Microgrid optimization operation method, device and equipment based on universal gravitation algorithm

Abstract

The invention relates to the technical field of microgrid operation, in particular to a universal gravitation algorithm-based microgrid optimization operation method, device, equipment and medium, and the method comprises the steps: randomly generating a plurality of object initial positions in a D-dimensional search space based on a universal gravitation search algorithm, and obtaining an original solution group; optimizing the original solution group by using a reverse learning mechanism to generate a reverse solution group; sorting and screening the reverse solution group and the original solution group according to fitness values based on an elitist strategy to obtain an optimization group; calculating the fitness value of each object in the optimization population, and setting the current position of each object as the optimal position; gravitation parameters are updated, and population object positions are updated; and optimizing the population through a reverse learning mechanism and an elitist strategy, and repeating the steps until a preset iteration number threshold value is reached. Through a reverse learning mechanism and an elitist strategy, the optimization performance and convergence speed of the algorithm are improved, the problem of oscillation near an optimal solution is effectively avoided, and the robustness of the algorithm is improved.

Description

Technical Field

[0001] The present application relates to the field of microgrid operation technology, and in particular to a microgrid optimization operation method, device, equipment and medium based on a universal gravitation algorithm. Background Art

[0002] Distributed generation, a major form of renewable energy, includes micro-turbines, biomass power generation, fuel cells, photovoltaic power generation, and wind power generation. It offers numerous advantages, including easing energy pressures, reducing pollutant emissions, enabling local energy utilization, and minimizing transmission losses. However, due to the immaturity of distributed generation technology, photovoltaic and wind power generation exhibit significant randomness, volatility, and intermittency. Connecting these to the grid in large quantities can negatively impact its reliability and security.

[0003] Against this backdrop, microgrids have emerged as an integrated system consisting of distributed power sources, loads, energy storage devices, and related supporting facilities. Microgrids are connected to the main grid through a common coupling point, and each unit is connected to the microgrid via power electronics, forming a flexible and controllable subsystem. The microgrid's unique digital information environment offers significant advantages in integrating distributed generation and improving energy efficiency. However, the complex source-load coupling characteristics, diverse operating modes, and high uncertainty of microgrids make traditional grid operation and control methods difficult to effectively manage. Therefore, optimizing the operational strategies of microgrid management platforms to improve their economic efficiency, stability, and environmental performance has become a key issue that needs to be addressed.

[0004] However, when dealing with microgrid scheduling problems in complex scenarios, existing algorithms often find it difficult to take into account the requirements of multi-objective optimization and high-dimensional search space, which limits their practical application effects.

[0005] In summary, how to achieve efficient and stable operation of microgrids is an urgent problem that needs to be solved. Summary of the Invention

[0006] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0007] To this end, the first purpose of this application is to propose a microgrid optimization operation method based on the universal gravitation algorithm to solve the problems of low optimization efficiency, slow convergence speed and insufficient robustness existing in the existing technical means.

[0008] The second object of this application is to provide a device.

[0009] The third objective of this application is to provide an electronic device.

[0010] The fourth object of this application is to provide a computer-readable storage medium.

[0011] To achieve the above objectives, the first embodiment of the present application proposes a microgrid optimization operation method based on a universal gravitation algorithm, comprising:

[0012] Based on the gravitational search algorithm, multiple initial positions of objects are randomly generated in the D-dimensional search space to obtain the original solution group;

[0013] Optimizing the original solution group using a reverse learning mechanism to generate a reverse solution group;

[0014] Based on the elite strategy, the reverse solution group and the original solution group are sorted and screened according to the fitness value to obtain the optimal population;

[0015] Calculating the fitness value of each object in the optimization population and setting the current position of each object as the optimal position;

[0016] Update the gravity parameters and update the positions of objects in the population based on the net force, acceleration, and velocity of the objects in the population;

[0017] The population is optimized through the reverse learning mechanism and elite strategy and the above steps are repeated until the preset iteration threshold is reached.

