following is a specific embodiment and the attached Figure 7 To illustrate, this embodiment includes the following contents:

[0157] S100, the control end receives the current and voltage transmitted by the power measuring device, and obtains real-time energy power data by calculating the current and voltage.

[0158] Specifically, the power measurement equipment such as sensors or measuring equipment in the energy storage power system can transmit the collected current, voltage and other data of each device to the control end in real time. For example, it can be to obtain the current and voltage data of renewable energy through sensors or measuring equipment, obtain the current and voltage data of loads, measure the current and voltage data of batteries or energy storage devices, and measure the current and voltage data of incoming lines.

[0159] Real-time energy power forecast data includes renewable energy power, total load power, energy storage charging and discharging power, and incoming line power.

[0160] S102, the control end obtains historical energy power data, and performs data preprocessing on the real-time energy power data and the historical energy power data.

[0161] Specifically, data preprocessing includes operations such as data cleaning, denoising and normalization.

[0162] S104, the control end predicts the energy power within the total prediction step based on the pre-processed real-time energy power data and historical energy power data through a preset multi-dimensional time series prediction algorithm, and obtains the energy power prediction data of the energy storage power system within the total prediction step.

[0163] After the above data preprocessing, the features of the real-time energy power data and historical energy power data after data preprocessing can be extracted. Based on the extracted features, a multi-dimensional time series prediction algorithm is used to predict the energy power within the total prediction step, and the energy power prediction data of the energy storage power system within the total prediction step is obtained.

[0164] S106, based on the energy power prediction data, the pre-built linear programming model of energy storage charging and discharging power, and the preset constraints, the control end uses the minimum charging and discharging power adjustment step of the energy storage system as the step interval, and generates multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step by enumeration.

[0165] In this embodiment, the energy storage charge and discharge power linear programming model can be an energy storage charge and discharge power integer linear programming model. Taking the calculation of demand electricity charges as an example, the sliding window period for industrial and commercial users to calculate demand electricity charges is 15 minutes, then in this embodiment, the prediction step interval can be 5 minutes, that is, from the predicted energy power forecast data for the next 24 hours, the energy power forecast data is collected at an interval of 5 minutes, and the process of screening out the target energy storage system operation strategy within each prediction step can be: input the collected energy power forecast data into the pre-built energy storage charge and discharge power integer linear programming model, take the minimum charge and discharge power adjustment step of the energy storage system as the step interval, and use an integer linear programming solution algorithm such as a Monte Carlo search algorithm to generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step of 5 minutes, and each candidate energy storage system operation strategy includes the charge and discharge power value of the energy storage system within the prediction step and the reactive content of the discharge power, etc.

[0166] S108, the control end determines the electricity charges corresponding to each candidate energy storage system operation strategy.

[0167] S110, the control end selects a target energy storage system operation strategy within each prediction step from a plurality of candidate energy storage system operation strategies according to the electricity charges corresponding to each candidate energy storage system operation strategy.

[0168] Then, the operation strategies of each candidate energy storage system are evaluated, and the charging and discharging power values ​​of the energy storage system and the reactive content of the discharge power in each candidate energy storage operation strategy are substituted into the integer linear programming model of the energy storage charging and discharging power. Combined with the billing rules and billing rates of the power grid electricity charges, the power grid electricity charges corresponding to each candidate energy storage system operation strategy are calculated. Then, for each prediction step, the candidate energy storage system operation strategy with the smallest power grid electricity charge is determined as the target energy storage system operation strategy within each prediction step.

[0169] S112, adjusting the charging and discharging strategy in the target energy storage system operation strategy so that the rate of change of the charging and discharging power of the energy storage system in the energy storage power system is within a preset rate of change range.

