Compressed air energy storage and heat storage-containing power system planning optimization method, equipment and medium

Abstract

The invention discloses an electric power system planning optimization method and device containing compressed air energy storage and heat storage and a medium, and relates to the technical field of electric power optimization planning. The method comprises the steps of training a Transform model to obtain a power grid load demand prediction model according to historical operation data of a power system and historical load demands of a power grid; establishing a power system planning optimization model related to the predicted load demand of the power grid; inputting real-time operation data of the power system into the power grid load demand prediction model, and outputting a power grid predicted load demand of the power system in future time; and solving the power system planning optimization model by adopting a non-dominated sorting genetic optimization algorithm according to the power grid prediction load demand of the power system in the future time by taking the minimization of the total cost of the power system and the wind curtailment and light curtailment amount as the target, and obtaining the scheduling plan of various power supplies in the power system in the future time. According to the invention, the accuracy and adaptability of power system planning optimization can be improved in the face of power grid demand change.

Description

Technical Field

[0001] The present application relates to the technical field of power optimization planning, and in particular to a method, device and medium for optimizing power system planning including compressed air energy storage and heat storage. Background Art

[0002] With the rapid development of the economy, the whole society has put forward higher and higher requirements for the reliability and stability of power supply. In the context of the current vigorous development of new energy, new energy power generation has obvious volatility and instability, so the regulation ability of the power system is particularly important. In particular, power units with energy storage units can flexibly adjust the output power within a certain range through energy storage technology, which plays an important role in balancing the power fluctuations of new energy and alleviating the problem of new energy consumption.

[0003] In recent years, with the continuous advancement of big data and artificial intelligence technologies, machine learning and intelligent algorithms have been increasingly used in power systems. In terms of unit load forecasting, a variety of modeling methods have been applied. There are two main unit modeling methods: one is mechanism modeling based on the unit operation mechanism, which predicts its load by studying the physical operation laws of the unit; the other is an analysis method based on data mining, which uses the historical operation data of the unit and combines intelligent algorithms to establish a mapping relationship between input and output.

[0004] Although these methods have improved the accuracy of prediction to a certain extent, there are still some problems: the unit modeling method often only focuses on the main operating parameters of the unit, and constructs a regression model of the unit load and these parameters to achieve real-time calculation of the unit's operating status. However, with the popularization of energy storage units and the advancement of power grid intelligence, the temporal characteristics of power grid demand have become increasingly obvious. For example, the difference in load demand in the morning and evening, and in power grid demand on weekdays and holidays, have an important impact on the operation of energy storage units. Traditional regression models fail to fully consider these factors, resulting in insufficient accuracy and poor adaptability when facing changes in power grid demand. Summary of the invention

[0005] The purpose of this application is to provide a method, device and medium for optimizing power system planning including compressed air energy storage and heat storage, which can improve the accuracy and adaptability of power system planning optimization when facing changes in grid demand.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In the first aspect, the present application provides a method for optimizing the planning of an electric power system containing compressed air energy storage and heat storage, including: obtaining historical operating data of the electric power system and historical load demands of the power grid; training a Transformer model based on the historical operating data of the electric power system and the historical load demands of the power grid to obtain a power grid load demand prediction model; establishing an electric power system planning optimization model related to the predicted load demand of the power grid; inputting the real-time operating data of the electric power system into the power grid load demand prediction model, and outputting the predicted load demand of the power grid for the future time of the electric power system; based on the predicted load demand of the power grid for the future time of the electric power system, with the goal of minimizing the total cost of the electric power system and the amount of wind and solar power abandoned, a non-dominated sorting genetic optimization algorithm is used to solve the electric power system planning optimization model to obtain a scheduling plan for various power sources in the electric power system in the future time; the scheduling plan for various power sources in the electric power system includes wind power installed capacity, photovoltaic installed capacity and energy storage installed capacity.

[0008] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned methods for optimizing power system planning containing compressed air energy storage and heat storage.

[0009] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for optimizing power system planning containing compressed air energy storage and heat storage.

