Energy storage system power optimization adjustment method, device, equipment, medium and product

Abstract

The application discloses an energy storage system power optimization adjustment method, device, equipment, medium and product, and relates to the technical field of energy storage system management. The method is to firstly predict an electricity price estimation value and a load estimation value in at least one unit period in the future, then establish a function relationship between the charging and discharging cost and the battery capacity loss of the energy storage system and the power of the energy storage system based on the electricity price estimation value, and comprehensively convert the function relationship into a single objective function, and also establish a constraint condition of the objective function based on the load estimation value, then obtain an optimal search result of the power of the energy storage system based on an optimization algorithm according to the objective function and the constraint condition, and the optimal search result is used to minimize the objective function, and finally, the power of the energy storage system is dynamically adjusted according to the search result, so that the problem that the existing energy storage system power optimization adjustment scheme does not consider the health state, and the energy storage cells are prone to aging loss and capacity attenuation can be solved, and different energy storage systems can be adapted in various cases.

Description

Technical Field

[0001] This invention belongs to the field of energy storage system management technology, specifically relating to a method, device, equipment, medium, and product for optimizing and adjusting the power of an energy storage system. Background Technology

[0002] With the continuous development of renewable energy and the increasing demand for energy storage, electrochemical energy storage systems are playing an increasingly important role in modern energy infrastructure. Electrochemical energy storage systems are applied in virtual power plants as energy storage units capable of rapid dispatch and response.

[0003] In the electricity spot market, electricity prices fluctuate daily with market quotes. To maximize economic benefits, the power of electrochemical energy storage systems needs to be adjusted in real time to accommodate these price fluctuations. However, charging and discharging electrochemical energy storage systems at high power can lead to rapid aging of the internal battery cells, and frequent charge-discharge cycles can also cause rapid battery degradation.

[0004] Currently, existing power optimization and adjustment schemes for electrochemical energy storage systems calculate and dynamically adjust the system's power based on maximizing revenue. However, this optimization scheme frequently schedules the charging and discharging of the energy storage system according to fluctuations in electricity prices, causing rapid capacity decay of the energy storage cells. Additionally, some technologies use empirical functions to estimate the State of Health (SOH) of the energy storage unit at different power levels (simply put, the ratio of battery performance parameters to nominal parameters after a period of use) and dynamically adjust the power. However, empirical functions have high a priori dependence and cannot guarantee adaptability to different energy storage systems under various conditions. Summary of the Invention

[0005] The purpose of this invention is to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for power optimization and adjustment of energy storage systems, in order to solve the problems of existing power optimization and adjustment schemes for energy storage systems, such as easy aging and loss of energy storage cells and easy capacity decay due to the failure to consider the health status of the optimization target, and the inability to guarantee adaptability to different energy storage systems under various conditions.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] Firstly, a method for optimizing and adjusting the power of an energy storage system is provided, including:

[0008] The estimated electricity price for at least one unit period in the future is predicted based on historical electricity price time-series data, and the estimated load of the user load system for at least one unit period in the future is predicted based on historical load time-series data of the user load system.

[0009] Based on the estimated electricity price for at least one unit period in the future, a functional relationship between the charging and discharging cost of the energy storage system and the power of the energy storage system is established according to the following formula:

[0010]

[0011] In the formula, f1 represents the charging and discharging cost, N represents the total number of time periods of at least one future unit time period, n represents a positive integer less than or equal to N, and p n P represents the estimated electricity price for the nth unit time period within the at least one future unit time period. n This represents the power of the energy storage system in the nth time period, wherein the energy storage system and the user load system exist in the same microgrid and are connected to the same transformer;

[0012] Based on the parameters of the energy storage system, the functional relationship between the battery capacity loss and the power of the energy storage system is established according to the following formula:

[0013]

[0014] In the formula, f2 represents the battery capacity loss, λ s λ represents the penalty weighting coefficient used to control calendar aging. d SOC represents the penalty weighting coefficient used to control cyclic aging. n The state of charge (SOC) of the energy storage system in the nth unit time period represents the battery state of charge (SOC). Δ represents the differential operator. n-1 The state of charge (SOC) of the energy storage system is defined as the (n-1)th unit time period within the next at least one unit time period, and SOC0 represents the state of charge of the energy storage system in the most recent unit time period preceding the next at least one unit time period. T s C represents the duration of a unit of time period. bess P represents the energy storage capacity of the energy storage system. n-1 P0 represents the energy storage system power in the (n-1)th unit time period, and P0 represents the energy storage system power in the most recent unit time period.

[0015] Based on the charging and discharging cost of the energy storage system and the functional relationship between battery capacity loss and energy storage system power, the objective function F is established according to the following formula:

[0016]

[0017] In the formula, f1 * This represents the normalized form of the charge / discharge cost f1. The normalized form of the battery capacity loss f2 is represented by w1 and w2, which represent preset weighting coefficients and w1 + w2 = 1.

[0018] Based on the estimated load of the user load system in at least one future unit time period, the maximum allowable power of the transformer, and the upper and lower limits of the battery state of charge and the upper and lower limits of the energy storage system power, the following constraints are established for the objective function F:

[0019]

[0020] In the formula, P n,load P represents the estimated load of the user load system in the nth time period. tf,max The SOC indicates the maximum permissible power of the transformer. min The State of Charge (SOC) of the energy storage system indicates the battery's state of charge limit. max P represents the upper limit of the battery state of charge of the energy storage system. min P represents the lower limit of the energy storage system's power. max This indicates the upper limit of the energy storage system's power;

[0021] Based on the objective function F and the constraints, the energy storage system power of the energy storage system in the next at least one unit time period is optimized using an optimization algorithm to obtain the energy storage system power and the optimal search result used to minimize the objective function F;

[0022] Based on the optimized search results, the energy storage system power of the energy storage system is dynamically adjusted in the next at least one unit time period.

