Energy storage system multi-scene optimization scheduling method, device, equipment, medium and product

Abstract

The invention discloses an energy storage system multi-scene optimization scheduling method and device, equipment, a medium and a product, and relates to the field of model optimization, and the method comprises the steps: obtaining an initial decision variable and a constraint term which are used for training a scheduling model; obtaining a prediction data set; based on the predicted photovoltaic output in the prediction data set, the first predicted electricity price set, the second predicted electricity price set, the initial decision variable and the constraint term, generating the predicted total income of the electric energy market and the auxiliary service market; on the basis of the predicted total income, updating the initial decision variable so as to optimize the scheduling model, and obtaining an optimized target scheduling model; based on the optimal decision variable of the target scheduling model, adjusting a charging and discharging control strategy of the energy storage system; according to the predicted electricity price and total income, the charging and discharging strategy of the energy storage system is dynamically adjusted, so that the energy storage system can participate in an electric energy market and an auxiliary service market at the same time, and the economic benefit of the whole electric power market is maximized.

Description

Technical Field

[0001] The present application relates to the technical field of model optimization, and particularly to a multi-scenario optimal scheduling method, device, equipment, medium and product for an energy storage system. Background Art

[0002] In related technologies, it mainly involves the application of an energy storage system in a single scenario, such as participating in the electric energy market. However, the economic benefits of the energy storage system in a single scenario are relatively low, and its potential in multiple markets cannot be fully utilized; with the continuous development of the power market, the demand for the energy storage system to participate in multi-scenario scheduling is increasing day by day.

[0003] How to maximize the economic benefits of the energy storage system in the power market through dynamic charge and discharge control of the energy storage system has become an urgent problem to be solved. Summary of the Invention

[0004] The purpose of the present application is to provide a multi-scenario optimal scheduling method, device, equipment, medium and product for an energy storage system.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In the first aspect, the present application provides a multi-scenario optimal scheduling method for an energy storage system, including:

[0007] Obtain initial decision variables for training a scheduling model and constraint terms generated based on constraint conditions;

[0008] Obtain a prediction data set, where the prediction data set includes predicted photovoltaic output, a first predicted electricity price set in the electric energy market, and a second predicted electricity price set in the ancillary service market;

[0009] Generate predicted total revenues in the electric energy market and the ancillary service market based on the predicted photovoltaic output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variables, and the constraint terms;

[0010] Update the initial decision variables based on the predicted total revenues to optimize the scheduling model;

[0011] When the predicted total revenues meet preset conditions or the scheduling model reaches a preset number of iterations, obtain an optimized target scheduling model;

[0012] Adjust the charge and discharge control strategy of the energy storage system based on the optimal decision variables of the target scheduling model.

[0013] In the second aspect, the present application provides a multi-scenario optimal scheduling device for an energy storage system, including:

[0014] The first acquisition module is configured to acquire initial decision variables for training a scheduling model and constraint terms generated based on constraint conditions;

[0015] The second acquisition module is configured to acquire a prediction data set, where the prediction data set includes predicted photovoltaic power output, a first predicted electricity price set in the electricity energy market, and a second predicted electricity price set in the ancillary service market;

[0016] The generation module is configured to generate predicted total revenues in the electricity energy market and the ancillary service market based on the predicted photovoltaic power output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variables, and the constraint terms;

[0017] The update module is configured to update the initial decision variables based on the predicted total revenues to optimize the scheduling model;

[0018] The completion module is configured to obtain an optimized target scheduling model when the predicted total revenues meet preset conditions or the scheduling model reaches a preset number of iterations;

[0019] The adjustment module is configured to adjust the charge and discharge control strategy of the energy storage system based on the optimal decision variables of the target scheduling model.

[0020] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the multi-scenario optimal scheduling method for an energy storage system described in any one of the above.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the multi-scenario optimal scheduling method for an energy storage system described in any one of the above are implemented.

[0022] In a fifth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the multi-scenario optimal scheduling method for an energy storage system described in any one of the above are implemented.

[0023] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0024] The present application provides a multi-scenario optimal scheduling method, device, equipment, medium and product for an energy storage system. By obtaining the initial decision variables for training the scheduling model and the constraint terms generated based on the constraint conditions, it helps the scheduling model make scheduling decisions. The incorporated constraint conditions enable the scheduling model to still effectively schedule in a complex environment. By generating the predicted total revenue of the electricity energy market and the ancillary service market based on the predicted photovoltaic output, electricity energy market price, ancillary service market price, decision variables and constraint terms, it comprehensively evaluates the overall revenue of the power market, avoids the limitations of single-market analysis, diversifies risks, enhances the stability of revenue, and improves market competitiveness. By predicting the total revenue and iteratively updating the initial decision variables, when the predicted total revenue meets the preset conditions or the scheduling model reaches the preset number of iterations, the optimization of the scheduling model is completed, and the charge and discharge strategy of the energy storage system is adjusted according to the optimal decision variables corresponding to the optimized target scheduling model. Thus, the charge and discharge strategy of the energy storage system can be dynamically adjusted according to the predicted electricity price and total revenue, enabling the energy storage system to participate in both the electricity energy market and the ancillary service market, and maximizing the economic benefits of the entire power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0026] Figure 1 It is an application environment diagram of a multi-scenario optimal scheduling method for an energy storage system in an embodiment of the present application;

[0027] Figure 2 It is a flowchart of a multi-scenario optimal scheduling method for an energy storage system provided in an embodiment of the present application;

[0028] Figure 3 It is a flowchart of a multi-scenario optimal scheduling method for an energy storage system provided in another embodiment of the present application;

[0029] Figure 4 It is a flowchart of a multi-scenario optimal scheduling method for an energy storage system provided in yet another embodiment of the present application;

[0030] Figure 5 It is a flowchart of a multi-scenario optimal scheduling method for an energy storage system provided in still another embodiment of the present application;

[0031] Figure 6Schematic flow chart of a multi-scenario optimal scheduling method for an energy storage system provided by another embodiment of the present application;

[0032] Figure 7 Schematic diagram of functional modules of an optimal scheduling framework provided by an embodiment of the present application;

[0033] Figure 8 Schematic diagram of functional modules of a multi-scenario optimal scheduling device for an energy storage system provided by an embodiment of the present application;

[0034] Figure 9 Schematic diagram of the structure of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0035] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0036] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0037] As a renewable and low-pollution clean energy, photovoltaic power generation has been widely used globally in recent years. A photovoltaic generation system, abbreviated as a PV system or PV, refers to a power generation system that directly converts solar radiant energy into electrical energy by using the photovoltaic effect of photovoltaic cells. However, photovoltaic power generation has significant volatility and randomness, mainly affected by factors such as weather, climate, and geographical location. With the continuous expansion of the scale of photovoltaic grid connection, the intermittency and instability of photovoltaic power generation pose a threat to the stable operation of the power system, and at the same time lead to energy waste and a reduction in the revenue of photovoltaic power plants.