[0018] Preferably, the reverse learning mechanism includes: for each object in the original solution group, calculating the reverse value corresponding to each dimensional component thereof, and the calculation formula is:

[0019] x′ ij =a j +b j -x ij

[0020] X′ i =(x′ i1 ,x′ i2 ,..,x′ ij ,..,x′ iD )

[0021] Among them, X′ i is the reverse solution vector, x′ ij is the original solution, i is the i-th object in the group, and j is the dimension.

[0022] Preferably, the step of sorting and screening the reverse solution population and the original solution population according to fitness values ​​based on the elite strategy to obtain the optimal population includes:

[0023] The original solution group and the reverse solution group are sorted according to the fitness values ​​of the forward objects and the reverse objects as a whole using the elite strategy. New solutions are generated based on the solutions that meet the first fitness and added to the original solution group and the reverse solution group. The groups with the new solutions are re-sorted by fitness, and then the solutions that meet the second fitness are removed to obtain the optimal population.

[0024] Preferably, calculating the fitness value of each object in the optimization population and setting the current position of each object as the optimal position includes: calculating the fitness value of each object in the optimization population, recording the current optimal solution and its corresponding position, and setting the current position of each object as its individual optimal position.

[0025] Preferably, the updated gravitational parameters include: a gravitational constant, an inertial mass, a current optimal value, and a current worst value, wherein the gravitational constant decreases with the number of iterations, and the inertial mass is adjusted according to the fitness value of the current object.

[0026] Preferably, updating the positions of objects in the population includes optimizing a speed update formula using a global memory and a group communication algorithm, wherein the iterative formula is:

[0027]

[0028] Among them, rand1, rand2, rand3 are random numbers between [0, 1], c1, c2 are constants between [0, 1], is the historical optimal value experienced by particle i; The optimal value experienced by all particles in the population.

[0029] Preferably, the formula for calculating the resultant force on objects in the population is:

[0030]

[0031] Among them, M ai (t) and M pi (t) are the inertial mass of the acting ion j and the inertial mass of the acted object i, G(t) represents the gravitational constant, ε is a very small constant, R ij (t) represents the Euclidean distance between object i and object j.

[0032] To achieve the above objectives, the second embodiment of the present application proposes a microgrid optimization operation device based on the universal gravitation algorithm, comprising:

[0033] The original solution acquisition module randomly generates multiple initial positions of objects in the D-dimensional search space based on the gravitational search algorithm to obtain the original solution group;

[0034] A reverse solution acquisition module optimizes the original solution group using a reverse learning mechanism to generate a reverse solution group;

[0035] A screening module, based on an elite strategy, sorts and screens the reverse solution population and the original solution population according to fitness values ​​to obtain an optimal population;

[0036] An optimal position calculation module calculates the fitness value of each object in the optimization population and sets the current position of each object as the optimal position;

[0037] The position update module updates the gravity parameters and updates the positions of objects in the population based on the net force, acceleration, and velocity of the objects in the population.

[0038] The iteration module optimizes the population through the reverse learning mechanism and elite strategy and repeats the above steps until the preset iteration number threshold is reached.

[0039] To achieve the above-mentioned purpose, a third embodiment of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0040] The memory stores computer-executable instructions;

[0041] The processor executes the computer-executable instructions stored in the memory to implement any of the above methods.

[0042] To achieve the above-mentioned purpose, the fourth embodiment of the present application proposes a computer-readable storage medium, including computer-executable instructions stored in the computer-readable storage medium, and the computer-executable instructions are used to implement any of the methods described above when executed by a processor.

[0043] This application provides a microgrid optimization operation method based on the universal gravitational algorithm. By combining a reverse learning mechanism with an elite strategy, the algorithm's optimization performance and convergence speed are significantly improved. The improved speed update formula effectively avoids the problem of oscillation near the optimal solution of the traditional universal gravitational search algorithm, improving the robustness of the algorithm, significantly reducing operating costs, and improving the economy and stability of the microgrid. By introducing a reverse learning mechanism, global memory, and an elite strategy, the algorithm's optimization performance is improved. This not only effectively addresses the complex electrical characteristics and high uncertainty of multiple types of micro-power sources in the microgrid, but also achieves economical, stable, and environmentally friendly operation of the microgrid while meeting system constraints.