[0023] Based on the above-mentioned invention, a novel scheme for optimizing the power adjustment of an energy storage system to achieve optimal economic benefits and health status is provided. This involves first predicting the estimated electricity price and load for at least one unit period in the future. Then, based on the electricity price estimate, a functional relationship is established between the charging and discharging costs and battery capacity loss of the energy storage system and its power, which is then transformed into a single objective function. Constraints are also established for the objective function based on the load estimate. Next, based on the objective function and constraints, an optimization algorithm is used to obtain the optimal search result for the energy storage system power that minimizes the objective function. Finally, the energy storage system power is dynamically adjusted based on the search result. This approach introduces [a specific optimization method] into the power optimization process. The capacity loss function takes into account the negative impact of high SOC and frequent charge-discharge cycles on the energy storage cabinet capacity during the optimization process. This allows the optimized result to maximize the charging and discharging benefits while enabling the energy storage system to charge and discharge at the lowest possible power and reducing the duration of the energy storage cabinet at high SOC. This solves the problems of easy aging and capacity decay of energy storage cells caused by the failure to consider the health status of the cells in the existing energy storage system power optimization and adjustment schemes. Furthermore, since the parameters in the aforementioned capacity loss function can be flexibly adjusted, it can also be adapted to different cell models, ensuring compatibility with different energy storage systems under various conditions. This makes it highly valuable and easy to apply and promote in practice.

[0024] In one possible design, when power generation equipment is also present in the microgrid, the method further includes:

[0025] The estimated power generation of the power generation equipment in the next at least one unit period is predicted based on the historical power generation time series data of the power generation equipment.

[0026] The constraint condition 0≤P n,load -P n ≤P tf,max Replace with the following formula:

[0027] 0≤P n,load -P n,gt -P n ≤P tf,max

[0028] In the formula, P n,gt This represents the estimated power output of the power generation equipment in the nth time period.

[0029] In one possible design, the estimated power generation of the power generation equipment in the next at least one unit period is predicted based on the historical power generation time-series data of the power generation equipment, including:

[0030] Based on the historical power generation time series data of the power generation equipment, a power generation prediction model pre-trained using a third artificial intelligence algorithm is used to predict the estimated power generation of the power generation equipment in at least one unit period in the future.

[0031] In one possible design, the power generation equipment includes photovoltaic panels and / or a wind turbine.

[0032] In one possible design, the estimated electricity price for at least one unit period in the future is predicted based on historical electricity price time series data, including: using a pre-trained electricity price prediction model based on a first artificial intelligence algorithm to predict the estimated electricity price for at least one unit period in the future based on historical electricity price time series data.

[0033] And / or, predicting the load estimate of the user load system in the next at least one unit period based on the historical load time series data of the user load system includes: predicting the load estimate of the user load system in the next at least one unit period based on the historical load time series data of the user load system using a load prediction model pre-trained based on a second artificial intelligence algorithm.

[0034] In one possible design, the optimization algorithm may employ particle swarm optimization, Newton's optimization, genetic optimization, gray wolf optimization, or tuna swarm optimization.

[0035] Secondly, an energy storage system power optimization and adjustment device is provided, including an electricity price load prediction unit, a first function establishment unit, a second function establishment unit, an objective function establishment unit, a constraint condition establishment unit, a system power optimization unit, and a power dynamic adjustment unit;

[0036] The electricity price load forecasting unit is used to forecast the estimated electricity price for at least one unit period in the future based on historical electricity price time series data, and to forecast the estimated load of the user load system for at least one unit period in the future based on historical load time series data of the user load system.

[0037] The first function establishment unit, communicatively connected to the electricity price load forecasting unit, is used to establish a functional relationship between the charging and discharging cost of the energy storage system and the power of the energy storage system according to the estimated electricity price for at least one future unit period, using the following formula:

[0038]

[0039] In the formula, f1 represents the charging and discharging cost, N represents the total number of time periods of at least one future unit time period, n represents a positive integer less than or equal to N, and p nP represents the estimated electricity price for the nth unit time period within the at least one future unit time period. n This represents the power of the energy storage system in the nth time period, wherein the energy storage system and the user load system exist in the same microgrid and are connected to the same transformer;

[0040] The second function establishment unit is used to establish a functional relationship between the battery capacity loss and the power of the energy storage system according to the parameters of the energy storage system, using the following formula:

[0041]

[0042] In the formula, f2 represents the battery capacity loss, λ s λ represents the penalty weighting coefficient used to control calendar aging. d SOC represents the penalty weighting coefficient used to control cyclic aging. n The state of charge (SOC) of the energy storage system in the nth unit time period represents the battery state of charge (SOC). Δ represents the differential operator. n-1 The state of charge (SOC) of the energy storage system is defined as the (n-1)th unit time period within the next at least one unit time period, and SOC0 represents the state of charge of the energy storage system in the most recent unit time period preceding the next at least one unit time period. T s C represents the duration of a unit of time period. bess P represents the energy storage capacity of the energy storage system. n-1 P0 represents the energy storage system power in the (n-1)th unit time period, and P0 represents the energy storage system power in the most recent unit time period.

[0043] The objective function establishment unit is communicatively connected to the first function establishment unit and the second function establishment unit, respectively, and is used to establish the objective function F according to the following formula based on the charging and discharging cost of the energy storage system and the functional relationship between battery capacity loss and energy storage system power:

[0044]

[0045] In the formula, f1 * This represents the normalized form of the charge / discharge cost f1. The normalized form of the battery capacity loss f2 is represented by w1 and w2, which represent preset weighting coefficients and w1 + w2 = 1.