[0038] As a flexible resource, an energy storage system (ESS) has the advantages of flexible configuration of power and energy according to different application requirements, fast response speed, and no geographical resource restrictions. The energy storage system is built in conjunction with a photovoltaic power plant to form a PV-ESS system, which can effectively suppress the fluctuations of photovoltaic power generation and improve the stability and reliability of photovoltaic grid connection. In addition, the energy storage system can further improve the economic benefits of the PV-ESS system by participating in power market transactions.

[0039] The multi-scenario optimal scheduling method for an energy storage system provided by the embodiments of the present application can be applied to such asFigure 1 In the application environment shown. Among them, the photovoltaic system 101 and the energy storage system 102 are built in combination. The photovoltaic modules of the photovoltaic system 101 can convert solar energy into direct current, and the inverter of the photovoltaic system 101 converts the direct current into alternating current for use by households or the power grid 103; the energy storage system 102 can store the excess electric energy of the photovoltaic system 101 for use by households or the power grid 103. When the electric energy of the energy storage system 102 is insufficient, it can obtain electric energy from the power grid 103.

[0040] In an exemplary embodiment, as Figure 2 shown, a multi-scenario optimal scheduling method for an energy storage system is provided. This method is executed by a computer device. Specifically, it can be executed alone by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the energy storage system in as an example for illustration, it includes the following steps 202 to step 212. Among them:

[0041] Step 202: Obtain the initial decision variables for training the scheduling model and the constraint terms generated based on the constraint conditions;

[0042] Among them, the scheduling model can be used to solve the maximum revenue problem in the electricity market. The objective function can be used to guide the optimization process of the scheduling model. The objective function includes decision variables and constraint terms. The decision variables are the unknowns that need to be determined in the model optimization. The initial decision variables are the initial values of the decision variables. The constraint conditions can constrain the decision variables and / or the input parameters of the scheduling model. The constraint conditions limit the feasible solutions of the decision variables within a specific range. By continuously updating the decision variables, the optimal value (i.e., the maximum revenue) of the objective function can be found. Exemplarily, the decision variables can be the power generation plan or the energy storage control strategy. Specifically, they can be the working parameter values in the charge and discharge control strategy of the energy storage system, such as the charge and discharge power, frequency modulation capacity, frequency modulation mileage, and scheduling duration of the energy storage system at different time periods.

[0043] Step 204: Obtain a prediction data set, where the prediction data set includes predicted photovoltaic power output, the first predicted electricity price set in the electric energy market, and the second predicted electricity price set in the ancillary service market;

[0044] The electricity energy market and the ancillary service market are two important components in the power market, responsible for different functions respectively; the electricity energy market is the most fundamental market in the power system, mainly trading electric energy, that is, power generation enterprises supply electricity to users or retailers, and users pay corresponding fees; the ancillary service market provides various services required to maintain the stable operation of the power system, such as frequency regulation, peak shaving, reserve, black start, voltage control, etc. The ancillary service market can include a frequency regulation ancillary service market, a peak shaving ancillary service market, a reserve ancillary service market, a black start ancillary service market, etc. according to different services provided. These ancillary service markets jointly ensure the stability and reliability of the power system; the electricity energy market and the ancillary service market cooperate with each other to ensure the reliability and economy of the power system. Photovoltaic output refers to the electric power output by a photovoltaic power generation system under specific conditions. The photovoltaic output is also called the output power of the photovoltaic, usually expressed in kilowatts (kW) or megawatts (MW); the first predicted electricity price set centrally contains multiple possible electricity prices in the electricity energy market for a future day predicted, and the second predicted electricity price set contains multiple possible electricity prices in the ancillary service market for a future day predicted.

[0045] Step 206: Based on the predicted photovoltaic output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variables, and the constraint terms, generate the predicted total revenue of the electricity energy market and the ancillary service market;

[0046] Among them, the predicted total revenue is the sum of the revenues of the electricity energy market and the ancillary service market.

[0047] Step 208: Based on the predicted total revenue, update the initial decision variables to optimize the scheduling model.

[0048] Step 210: When the predicted total revenue meets the preset conditions or the scheduling model reaches the preset number of iterations, obtain the optimized target scheduling model;

[0049] Step 212: Based on the optimal decision variables of the target scheduling model, adjust the charge and discharge control strategy of the energy storage system.

[0050] Among them, the preset condition can be that the growth of the predicted total revenue is lower than a certain threshold (that is, the growth of the predicted total revenue no longer changes significantly), or that the predicted total revenue reaches or exceeds a certain set value. The preset number of iterations is the preset maximum number of iterations allowed for iteration. After reaching the preset number of iterations, the iteration is stopped. Setting the maximum number of iterations can prevent the algorithm from looping infinitely or running for too long. The initial decision variables can be adjusted according to the predicted total revenue to obtain updated decision variables. Common methods include gradient descent, genetic algorithm, etc., and then the updated decision variables are used as the initial decision variables for the next round of iterations. In the next round of iterations, based on the predicted photovoltaic output, the first predicted electricity price set, the second predicted electricity price set, the updated initial decision variables, and the constraints, a new predicted total revenue is generated again, and the updated decision variables are adjusted again according to the new predicted total revenue. The updated decision variables are used as the initial decision variables for the next round, and the above steps are repeated to gradually optimize the decision variables until the predicted total revenue reaches the expectation or cannot be further improved or the maximum number of iterations is reached, then the model optimization process ends.

[0051] It should be noted that the optimal decision variable can be the optimal decision variable determined based on the predicted photovoltaic output, electric energy market electricity price, and ancillary service market electricity price. When the predicted photovoltaic output, electric energy market electricity price, and ancillary service market electricity price change, the optimal decision variable will also change accordingly. Specifically, the predicted total revenue of the electric energy market and the ancillary service market can be generated based on the predicted photovoltaic output, electric energy market electricity price, and ancillary service market electricity price after the change, and the optimal decision variables and constraints before the change of electricity price and photovoltaic output. Based on the predicted total revenue, the optimal decision variable is updated to optimize the scheduling model, and the target scheduling model that has been optimized again is obtained. Based on the decision variables corresponding to the target scheduling model that has been optimized again, the charging and discharging control strategy of the energy storage system is adjusted.

[0052] Implement the above steps 202 to 212. Based on the predicted photovoltaic power output, the electricity energy market price, and the ancillary service market price, as well as the decision variables and constraint terms, generate the predicted total revenue of the electricity energy market and the ancillary service market. Through the predicted total revenue, iteratively update the initial decision variables. When the predicted total revenue meets the preset conditions or the scheduling model reaches the preset number of iterations, complete the optimization of the scheduling model, and adjust the charging and discharging strategy of the energy storage system according to the optimal decision variables corresponding to the optimized target scheduling model. Thus, the charging and discharging strategy of the energy storage system can be dynamically adjusted according to the predicted electricity price, enabling the energy storage system to participate in both the electricity energy market and the ancillary service market simultaneously, and maximizing the economic benefits of the entire power market; by combining the revenues of the electricity energy market and the ancillary service market, the overall revenue of the power market can be evaluated more comprehensively, avoiding the limitations of single-market analysis; relying on a single market may face greater risks, while combining the revenues of multiple markets can diversify risks and enhance the stability of revenues; the electricity prices and demands in the electricity energy market and the ancillary service market fluctuate differently, and combining the revenues of the two can better respond to market changes and ensure stable revenues; by optimizing the participation strategies in the two markets, a more favorable position can be occupied in the competition, enhancing market competitiveness.

