Optimal energy management method for micro-grid energy storage equipment

Abstract

The invention relates to the technical field of micro-grids, in particular to an energy optimal management method for micro-grid energy storage equipment, and mainly solves the technical problem that a method for performing optimal management on micro-grid energy is lacked in the prior art. The method comprises the following steps: S1, establishing a micro-grid system model; s2, constructing a performance index function of micro-grid energy management; and S3, solving the optimal performance index function and the optimal control strategy by adopting an iterative approximate dynamic programming algorithm so as to obtain an optimal management method. According to the method, an iterative approximate dynamic programming algorithm is designed to obtain an optimal management method so as to realize optimal management of micro-grid energy.

Description

Technical Field

[0001] The present invention relates to the technical field of microgrids, and in particular to an optimal energy management method for microgrid energy storage equipment. Background Art

[0002] In recent years, the development of renewable energy has created a new landscape for power generation and distribution. Microgrids have become a key solution for improving energy efficiency, reliability, and sustainability due to their ability to integrate renewable energy sources such as wind and photovoltaic power, as well as their ability to operate independently when the main power grid is disrupted. In this evolving context, it is critical to study the energy management of microgrids given their potential to improve energy efficiency and reliability.

[0003] However, in the prior art, the research on microgrid energy management is still in the development stage, and there is no mature method to optimally manage the energy of microgrids. Therefore, there is an urgent need for an optimal energy management method for microgrid energy storage equipment. Summary of the invention

[0004] In order to overcome the technical defect of the prior art that there is a lack of a method for optimally managing the energy of a microgrid, the present invention provides a method for optimally managing the energy of a microgrid energy storage device.

[0005] The method for optimal energy management of microgrid energy storage equipment provided by the present invention comprises the following steps:

[0006] S1. Establish a microgrid system model, including the main grid, load, tram, photovoltaic modules and batteries. The total power of the main grid, photovoltaic modules and batteries must meet the needs of the load and tram and satisfy the energy balance equation:

[0007] ;

[0008] in, is the battery charging and discharging power, is the main grid power, is the photovoltaic power, is the load power, is the tram power;

[0009] The battery model is:

[0010] ;

[0011] in, for The battery level at the moment, The battery charging and discharging efficiency;

[0012] Define the system status as:

[0013] ;

[0014] in, ;

[0015] Control strategy ;

[0016] Then, the expression of the microgrid system model is:

[0017] ;

[0018] S2. Construct a performance indicator function for microgrid energy management, the expression of which is:

[0019] ;

[0020] in, , the first item is the cost or profit generated by the transaction between the microgrid and the main grid. The purpose is to store energy closer to the center of its charge. The purpose is to avoid excessive charging and discharging power. , and is the weight parameter;

[0021] According to Bellman's optimality principle, the expressions of the optimal performance index function and the optimal control strategy are:

[0022] ;

[0023] in, is the optimal performance indicator function, is the optimal control strategy;

[0024] S3. Use iterative approximate dynamic programming algorithm to solve the optimal performance index function and optimal control strategy to obtain the optimal management method:

[0025] A value function is constructed to solve the optimal performance index function. The expression of the value function is:

[0026] ;

[0027] in, Iterate over the index;

[0028] Then, the expression of the battery control strategy is:

[0029] ;

[0030] along with With the increase of , the optimal performance index function and the optimal control strategy can be obtained.

[0031] Optionally, an evaluation neural network is used to approximate the value function, and an action neural network is used to approximate the control strategy.