[0046] The constraint establishment unit, communicatively connected to the electricity price load forecasting unit, is used to establish the following constraints on the objective function F based on the estimated load of the user load system in at least one future unit time period, the maximum allowable power of the transformer, and the upper and lower limits of the battery state of charge and the upper and lower limits of the energy storage system's power:

[0047]

[0048] In the formula, P n,load P represents the estimated load of the user load system in the nth time period. tf,max The SOC indicates the maximum permissible power of the transformer. min The State of Charge (SOC) of the energy storage system indicates the battery's state of charge limit. max P represents the upper limit of the battery state of charge of the energy storage system. min P represents the lower limit of the energy storage system's power. max This indicates the upper limit of the energy storage system's power;

[0049] The system power optimization unit is communicatively connected to the objective function establishment unit and the constraint condition establishment unit, respectively. It is used to optimize the energy storage system power of the energy storage system in the next at least one unit time period based on the objective function F and the constraint conditions and an optimization search result for minimizing the objective function F.

[0050] The power dynamic adjustment unit is communicatively connected to the system power optimization unit and is used to dynamically adjust the energy storage system power of the energy storage system in the next at least one unit time period based on the optimization search result.

[0051] Thirdly, the present invention provides a computer device comprising a memory, a processor, and a transceiver connected in sequence for communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the energy storage system power optimization adjustment method as described in the first aspect or any possible design in the first aspect.

[0052] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the energy storage system power optimization adjustment method as described in the first aspect or any possible design in the first aspect.

[0053] Fifthly, the present invention provides a computer program product, including a computer program or instructions, which, when executed by a computer, implement the energy storage system power optimization adjustment method as described in the first aspect or any possible design in the first aspect.

[0054] The beneficial effects of the above scheme are:

[0055] (1) This invention creatively provides a new scheme for optimizing and adjusting the power of an energy storage system to achieve optimal economic benefits and health status. First, the estimated electricity price and load value for at least one unit period in the future are predicted. Then, based on the estimated electricity price value, a functional relationship between the charging and discharging cost of the energy storage system, the battery capacity loss, and the power of the energy storage system is established and transformed into a single objective function. The constraint conditions of the objective function are also established based on the load estimate. Then, based on the objective function and the constraint conditions, the optimal search result for minimizing the objective function is obtained by the optimization algorithm. Finally, the power of the energy storage system is dynamically adjusted based on the search result. In this way, by introducing a capacity loss function in the power optimization process and considering the negative impact of high SOC and frequent charge and discharge cycles on the capacity of the energy storage cabinet, the optimization result can maximize the charging and discharging benefits while making the energy storage system charge and discharge at a lower power as much as possible and reducing the duration of the energy storage cabinet at high SOC. This solves the problem of easy aging and loss of energy storage cells and easy capacity decay caused by the failure to consider the health status in the optimization objective of the existing energy storage system power optimization and adjustment scheme.

[0056] (2) Furthermore, since the parameters in the aforementioned capacity loss function can be flexibly adjusted, it can also be adapted to different types of battery cells, ensuring that it can be adapted to different energy storage systems under various circumstances, and has high application value.

[0057] (3) The constraints can also be updated and adjusted when there are power generation devices in the microgrid, so as to further ensure that different energy storage systems can be adapted in various situations, which is convenient for practical application and promotion. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a flowchart illustrating the power optimization and adjustment method for an energy storage system provided in an embodiment of this application.

[0060] Figure 2This is an example diagram showing the fluctuation of the optimized SOC with electricity price, obtained by using three days' day-ahead electricity price data from Europe to optimize the power of the energy storage system in an embodiment of this application.

[0061] Figure 3 A schematic diagram of the structure of the energy storage system power optimization and adjustment device provided in the embodiments of this application.

[0062] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0063] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these embodiments without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0064] It should be understood that although the terms "first" and "second", etc., may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the invention.

[0065] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, or A and B exist simultaneously. Another example is A, B and / or C, which can mean that any one of A, B, and C or any combination thereof exists. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone or A and B exist simultaneously. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0066] Example

[0067] like Figure 1 As shown, the energy storage system power optimization and adjustment method provided in the first aspect of this embodiment can be executed, but is not limited to, by a computer device with certain computing resources, such as by a cloud server. Figure 1As shown, the energy storage system power optimization and adjustment method may include, but is not limited to, the following steps S1 to S7.

[0068] S1. Based on historical electricity price time-series data, predict the estimated electricity price for at least one unit period in the future, and based on historical load time-series data of the user load system, predict the estimated load of the user load system for at least one unit period in the future.

[0069] In step S1, the historical electricity price time-series data specifically includes, but is not limited to, multiple historical time periods that are sequentially consecutive in time and the electricity value of each historical time period within those multiple historical time periods. The historical load time-series data specifically includes, but is not limited to, multiple historical time periods that are sequentially consecutive in time and the load value of the user load system within those multiple historical time periods; both can be conventionally recorded. The time period can specifically be, but is not limited to, 15 minutes, half an hour, an hour, a quarter of an hour, half a day, or a day, etc. Furthermore, at least one future time period needs to be sequentially consecutive in time to serve as the future time zone for dynamic power adjustment of the energy storage system.