[0170] Specifically, the process of adjusting the charging strategy includes: locating the charging strategy in the target energy storage system operation strategy, identifying the continuous charging strategy in the target energy storage system operation strategy, and in the case of uneven charging power in the continuous charging strategy, adjusting the charging power in the continuous charging strategy according to the preset power change rate, so that the change rate of the charging power is within the preset change rate range. It also includes smoothing or interpolating the abnormal charging power when there is abnormal charging power in the charging strategy in the target energy storage system operation strategy, wherein the abnormal charging power includes the charging power with a change rate greater than the preset change rate threshold.

[0171] It can be understood that in other embodiments, a continuous discharge strategy can also be identified. If the discharge power is unbalanced in the continuous discharge strategy, the discharge power can be adjusted according to a preset discharge power change rate to balance the discharge power. The discharge sequence, discharge duration and discharge power of each battery can also be adjusted again to balance the discharge power.

[0172] According to the above scheme, after the simulation system executes the adjusted energy storage system operation strategy, the system's profit effect is as follows: Figure 8 As shown. In the figure, P_load (curve A): park electricity load curve; P-pv (curve B): photovoltaic power generation power curve; P_in (curve C): city grid incoming line power curve; P_bat (curve D): energy storage charging and discharging curve. The simulation results show that in the absence of an energy storage system, the electricity bill for the park is 1,590 yuan, and the energy storage system saves 436 / 446 yuan by operating in conservative mode (two charges and two discharges); the cost saved by using the scheme in the embodiment of the energy storage system operation strategy determination method provided in this embodiment is 730 yuan. It can be seen that the adoption of this scheme can not only reduce the adverse effects on battery performance and extend the service life of the energy storage system, but also improve the economic benefits of the energy storage power system.

[0173] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed 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 part of the steps or stages in other steps.

[0174] Based on the same inventive concept, the embodiment of the present application also provides an energy storage system operation strategy determination device for implementing the energy storage system operation strategy determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more energy storage system operation strategy determination device embodiments provided below can refer to the limitations of the energy storage system operation strategy determination method above, and will not be repeated here.

[0175] In some embodiments, Fig. 9As shown, a device 800 for determining an operation strategy of an energy storage system is provided, comprising: a data prediction module 810, an operation strategy generation module 820 and a strategy adjustment module 830, wherein:

[0176] The data prediction module 810 is used to obtain energy power prediction data of the energy storage power system within the total prediction step.

[0177] The operation strategy generation module 820 is used to determine the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the preset optimization target, and the preset constraint conditions.

[0178] The strategy adjustment module 830 is used to adjust the target energy storage system operation strategy so that the change rate of the charging and discharging power of the energy storage system in the energy storage power system is within a preset change rate range.

[0179] In some embodiments, the operation strategy generation module 820 is also used to determine the target energy storage system operation strategy within each prediction step based on energy power prediction data, a pre-built energy storage charging and discharging power linear programming model, and preset constraints. The energy storage charging and discharging power linear programming model is constructed based on a preset optimization goal.

[0180] In some embodiments, the operation strategy generation module 820 is also used to generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step based on energy power prediction data, a pre-built energy storage charging and discharging power linear programming model, and preset constraints, with the minimum charging and discharging power adjustment step of the energy storage system as the step interval, determine the target value corresponding to each candidate energy storage system operation strategy, and according to the target value corresponding to each candidate energy storage system operation strategy, select the target energy storage system operation strategy within each prediction step from multiple candidate energy storage system operation strategies, wherein the target value includes any one of electricity cost, energy storage system income and energy storage system life.

[0181] In some embodiments, the operation strategy generation module 820 is also used to generate multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step by enumeration based on energy power prediction data, a pre-built energy storage charging and discharging power linear programming model, and preset constraints, with the minimum charging and discharging power adjustment step of the energy storage system as the step interval.