[0032] Optionally, The optimal value function at the moment is expressed as:

[0033] ;

[0034] in, For the ideal output weight, is the output basis vector, is the input of the hidden layer, is the network error of the value function;

[0035] The approximate value function is:

[0036] ;

[0037] in, For The first The weight parameters of the hidden layer at the iteration, Is a sigmoid function, the input of the hidden layer for:

[0038] ;

[0039] Among them, the weight of the input layer is fixed to a constant in the range [-1,1], is the input of the input layer;

[0040] The expression for evaluating the iterative error of the neural network is:

[0041] ;

[0042] definition , ;

[0043] Then the expression for evaluating the iterative error of the neural network is rewritten as:

[0044] ;

[0045] Define the auxiliary matrix and for:

[0046] ;

[0047] in, is the weight sequence of historical iteration information, is the forgetting factor, whose value range is (0,1);

[0048] and The iteration form is:

[0049] ;

[0050] The update formula of the weight parameters of the hidden layer is:

[0051] ;

[0052] in, is the time-varying gain matrix, Represents the weighted sum of historical iteration information, updated by the following formula:

[0053] .

[0054] Optionally, The optimal control strategy at the moment is expressed as:

[0055] ;

[0056] in, is the optimal weight parameter of the action network, is the sigmoid function;

[0057] The approximate control strategy is:

[0058] ;

[0059] in, is the approximate weight, the input of the hidden layer It can be expressed as:

[0060] ;

[0061] in, is a fixed weight vector ranging from -1 to 1;

[0062] The iterative error of the action neural network is:

[0063] ;

[0064] in, represents the overall cost objectives i and k for all sums;

[0065] The weight parameter update formula of the action neural network is:

[0066] ;

[0067] The learning rate It is set based on experience.

[0068] The technical solution provided by the present invention has the following advantages compared with the prior art:

[0069] The present invention provides a method for optimal management of energy of a microgrid energy storage device, and designs an iterative approximate dynamic programming algorithm to obtain an optimal management method to achieve optimal management of microgrid energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0071] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0072] Figure 1 A structural diagram showing a microgrid in an embodiment of the present invention;

[0073] Figure 2 A distribution diagram of solar power within 168 hours in an embodiment of the present invention is shown;

[0074] Figure 3 A load distribution diagram of a household within 168 hours in an embodiment of the present invention is shown;

[0075] Figure 4 A power consumption distribution diagram of an electric vehicle within 168 hours in an embodiment of the present invention is shown;

[0076] Figure 5 A structural diagram showing an approximate dynamic programming algorithm in an embodiment of the present invention;

[0077] Figure 6 An electricity price chart within 168 hours in an embodiment of the present invention is shown;

[0078] Figure 7 (a) shows a grid power learning performance diagram at the 95th hour in an embodiment of the present invention;

[0079] Figure 7 (b) a graph showing the learning performance of the battery control strategy at the 95th hour in an embodiment of the present invention;

[0080] Figure 8 A main power grid power performance diagram is shown in an embodiment of the present invention;

[0081] Fig. 9A diagram showing a battery control strategy in an embodiment of the present invention;

[0082] Fig.10 A schematic diagram showing the energy performance of a battery in an embodiment of the present invention;

[0083] Fig.11 A comparison chart showing the value function of the gradient descent method at the 95th hour in an embodiment of the present invention and the proposed adaptive law. DETAILED DESCRIPTION

[0084] In order to more clearly understand the above-mentioned objectives, features and advantages of the present invention, the scheme of the present invention will be further described below. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0085] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present invention, rather than all of the embodiments.

[0086] Combine the following Figures 1 to 11 The specific embodiments of the present invention are described in detail.

[0087] This embodiment provides a method for optimal energy management of microgrid energy storage equipment, including steps S1 to S3.

[0088] S1. Establish a microgrid system model, including the main grid, load, tram, photovoltaic modules and batteries. The total power of the main grid, photovoltaic modules and batteries must meet the needs of the load and tram and satisfy the energy balance equation:

[0089] ;

[0090] in, is the battery charging and discharging power, is the main grid power, is the photovoltaic power, is the load power, is the tram power;

[0091] The battery model is:

[0092] ;

[0093] in, for The battery level at the moment, The battery charging and discharging efficiency;

[0094] Define the system status as:

[0095] ;

[0096] in, ;

[0097] Control strategy ;

[0098] Then, the expression of the microgrid system model is:

[0099] .