[0070] In step S1, specifically, predicting the estimated electricity price for at least one unit period in the future based on historical electricity price time-series data includes, but is not limited to, the following steps: using a pre-trained electricity price prediction model based on the first artificial intelligence algorithm to predict the estimated electricity price for at least one unit period in the future based on the historical electricity price time-series data. The aforementioned artificial intelligence algorithm is a core algorithm specifically designed to study how computers can simulate or implement human learning behavior to acquire new knowledge or skills, reorganize existing knowledge structures to continuously improve their performance, and is the fundamental way to make computers intelligent. Specifically, the first artificial intelligence algorithm may, but is not limited to, employ machine learning algorithms based on support vector machines, stochastic gradient descent, multivariate linear regression, multilayer perceptrons, decision trees, backpropagation neural networks, radial basis function networks, ARIMA (Autoregressive Integrated Moving Average Model), or LSTM (Long Short-Term Memory) to quickly and accurately identify patterns in the data. Therefore, the electricity price prediction model can be pre-trained based on a certain amount of sample data (e.g., the model input consists of electricity values ​​in the previous multiple time periods, and the model output consists of electricity values ​​in at least the next time period). This can be achieved through a conventional calibration and verification modeling process (specifically including model calibration and verification processes, i.e., first comparing the model simulation results with measured data, and then adjusting the model parameters based on the comparison results to ensure the simulation results match reality). Preferably, during the calibration and verification modeling process of the electricity price prediction model, a tree-based Bayesian optimization algorithm is used to fine-tune the model parameters. Furthermore, specifically, the electricity values ​​in the most recent multiple historical time periods (including the current time period) can be extracted from the historical electricity price time-series data and imported into the electricity price prediction model to output an estimated electricity price value for at least the next future time period.

[0071] In step S1, specifically, the estimated load value of the user load system in the next at least one unit period is predicted based on the historical load time series data of the user load system. This includes, but is not limited to, the following steps: using a pre-trained load prediction model based on a second artificial intelligence algorithm, the estimated load value of the user load system in the next at least one unit period is predicted based on the historical load time series data of the user load system. The aforementioned second artificial intelligence algorithm may also be, but is not limited to, machine learning algorithms based on support vector machines, stochastic gradient descent, multivariate linear regression, multilayer perceptron, decision trees, backpropagation neural networks, radial basis function networks, ARIMA, or LSTM, etc., to quickly and accurately identify patterns in the data. Therefore, the load prediction model can also be trained in advance based on a certain amount of sample data (e.g., the model input is the load value in the previous several unit periods, and the model output is the load value in the next at least one unit period) through a conventional calibration and verification modeling process. Preferably, in the calibration and verification modeling process of the load prediction model, a tree-based Bayesian optimization algorithm can also be used to fine-tune the model parameters. In addition, load values ​​for the most recent historical time periods (including the current time period) can be extracted from the historical load time series data and imported into the load prediction model to output load estimates for at least one future time period.

[0072] S2. Based on the estimated electricity price for at least one unit period in the future, establish a functional relationship between the charging and discharging cost of the energy storage system and the power of the energy storage system according to the following formula:

[0073]

[0074] In the formula, f1 represents the charging and discharging cost, N represents the total number of time periods of at least one future unit time period, n represents a positive integer less than or equal to N, and p n P represents the estimated electricity price for the nth unit time period within the at least one future unit time period. n This represents the power of the energy storage system in the nth time period, wherein the energy storage system and the user load system exist in the same microgrid and are connected to the same transformer.

[0075] In step S2, the power P of the energy storage system n These are the parameters to be optimized later (there will be N in total). The microgrid refers to a small power generation and distribution system composed of distributed power sources, energy storage devices, energy conversion devices, loads, monitoring and protection devices, etc., wherein the distributed power sources include, but are not limited to, the mains power grid and power generation equipment.

[0076] S3. Based on the parameters of the energy storage system, establish the functional relationship between the battery capacity loss and the power of the energy storage system according to the following formula:

[0077]

[0078] In the formula, f2 represents the battery capacity loss, λ s λ represents the penalty weighting coefficient used to control calendar aging. d SOC represents the penalty weighting coefficient used to control cyclic aging. n The state of charge (SOC) of the energy storage system in the nth unit time period represents the battery state of charge (SOC). Δ represents the differential operator. n-1 The state of charge (SOC) of the energy storage system is defined as the (n-1)th unit time period within the next at least one unit time period, and SOC0 represents the state of charge of the energy storage system in the most recent unit time period preceding the next at least one unit time period. T s C represents the duration of a unit of time period. bess P represents the energy storage capacity of the energy storage system. n-1 P0 represents the energy storage system power in the (n-1)th unit time period, and P0 represents the energy storage system power in the most recent unit time period.

[0079] In step S3, the energy storage system capacity C bess This refers to the parameters of the energy storage system. Battery capacity loss is mainly caused by two factors: (1) calendar aging caused by the battery remaining in a high-charge state; and (2) cycle aging caused by battery charge-discharge cycles. Therefore, this embodiment uses λ. s ×(SOC n ) 2 This represents the loss caused by calendar aging, and is represented by λ. d ×(ΔSOC n ) 2 This represents the capacity loss due to charge-discharge cycles, where the penalty weighting coefficient λ... s and λ d This can be pre-set according to specific business needs. Furthermore, for example, if the at least one future time period is the same as the at least one future time period, then the most recent time period is the current time period.

[0080] S4. Based on the charging and discharging cost of the energy storage system and the functional relationship between battery capacity loss and energy storage system power, the objective function F is established according to the following formula:

[0081]

[0082] In the formula, f1 *This represents the normalized form of the charge / discharge cost f1. The normalized form of the battery capacity loss f2 is represented by w1 and w2, which represent preset weighting coefficients and have w1+w2=1.