[0044] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0046] Figure 1 This is a flowchart of a first specific embodiment of a microgrid optimization operation method based on a universal gravitation algorithm provided by the present invention;

[0047] Figure 2 This is a flow chart of a microgrid optimization operation method based on the universal gravitation algorithm;

[0048] Figure 3 It is a generalized load curve diagram of the units in the microgrid topology within 24 hours;

[0049] Figure 4 It is the total load forecast curve of the units in the microgrid topology within 24 hours;

[0050] Figure 5 Schematic diagram of various operating costs;

[0051] Figure 6 Schematic diagram of network loss of different feeders in the topology network;

[0052] Figure 7 This is a schematic diagram of the topology of the microgrid management platform;

[0053] Figure 8 This is a structural block diagram of a microgrid optimization operation device based on the universal gravitation algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The core of the present invention is to provide a microgrid optimization operation method, device, electronic equipment and medium based on the universal gravitation algorithm, which improves the algorithm's optimization performance and robustness by introducing a reverse learning mechanism, global memory and elite strategy.

[0055] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0056] Please refer to Figure 1 , Figure 1 This is a flowchart of a first specific embodiment of a microgrid optimization operation method based on a universal gravitation algorithm provided by the present invention; the specific operation steps are as follows:

[0057] Step S101: randomly generating multiple initial positions of objects in a D-dimensional search space based on a universal gravitational search algorithm to obtain an original solution group;

[0058] According to the original initialization method or iterative method of the gravitational search algorithm to the original solution vector, the solution represented by all objects is shown as follows:

[0059] X i =(x i1 ,x i2 ,…,x ij ,…,x iD )

[0060] Where: x ij The value range is [a j ,b j ], i represents the i-th object in the group, and j represents the dimension.

[0061] Step S102: Optimizing the original solution group using the reverse learning mechanism to generate a reverse solution group;

[0062] The reverse learning mechanism includes: for each object in the original solution group, calculating the reverse value corresponding to each dimensional component, and the calculation formula is:

[0063] x′ ij =a j +b j -x ij

[0064] X′ i =(x′ i1 ,x′ i2 ,..,x′ ij ,..,x′ iD )

[0065] Among them, X′ i is the reverse solution vector, x′ ij is the original solution, i is the i-th object in the group, and j is the dimension.

[0066] Step S103: Based on the elite strategy, the reverse solution population and the original solution population are sorted and screened according to the fitness value to obtain the optimal population;

[0067] The original solution group and the reverse solution group are sorted according to the fitness values ​​of the forward objects and the reverse objects as a whole using the elite strategy. New solutions are generated based on the solutions that meet the first fitness and added to the original solution group and the reverse solution group. The groups with the new solutions are re-sorted by fitness, and then the solutions that meet the second fitness are removed to obtain the optimal population.

[0068] Step S104: Calculate the fitness value of each object in the optimal population and set the current position of each object as the optimal position;

[0069] The fitness value of each object in the optimization population is calculated, and the current optimal solution and its corresponding position are recorded, and the current position of each object is set as its individual optimal position.

[0070] Step S105: updating the gravitational parameters and updating the positions of the objects in the population based on the net force, acceleration and velocity of the objects in the population;

[0071] The gravitational parameters include: gravitational constant, inertial mass, current optimal value and current worst value, wherein the gravitational constant decreases with the number of iterations, and the inertial mass is adjusted according to the fitness value of the current object.

[0072] Updating the positions of objects in the population includes optimizing the speed update formula using global memory and group communication algorithm. The iterative formula is:

[0073]

[0074] Among them, rand1, rand2, rand3 are random numbers between [0, 1], c1, c2 are constants between [0, 1], is the historical optimal value experienced by particle i; The optimal value experienced by all particles in the population.