[0100] It is easy to understand that there are maximum and minimum limits on battery charging and discharging power, photovoltaic power, and electric vehicle power. The limits are as follows:

[0101] , , .

[0102] Specifically, the calculation formula for battery charging and discharging efficiency is:

[0103] .

[0104] S2. Construct a performance indicator function for microgrid energy management, the expression of which is:

[0105] ;

[0106] in, , the first item is the cost or profit generated by the transaction between the microgrid and the main grid. The purpose is to store energy closer to the center of its charge. The purpose is to avoid excessive charging and discharging power. , and is the weight parameter;

[0107] According to Bellman's optimality principle, the expressions of the optimal performance index function and the optimal control strategy are:

[0108] ;

[0109] in, is the optimal performance indicator function, is the optimal control strategy.

[0110] It is easy to understand that this embodiment adopts a multi-objective cost function as a performance indicator function, which can reduce electricity purchase costs and extend battery life.

[0111] It should be noted that and Cooperation can protect the battery and extend the battery life.

[0112] It is easy to understand that by adjusting , and , able to adapt to different needs.

[0113] S3. Use iterative approximate dynamic programming algorithm to solve the optimal performance index function and optimal control strategy to obtain the optimal management method:

[0114] A value function is constructed to solve the optimal performance index function. The expression of the value function is:

[0115] ;

[0116] in, Iterate over the index;

[0117] Then, the expression of the battery control strategy is:

[0118] ;

[0119] along with With the increase of , the optimal performance index function and the optimal control strategy can be obtained.

[0120] It should be noted that the expressions of the optimal performance indicator function and the optimal control strategy obtained according to Bellman's optimality principle are difficult to solve directly, so this embodiment adopts an iterative approximate dynamic programming algorithm to solve the optimal performance indicator function and the optimal control strategy.

[0121] Specifically, in order to facilitate the implementation of the iterative approximate dynamic programming algorithm, this embodiment adopts an evaluation neural network to approximate the value function and an action neural network to approximate the control strategy.

[0122] More specifically, the steps of using the evaluation neural network to approximate the value function are as follows:

[0123] Will The optimal value function at the moment is expressed as:

[0124] ;

[0125] in, For the ideal output weight, is the output basis vector, is the input of the hidden layer, is the network error of the value function;

[0126] The approximate value function is:

[0127] ;

[0128] in, For The first The weight parameters of the hidden layer at the iteration, Is a sigmoid function, the input of the hidden layer for:

[0129] ;

[0130] Among them, the weight of the input layer is fixed to a constant in the range [-1,1], is the input of the input layer;

[0131] The expression for evaluating the iterative error of the neural network is:

[0132] ;

[0133] definition , ;

[0134] Then the expression for evaluating the iterative error of the neural network is rewritten as:

[0135] ;

[0136] Define the auxiliary matrix and for:

[0137] ;

[0138] in, is the weight sequence of historical iteration information, is the forgetting factor, whose value range is (0,1);

[0139] and The iteration form is:

[0140] ;

[0141] The update formula of the weight parameters of the hidden layer is:

[0142] ;

[0143] in, is the time-varying gain matrix, Represents the weighted sum of historical iteration information, updated by the following formula:

[0144] .

[0145] It should be noted that this embodiment adopts a new discrete adaptive law to update the weight parameters of the evaluation neural network, which can accelerate the convergence speed and alleviate the risk of falling into a local optimal solution, ensuring that the value function successfully approaches the optimal performance indicator function.

[0146] It should be noted that this embodiment establishes a new composite performance indicator function for the energy management system in the microgrid, which can minimize the cost of the microgrid and extend the battery life.

[0147] More specifically, the steps of using the action neural network to approximate the control strategy are as follows:

[0148] Will The optimal control strategy at the moment is expressed as:

[0149] ;

[0150] in, is the optimal weight parameter of the action network, is the sigmoid function;

[0151] The approximate control strategy is:

[0152] ;

[0153] in, is the approximate weight, the input of the hidden layer It can be expressed as:

[0154] ;

[0155] in, is a fixed weight vector ranging from -1 to 1;

[0156] The iterative error of the action neural network is:

[0157] ;

[0158] in, represents the overall cost objectives i and k for all sums;

[0159] The weight parameter update formula of the action neural network is:

[0160] ;

[0161] The learning rate It is set based on experience.