[0010] According to the specific embodiments provided in this application, this application has the following technical effects:

[0011] The present application provides a method, device and medium for optimizing the planning of an electric power system including compressed air energy storage and heat storage. The Transformer model is used to predict the predicted load demand of the power grid in the future, and the time series characteristics of the load demand of the power grid are obtained. The time series characteristics of the load demand of the power grid are considered, and the total cost of the power system and the amount of wind and solar power abandoned are minimized. A non-dominated sorting genetic optimization algorithm is used to solve the power system planning optimization model, and the scheduling plan of various power sources in the power system in the future is obtained, which more accurately reflects the dynamic changes of the power grid load and the regulation capacity of the energy storage unit, so that the power system can better cope with the volatility and intermittent challenges of renewable energy power generation, and improve the accuracy and adaptability when facing changes in power grid demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0013] Figure 1 A schematic diagram of a flow chart of a method for optimizing power system planning including compressed air energy storage and heat storage in one embodiment of the present application;

[0014] Figure 2 A schematic diagram of a flow chart of a method for optimizing power system planning including compressed air energy storage and heat storage provided in one embodiment of the present application;

[0015] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0017] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0018] In order to comprehensively consider the timing characteristics of the grid demand, so as to more accurately reflect the dynamic changes of the grid load and the regulation capacity of the energy storage unit. Figure 1 As shown, the present application provides a method for optimizing power system planning including compressed air energy storage and heat storage, including the following steps 101 to 105. Among them:

[0019] Step 101: Obtain historical operation data of the power system and historical load demand of the power grid.

[0020] Step 102: Based on the historical operation data of the power system and the historical load demand of the power grid, a Transformer model is trained to obtain a power grid load demand prediction model.

[0021] Step 103: Establish a power system planning optimization model related to the predicted load demand of the power grid.

[0022] Step 104: input the real-time operation data of the power system into the power grid load demand prediction model, and output the power grid predicted load demand of the power system in the future.

[0023] Step 105: Based on the predicted load demand of the power grid in the future of the power system, with the goal of minimizing the total cost of the power system and the amount of wind and solar power abandoned, a non-dominated sorting genetic optimization algorithm is used to solve the power system planning optimization model to obtain a dispatch plan for various power sources in the power system in the future; the dispatch plan for various power sources in the power system includes wind power installed capacity, photovoltaic installed capacity and energy storage installed capacity.

[0024] By implementing the above steps 101 to 105, the planning of the power system containing compressed air energy storage and heat storage is optimized, so that the power system can better cope with the volatility and intermittent challenges of renewable energy power generation. The present application provides a compressed air energy storage and heat storage power system planning optimization based on the Transformer algorithm and the non-dominated sorting genetic optimization algorithm, which fully mines historical information and uses big data analysis methods to flexibly adjust the configuration and scheduling strategy of the energy storage system.

[0025] The non-dominated sorting genetic optimization algorithm refers to the non-dominated sorting genetic algorithm (NSGA) with an elite strategy, referred to as the NSGA-Ⅱ algorithm. By combining the Transformer algorithm and the NSGA-Ⅱ algorithm, an efficient power system planning optimization method is provided. Compared with traditional methods, this application has higher accuracy and flexibility in predicting grid load demand and optimizing power system configuration. By reasonably configuring the energy storage system and the heat storage system, and optimizing the system operation strategy, the total system cost and the amount of wind and solar power abandoned can be significantly reduced, and the economy and sustainability of the power system can be improved. At the same time, this application can be flexibly adjusted according to the characteristics and development needs of the power grid in different regions and time periods, laying a solid foundation for the long-term sustainable development of the power system.

[0026] In another exemplary embodiment of the present application, the historical operation data of the power system in the above step 101 includes: grid load data of different historical periods, installed capacity of new energy units, operation data of new energy units and output characteristics of new energy units.

[0027] In another exemplary embodiment of the present application, the detailed process of training the Transformer model in step 101 above can be replaced by the following steps 201 to 204:

[0028] Step 201: Use the isolation forest algorithm to perform anomaly detection on the historical operation data of the power system and the historical load demand of the power grid, and remove outliers to obtain pre-processed historical operation data and historical load demand of the power grid.

[0029] The specific steps of using the Isolation Forest algorithm for anomaly detection include: constructing an isolation tree, isolating the sample x, and calculating the isolation path length h(x). The average path length of the tree is:

[0030]

[0031] Where H(l) is the harmonic number, which can be approximated as ln(l)+0.5772156649, where n is the number of samples, l=1,2,…,n.

[0032] Step 202: Taking the pre-processed historical operation data as input and the historical load demand of the power grid as output, they together constitute a power system data set.

[0033] Step 203: Divide the power system data set into a training set and a test set. Exemplarily, 70% of the power system data set is used as the training set, and 30% of the power system data set is used as the test set.