[0075] The formula for calculating the net force acting on objects in the population is:

[0076]

[0077] Among them, M ai (t) and M pi (t) are the inertial mass of the acting ion j and the inertial mass of the acted object i, G(t) represents the gravitational constant, ε is a very small constant, R ij (t) represents the Euclidean distance between object i and object j.

[0078] Step S106: Optimize the population through the reverse learning mechanism and the elite strategy and repeat the above steps until the preset iteration number threshold is reached.

[0079] Repeat the above steps until a preset threshold number of iterations is reached. The threshold number of iterations is set according to the actual problem size and complexity to ensure that the algorithm can complete the optimization task within a reasonable time.

[0080] This embodiment provides a microgrid optimization operation method based on the universal gravitational algorithm. By combining a reverse learning mechanism with an elitist strategy, the algorithm's optimization performance and convergence speed are significantly improved. The improved speed update formula effectively avoids the oscillation of the traditional universal gravitational search algorithm near the optimal solution, enhancing the algorithm's robustness, significantly reducing operating costs, and improving the economy and stability of the microgrid. By introducing a reverse learning mechanism, global memory, and an elitist strategy, the algorithm's optimization performance is enhanced. This not only effectively addresses the complex electrical characteristics and high uncertainty of multiple types of micro-sources in a microgrid, but also enables economical, stable, and environmentally friendly operation of the microgrid while satisfying system constraints.

[0081] Based on the above embodiment, this embodiment describes the microgrid optimization operation method based on the universal gravitation algorithm. Figure 2 As shown, the details are as follows:

[0082] Before describing this method, this embodiment briefly explains the core of the algorithm, as follows:

[0083] In the gravitational search algorithm, the solution to the optimization problem is regarded as a group of objects moving in space. The objects attract each other through the gravitational force, and the movement of objects follows the law of dynamics. The gravitational force makes the objects move towards the object with the largest mass, and the object with the largest mass occupies the optimal position, so the optimization problem can be solved.

[0084] The algorithm achieves the sharing of optimization information through the gravitational interaction between individuals, guiding the group to search for the optimal solution area.

[0085] First, the positions of the swarm are initialized, and the swarm is considered the solution set for the optimization problem. An initial solution set is generated using a reverse learning mechanism. Second, the gravitational forces and accelerations between the objects are calculated, and the positions of the objects are updated and the optimal values ​​are recorded. Finally, the distribution of the swarm is adjusted by combining an elitist strategy and global memory, gradually approaching the optimal solution. This method optimizes the output of distributed generation in a microgrid while satisfying system constraints.

[0086] During the implementation process, a multidimensional optimization space was constructed to simulate the microgrid operating environment. This space consists of multiple dimensions, each corresponding to a variable relevant to microgrid operation, such as power output, load demand, or the charge / discharge status of energy storage devices. The positions of the object clusters represent the combination of variables in the current microgrid operating state, and their fitness values ​​are calculated using an objective function. This objective function comprehensively considers multiple sub-goals, including economic efficiency, stability, and environmental protection, corresponding to minimizing operating costs, maximizing power supply reliability, and minimizing carbon emissions, respectively.

[0087] (1) Initialization:

[0088] Enter initial values ​​and determine the number of iterations. For a D-dimensional optimization space containing N objects, the position of each object represents the solution to the optimization problem. Initialize each data set randomly and determine the maximum number of iterations. Calculate the fitness value of each object.

[0089] Assume that in the D-dimensional search space, there is a population of N objects, which can be expressed as:

[0090] X=(x1,x2,…,x N )

[0091] The position of an object can be expressed as:

[0092]

[0093] Where: is the position of the i-th object in the d-th dimension.

[0094] The magnitude of the gravitational force exerted by any object j on object i at time t is:

[0095]

[0096] Where: M ai (t) and M pi (t) are the inertial mass of the acting ion j and the inertial mass of the acted object i, G(t) represents the gravitational constant, ε is a very small constant, R ij (t) represents the Euclidean distance between object i and object j.