[0053] In another exemplary embodiment of the present application, in order to accurately obtain the prediction dataset, a scenario generation and reduction method can be used to simulate the uncertain electricity price. First, generate multiple prediction samples through Monte Carlo simulation, and then, based on the Euclidean distance metric criterion, optimize the original scenario set through scenario reduction technology to obtain typical scenarios. As Figure 3 shown, the above step 204 of "obtaining the prediction dataset" can be replaced by the following steps 2041 to 2043:

[0054] Step 2041: Obtain the historical photovoltaic power output data, the historical electricity price data of the electricity energy market and the ancillary service market;

[0055] Among them, the historical electricity price data of the electricity energy market and the ancillary service market can be obtained, the historical photovoltaic power output data of the photovoltaic system can also be recorded, and other relevant data that may affect the electricity price or photovoltaic power output, such as demand fluctuations, fuel price changes, weather, and seasons, can also be obtained; perform preprocessing on the obtained data, such as data cleaning, normalization, and feature extraction; establish an electricity price model and a photovoltaic power output model. The electricity price model is used to fit the probability distributions of the electricity energy market price and the ancillary service market price based on the preprocessed historical electricity price data, and the photovoltaic power output model is used to fit the probability distribution of the photovoltaic power output based on the preprocessed historical photovoltaic power output data.

[0056] Step 2042: Use the Monte Carlo algorithm to perform random sampling and simulation processing on the historical photovoltaic power output data and the historical electricity price data to generate a prediction sample set;

[0057] Among them, the Monte Carlo algorithm can be used to generate a large number of random samples from the probability distributions of electricity prices and photovoltaic power outputs. Combining the random samples, multiple possible future scenarios are simulated. Through the simulated scenarios, the expected values and confidence intervals of electricity prices in the electricity energy market, electricity prices in the ancillary service market, and photovoltaic power outputs are calculated, and the uncertainty of the prediction results is evaluated to provide probabilistic predictions. The generated prediction sample set may include multiple electricity prices in the electricity energy market and the prediction probabilities corresponding to each electricity price in the electricity energy market, multiple electricity prices in the ancillary service market and the prediction probabilities corresponding to each electricity price in the ancillary service market, multiple predicted photovoltaic power outputs and the prediction probabilities corresponding to each predicted photovoltaic power output.

[0058] Step 2043: Based on the Euclidean distance metric criterion, perform scenario reduction processing on the prediction sample set to obtain the prediction data set.

[0059] Among them, the Euclidean distance metric criterion is a method for measuring the straight-line distance between two points, applicable to multi-dimensional spaces. It can merge or delete similar or redundant points through the Euclidean distances between various points in the scenario. If the Euclidean distance between two points is less than a certain preset threshold, it is considered that these two points are similar, and these two points can be retained, and their similarity can be used for clustering, dimensionality reduction, or classification. If the Euclidean distance between two points is very small (close to zero), it is considered that these two points are redundant, and one of the points can be deleted; thus, the scenario is reduced, and important information is retained.

[0060] In the embodiment of the present application, various uncertain factors such as demand fluctuations and weather conditions that affect electricity prices can be randomly simulated through the Monte Carlo algorithm, so that uncertainties can be effectively captured and more comprehensive predictions can be provided. Through a large number of simulations using the Monte Carlo algorithm, not only can electricity prices be predicted, but also probability distributions can be generated to help evaluate the possibilities of different results and support more comprehensive risk analysis. The high computational efficiency and visualization ability of the Monte Carlo algorithm can predict electricity prices efficiently and accurately, and the simulation results can be intuitively displayed through visual data, facilitating decision-makers to understand electricity price fluctuations and potential risks. Through scenario reduction processing using the Euclidean distance metric criterion, similar scenarios can be quickly identified and removed, reducing the data volume, improving the computational efficiency, and ensuring that the reduced data still retains important features and reduces information loss.

[0061] In another exemplary embodiment of the present application, the constraint term includes a constraint term for suppressing photovoltaic fluctuations. The constraint term for suppressing photovoltaic fluctuations is used to control the energy storage system to charge or discharge when the fluctuation range of the predicted photovoltaic power output is greater than a preset fluctuation limit value, so as to reduce the fluctuation of the predicted photovoltaic power output.

[0062] Among them, suppressing PV fluctuations means reducing the fluctuations in the output power of PV power generation (i.e., PV output), ensuring its stability and reliability. When the predicted PV output increases by more than a preset fluctuation limit within a preset time period, the energy storage system can be charged to absorb the predicted PV output. When the predicted PV output decreases by more than the preset fluctuation limit within the preset time period, the energy storage system can be discharged to supplement the predicted PV output, thereby suppressing PV fluctuations can be achieved.

[0063] In the embodiments of the present application, through the dynamic charge and discharge control of the energy storage system, the fluctuations in PV power generation are suppressed, and at the same time, it participates in the electricity energy market and the ancillary service market, thereby realizing the multi-objective coordination of PV output fluctuation suppression, maximizing the electricity energy market revenue, and optimizing the frequency regulation market revenue, and improving the stability and economy of the system.

[0064] In another exemplary embodiment of the present application, in order to more accurately and efficiently find the optimal solution of the predicted total revenue, as Figure 4 shown, the above step 206 can be replaced by the following steps 2061 to 2062:

[0065] Step 2061: Based on the constraint terms, constrain the predicted PV output and the initial decision variables to obtain the target PV output for suppressing fluctuations and the target decision variables.

[0066] Among them, there can be one or more constraint terms in the objective function, and each constraint term can include one or more constraint conditions. The constraint conditions can be equations or inequalities. Constraining the predicted PV output means restricting the value range of the predicted PV output through one or more constraint conditions. The target PV output for suppressing fluctuations is the predicted PV output that satisfies all constraint conditions, and the target PV output for suppressing fluctuations can be the PV output that can suppress PV fluctuations. Similarly, constraining the initial decision variables means restricting the value range of the initial decision variables through one or more constraint conditions, and the target decision variables are the initial decision variables that satisfy all constraint conditions.

[0067] Step 2062: Based on the target PV output for suppressing fluctuations, the first set of predicted electricity prices, the second set of predicted electricity prices, and the target decision variables, generate the predicted total revenue of the electricity energy market and the ancillary service market.

[0068] Among them, since the constraint terms limit the value ranges of the predicted PV output and the initial decision variables, the constraint terms will affect the value range of the predicted total revenue, and thus affect the value of the maximum revenue.