[0034] Step 204: Use the training set and the test set to train and test the Transformer model respectively to obtain a power grid load demand prediction model. The accuracy of the model is evaluated through the test set.

[0035] The Transformer algorithm model includes a self-attention mechanism, which specifically uses a multi-head self-attention mechanism to capture long-term dependencies in power grid load demand data.

[0036] Q i =W Q x i .

[0037] K i =W K x i .

[0038] V i =W V x i .

[0039]

[0040] In the formula, Q i is the query matrix, x i is the input vector, representing the characteristic data of load and time step, K i is the bond matrix, V iis the value matrix, W Q , W K and W V is the weight matrix to be learned, score ij is the i-th query matrix Q i With the j-th key matrix K j The similarity score between j T is the transpose of the jth key matrix and is used to compare with the query matrix Q i Perform dot product to calculate similarity, d k is the key matrix K i The dimension is used to normalize the scaling to stabilize the gradient, i represents the time step or position of the current query, and j represents the target position compared with the query.

[0041] The loss function used by the Transformer algorithm during training is the mean square error (MSE).

[0042]

[0043] In the formula, y a is a real value, and in this application refers to the historical load demand of the power grid obtained in step 101. is the predicted value and N is the number of samples.

[0044] In another exemplary embodiment of the present application, the power grid load demand prediction model is:

[0045]

[0046] In the formula, is the load forecast at time step t', W is the weight matrix, Attention(X+P) is the output of the attention mechanism, X is the input historical operation data, P is the position code, and b is the bias term.

[0047] In another exemplary embodiment of the present application, the objective function of the power system planning optimization model is:

[0048]

[0049] W discard =W t -W u -W stored ;

[0050] In the formula, C total is the total cost of the power system, W discard C is the amount of wind and solar power abandoned; storage (t) is the energy storage installed capacity at time t, r is the unit cost of the energy storage system, Coperation (t) is the operating cost at time t, T is the optimization period; W t is the total power generation of wind and solar units, W u is the amount of electricity that the wind and solar generators finally input into the grid, W stored Input the electricity of energy storage device to the wind and solar power units.

[0051] C storage (t) = C base +k·E(t);

[0052] E(t)=D future (t)-D actual (t);

[0053] W t =k w x(1)+k s x(2);

[0054] In the formula, C base is the basic configuration capacity, k is the adjustment coefficient, E(t) is the error between the predicted load demand of the power grid and the actual load demand of the power grid at time t; D future (t) is the predicted load demand of the power grid at the future time corresponding to time t, D actual (t) is the actual load of the power grid at time t; k w is the output characteristic of wind power, k s is the output characteristic of photovoltaic power generation, x(1) is the installed capacity of wind power generation, and x(2) is the installed capacity of photovoltaic power generation.

[0055] By calculating the load demand value D of the power system in the future future (t) Make predictions and adjust the configuration strategy of the power system containing compressed air energy storage and thermal storage to achieve long-term sustainable development of the power system.

[0056] In another exemplary embodiment of the present application, the constraints of the power system planning optimization model include: energy storage capacity constraints, power generation capacity constraints, heat storage demand constraints, grid constraints, power balance constraints and energy storage charging and discharging efficiency constraints.

[0057] The energy storage capacity constraint is: 0≤C storage ≤C max Where, C storage is the installed capacity of energy storage, C max is the maximum capacity of the energy storage system.

[0058] The power generation capacity constraint is: Where P f (t), P s (t), P w(t) are the power generation of thermal power, photovoltaic power and wind power generation units at time t, P f,max , P s,max , P w,max They are the maximum power generation capacities of thermal power, photovoltaic and wind turbines respectively.

[0059] The heat storage demand constraint is: In the formula, Q storage (t) is the actual heat storage at time t, Q demand (t) is the heat storage demand at time t, Q max is the maximum heat storage capacity of the heat storage system.

[0060] The grid constraint is: 0≤P line (t)≤P line,max Where, P line (t) is the transmission line load at time t, P line,max is the maximum carrying capacity of the transmission line.

[0061] The power balance constraint is: P gen (t)+E charge (t)-E discharge (t) = D(t); where P gen (t) is the total power generation of the thermal wind and solar system at time t, E charge (t) is the charge capacity of the energy storage system at time t, E discharge (t) is the discharge capacity of the energy storage system at time t, and D(t) is the load demand at time t.