[0097] The population is initialized using the reverse learning method; (2* / 5)N objects with the best fitness values ​​are selected from the total set of forward solutions and reverse solutions, and new solutions are generated according to the elite strategy and incorporated into the solution set. The (2* / 5)N objects with the worst fitness values ​​in the solution set are eliminated to form a new solution set.

[0098] In one embodiment, the reverse learning mechanism is an effective method proposed by Tizhoosh to optimize the population distribution problem. If x takes a value in the range [a, b], then the reverse particle of x can be expressed as x′=a+bx. In N-dimensional space, the concept of reverse learning can still be applied. For an N-dimensional search space, let S(x1, x2,…, x N ), x i ∈[a i ,b i ](i=1,2,…,N) is the forward solution of the problem, then the corresponding reverse vector can be expressed as S′(x1′,x2′,…,x N ′), x i ′=a i ′+bi ′-x i '. The reverse vectors of all solutions in the optimization space are calculated, and the original forward solution set and the reverse solution set are sorted by their fitness values ​​as a whole. That is, they are sorted according to the distance of the forward and reverse object positions in the optimization space from the optimal position. By directly screening or using other optimization strategies, the N objects with the best fitness values ​​are selected as the new optimization group, which can quickly converge the objects in the optimization space toward the optimal solution position. For the gravitational algorithm, using a reverse learning mechanism to improve the iterative optimization process is effective and reasonable.

[0099] For the gravitational search algorithm, first use the original solution vector of the GSA original initialization method or iterative method. The solution represented by all objects is shown as follows:

[0100] X i =(x i1 ,x i2 ,…,x ij ,…,x iD )

[0101] Where: x ij The value range is [a j ,b j ], i represents the i-th object in the group, and j represents the dimension.

[0102] Adopt OL mechanism to optimize the original solution group S and generate the reverse solution group X i ′∈S′, where the dimensional components x′ of the reverse solution ij As shown in the following formula:

[0103] x′ ij =a j +b j -x ij

[0104] Then, the reverse solution vector is:

[0105] X′ i =(x′ i1 ,x′ i2 ,..,x′ ij ,..,x′ iD )

[0106] The original forward and reverse solution sets are sorted by their overall fitness values, that is, by their distance from the optimal position in the optimization space. Through direct screening or other optimization strategies, the N objects with the best fitness values ​​are selected as the new optimization group. To address this problem, an elitist strategy is proposed for further improvement.

[0107] (2) Calculate the fitness value of each object, take the minimum value as the current optimal solution of the group Fbest, and record the position of the object as the current global optimal point Xgbest, and set the current position of each object as the individual optimal point Xpbest.

[0108] In one embodiment, based on the reverse learning mechanism, an elitist strategy is used to further improve the gravitational search algorithm to overcome its shortcomings and improve the reliability and convergence speed of the optimization. After the reverse learning mechanism generates a comprehensive set of original solution vectors and reverse solution vectors, the elitist strategy is used to generate a new 20% of solutions with the best fitness values ​​in the set. These solutions are added to the total set of original solutions and reverse solutions, and the fitness values ​​of the solutions in the set are re-ranked. The 20% of solutions with the worst fitness values ​​in the set are removed to generate a new optimization group.

[0109] Entering the core step of the gravitational search algorithm. The position updates of the swarm follow the laws of dynamics, gradually adjusting the positions of each object by calculating the gravitational forces and accelerations between them. For example, during a given iteration, if the output power of the photovoltaic power generation system is high, the relevant variables in the swarm will be subject to a greater gravitational pull, causing them to move toward higher power values. The elitist strategy comes into play at this stage, retaining the top 20% of objects with the highest fitness values ​​and removing the 20% with the lowest fitness values, ensuring that the swarm converges to the optimal solution while maintaining diversity.

[0110] To further avoid the occurrence of oscillation, global memory is used to adjust the object's speed update formula by introducing individual historical optimal values ​​and group optimal values.