[0069] In the embodiments of the present application, the output power of the energy storage for suppressing photovoltaic fluctuations and the decision variables are constrained by constraint terms, and based on the output power of suppressing photovoltaic fluctuations, electricity prices, and decision variables after constraint, a predicted total revenue is generated, so that the revenue can be within a reasonable range and invalid solutions can be avoided; the constraint terms can guide the algorithm of the model to search in a specific direction, accelerate convergence, and find a better solution; the constraint terms can also improve the robustness of the model to noise and outliers, making the model perform more stably in an uncertain environment; in short, the constraint terms can improve the value of the objective function and the optimization effect by restricting the solution space, improving feasibility, and guiding the optimization direction.

[0070] In another exemplary embodiment of the present application, the ancillary service market includes a frequency regulation ancillary service market, the first predicted electricity price set includes a plurality of first electricity prices and the probability of each first electricity price; the second predicted electricity price set includes a plurality of second electricity prices and the probability of each second electricity price, and a plurality of third electricity prices and the probability of each third electricity price; the initial decision variables include the first charging power and the first discharging power of the energy storage system participating in the energy market, the first frequency regulation capacity and the first frequency regulation mileage of the energy storage system participating in the frequency regulation ancillary service market, and the first scheduling duration.

[0071] Among them, the first electricity price can be the electricity price of the energy market. The electricity price of the energy market is the price when electric energy is traded as a commodity, which can reflect the relationship between power supply and demand. The first electricity price can be expressed as The probability of the first electricity price can be expressed as ρ p ; in the frequency regulation ancillary service market, the frequency regulation capacity and the frequency regulation mileage are two key indicators, which can be used to measure and compensate the resources providing frequency regulation services. The frequency regulation capacity is the maximum frequency regulation power that the resources can provide within a specific time, and the frequency regulation mileage is the total amount of change in the actual frequency regulation power provided by the resources within a specific time; the second electricity price can be the frequency regulation capacity electricity price of the frequency regulation ancillary service market. The frequency regulation capacity electricity price is the fee paid by the power system to maintain frequency stability, which can be expressed as The probability of the second electricity price can be expressed as p q ; the third electricity price can be the frequency regulation mileage electricity price of the ancillary service market. The frequency regulation mileage electricity price is the fee paid by the power system for the electricity actually provided for frequency regulation services, which can be expressed as The probability of the third electricity price can be expressed as ρ r ; the first charging power can be the charging power of the energy storage system participating in the energy market, which can be expressed as The first discharging power can be the discharging power of the energy storage system participating in the energy market, which can be expressed as The first frequency regulation capacity can be expressed as The first frequency regulation mileage can be expressed as t is the time for the energy storage system to participate in the electricity energy duration trading and the ancillary service market trading. The first dispatching duration can be the dispatching duration for the energy storage system to participate in the electricity energy market trading and the ancillary service market trading. The first dispatching duration can be expressed as Δt, and the first dispatching duration can be 0.5 hours, 1 hour, 2 hours, etc.

[0072] To more accurately predict the revenues of the electricity energy market and the frequency regulation ancillary service market, as Figure 5 shown, the above step 2061 can be replaced by the following step 20611:

[0073] Step 20611: Based on the constraint items, respectively constrain the predicted photovoltaic output, the first charging power, the first discharging power, the first frequency regulation capacity, the first frequency regulation mileage, and the first dispatching duration to obtain the target photovoltaic output for suppressing fluctuations, the target charging power, the target discharging power, the target frequency regulation capacity, the target frequency regulation mileage, and the target dispatching duration;

[0074] The above step 2062 can be replaced by the following steps 20621 to 20623:

[0075] Step 20621: Based on each of the first electricity prices, the probability corresponding to the first electricity price, the target charging power, the target discharging power, and the target dispatching duration, generate the first revenue of the electricity energy market;

[0076]

[0077] Among them, the first revenue of the electricity energy market can be expressed as C1, and the first revenue can be calculated by the above formula (1).

[0078] Step 20622: Based on each of the second electricity prices, the probability corresponding to the second electricity price, the target frequency regulation capacity, each of the third electricity prices, the probability corresponding to the third electricity price, the target frequency regulation mileage, and the target dispatching duration, generate the second revenue of the frequency regulation ancillary service market;

[0079]

[0080] Among them, the second revenue of the frequency regulation ancillary service market can be expressed as C2, and the second revenue can be calculated by the above formula (2).

[0081] Step 20623: Based on the first revenue and the second revenue, generate the predicted total revenue.

[0082] max F = C1 + C2 (3);

[0083] Among them, the predicted total revenue can be expressed as maxF, and the predicted total revenue can be calculated by the above formula (3).

[0084] In the embodiments of the present application, by combining the revenues of the electric energy market and the frequency modulation ancillary service market, the overall revenue can be evaluated more comprehensively, avoiding the limitations of single-market analysis; considering the revenues of the two markets comprehensively helps to optimize the charge and discharge strategies of energy storage systems or power generation resources and improve the resource utilization efficiency; relying on a single market may face greater risks, while combining the revenues of multiple markets can diversify risks and enhance the stability of revenues; the electricity prices and demands in the electric energy market and the frequency modulation ancillary service market fluctuate differently, and combining the revenues of the two can better respond to market changes and ensure stable revenues; by optimizing the participation strategies in the two markets, a more favorable position can be occupied in the competition and the market competitiveness can be enhanced.

[0085] In another exemplary embodiment of the present application, as Figure 6 shown, the above step 20611 can be replaced by the following steps S1 to S4:

[0086] Step S1: Based on the photovoltaic fluctuation suppression constraint term, constrain the predicted photovoltaic output to obtain the target photovoltaic output for suppressing fluctuations;

[0087] Among them, the photovoltaic fluctuation suppression constraint term can include the following formulas (4) to (8).

[0088]

[0089] As shown in the above formula (4), t′ is the time for the energy storage system to suppress photovoltaic fluctuations, and the second scheduling duration for the energy storage system to suppress photovoltaic fluctuations can be expressed as Δt′, P p,t′ is the output power of the photovoltaic at time t’ (i.e., the predicted photovoltaic output), P p，t′-Δt′ is the output power of the photovoltaic at time t′ - Δt′, is the charging state of the energy storage system for suppressing photovoltaic fluctuations. When is 1, the energy storage system charges to absorb the excess photovoltaic power; M is a maximum value, which can take a value of 10 9 , P δ can be the maximum allowable fluctuation amplitude of the photovoltaic output within the time scale of Δt′. Δt′ can be 10 minutes, 15 minutes, etc. When the photovoltaic output fluctuates beyond the preset fluctuation limit within the time scale of Δt′ (such as within 10 minutes), the energy storage system starts to charge and discharge. When the photovoltaic output increases beyond the limit within 10 minutes, the energy storage system needs to charge to absorb the photovoltaic output and needs to satisfy the constraint conditions in the above formula (4).