[0083] In step S4, the objective function F is the function that needs to be minimized (i.e., minF) in order to achieve the optimal economic benefits and health status.

[0084] S5. Based on the estimated load of the user load system in the next at least one unit time period, the maximum allowable power of the transformer, and the upper and lower limits of the battery state of charge and the upper and lower limits of the energy storage system power, the following constraints are established for the objective function F:

[0085]

[0086] In the formula, P n,load P represents the estimated load of the user load system in the nth time period. tf,max The SOC indicates the maximum permissible power of the transformer. min The State of Charge (SOC) of the energy storage system indicates the battery's state of charge limit. max P represents the upper limit of the battery state of charge of the energy storage system. min P represents the lower limit of the energy storage system's power. max This indicates the upper limit of the energy storage system's power.

[0087] S6. Based on the objective function F and the constraints, optimize the energy storage system power of the energy storage system in the next at least one unit time period using an optimization algorithm to obtain the energy storage system power and the optimal search result used to minimize the objective function F.

[0088] In step S6, specifically, the optimization algorithm may include, but is not limited to, particle swarm optimization, Newton's optimization, genetic optimization, gray wolf optimization, or tuna swarm optimization. All of the aforementioned optimization algorithms are optimization algorithms that can conventionally search for the energy storage system power (i.e., constituting the optimal search result) that minimizes the objective function F under the constraints. Taking particle swarm optimization as an example, the specific optimization process includes the following steps (A) to (F).

[0089] (A) Initialize the particle swarm: Randomly generate a certain number of particles, each representing a potential solution; initialize the position and velocity of each particle.

[0090] (B) Fitness assessment: The fitness value of each particle is calculated, usually by evaluating it using an objective function.

[0091] (C) Update individual and global optimum: Each particle updates its velocity and position based on its own historical best position (individual optimum) and the best position of the entire group (global optimum).

[0092] (D) Update velocity and position: Update the particle's velocity and position using the following formula:

[0093] Speed ​​update formula:

[0094] v i =wv i +c1r1(p i -x i )+c2r2(gx i )

[0095] Position update formula:

[0096] x i =x i +v i

[0097] Where w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers, and p i is the optimal position of the particle, and g is the global optimal position.

[0098] (E) Check termination conditions: Determine whether to terminate the algorithm based on the set conditions (such as reaching the maximum number of iterations or the fitness reaching the threshold).

[0099] (F) Output: If the termination condition is met, output the global optimal solution; otherwise, return to step (C).

[0100] S7. Based on the optimized search results, dynamically adjust the energy storage system power of the energy storage system in the next at least one unit time period.

[0101] Compared with existing energy storage system power optimization and adjustment schemes, the technical solution described in steps S1 to S7 above introduces a capacity loss function (i.e., f2 in step S3) during the power optimization process and considers the negative impact of high SOC (State of charge, the percentage of battery capacity remaining) and frequent charge-discharge cycles on the energy storage cabinet capacity during the optimization process. This allows the optimization results to maximize the charging and discharging benefits while enabling the energy storage system to charge and discharge at a lower power (i.e., slow charging and slow discharging) and reduce the duration of high SOC in the energy storage cabinet. This can solve the problem of easy aging and loss of energy storage cells and easy capacity decay caused by the failure to consider the health status of the energy storage cells in the existing energy storage system power optimization and adjustment schemes. Figure 2 The simulation results show the optimized SOC of the energy storage system based on three days' day-ahead electricity price data from Europe (because the European electricity market is a spot market with large price fluctuations). The simulated energy storage system capacity is 100kWh, with power upper and lower limits of 10kW and SOC upper and lower limits of 0.95 / 0.05. In order to reflect the optimization effect of the power, the user load and transformer capacity are much higher than the energy storage system power to reduce the impact of the constraints on the results. It can be seen that: (1) the SOC state of the energy storage system will be optimized in real time with the fluctuation of electricity price to maximize the benefits; (2) the health state of the energy storage system is included in the optimization objective (i.e. Figure 2 Following the red curve in the image, small fluctuations in electricity prices will not cause the energy storage system to switch between charging and discharging modes (i.e., ...). Figure 2 (The orange box in the image), and the time spent in the high SOC state is relatively short (i.e. Figure 2 (as shown in the red box in the diagram), thus proving that the method of this embodiment can reduce calendar aging and cycle aging of the energy storage system while ensuring profitability. Furthermore, since the parameters in the aforementioned capacity loss function can be flexibly adjusted, it can also be adapted to different types of battery cells, ensuring compatibility with different energy storage systems under various conditions.

[0102] Therefore, based on the energy storage system power optimization and adjustment method described in steps S1 to S7 above, a new scheme for optimizing and adjusting the energy storage system power to achieve optimal economic benefits and health status is provided. This involves first predicting the estimated electricity price and load for at least one unit period in the future; then establishing a functional relationship between the energy storage system's charging and discharging costs, battery capacity loss, and energy storage system power based on the electricity price estimate, and comprehensively transforming this into a single objective function; furthermore, establishing constraints for the objective function based on the load estimate; then, based on the objective function and constraints, obtaining the optimal search result for minimizing the objective function using an optimization algorithm; and finally, dynamically adjusting the energy storage system power based on the search result. This process is repeated continuously. By introducing a capacity loss function during the power optimization process and considering the negative impact of high SOC and frequent charge-discharge cycles on the energy storage cabinet capacity, the optimization results can maximize the charging and discharging benefits while enabling the energy storage system to charge and discharge at lower power as much as possible and reducing the duration of the energy storage cabinet at high SOC. This solves the problems of easy aging and loss of energy storage cells and easy capacity decay caused by the failure to consider the health status of the energy storage cells in the existing power optimization adjustment schemes. Furthermore, since the parameters in the aforementioned capacity loss function can be flexibly adjusted, it can also be adapted to different types of cells, ensuring compatibility with different energy storage systems under various conditions. It has high practical value and is easy to apply and promote.