[0182] In some embodiments, the energy power prediction data includes a renewable energy power prediction value and a load total power prediction value;

[0183] like Fig.10As shown, the device also includes a model building module 802, which is used to obtain the latest demand electricity price, interest rate adjustment fee and time-of-use electricity price, based on energy power prediction data, demand electricity price, interest rate adjustment fee, time-of-use electricity price, and preset constraints, combined with the minimum charging and discharging power adjustment step of the energy storage system, with the goal of maximizing the rate of return of the energy storage power system, to build an energy storage charging and discharging power linear programming model, wherein the preset constraints include: when it is monitored that the renewable energy power prediction value exceeds the total load power prediction value, the remaining power is directed to the energy storage system to charge the energy storage system, and the remaining power is determined based on the renewable energy power prediction value and the total load power prediction value.

[0184] In some embodiments, the strategy adjustment module 830 is also used to locate the charging strategy in the target energy storage system operation strategy, identify the continuous charging strategy in the target energy storage system operation strategy, and in the case of an unbalanced charging power in the continuous charging strategy, adjust the charging power in the continuous charging strategy according to a preset power change rate so that the change rate of the charging power is within a preset change rate range.

[0185] In some embodiments, the strategy adjustment module 830 is also used to smooth or interpolate the abnormal charging power when there is abnormal charging power in the charging strategy in the target energy storage system operation strategy, wherein the abnormal charging power includes the charging power with a change rate greater than a preset change rate threshold.

[0186] In some embodiments, the data prediction module 810 is also used to obtain real-time energy power data and historical energy power data of the energy storage power system, and based on the real-time energy power data and the historical energy power data, predict the energy power within the total prediction step to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0187] In some embodiments, the data prediction module 810 is also used to perform data preprocessing on the real-time energy power data and the historical energy power data. Based on the preprocessed real-time energy power data and the historical energy power data, the energy power within the total prediction step is predicted through a preset multi-dimensional time series prediction algorithm to obtain the energy power prediction data of the energy storage power system within the total prediction step.

[0188] Each module in the above energy storage system operation strategy determination device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0189] In some embodiments, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, 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 an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining an energy storage system operation strategy is implemented. The display unit of the computer device is used to form a visually visible picture, which 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 shell, or an external keyboard, touchpad or mouse.

[0190] Those skilled in the art will understand that Fig.11 The 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 those shown in the figure, or combine certain components, or have a different arrangement of components.

[0191] In some embodiments, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned energy storage system operation strategy determination method embodiments are implemented.

[0192] In some embodiments, 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 energy storage system operation strategy determination method embodiments are implemented.

[0193] In some embodiments, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in the above-mentioned energy storage system operation strategy determination method embodiments.

[0194] 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 laws, regulations and standards in the relevant regions.

[0195] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0196] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and specification of the present application. In particular, as long as there is no structural conflict, the various technical features mentioned in the various embodiments can be combined in any way. The present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions that fall within the scope of the claims.

Claims

1. A method for determining an energy storage system operation strategy, characterized in that: The method comprises: Obtain energy power prediction data of the energy storage power system within the total prediction step length; Determine the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the preset optimization target, and the preset constraint conditions; The target energy storage system operation strategy is adjusted so that the rate of change of the charging and discharging power of the energy storage system in the energy storage power system is within a preset rate of change range.

2. The method according to claim 1, characterized in that The step of determining the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the preset optimization target, and the preset constraint conditions includes: Based on the energy power prediction data, the pre-constructed energy storage charging and discharging power linear programming model, and the preset constraints, the target energy storage system operation strategy within each prediction step is determined, and the energy storage charging and discharging power linear programming model is constructed based on the preset optimization target.

3. The method according to claim 2, characterized in that The step of determining the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the preset optimization target, and the preset constraint conditions includes: Based on the energy power prediction data, the pre-built energy storage charging and discharging power linear programming model, and the preset constraints, a plurality of candidate energy storage system operation strategies that meet the preset constraints are generated with the minimum charging and discharging power adjustment step of the energy storage system as the step interval; Determine the optimization target value corresponding to each candidate energy storage system operation strategy; According to the optimization target value corresponding to each candidate energy storage system operation strategy, a target energy storage system operation strategy within each prediction step is selected from multiple candidate energy storage system operation strategies; The target value includes any one of electricity cost, energy storage system income and energy storage system life.