[0090]

[0091] As shown in the above formula (5), is the discharging state of the energy storage system for suppressing the fluctuations of photovoltaic power. When is 1, the energy storage system discharges to supplement the photovoltaic power generation. When the photovoltaic output power decreases by more than the limit within ten minutes, the energy storage system needs to discharge to supplement the photovoltaic output power and must meet the constraint conditions in the above formula (5).

[0092] P p，t′ ≥0 (6);

[0093] Meanwhile, it is necessary to ensure that the photovoltaic output power is non - negative, as shown in the above formula (6).

[0094]

[0095] As shown in the above formula (7), is the grid - connected power of the photovoltaic system and the energy storage system, is the charging power of the energy storage system for suppressing the fluctuations of photovoltaic power, is the discharging power of the energy storage system for suppressing the fluctuations of photovoltaic power. Formula (7) indicates that during the process of suppressing the fluctuations of photovoltaic power, the grid - connected power of the photovoltaic - energy storage system is jointly determined by the predicted photovoltaic output power and the planned output power of the energy storage, and its value is the sum of the two.

[0096]

[0097] As shown in the above formula (8), when the energy storage system executes the function of suppressing fluctuations, the grid - connected power of the photovoltaic - energy storage system after suppression processing must strictly meet the technical requirements for grid connection.

[0098] Step S2: Based on the energy storage power constraint term, the power coupling constraint term, and the energy storage energy constraint term, constrain the first charging power and the first discharging power to obtain the target charging power and the target discharging power;

[0099] Among them, the energy storage power constraint term can include the following formulas (9) to (14), the power coupling constraint term can include the following formulas (15) and (16), and the energy storage energy constraint term can include the following formulas (17) to (20).

[0100]

[0101] As shown in the above formula (9), is the rated charge - discharge power of the energy storage system, and can constrain the charging power and of the energy storage system for suppressing the fluctuations of photovoltaic power through the charging state variables of the energy storage system for suppressing the fluctuations of photovoltaic power.

[0102]

[0103] As shown in the above formula (10), the discharge state variable for suppressing the PV fluctuations by the energy storage system and the rated charge-discharge power of the energy storage system are used to constrain the discharge power of the energy storage system for suppressing the PV fluctuations

[0104]

[0105] As shown in the above formula (11), is the charge state variable of the energy storage system participating in the electric energy market. When is 1, the energy storage system charges. It can be achieved through and the rated charge-discharge power of the energy storage system to constrain the first charging power of the energy storage system participating in the electric energy market

[0106]

[0107] As shown in the above formula (12), is the discharge state variable of the energy storage system participating in the electric energy market. It can be achieved through and the rated charge-discharge power of the energy storage system to constrain the first discharge power of the energy storage system participating in the electric energy market. Formulas (9) to (12) ensure that the charge-discharge power of the energy storage system for suppressing PV fluctuations and participating in the power market is within the rated power range

[0108]

[0109] As shown in the above formulas (13) and (14), the sum of the charge state variable and the discharge state variable for suppressing the PV fluctuations by the energy storage system can be constrained. Also, the sum of the charge state variable and the discharge state variable of the energy storage system participating in the electric energy market can be constrained, that is, it is not allowed for the energy storage system to charge and discharge simultaneously

[0110]

[0111] As shown in the above formula (15), the sum of the first charging power of the energy storage system participating in the electric energy market and the first frequency regulation capacity of the energy storage system participating in the frequency regulation ancillary service market can be constrained by the rated charge-discharge power

[0112] ​

[0113] As shown in the above formula (16), the rated charge-discharge power of the energy storage system can be used to constrain the first discharge power of the energy storage system participating in the electricity energy market and the first frequency regulation capacity of the energy storage system participating in the frequency regulation ancillary service market in sum.

[0114]

[0115] As shown in the above formula (17), E e,t′ is the energy value of the energy storage system participating in the period t′ of suppressing PV fluctuations, is the rated capacity of the energy storage system, and it can be achieved through constraining E e,t′ .

[0116]

[0117] As shown in the above formula (18), E e,t is the energy value of the energy storage system participating in the period t of the electricity energy market, and it can be constrained by the rated capacity of the energy storage system for E e,t . Formulas (17) and (18) ensure that the energy storage system does not exceed the rated capacity limit during operation.

[0118]

[0119] As shown in the above formula (19), η ch is the charging efficiency of the energy storage, and ηdis is the discharging efficiency of the energy storage.

[0120]

[0121] As shown in the above formulas (19) and (20), the capacity continuity of the energy storage system can be constrained.

[0122] Step S3: Based on the power coupling constraint term, constrain the first frequency regulation capacity and the first frequency regulation mileage to obtain the target frequency regulation capacity and the target frequency regulation mileage;

[0123] As shown in the above formulas (15) and (16), the rated charge-discharge power of the energy storage system can be used to constrain the first charging power of the energy storage system participating in the electricity energy market and the first frequency regulation capacity of the energy storage system participating in the frequency regulation ancillary service market in sum; the rated charge-discharge power of the energy storage system can be used to constrain the first discharge power of the energy storage system participating in the electricity energy market is constrained by the sum of the first frequency regulation capacity of the energy storage system participating in the frequency regulation ancillary service market. And the sum is constrained.

[0124] It should be noted that the power coupling constraint term also includes the following formulas (21) and (22).

[0125]

[0126] As shown in the above formula (21), is a state 0-1 variable for the energy storage system to participate in the frequency regulation ancillary service market. When it is 1, the energy storage system participates in the frequency regulation ancillary service market. When it is 0, the energy storage system does not participate in the frequency regulation ancillary service market. is the maximum frequency regulation capacity of the energy storage system, which can be obtained through and to constrain the first frequency regulation capacity of the energy storage system participating in the frequency regulation ancillary service market. And the sum is constrained.

[0127]

[0128] As shown in the above formula (22), S is the historical frequency regulation mileage multiplier of the energy storage system, which can be used to constrain the first frequency regulation mileage of the energy storage participating in the frequency regulation ancillary service market through the maximum frequency regulation capacity of the energy storage system and S. And the sum is constrained.

[0129] Step S4: Based on the time-scale coupling constraint term, constrain the first scheduling duration to obtain the target scheduling duration.

[0130] Among them, the time-scale coupling constraint term can include the following formulas (23) to (26).

[0131] E t = E e，t′ + E e，t , t' = 6t (23);

[0132] Among them, as shown in the above formula (23), E t is the sum of the energy E e,t′ for the energy storage system to suppress PV fluctuations and the energy E e,t in the application scenario of participating in the electricity energy market; formula (23) integrates the energy states of the energy storage system in PV fluctuation suppression and electricity energy market participation through the energy coupling mechanism.

[0133] E1 = E 24 (24);

[0134] As shown in the above formula (24), with a 24-hour scheduling period, the energy value of the energy storage in the first period is equal to that in the 24th period. By setting the boundary conditions of the scheduling period, it is required that the energy values of the energy storage at the beginning and end of the period remain consistent to ensure the continuity of system operation.