[0103] Based on the technical solution of the first aspect mentioned above, this embodiment also provides a possible design for adjusting the constraints when there are power generation devices in the microgrid. That is, when there are power generation devices in the microgrid, the method also includes, but is not limited to, the following steps S51 to S52.

[0104] S51. Based on the historical power generation time series data of the power generation equipment, predict the estimated power generation value of the power generation equipment in the next at least one unit period.

[0105] In step S51, the power generation equipment specifically includes, but is not limited to, new energy power generation equipment such as photovoltaic panels and / or wind turbines. The historical power generation time series data specifically includes, but is not limited to, multiple historical time periods that are sequentially consecutive in time, and the power generation value of the power generation equipment in each of these historical time periods; it can also be obtained through conventional recording. Specifically, predicting the estimated power generation value of the power generation equipment in at least one future time period based on the historical power generation time series data includes, but is not limited to, the following steps: based on the historical power generation time series data of the power generation equipment, using a pre-trained power generation prediction model based on a third artificial intelligence algorithm to predict the estimated power generation value of the power generation equipment in at least one future time period. The aforementioned third artificial intelligence algorithm may also specifically employ machine learning algorithms based on support vector machines, stochastic gradient descent, multivariate linear regression, multilayer perceptrons, decision trees, backpropagation neural networks, radial basis function networks, ARIMA, or LSTM, etc., to quickly and accurately identify patterns in the data. Therefore, the power generation prediction model can be trained in advance based on a certain amount of sample data (e.g., the model input consists of power generation values ​​in the previous multiple time periods, and the model output consists of power generation values ​​in at least the next time period), through a conventional calibration and verification modeling process. Preferably, during the calibration and verification modeling process of the power generation prediction model, a tree-based Bayesian optimization algorithm can also be used to fine-tune the model parameters. Furthermore, specifically, power generation values ​​from the most recent multiple historical time periods (including the current time period) can be extracted from the historical power generation time series data and imported into the power generation prediction model to output an estimated power generation value for at least the next future time period.

[0106] S52. Change the constraint condition 0≤P n,load -P n ≤P tf,max Replace with the following formula:

[0107] 0≤P n,load -P n,gt -P n ≤P tf,max

[0108] In the formula, P n,gt This represents the estimated power output of the power generation equipment in the nth time period.

[0109] Therefore, based on the aforementioned possible design one, the constraints can be updated and adjusted when there are power generation devices in the microgrid, so as to further ensure that different energy storage systems can be adapted under various conditions.

[0110] like Figure 3As shown, the second aspect of this embodiment provides a virtual device for implementing the energy storage system power optimization and adjustment method described in the first aspect or possibly designed in the first aspect, including an electricity price load prediction unit, a first function establishment unit, a second function establishment unit, an objective function establishment unit, a constraint condition establishment unit, a system power optimization unit, and a power dynamic adjustment unit;

[0111] The electricity price load forecasting unit is used to forecast the estimated electricity price for at least one unit period in the future based on historical electricity price time series data, and to forecast the estimated load of the user load system for at least one unit period in the future based on historical load time series data of the user load system.

[0112] The first function establishment unit, communicatively connected to the electricity price load forecasting unit, is used to establish a functional relationship between the charging and discharging cost of the energy storage system and the power of the energy storage system according to the estimated electricity price for at least one future unit period, using the following formula:

[0113]

[0114] In the formula, f1 represents the charging and discharging cost, N represents the total number of time periods of at least one future unit time period, n represents a positive integer less than or equal to N, and p n P represents the estimated electricity price for the nth unit time period within the at least one future unit time period. n This represents the power of the energy storage system in the nth time period, wherein the energy storage system and the user load system exist in the same microgrid and are connected to the same transformer;

[0115] The second function establishment unit is used to establish a functional relationship between the battery capacity loss and the power of the energy storage system according to the parameters of the energy storage system, using the following formula:

[0116]

[0117] In the formula, f2 represents the battery capacity loss, λ s λ represents the penalty weighting coefficient used to control calendar aging. d SOC represents the penalty weighting coefficient used to control cyclic aging. n The state of charge (SOC) of the energy storage system in the nth unit time period represents the battery state of charge (SOC). Δ represents the differential operator. n-1 The state of charge (SOC) of the energy storage system is defined as the (n-1)th unit time period within the next at least one unit time period, and SOC0 represents the state of charge of the energy storage system in the most recent unit time period preceding the next at least one unit time period. T s C represents the duration of a unit of time period. bessP represents the energy storage capacity of the energy storage system. n-1 P0 represents the energy storage system power in the (n-1)th unit time period, and P0 represents the energy storage system power in the most recent unit time period.

[0118] The objective function establishment unit is communicatively connected to the first function establishment unit and the second function establishment unit, respectively, and is used to establish the objective function F according to the following formula based on the charging and discharging cost of the energy storage system and the functional relationship between battery capacity loss and energy storage system power:

[0119]

[0120] In the formula, f1 * This represents the normalized form of the charge / discharge cost f1. The normalized form of the battery capacity loss f2 is represented by w1 and w2, which represent preset weighting coefficients and w1 + w2 = 1.