[0111] set up The position of the first 20% of objects that can generate new solutions. Then the new solution X is generated. inew The optimization process is as follows:

[0112] Q=R istar *rand(-0.5,0.5) / D

[0113] X inew =X i *Q

[0114] Where: R istar is the Euclidean distance between the optimal solution and the solution closest to the optimal solution, rand(-0.5,0.5) is a random number between -0.5 and 0.5, Q is the change factor for generating new solutions, and D is the dimension of the solution space.

[0115] After sorting the fitness values ​​of the solution vectors in the new set, remove the 20%*N solutions with the worst fitness values ​​Xiworst , generating new optimization groups.

[0116] (3) Update the variables G(t), Mi(t), best(t) and worst(t).

[0117] (4) Calculate the net force acting on objects in the population.

[0118] (5) Calculate the acceleration and velocity of objects in the population.

[0119] (6) Update the positions of objects in the population.

[0120] (7) Calculate the object fitness value and generate a new population through reverse learning strategy and elite strategy to save the global optimal and historical optimal values ​​of the group.

[0121] In one embodiment, an analysis of the velocity and position update formulas of the GSA algorithm reveals that the gravitational search algorithm only considers the influence of the current position when updating an object's position, without taking into account the object's social and memory properties. When an object moves to or near the optimal solution, according to the universal gravitational formula, the gravitational force on the object increases, and the particle's velocity continuously accelerates. Therefore, when the optimal solution or near the optimal solution is reached, the particle's velocity may be very high. According to the laws of kinematics, this will cause the object to oscillate repeatedly near the optimal solution, affecting the algorithm's accuracy. Therefore, memory and group communication are introduced to improve GSA, improve the velocity update formula, and prevent the object from oscillating near the optimal value.

[0122] The solution found by the gravitational search algorithm is determined by the position changes of objects in the optimization space. The direction of the object's acceleration is determined by the net force of gravity acting on the object in the optimization space. The updating process of the object's position, i.e., the solution to the problem, does not take into account the group's optimal and historical optimality. The PSO algorithm, on the other hand, takes into account the object's historical optimality and the group optimality of the entire population. The PSO algorithm's iterative formula is as follows:

[0123]

[0124] Where: w represents the inertia weight; rand j , rand k represents a random variable between [0, 1]; c1, c2 represent constants between [0, 1]; is the historical optimal value experienced by particle i; The optimal value experienced by all particles in the population is the group optimal value.

[0125] GSA is improved by introducing the memory and group communication of the PSO algorithm. The improved spatial search method follows a new strategy, obeying the laws of motion while incorporating memory and group information communication. The new velocity update formula is defined as follows:

[0126]

[0127] Where rand1, rand2, and rand3 represent random numbers between [0, 1]. c1 and c2 represent constants between [0, 1]. By adjusting the values ​​of c1 and c2, the effects of gravity, memory, and social information on search can be balanced.

[0128] (8) Return to (2) and repeat the iteration until the number threshold is reached.

[0129] This embodiment provides a microgrid optimization operation method based on the universal gravitational algorithm. By combining a reverse learning mechanism with an elitist strategy, the algorithm's optimization performance and convergence speed are significantly improved. The improved speed update formula effectively avoids the oscillation of the traditional universal gravitational search algorithm near the optimal solution, enhancing the algorithm's robustness, significantly reducing operating costs, and improving the economy and stability of the microgrid. By introducing a reverse learning mechanism, global memory, and an elitist strategy, the algorithm's optimization performance is enhanced. This not only effectively addresses the complex electrical characteristics and high uncertainty of multiple types of micro-sources in a microgrid, but also enables economical, stable, and environmentally friendly operation of the microgrid while satisfying system constraints.