[0135]

[0136] As shown in the above formula (25), is the initial capacity of the energy storage system; formula (25) is used to initialize the energy state of the energy storage system.

[0137]

[0138] In addition, to avoid multi-time scale scheduling conflicts, it is stipulated in formula (26) that when the energy storage system is used to suppress PV fluctuations, its energy cannot participate in the electricity energy market trading or frequency regulation auxiliary service market trading simultaneously, so as to achieve the decoupled optimization of different time scale scenarios. Exemplarily, the future 24 hours can be divided into multiple first scheduling durations and multiple second scheduling durations. Analyze the PV fluctuation range within each second scheduling duration. If the PV fluctuation range within this second scheduling duration is greater than the preset fluctuation limit, suppress the PV fluctuations, and control that within the first scheduling duration corresponding to this second scheduling duration, the energy of the energy storage system cannot participate in the electricity energy market trading or frequency regulation auxiliary service market trading simultaneously. If the PV fluctuation range within this second scheduling duration is less than or equal to the preset fluctuation limit, control that within the first scheduling duration corresponding to this second scheduling duration, the energy of the energy storage system can participate in the electricity energy market trading or frequency regulation auxiliary service market trading simultaneously; specifically, when the first scheduling duration is 1 hour and the second scheduling duration is 10 minutes, a PV fluctuation suppression output power plan at a 10-minute scale, an electricity energy market output power plan at a 1-hour scale, and a frequency regulation auxiliary service market output power plan at a 1-hour scale can be made. This plan can divide the future 24 hours into 24 first scheduling durations and 144 second scheduling durations. If it is predicted that the PV fluctuation range within the second scheduling duration from 5 o'clock to 5:10 is greater than the preset fluctuation limit, suppress the PV fluctuations, and control that within the first scheduling duration from 5 o'clock to 6 o'clock, the energy of the energy storage system does not participate in the electricity energy market trading or frequency regulation auxiliary service market trading. If it is predicted that the PV fluctuation range within the second scheduling duration from 5 o'clock to 5:10 is less than or equal to the preset fluctuation limit, control that within the first scheduling duration from 5 o'clock to 6 o'clock, the energy of the energy storage system can participate in the electricity energy market trading or frequency regulation auxiliary service market trading simultaneously.

[0139] In the embodiments of the present application, by suppressing the photovoltaic fluctuation constraint term, the predicted photovoltaic output is constrained, so that the fluctuation of photovoltaic power generation can be suppressed through the dynamic charge and discharge control of the energy storage system. Through the energy storage power constraint term, the power coupling constraint term, and the energy storage energy constraint term, the charge and discharge power, the state of charge, and the frequency regulation ability of the energy storage system can be restricted, so that the system operates within a safe range; through the time-scale coupling constraint term, it is possible to avoid the multi-time-scale scheduling conflict that the energy of the energy storage system participates in the electricity energy market transaction at the same time when the energy storage system is used to suppress the photovoltaic fluctuation, and realize the decoupled optimization of different time-scale scenarios.

[0140] The research in the related technology mainly focuses on the application of the energy storage system in a single scenario, such as suppressing photovoltaic fluctuations or participating in the electricity energy market. However, the economic benefits of the energy storage system in a single scenario are relatively low, and its potential in multiple markets cannot be fully utilized. With the continuous development of the power market, the demand for the energy storage system to participate in multi-scenario scheduling is increasing.

[0141] In another exemplary embodiment of the present application, as Figure 7 shown, an optimized scheduling framework is provided, including: a photovoltaic output prediction module 31, an electricity energy market electricity price prediction module 32, a frequency modulation auxiliary service market electricity price prediction module 33, an operation constraint module 34, and an objective function module 35;

[0142] Among them, the photovoltaic output prediction module 31 is used to predict the photovoltaic power generation volume within the next 24 hours and provide basic power generation data for the model. The electricity energy market electricity price prediction module 32 and the frequency modulation auxiliary service market electricity price prediction module 33 respectively predict the electricity prices in the electricity energy market and the frequency modulation market, providing a basis for revenue calculation. The operation constraint module 34 considers technical constraints such as the output limit of power generation equipment and the grid transmission capacity to ensure the feasibility of the scheduling plan. The optimized scheduling model can be used to solve the problem of maximizing the revenue in the power market. The objective function module 35 aims to maximize the total revenue in the electricity energy market and the frequency modulation market and guide the optimization process.

[0143] The operation constraint module 34 may include a fluctuation suppression constraint module, an energy storage power constraint module, an energy storage electricity constraint module, and a frequency modulation power constraint module. The fluctuation suppression constraint module, the energy storage power constraint module, the energy storage electricity constraint module, and the frequency modulation power constraint module are respectively used to restrict the charge and discharge power, the state of charge, and the frequency regulation ability of the energy storage system to ensure that the system operates within a safe range; these modules cooperate together to realize the optimal scheduling and revenue maximization of the power system through the 10-minute scale photovoltaic fluctuation suppression plan and the 1-hour scale electricity energy market and frequency modulation market output plan.

[0144] The embodiments of the present application propose a multi-scenario optimized scheduling strategy for a photovoltaic energy storage system, and the optimized scheduling strategy can be applied to Figure 7The optimized scheduling framework shown aims to address the threats posed by the volatility of photovoltaic power generation to the stability of the power system, the low economic efficiency of energy storage systems in a single scenario, and the difficulty of coordinated optimization of multi-scenario scheduling. By establishing a model for energy storage to suppress photovoltaic fluctuations and combining the uncertainty of electricity prices, a scheduling strategy for energy storage systems to participate in the electricity energy market and the frequency regulation ancillary service market is proposed. Using a multi-time scale optimized scheduling framework, the power coupling problem between energy storage systems in suppressing photovoltaic fluctuations and participating in the power market is coordinated to achieve multi-objective coordination of suppressing photovoltaic output fluctuations, maximizing the revenue of the electricity energy market, and optimizing the revenue of the frequency regulation market, significantly enhancing the stability and economy of the system.

[0145] The optimized scheduling strategy described above may include the following steps S5 to S8:

[0146] Step S5: Build a multi-scenario optimized scheduling model for the photovoltaic energy storage system;

[0147] Among them, a multi-scenario optimized scheduling model for the photovoltaic energy storage system can be built on the MATLAB platform;

[0148] Step S6: Construct an optimized scheduling objective function for the photovoltaic energy storage system;

[0149] Among them, the optimization goal of the energy storage system is to maximize its revenue in the electricity energy market and the frequency regulation ancillary service market while suppressing photovoltaic fluctuations. The objective function can be as shown in Formulas (1) to (3) above, which will not be elaborated here. The optimized scheduling constraint conditions for the photovoltaic energy storage system can be as shown in Formulas (4) to (26) above, which will not be elaborated here.