[0121] The constraint establishment unit, communicatively connected to the electricity price load forecasting unit, is used to establish the following constraints on the objective function F based on the estimated load of the user load system in at least one future unit time period, the maximum allowable power of the transformer, and the upper and lower limits of the battery state of charge and the upper and lower limits of the energy storage system's power:

[0122]

[0123] In the formula, P n,load P represents the estimated load of the user load system in the nth time period. tf,max The SOC indicates the maximum permissible power of the transformer. min The State of Charge (SOC) of the energy storage system indicates the battery's state of charge limit. max P represents the upper limit of the battery state of charge of the energy storage system. min P represents the lower limit of the energy storage system's power. max This indicates the upper limit of the energy storage system's power;

[0124] The system power optimization unit is communicatively connected to the objective function establishment unit and the constraint condition establishment unit, respectively. It is used to optimize the energy storage system power of the energy storage system in the next at least one unit time period based on the objective function F and the constraint conditions and an optimization search result for minimizing the objective function F.

[0125] The power dynamic adjustment unit is communicatively connected to the system power optimization unit and is used to dynamically adjust the energy storage system power of the energy storage system in the next at least one unit time period based on the optimization search result.

[0126] The working process, working details and technical effects of the aforementioned device provided in the second aspect of this embodiment can be found in the first aspect or the energy storage system power optimization and adjustment method that may be designed in the first aspect, and will not be repeated here.

[0127] like Figure 4 As shown, the third aspect of this embodiment provides a computer device for executing the energy storage system power optimization and adjustment method as described in the first aspect or possibly designed in the first aspect. The device includes a memory, a processor, and a transceiver connected in sequence. The memory stores a computer program, the transceiver sends and receives messages, and the processor reads the computer program and executes the energy storage system power optimization and adjustment method as described in the first aspect or possibly designed in the first aspect. Specifically, the memory may include, but is not limited to, random-access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; the processor may include, but is not limited to, a microprocessor of the STM32F105 series. Furthermore, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0128] The working process, working details and technical effects of the aforementioned computer equipment provided in the third aspect of this embodiment can be found in the first aspect or the energy storage system power optimization and adjustment method that may be designed in the first aspect, and will not be repeated here.

[0129] This fourth aspect of the embodiment provides a computer-readable storage medium storing instructions comprising the energy storage system power optimization adjustment method as described in the first aspect or possibly designed in the first aspect. Specifically, the computer-readable storage medium stores instructions that, when executed on a computer, perform the energy storage system power optimization adjustment method as described in the first aspect or possibly designed in the first aspect. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0130] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be found in the energy storage system power optimization and adjustment method described in the first aspect or possibly designed in the first aspect, and will not be repeated here.

[0131] This fifth aspect of the embodiment provides a computer program product, including a computer program or instructions, which, when executed by a computer, implement the energy storage system power optimization adjustment method as described in the first aspect or possibly designed in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.

[0132] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing and adjusting the power of an energy storage system, characterized in that, include: The estimated electricity price for at least one unit period in the future is predicted based on historical electricity price time-series data, and the estimated load of the user load system for at least one unit period in the future is predicted based on historical load time-series data of the user load system. Based on the estimated electricity price for at least one unit period in the future, a functional relationship between the charging and discharging cost of the energy storage system and the power of the energy storage system is established according to the following formula: In the formula, f1 represents the charging and discharging cost, N represents the total number of time periods of at least one future unit time period, n represents a positive integer less than or equal to N, and p n P represents the estimated electricity price for the nth unit time period within the at least one future unit time period. n This represents the power of the energy storage system in the nth time period, wherein the energy storage system and the user load system exist in the same microgrid and are connected to the same transformer; Based on the parameters of the energy storage system, the functional relationship between the battery capacity loss and the power of the energy storage system is established according to the following formula: In the formula, f2 represents the battery capacity loss, λ s λ represents the penalty weighting coefficient used to control calendar aging. d SOC represents the penalty weighting coefficient used to control cyclic aging. n The state of charge (SOC) of the energy storage system in the nth unit time period represents the battery state of charge (SOC). Δ represents the differential operator. n-1 The state of charge (SOC) of the energy storage system is defined as the (n-1)th unit time period within the next at least one unit time period, and SOC0 represents the state of charge of the energy storage system in the most recent unit time period preceding the next at least one unit time period. T s C represents the duration of a unit of time period. bess P represents the energy storage capacity of the energy storage system. n-1 P0 represents the energy storage system power in the (n-1)th unit time period, and P0 represents the energy storage system power in the most recent unit time period. Based on the charging and discharging cost of the energy storage system and the functional relationship between battery capacity loss and energy storage system power, the objective function F is established according to the following formula: In the formula, This represents the normalized form of the charge / discharge cost f1. The normalized form of the battery capacity loss f2 is represented by w1 and w2, which represent preset weighting coefficients and w1 + w2 = 1. Based on the estimated load of the user load system in at least one future unit time period, the maximum allowable power of the transformer, and the upper and lower limits of the battery state of charge and the upper and lower limits of the energy storage system power, the following constraints are established for the objective function F: In the formula, P n,load P represents the estimated load of the user load system in the nth time period. tf,max The SOC indicates the maximum permissible power of the transformer. min The State of Charge (SOC) of the energy storage system indicates the battery's state of charge limit. max P represents the upper limit of the battery state of charge of the energy storage system. min P represents the lower limit of the energy storage system's power. max This indicates the upper limit of the energy storage system's power; Based on the objective function F and the constraints, the energy storage system power of the energy storage system in the next at least one unit time period is optimized using an optimization algorithm to obtain the energy storage system power and the optimal search result used to minimize the objective function F; Based on the optimized search results, the energy storage system power of the energy storage system is dynamically adjusted in the next at least one unit time period.