[0130] Based on the above examples, this example uses experimental data to illustrate the method. Figure 3 、 Figure 4 、 Figure 5 、 Figure 6 As shown, the details are as follows:

[0131] Figure 3 、 Figure 4 The algorithm provides the total load forecast curve, wind power generation, photovoltaic power generation power forecast curve and generalized load curve of the units in the microgrid topology within 24 hours;

[0132] Figure 5 、 Figure 6 Calculation and optimization curves for various operating costs;

[0133] In order to further verify the advantages of the IGSA algorithm proposed in this paper in solving the microgrid optimization operation problem, the PSO, GSA, and IGSA algorithms were used to solve the problem ten times under the same conditions. The statistical experimental comparison results are shown in Table 1:

[0134] Table 1 Statistical experimental comparison results

[0135]

[0136] Table 1

[0137] From the comparative experimental results, it can be seen that the improved universal gravitational search algorithm has good optimization performance, fast convergence speed and strong robustness, and can be better applied to the research on microgrid optimization operation.

[0138] Based on the above embodiment, this embodiment briefly describes the microgrid management platform. Figure 7 As shown, the details are as follows:

[0139] The distributed power generation system includes photovoltaic and wind power generation systems. The load demand device collects real-time user electricity usage data, while the energy storage device monitors the charge and discharge status of the battery pack. The data acquisition and processing device aggregates this information via a communication bus and transmits it to the optimization and scheduling device. The optimization and scheduling device generates a scheduling plan based on an improved gravitational search algorithm, and the control execution device dynamically adjusts the operating status of each module based on this plan.

[0140] During implementation, the data acquisition and processing device first acquires the current operating parameters of the microgrid system. For example, in an industrial park, assuming sufficient photovoltaic power generation and low load demand during the morning hours, the optimization and scheduling device uses an improved gravitational search algorithm to calculate a scheduling strategy that prioritizes charging the energy storage device. The core of this process is to simulate the microgrid operating environment through a multi-dimensional optimization space, where the first dimension represents the output power of the distributed generation (DGs), the second dimension represents the real-time power consumption of the load demand devices, and the third dimension represents the charge and discharge status of the energy storage device.

[0141] Please refer to Figure 8 , Figure 8 This is a structural block diagram of a microgrid optimization operation device based on a universal gravitation algorithm provided in an embodiment of the present invention; the specific device may include:

[0142] The original solution acquisition module 100 randomly generates multiple initial positions of objects in a D-dimensional search space based on a gravitational search algorithm to obtain an original solution group;

[0143] The reverse solution acquisition module 200 optimizes the original solution group using the reverse learning mechanism to generate a reverse solution group;

[0144] The screening module 300 sorts and screens the reverse solution population and the original solution population according to fitness values ​​based on the elite strategy to obtain an optimal population;

[0145] The optimal position calculation module 400 calculates the fitness value of each object in the optimization population and sets the current position of each object as the optimal position;

[0146] The position updating module 500 updates the gravitational parameters and updates the positions of the objects in the population based on the net force, acceleration, and velocity of the objects in the population.

[0147] The iteration module 600 optimizes the population through the reverse learning mechanism and the elite strategy and repeats the above steps until a preset iteration number threshold is reached.

[0148] A microgrid optimization operation device based on the universal gravitation algorithm of this embodiment is used to implement the aforementioned microgrid optimization operation method based on the universal gravitation algorithm. Therefore, the specific implementation method of a microgrid optimization operation device based on the universal gravitation algorithm can be seen in the embodiment part of the microgrid optimization operation method based on the universal gravitation algorithm in the previous text. For example, the original solution acquisition module 100, the reverse solution acquisition module 200, the screening module 300, the optimal position calculation module 400, the position update module 500, and the iteration module 600 are respectively used to implement steps S101, S102, S103, S104, S105, and S106 in the aforementioned microgrid optimization operation method based on the universal gravitation algorithm. Therefore, its specific implementation method can refer to the description of the corresponding embodiments of each part and will not be repeated here.