[0062] The energy storage charging and discharging efficiency constraint is: In the formula, E input (t) is the actual charge capacity of the energy storage system at time t, E output (t) is the actual discharge capacity of the energy storage system at time t, η charge is the charging efficiency, η discharge is the discharge efficiency.

[0063] It can be seen that the set constraints include the operation restrictions of the power system, the charging and discharging restrictions of energy storage equipment, and the volatility constraints of wind power and photovoltaic power generation.

[0064] In another exemplary embodiment of the present application, a penalty function method and a repair operation are introduced into a non-dominated sorting genetic optimization algorithm to process individuals that do not meet the constraints.

[0065] In another exemplary embodiment of the present application, the non-dominated sorting genetic optimization algorithm uses weighted roulette for selection, the crossover operation uses adaptive crossover, the mutation operation uses non-uniform mutation, and the Pareto frontier selection strategy is used to obtain the optimal Pareto frontier. The Pareto frontier selection strategy is used to increase the diversity and coverage of the solution set. The formula involved is as follows:

[0066]

[0067] p cross (g) = p cross,max ·e -λg .

[0068]

[0069] Where P c represents the weight ratio, normalizes the target weight, F is the number of populations, w c is the weight of individual c, w f is the weight of individual f, P c is the selection probability; p cross (g) is the crossover probability of the gth generation, describing the decay of the crossover probability, p cross,max is the initial crossover rate, λ is the decay coefficient; σ(g) is the mutation standard deviation, describing the decay of the mutation probability, σ0 is the initial standard deviation, and G is the maximum number of iterations.

[0070] The general idea of ​​the method of this application is: the established grid load demand prediction model can obtain the grid load demand data in the future. On this basis, combined with the existing new energy output data, the NSGA-Ⅱ algorithm is used to optimize the power system scheduling and compressed air energy storage and heat storage unit planning. The NSGA-Ⅱ algorithm uses the installed capacity of wind power, photovoltaic, and energy storage devices as decision variables to minimize the total cost C of the power system. total and the amount of wind and solar power abandoned discard As the goal, under various constraints, the Pareto frontier is obtained, and the cost and amount of wind and solar power abandoned are comprehensively considered to select the appropriate configuration scheme, that is, the installed capacity of wind power, photovoltaic power, and energy storage C storage , x(1) and x(2), the scheduling plans for various types of power sources can be obtained.

[0071] Figure 2 A more detailed process of a method for optimizing power system planning including compressed air energy storage and heat storage in this application.

[0072] This application proposes a method for optimizing the planning of a power system with compressed air energy storage and heat storage, which can better cope with the volatility and intermittent challenges of renewable energy generation, achieve a balance between power generation and consumption, and stable operation of the power grid. At the same time, this method also helps to improve the flexibility and resilience of the power system, laying a solid foundation for the long-term sustainable development of the power system.

[0073] Based on the same inventive concept, the present application also provides a computer device, which may be a server or a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to 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 scheduling plans for various types of power sources in the power system in the future. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for optimizing the planning of a power system containing compressed air energy storage and heat storage is implemented.

[0074] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0075] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0076] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0077] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0078] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0079] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for optimizing power system planning with compressed air energy storage and heat storage, characterized in that: include: Obtain historical operation data of the power system and historical load demand of the power grid; According to the historical operation data of the power system and the historical load demand of the power grid, the Transformer model is trained to obtain the power grid load demand prediction model; Establishment of power system planning optimization model related to grid forecasted load demand; Inputting the real-time operation data of the power system into the power grid load demand prediction model, and outputting the power grid predicted load demand of the power system in the future; According to the predicted load demand of the power grid in the future of the power system, with the goal of minimizing the total cost of the power system and the amount of wind and solar power abandoned, a non-dominated sorting genetic optimization algorithm is used to solve the power system planning optimization model to obtain the scheduling plan of various power sources in the power system in the future; the scheduling plan of various power sources in the power system includes wind power installed capacity, photovoltaic installed capacity and energy storage installed capacity.

2. The method for optimizing power system planning with compressed air energy storage and heat storage according to claim 1, characterized in that: The historical operation data of the power system includes: grid load data in different historical periods, installed capacity of new energy units, operation data of new energy units and output characteristics of new energy units.