[0150] Step S7: Establish a day-ahead data prediction model;

[0151] Among them, the scenario generation and reduction method can be used to simulate uncertainty events. 1000 prediction samples are generated through Monte Carlo simulation. Based on the Euclidean distance metric criterion, the original scenario set is optimized through scenario reduction technology to obtain typical scenarios, and the day-ahead photovoltaic output prediction, electricity energy market electricity price prediction, and frequency regulation ancillary service market electricity price prediction are obtained respectively.

[0152] Step S8: Solve the multi-scenario optimized scheduling model for the energy storage system;

[0153] Based on the given logical framework, the solution process of the multi-scenario optimal scheduling model for the energy storage system is as follows: First, the data for the previous 24 hours are obtained through the prediction method in step S7, including the predicted photovoltaic output, the predicted electricity price in the electricity energy market, and the predicted electricity price in the frequency regulation ancillary service market. These data are used as inputs into the optimal scheduling model. The objective function of the model aims to maximize the revenue in the electricity energy market and the revenue in the frequency regulation ancillary service market, while being subject to operating constraints such as the constraint of suppressing fluctuations, the energy storage power constraint, the energy storage capacity constraint, and the frequency regulation power constraint. By solving the optimal scheduling model, the optimal scheduling strategy for the previous day is obtained, including the plan for suppressing the fluctuating photovoltaic output at a 10-minute scale, the output plan in the electricity energy market at a 1-hour scale, and the output plan in the frequency regulation ancillary service market at a 1-hour scale. These plans ensure the economy and reliability of the energy storage system under different scenarios.

[0154] Based on the same inventive concept, an embodiment of the present application also provides an energy storage system multi-scenario optimal scheduling device for implementing the above-mentioned energy storage system multi-scenario optimal scheduling method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the energy storage system multi-scenario optimal scheduling device provided below can refer to the limitations on the energy storage system multi-scenario optimal scheduling method in the above text, and will not be elaborated here.

[0155] In an exemplary embodiment, as Figure 8 shown, an energy storage system multi-scenario optimal scheduling device 400 is provided, including:

[0156] A first acquisition module 401, configured to acquire an initial decision variable for training the scheduling model and constraint terms generated based on constraint conditions;

[0157] A second acquisition module 402, configured to acquire a prediction data set, where the prediction data set includes predicted photovoltaic output, a first predicted electricity price set in the electricity energy market, and a second predicted electricity price set in the ancillary service market;

[0158] A generation module 403, configured to generate a predicted total revenue for the electricity energy market and the ancillary service market based on the predicted photovoltaic output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variable, and the constraint terms;

[0159] An update module 404, configured to update the initial decision variable based on the predicted total revenue to optimize the scheduling model;

[0160] A completion module 405, configured to obtain an optimized target scheduling model when the predicted total revenue meets a preset condition or the scheduling model reaches a preset number of iterations;

[0161] An adjustment module 406, configured to adjust the charge and discharge control strategy of the energy storage system based on the optimal decision variables of the target scheduling model.

[0162] Exemplarily, the multi-scenario optimal scheduling device 400 of the energy storage system may be the scheduling model itself. In some embodiments, the multi-scenario optimal scheduling device 400 of the energy storage system may also be a device independent of the scheduling model. In other embodiments, part of the functions of the multi-scenario optimal scheduling device 400 of the energy storage system (such as the functions of the generation module 403, the update module 404, and the completion module 405) may be implemented by the scheduling model, and the other part of the functions may be implemented by other devices.

[0163] As an alternative implementation manner, the constraint item includes a constraint item for suppressing photovoltaic fluctuations, and the constraint item for suppressing photovoltaic fluctuations is configured to control the energy storage system to charge or discharge when the fluctuation range of the predicted photovoltaic output power is greater than a preset fluctuation limit value, so as to reduce the fluctuation of the predicted photovoltaic output power.

[0164] As an alternative implementation manner, the second acquisition module 402 includes: an acquisition sub-module, configured to acquire historical photovoltaic output power data, historical electricity price data of the electric energy market and the ancillary service market; a simulation sub-module, configured to perform random sampling and simulation processing on the historical photovoltaic output power data and the historical electricity price data by using the Monte Carlo algorithm to generate a prediction sample set; a reduction sub-module, configured to perform scenario reduction processing on the prediction sample set based on the Euclidean distance metric criterion to obtain the prediction data set.

[0165] As an alternative implementation manner, the generation module 403 includes: a constraint sub-module, configured to constrain the predicted photovoltaic output power and the initial decision variables based on the constraint item to obtain a target photovoltaic output power for suppressing fluctuations and target decision variables; a generation sub-module, configured to generate a predicted total revenue of the electric energy market and the ancillary service market based on the target photovoltaic output power for suppressing fluctuations, the first predicted electricity price set, the second predicted electricity price set, and the target decision variables.

[0166] As an alternative implementation manner, the ancillary service market includes a frequency modulation ancillary service market, the first predicted electricity price set includes a plurality of first electricity prices and the probability of each first electricity price; the second predicted electricity price set includes a plurality of second electricity prices and the probability of each second electricity price, and a plurality of third electricity prices and the probability of each third electricity price; the initial decision variables include a first charging power and a first discharging power of the energy storage system participating in the electric energy market, a first frequency modulation capacity and a first frequency modulation mileage of the energy storage system participating in the frequency modulation ancillary service market, and a first scheduling duration.

[0167] The constraint sub-module includes: a constraint unit configured to, based on the constraint items, respectively constrain the predicted PV output power, the first charging power, the first discharging power, the first frequency regulation capacity, the first frequency regulation mileage, and the first scheduling duration, so as to obtain a target PV fluctuation suppressing output power, a target charging power, a target discharging power, a target frequency regulation capacity, a target frequency regulation mileage, and a target scheduling duration;

[0168] The generation sub-module includes: a generation unit configured to generate a first revenue of the electric energy market based on each of the first electricity prices, the probability corresponding to the first electricity price, the target charging power, the target discharging power, and the target scheduling duration; generate a second revenue of the frequency regulation ancillary service market based on each of the second electricity prices, the probability corresponding to the second electricity price, the target frequency regulation capacity, each of the third electricity prices, the probability corresponding to the third electricity price, the target frequency regulation mileage, and the target scheduling duration; and generate a predicted total revenue based on the first revenue and the second revenue.

[0169] As an alternative implementation, the constraint unit includes: a first constraint sub-unit configured to, based on the PV fluctuation suppressing constraint item, constrain the predicted PV output power to obtain a target PV fluctuation suppressing output power; a second constraint sub-unit configured to, based on the energy storage power constraint item, the power coupling constraint item, and the energy storage energy constraint item, constrain the first charging power and the first discharging power to obtain a target charging power and a target discharging power; a third constraint sub-unit configured to, based on the power coupling constraint item, constrain the first frequency regulation capacity and the first frequency regulation mileage to obtain a target frequency regulation capacity and a target frequency regulation mileage; and constrain the first scheduling duration based on the time scale coupling constraint item to obtain a target scheduling duration.