[0149] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0150] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0151] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0152] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0153] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0154] This application contemplates providing implementations that allow users to selectively block the use or access of personal information data. Specifically, this disclosure contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0155] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0156] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0157] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0158] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0159] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0160] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0161] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0162] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A microgrid optimization operation method based on universal gravitation algorithm, characterized in that: include: Based on the gravitational search algorithm, multiple initial positions of objects are randomly generated in the D-dimensional search space to obtain the original solution group; Optimizing the original solution group using a reverse learning mechanism to generate a reverse solution group; Based on the elite strategy, the reverse solution group and the original solution group are sorted and screened according to the fitness value to obtain the optimal population; Calculating the fitness value of each object in the optimization population and setting the current position of each object as the optimal position; Update the gravitational parameters and update the positions of objects in the population based on the net force, acceleration, and velocity of the objects in the population; The population is optimized through the reverse learning mechanism and elite strategy and the above steps are repeated until the preset iteration threshold is reached.

2. The microgrid optimization operation method based on the universal gravitation algorithm according to claim 1 is characterized in that: The reverse learning mechanism includes: for each object in the original solution group, calculating the reverse value corresponding to each dimensional component thereof, and the calculation formula is: x′ ij =a j +b j -x ij X′ i =(x′ i1 ,x′ i2 ,..,x′ ij ,..,x′ iD ) Among them, X′ i is the reverse solution vector, x′ ij is the original solution, i is the i-th object in the group, and j is the dimension.

3. The microgrid optimization operation method based on the universal gravitation algorithm according to claim 1 is characterized in that: The method of sorting and screening the reverse solution group and the original solution group according to fitness values ​​based on the elite strategy to obtain the optimal population includes: The original solution group and the reverse solution group are sorted according to the fitness values ​​of the forward objects and the reverse objects as a whole using the elite strategy. New solutions are generated based on the solutions that meet the first fitness and added to the original solution group and the reverse solution group. The groups with the new solutions are re-sorted by fitness, and then the solutions that meet the second fitness are removed to obtain the optimal population.

4. The microgrid optimization operation method based on the universal gravitation algorithm according to claim 1 is characterized in that: Calculating the fitness value of each object in the optimization population and setting the current position of each object as the optimal position includes: calculating the fitness value of each object in the optimization population, recording the current optimal solution and its corresponding position, and setting the current position of each object as its individual optimal position.

5. The microgrid optimization operation method based on the universal gravitation algorithm according to claim 1 is characterized in that: The updated gravitational parameters include: gravitational constant, inertial mass, current optimal value and current worst value, wherein the gravitational constant decreases with the number of iterations, and the inertial mass is adjusted according to the fitness value of the current object.

6. The microgrid optimization operation method based on the universal gravitation algorithm according to claim 5 is characterized in that: The updating of the position of the objects in the population includes: optimizing the speed update formula by using global memory and group communication algorithm, and the iterative formula is: Among them, rand1, rand2, rand3 are random numbers between [0, 1], c1, c2 are constants between [0, 1], is the historical optimal value experienced by particle i; The optimal value experienced by all particles in the population.

7. The microgrid optimization operation method based on the universal gravitation algorithm according to claim 6 is characterized in that: The formula for calculating the net force on objects in the population is: Among them, M ai (t) and M pi (t) are the inertial mass of the acting ion j and the inertial mass of the acted object i, G(t) represents the gravitational constant, ε is a very small constant, R ij (t) represents the Euclidean distance between object i and object j.

8. A microgrid optimization operation device based on universal gravitation algorithm, characterized in that: include: The original solution acquisition module randomly generates multiple initial positions of objects in the D-dimensional search space based on the gravitational search algorithm to obtain the original solution group; A reverse solution acquisition module optimizes the original solution group using a reverse learning mechanism to generate a reverse solution group; A screening module, based on an elite strategy, sorts and screens the reverse solution population and the original solution population according to fitness values ​​to obtain an optimal population; An optimal position calculation module calculates the fitness value of each object in the optimization population and sets the current position of each object as the optimal position; The position update module updates the gravity parameters and updates the positions of objects in the population based on the net force, acceleration, and velocity of the objects in the population. The iteration module optimizes the population through the reverse learning mechanism and elite strategy and repeats the above steps until the preset iteration number threshold is reached.

9. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images