3. The method for optimizing power system planning with compressed air energy and heat storage according to claim 1, characterized in that: According to the historical operation data of the power system and the historical load demand of the power grid, the Transformer model is trained to obtain the power grid load demand prediction model, which includes: The isolation forest algorithm is used to detect anomalies in the historical operation data of the power system and the historical load demand of the power grid, and outliers are removed to obtain the pre-processed historical operation data and historical load demand of the power grid; The pre-processed historical operation data is used as input, and the historical load demand of the power grid is used as output, which together constitute the power system data set; Dividing the power system data set into a training set and a test set; The Transformer model is trained and tested using the training set and test set respectively to obtain the power grid load demand forecasting model.

4. The method for optimizing power system planning with compressed air energy and heat storage according to claim 1, characterized in that: The power grid load demand prediction model is: In the formula, is the load forecast at time step t', W is the weight matrix, Attention(X+P) is the output of the attention mechanism, X is the input historical operation data, P is the position code, and b is the bias term.

5. The method for optimizing power system planning with compressed air energy and heat storage according to claim 1, characterized in that: The objective function of the power system planning optimization model is: IN discard =In t -IN u -IN stored ; In the formula, C total is the total cost of the power system, W discard C is the amount of wind and solar power abandoned; storage (t) is the energy storage installed capacity at time t, r is the unit cost of the energy storage system, C operation (t) is the operating cost at time t, T is the optimization period; W t is the total power generation of wind and solar units, W u is the amount of electricity that the wind and solar generator sets finally input into the grid, W stored Input electricity of energy storage equipment to wind and solar units; C storage (t)=C base +k·E(t); E(t)=D future (t)-D actual (t); W t =k w x(1)+k s x(2); In the formula, C base is the basic configuration capacity, k is the adjustment coefficient, E(t) is the error between the predicted load demand of the power grid and the actual load demand of the power grid at time t; D future (t) is the predicted load demand of the power grid at the future time corresponding to time t, D actual (t) is the actual load of the power grid at time t; k w is the output characteristic of wind power, k s is the output characteristic of photovoltaic power generation, x(1) is the installed capacity of wind power generation, and x(2) is the installed capacity of photovoltaic power generation.

6. The method for optimizing power system planning with compressed air energy and heat storage according to claim 1, characterized in that: The constraints of the power system planning optimization model include: energy storage capacity constraints, power generation capacity constraints, heat storage demand constraints, grid constraints, power balance constraints and energy storage charging and discharging efficiency constraints; The energy storage capacity constraint is: 0≤C storage ≤C max Where, C storage is the installed capacity of energy storage, C max is the maximum capacity of the energy storage system; The power generation capacity constraint is: Where P f (t), P s (t), P w (t) are the power generation of thermal power, photovoltaic power and wind power generation units at time t, P f,max , P s,max , P w,max They are the maximum power generation capacity of thermal power, photovoltaic and wind power units respectively; The heat storage demand constraint is: In the formula, Q storage (t) is the actual heat storage at time t, Q demand (t) is the heat storage demand at time t, Q max is the maximum heat storage capacity of the heat storage system; The grid constraint is: 0≤P line (t)≤P line,max Where, P line (t) is the transmission line load at time t, P line,max is the maximum carrying capacity of the transmission line; The power balance constraint is: P gen (t)+E charge (t)-E discharge (t) = D(t); where P gen (t) is the total power generation of the thermal wind and solar system at time t, E charge (t) is the charge capacity of the energy storage system at time t, E discharge (t) is the discharge capacity of the energy storage system at time t, and D(t) is the load demand at time t; The energy storage charging and discharging efficiency constraint is: In the formula, E input (t) is the actual charge capacity of the energy storage system at time t, E output (t) is the actual discharge capacity of the energy storage system at time t, η charge is the charging efficiency, η discharge is the discharge efficiency.

7. The method for optimizing power system planning with compressed air energy and heat storage according to claim 1, characterized in that: In the non-dominated sorting genetic optimization algorithm, penalty function method and repair operation are introduced to deal with individuals that do not meet the constraints.

8. The method for optimizing power system planning with compressed air energy and heat storage according to claim 1, characterized in that: The non-dominated sorting genetic optimization algorithm adopts weighted roulette for selection, adopts adaptive crossover for crossover operation, adopts non-uniform mutation for mutation operation, and adopts Pareto frontier selection strategy to obtain the optimal Pareto frontier.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for optimizing power system planning containing compressed air energy storage and heat storage according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing the planning of a power system containing compressed air energy storage and heat storage described in any one of claims 1 to 8 is implemented.

Images