[0170] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal, and its internal structure diagram may be as Figure 9As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a multi-scenario optimal scheduling method for an energy storage system.

[0171] Those skilled in the art can understand that Figure 9 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0172] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the steps in the above method embodiments are implemented.

[0173] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0174] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0175] 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 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 need to comply with relevant regulations.

[0176] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0177] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0178] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0179] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present application; at the same time, for those of ordinary skill in the art, according to the ideas of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A multi-scenario optimal scheduling method for an energy storage system, characterized in that Applied to an energy storage system, the multi-scenario optimal scheduling method for the energy storage system includes: Obtaining initial decision variables for training a scheduling model and constraint terms generated based on constraint conditions; Obtaining a prediction data set, where the prediction data set includes predicted photovoltaic power output, a first predicted electricity price set in the electricity energy market, and a second predicted electricity price set in the ancillary service market; Generating the predicted total revenue in the electricity energy market and the ancillary service market based on the predicted photovoltaic power output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variables, and the constraint terms; Updating the initial decision variables based on the predicted total revenue to optimize the scheduling model; Obtaining an optimized target scheduling model when the predicted total revenue meets a preset condition or the scheduling model reaches a preset number of iterations; Adjusting the charge and discharge control strategy of the energy storage system based on the optimal decision variables of the target scheduling model.

2. The multi-scenario optimal scheduling method for the energy storage system according to claim 1, wherein: The constraint terms include a photovoltaic fluctuation suppression constraint term, which is used to control the energy storage system to charge or discharge when the fluctuation range of the predicted photovoltaic power output is greater than a preset fluctuation limit value, so as to reduce the fluctuation of the predicted photovoltaic power output.

3. The multi-scenario optimal scheduling method for an energy storage system according to claim 1, characterized in that The obtaining of the prediction data set includes: Obtaining historical photovoltaic power output data, historical electricity price data in the electricity energy market, and historical electricity price data in the ancillary service market; Using the Monte Carlo algorithm to perform random sampling and simulation processing on the historical photovoltaic power output data and the historical electricity price data to generate a prediction sample set; Performing scenario reduction processing on the prediction sample set based on the Euclidean distance metric criterion to obtain the prediction data set.

4. The multi-scenario optimal scheduling method for the energy storage system according to claim 1, wherein, The generating of the predicted total revenue in the electricity energy market and the ancillary service market based on the predicted photovoltaic power output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variables, and the constraint terms includes: Constraining the predicted photovoltaic power output and the initial decision variables based on the constraint terms to obtain the target photovoltaic fluctuation suppression power output and the target decision variables; Generating the predicted total revenue in the electricity energy market and the ancillary service market based on the target photovoltaic fluctuation suppression power output, the first predicted electricity price set, the second predicted electricity price set, and the target decision variables.

5. The multi-scenario optimal scheduling method for the energy storage system according to claim 4, wherein: The ancillary service market includes a frequency modulation ancillary service market. The first predicted electricity price set includes multiple first electricity prices and the probability of each first electricity price; the second predicted electricity price set includes multiple second electricity prices and the probability of each second electricity price, and multiple third electricity prices and the probability of each third electricity price; the initial decision variables include the first charging power and the first discharging power of the energy storage system participating in the electricity energy market, the first frequency modulation capacity and the first frequency modulation mileage of the energy storage system participating in the frequency modulation ancillary service market, and the first scheduling duration. Based on the above constraints, constraints are imposed on the predicted PV output and the initial decision variables to obtain the target PV output for suppressing fluctuations and the target decision variables, including: Based on the above constraints, constraints are respectively imposed on the predicted PV output, the first charging power, the first discharging power, the first frequency regulation capacity, the first frequency regulation mileage, and the first scheduling duration to obtain the target PV output for suppressing fluctuations, the target charging power, the target discharging power, the target frequency regulation capacity, the target frequency regulation mileage, and the target scheduling duration; Based on the target PV output for suppressing fluctuations, the first predicted electricity price set in the electricity energy market, the second predicted electricity price set in the ancillary service market, and the target decision variables, generating the predicted total revenue in the electricity energy market and the ancillary service market, including: Based on each of the first electricity prices, the probability corresponding to the first electricity price, the target charging power, the target discharging power, and the target scheduling duration, generating the first revenue in the electricity energy market; Based on each of the second electricity prices, the probability corresponding to the second electricity price, the target frequency regulation capacity, each of the third electricity prices, the probability corresponding to the third electricity price, the target frequency regulation mileage, and the target scheduling duration, generating the second revenue in the frequency regulation ancillary service market; Based on the first revenue and the second revenue, generating the predicted total revenue.

6. The multi-scenario optimal scheduling method for an energy storage system according to claim 5, wherein Based on the above constraints, constraints are respectively imposed on the predicted PV output, the first charging power, the first discharging power, the first frequency regulation capacity, the first frequency regulation mileage, and the first scheduling duration to obtain the target PV output for suppressing fluctuations, the target charging power, the target discharging power, the target frequency regulation capacity, the target frequency regulation mileage, and the target scheduling duration, including: Based on the constraint for suppressing PV output fluctuations, imposing constraints on the predicted PV output to obtain the target PV output for suppressing fluctuations; Based on the energy storage power constraint, the power coupling constraint, and the energy storage energy constraint, imposing constraints on the first charging power and the first discharging power to obtain the target charging power and the target discharging power; Based on the power coupling constraint, imposing constraints on the first frequency regulation capacity and the first frequency regulation mileage to obtain the target frequency regulation capacity and the target frequency regulation mileage; Based on the time scale coupling constraint, imposing constraints on the first scheduling duration to obtain the target scheduling duration.

7. A multi-scenario optimized scheduling device for an energy storage system, characterized in that, The multi-scenario optimal scheduling device for the energy storage system includes: A first acquisition module, configured to acquire the initial decision variables for training the scheduling model and the constraints generated based on the constraint conditions; A second acquisition module, configured to acquire a prediction data set, where the prediction data set includes the predicted PV output, the first predicted electricity price set in the electricity energy market, and the second predicted electricity price set in the ancillary service market; A generation module, configured to generate the predicted total revenue in the electricity energy market and the ancillary service market based on the predicted PV output, the first predicted electricity price set, the second predicted electricity price set, the initial decision variables, and the constraints; An update module, configured to update the initial decision variables based on the predicted total revenue to optimize the scheduling model; A completion module, configured to obtain an optimized target scheduling model when the predicted total revenue meets a preset condition or the scheduling model reaches a preset number of iterations; An adjustment module, configured to adjust the charge and discharge control strategy of the energy storage system based on the optimal decision variables of the target scheduling model.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the multi-scenario optimal scheduling method for an energy storage system according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the multi-scenario optimal scheduling method for an energy storage system according to any one of claims 1-6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the multi-scenario optimal scheduling method for an energy storage system according to any one of claims 1-6 are implemented.

Images