2. The energy storage system power optimization and adjustment method according to claim 1, characterized in that, When power generation equipment also exists in the microgrid, the method further includes: The estimated power generation of the power generation equipment in the next at least one unit period is predicted based on the historical power generation time series data of the power generation equipment. The constraint condition 0≤P n,load -P n ≤P tf,max Replace with the following formula: 0≤P n,load -P n,gt -P n ≤P tf,max In the formula, P n,gt This represents the estimated power output of the power generation equipment in the nth time period.

3. The energy storage system power optimization and adjustment method according to claim 2, characterized in that, The estimated power generation of the power generation equipment in the next at least one unit period is predicted based on the historical power generation time series data of the power generation equipment, including: Based on the historical power generation time series data of the power generation equipment, a power generation prediction model pre-trained using a third artificial intelligence algorithm is used to predict the estimated power generation of the power generation equipment in at least one unit period in the future.

4. The energy storage system power optimization and adjustment method according to claim 2, characterized in that, The power generation equipment includes photovoltaic panels and / or wind turbines.

5. The power optimization and adjustment method for an energy storage system according to claim 1, characterized in that, The method involves predicting the estimated electricity price for at least one unit period in the future based on historical electricity price time-series data, including: using a pre-trained electricity price prediction model based on a first artificial intelligence algorithm to predict the estimated electricity price for at least one unit period in the future based on historical electricity price time-series data. And / or, predicting the load estimate of the user load system in the next at least one unit period based on the historical load time series data of the user load system includes: predicting the load estimate of the user load system in the next at least one unit period based on the historical load time series data of the user load system using a load prediction model pre-trained based on a second artificial intelligence algorithm.

6. The power optimization and adjustment method for an energy storage system according to claim 1, characterized in that, The optimization algorithm used is Particle Swarm Optimization, Newton's Optimization, Genetic Optimization, Gray Wolf Optimization, or Tuna Swarm Optimization.

7. A power optimization and adjustment device for an energy storage system, characterized in that, It includes an electricity price load forecasting unit, a first function establishment unit, a second function establishment unit, an objective function establishment unit, a constraint condition establishment unit, a system power optimization unit, and a power dynamic adjustment unit; The electricity price load forecasting unit is used to forecast the estimated electricity price for at least one unit period in the future based on historical electricity price time series data, and to forecast the estimated load of the user load system for at least one unit period in the future based on historical load time series data of the user load system. The first function establishment unit, communicatively connected to the electricity price load forecasting unit, is used to establish a functional relationship between the charging and discharging cost of the energy storage system and the power of the energy storage system according to the estimated electricity price for at least one future unit period, using the following formula: In the formula, f1 represents the charging and discharging cost, N represents the total number of time periods of at least one future unit time period, n represents a positive integer less than or equal to N, and p n P represents the estimated electricity price for the nth unit time period within the at least one future unit time period. n This represents the power of the energy storage system in the nth time period, wherein the energy storage system and the user load system exist in the same microgrid and are connected to the same transformer; The second function establishment unit is used to establish a functional relationship between the battery capacity loss and the power of the energy storage system according to the parameters of the energy storage system, using the following formula: In the formula, f2 represents the battery capacity loss, λ s λ represents the penalty weighting coefficient used to control calendar aging. d SOC represents the penalty weighting coefficient used to control cyclic aging. n The state of charge (SOC) of the energy storage system in the nth unit time period represents the battery state of charge (SOC). Δ represents the differential operator. n-1 The state of charge (SOC) of the energy storage system is defined as the (n-1)th unit time period within the next at least one unit time period, and SOC0 represents the state of charge of the energy storage system in the most recent unit time period preceding the next at least one unit time period. T s C represents the duration of a unit of time period. bess P represents the energy storage capacity of the energy storage system. n-1 P0 represents the energy storage system power in the (n-1)th unit time period, and P0 represents the energy storage system power in the most recent unit time period. The objective function establishment unit is communicatively connected to the first function establishment unit and the second function establishment unit, respectively, and is used to establish the objective function F according to the following formula based on the charging and discharging cost of the energy storage system and the functional relationship between battery capacity loss and energy storage system power: In the formula, This represents the normalized form of the charge / discharge cost f1. The normalized form of the battery capacity loss f2 is represented by w1 and w2, which represent preset weighting coefficients and w1 + w2 = 1. The constraint establishment unit, communicatively connected to the electricity price load forecasting unit, is used to establish the following constraints on the objective function F based on the estimated load of the user load system in at least one future unit time period, the maximum allowable power of the transformer, and the upper and lower limits of the battery state of charge and the upper and lower limits of the energy storage system's power: In the formula, P n,load P represents the estimated load of the user load system in the nth time period. tf,max The SOC indicates the maximum permissible power of the transformer. min The State of Charge (SOC) of the energy storage system indicates the battery's state of charge limit. max P represents the upper limit of the battery state of charge of the energy storage system. min P represents the lower limit of the energy storage system's power. max This indicates the upper limit of the energy storage system's power; The system power optimization unit is communicatively connected to the objective function establishment unit and the constraint condition establishment unit, respectively. It is used to optimize the energy storage system power of the energy storage system in the next at least one unit time period based on the objective function F and the constraint conditions and an optimization search result for minimizing the objective function F. The power dynamic adjustment unit is communicatively connected to the system power optimization unit and is used to dynamically adjust the energy storage system power of the energy storage system in the next at least one unit time period based on the optimization search result.

8. A computer device, characterized in that, The device includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the energy storage system power optimization adjustment method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that... The computer-readable storage medium stores instructions that, when executed on a computer, perform the energy storage system power optimization adjustment method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the energy storage system power optimization and adjustment method as described in any one of claims 1 to 6.

Images