[0162] In this embodiment, the battery capacity in the microgrid is 100 kWh. In order to extend its life, the available capacity is limited to the range of 20-80 kWh. The charge and discharge rate is limited to between -16 kw and 16 kw. The initial energy of the battery is set to 75 kWh. The weight parameter in the performance indicator function is set to , , The initial values ​​of the time-varying gain matrix and auxiliary matrix are set to , , The forgetting factor is set to , , , and Set in the range [−1, 1].

[0163] The above is only a specific implementation of the present invention, which enables those skilled in the art to understand or implement the present invention. Although detailed descriptions are given with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments, and they should all be covered by the protection scope of the claims.

Claims

1. A method for optimal energy management of microgrid energy storage equipment, characterized in that: The steps include: S1. Establish a microgrid system model, including the main grid, load, tram, photovoltaic modules and batteries. The total power of the main grid, photovoltaic modules and batteries must meet the needs of the load and tram and satisfy the energy balance equation: ； in, is the battery charging and discharging power, is the main grid power, is the photovoltaic power, is the load power, is the tram power; The battery model is: ； in, for The battery level at the moment, The battery charging and discharging efficiency; Define the system status as: ； in, ; Control strategy ; Then, the expression of the microgrid system model is: ； S2. Construct a performance indicator function for microgrid energy management, the expression of which is: ； in, , the first item is the cost or profit generated by the transaction between the microgrid and the main grid. The purpose is to store energy closer to the center of its charge. The purpose is to avoid excessive charging and discharging power. , and is the weight parameter; According to Bellman's optimality principle, the expressions of the optimal performance index function and the optimal control strategy are: ； in, is the optimal performance indicator function, is the optimal control strategy; S3. Use iterative approximate dynamic programming algorithm to solve the optimal performance index function and optimal control strategy to obtain the optimal management method: A value function is constructed to solve the optimal performance index function. The expression of the value function is: ； in, Iterate over the index; Then, the expression of the battery control strategy is: ； along with With the increase of , the optimal performance index function and the optimal control strategy can be obtained.

2. The method for optimal energy management of microgrid energy storage equipment according to claim 1, characterized in that: The evaluation neural network is used to approximate the value function, and the action neural network is used to approximate the control strategy.

3. The method for optimal energy management of microgrid energy storage equipment according to claim 2, characterized in that: Will The optimal value function at the moment is expressed as: ； in, For the ideal output weight, is the output basis vector, is the input of the hidden layer, is the network error of the value function; The approximate value function is: ； in, For The first The weight parameters of the hidden layer at the iteration, Is a sigmoid function, the input of the hidden layer for: ； Among them, the weight of the input layer is fixed to a constant in the range [-1,1], is the input of the input layer; The expression for evaluating the iterative error of the neural network is: ； definition , ; Then the expression for evaluating the iterative error of the neural network is rewritten as: ； Define the auxiliary matrix and for: ； in, is the weight sequence of historical iteration information, is the forgetting factor, whose value range is (0,1); and The iteration form is: ； The update formula of the weight parameters of the hidden layer is: ； in, is the time-varying gain matrix, Represents the weighted sum of historical iteration information, updated by the following formula: 。 4. The method for optimal energy management of microgrid energy storage equipment according to claim 2, characterized in that: Will The optimal control strategy at the moment is expressed as: ； in, is the optimal weight parameter of the action network, is the sigmoid function; The approximate control strategy is: ； in, is the approximate weight, the input of the hidden layer It can be expressed as: ； in, is a fixed weight vector ranging from -1 to 1; The iterative error of the action neural network is: ； in, represents the overall cost objectives i and k for all sums; The weight parameter update formula of the action neural network is: ； The learning rate It is set based on experience.

Images