4. The method according to claim 3, characterized in that The method of generating multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step based on the energy power prediction data, the pre-built energy storage charge and discharge power linear programming model, and the preset constraints, with the minimum charge and discharge power adjustment step of the energy storage system as the step interval, includes: Based on the energy power prediction data, the pre-built energy storage charging and discharging power linear programming model, and the preset constraints, the minimum charging and discharging power adjustment step of the energy storage system is used as the step interval, and multiple candidate energy storage system operation strategies that meet the preset constraints within each prediction step are generated by enumeration.

5. The method according to claim 2, characterized in that: The energy power prediction data includes a renewable energy power prediction value and a load total power prediction value; Before determining the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the pre-built energy storage charging and discharging power linear programming model, and the preset constraints, the method further includes: Get the latest demand electricity prices, rate adjustment charges, and time-of-use electricity prices; Based on the energy power forecast data, the demand electricity price, the interest rate adjustment fee, the time-of-use electricity price, and the preset constraints, combined with the minimum charging and discharging power adjustment step of the energy storage system, with the goal of maximizing the rate of return of the energy storage power system, a linear programming model for energy storage charging and discharging power is constructed; Among them, the preset constraints include: when it is monitored that the renewable energy power forecast value exceeds the total load power forecast value, the remaining power is directed to the energy storage system to charge the energy storage system, and the remaining power is determined based on the renewable energy power forecast value and the total load power forecast value.

6. The method according to any one of claims 1 to 5, characterized in that: The adjusting the target energy storage system operation strategy includes: Locate the charging strategy in the target energy storage system operation strategy, and identify the continuous charging strategy in the target energy storage system operation strategy; In the case where the charging power in the continuous charging strategy is unbalanced, the charging power in the continuous charging strategy is adjusted according to a preset power change rate so that the change rate of the charging power is within a preset change rate range.

7. The method according to any one of claims 1 to 5, characterized in that: The adjusting of the charging strategy in the target energy storage system operation strategy includes: When the charging strategy in the target energy storage system operation strategy has abnormal charging power, smoothing or interpolating the abnormal charging power; The abnormal charging power includes a charging power whose change rate is greater than a preset change rate threshold.

8. The method according to any one of claims 1 to 5, characterized in that: The obtaining of energy power prediction data of the energy storage power system within the total prediction step length includes: Obtain real-time energy power data and historical energy power data of energy storage power system; Based on the real-time energy power data and the historical energy power data, the energy power within the total prediction step is predicted to obtain energy power prediction data of the energy storage power system within the total prediction step.

9. The method according to claim 8, characterized in that The energy power within the total prediction step length is predicted based on the real-time energy power data and the historical energy power data to obtain energy power prediction data of the energy storage power system within the total prediction step length, including: Performing data preprocessing on the real-time energy power data and the historical energy power data; Based on the preprocessed real-time energy power data and the historical energy power data, the energy power within the total prediction step is predicted through a preset multi-dimensional time series prediction algorithm to obtain the energy power prediction data of the energy storage power system within the total prediction step.

10. A device for determining an energy storage system operation strategy, characterized in that: The device comprises: A data prediction module is used to obtain energy power prediction data of the energy storage power system within the total prediction step length; An operation strategy generation module, used to determine the target energy storage system operation strategy within each prediction step based on the energy power prediction data, the preset optimization target, and the preset constraint conditions; The strategy adjustment module is used to adjust the target energy storage system operation strategy so that the change rate of the charging and discharging power of the energy storage system in the energy storage power system is within a preset change rate range.

11. 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 9 are implemented.

12. 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 9 are implemented.

13. 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 9 are implemented.

Images