Zone area load adjustment planning method, system and equipment for power distribution network and medium

Abstract

The invention relates to the technical field of computer processing, and discloses a transformer area load adjustment planning method, system and device for a power distribution network and a medium, and the method comprises the steps: constructing a transformer area load adjustment planning model of the power distribution network, and determining a target function and a constraint condition of the transformer area load adjustment planning model; based on the objective function and the constraint condition, solving the transformer area load adjustment planning model by adopting an optimization improvement algorithm, and obtaining and executing a load adjustment planning strategy of all transformer areas in the power distribution network; the optimization improved algorithm is configured to be formed by combining a quantum ant colony algorithm introducing a multi-stage search strategy with a simulated annealing algorithm, and the simulated annealing algorithm is combined with the improved quantum ant colony algorithm, so that the search efficiency and the convergence speed of the algorithm are improved, the solving process is more efficient, and the calculation efficiency is improved. And meanwhile, the area load adjustment planning effect and planning efficiency of the power distribution network are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technologies, and in particular, to a method, system, device, and medium for load adjustment planning of a substation area in a distribution network. Background Art

[0002] With the continuous development of digital technologies, load adjustment planning of the substation area in a distribution network, as an essential step in building a digital power grid, has become increasingly important in terms of its effectiveness and accuracy.

[0003] In the prior art, when carrying out low-voltage load adjustment in a substation area of a distribution network, planners usually carry out planning based on experience. However, due to differences in the technical levels of planners, the planning effects vary, and this method has a low level of intelligence, takes a long time, and has low planning efficiency, resulting in low planning effects and planning efficiency for load adjustment planning of the substation area in a distribution network.

[0004] Therefore, how to improve the planning effects and planning efficiency of load adjustment planning of the substation area in a distribution network has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a method, system, device, and medium for load adjustment planning of a substation area in a distribution network, and solves the problem of how to improve the planning effects and planning efficiency of load adjustment planning of the substation area in a distribution network.

[0006] To solve the above technical problem, in a first aspect of the present invention, a method for load adjustment planning of a substation area in a distribution network is provided, including:

[0007] Constructing a load adjustment planning model for a substation area in a distribution network, and determining the objective function and constraint conditions of the load adjustment planning model for the substation area;

[0008] Based on the objective function and the constraint conditions, using an optimized improvement algorithm to solve the load adjustment planning model for the substation area, and obtaining a load adjustment planning strategy for all substations in the distribution network to execute; the optimized improvement algorithm is configured to be formed by combining a quantum ant colony algorithm with a simulated annealing algorithm by introducing a multi-stage search strategy.

[0009] As a preferred solution, the load adjustment planning model for the substation area is represented by the following formula:

[0010]

[0011] In the formula, F(X) is the load adjustment planning model for the substation area; r i is the load rate after adjustment of the i-th substation area in the distribution network; r target is the target load rate; n is the total number of substation areas in the distribution network; C iis the adjustment cost of the i-th substation area in the distribution network; C max is the total cost after adjustment of all substation areas in the distribution network; D i is the change in the power supply distance after adjustment of the i-th substation area in the distribution network; D max is the maximum change in the power supply distance after adjustment of all substation areas in the distribution network; v i is the voltage value at the end of the line after adjustment of the i-th substation area in the distribution network; v target is the target voltage value; w1, w2, w3, w4 are weight coefficients.

[0012] As one of the preferred solutions, based on the objective function and the constraint conditions, an optimization and improvement algorithm is used to solve the load adjustment planning model of the substation areas, and a load adjustment planning strategy for all substation areas in the distribution network is obtained for execution, including:

[0013] Initialize the algorithm parameters, and based on the initialized algorithm parameters, use the objective function as the fitness function. Under the constraint conditions, use the quantum ant colony algorithm introducing a multi-stage search strategy to search for the global optimal solution of each substation area;

[0014] Optimize each of the global optimal solutions through the simulated annealing algorithm to obtain several new solutions to update each of the global optimal solutions, and feedback the updated global optimal solutions to the quantum ant colony algorithm introducing a multi-stage search strategy to adjust the pheromone;

[0015] Based on each updated global optimal solution, iteratively execute the global optimal solution search step of the quantum ant colony algorithm introducing a multi-stage search strategy and the global optimal solution optimization step of the simulated annealing algorithm until a preset iteration condition is reached, and use each of the finally output global optimal solutions as the load adjustment planning strategy for all substation areas in the distribution network for execution.

[0016] As one of the preferred solutions, the quantum ant colony algorithm introducing a multi-stage search strategy includes:

[0017] Initialize the quantum bit probability amplitude, pheromone, maximum number of iterations, and the number of iterations in the global search stage, and assign initial values to the number of ants, the initial pheromone evaporation coefficient, and the initial quantum gate rotation gate coefficient;

[0018] In the global search stage, dynamically adjust the initial pheromone evaporation coefficient after assigning an initial value and the initial quantum gate rotation gate coefficient after assigning an initial value to obtain the first pheromone evaporation coefficient and the first quantum rotation gate adjustment coefficient;

[0019] Control each ant to construct a load adjustment planning strategy for the corresponding substation area according to the initialized quantum bit probability amplitude and the initialized pheromone to form several first global optimal solutions;

[0020] Calculate the fitness values of the first global optimal solutions based on the fitness function, and adaptively adjust the probability amplitudes of qubits through the quantum rotation gate according to the first quantum rotation gate adjustment coefficient;

[0021] Update the initialized pheromone through the first pheromone evaporation coefficient based on the fitness values of the first global optimal solutions and the updated global optimal solutions feedback by the simulated annealing algorithm at the corresponding iteration times;

[0022] Iteratively execute the generation steps of the first global optimal solutions in the global search phase through the adjusted probability amplitudes of qubits and the updated pheromone until reaching the iteration times of the global search phase, obtain several first global optimal target solutions and perform local search;

[0023] In the local search phase, dynamically adjust the first pheromone evaporation coefficient and the first quantum rotation gate adjustment coefficient respectively to obtain the second pheromone evaporation coefficient and the second quantum rotation gate adjustment coefficient;

[0024] Randomly select two load adjustment planning strategies of the substations from each of the first global optimal target solutions to exchange the load adjustment states to form several second global optimal solutions;

[0025] Calculate the fitness values of the second global optimal solutions based on the fitness function, and adaptively adjust the probability amplitudes of qubits through the quantum rotation gate according to the second quantum rotation gate adjustment coefficient;

[0026] Update the updated pheromone through the second pheromone evaporation coefficient based on the fitness values of the second global optimal solutions and the updated global optimal solutions feedback by the simulated annealing algorithm at the corresponding iteration times;

[0027] Iteratively execute the generation steps of the second global optimal solutions in the local search phase through the adjusted probability amplitudes of qubits and the updated pheromone until reaching the maximum iteration times, obtain several second global optimal target solutions as the global optimal solutions searched by the quantum ant colony algorithm introducing the multi-stage search strategy for output.

[0028] As one of the preferred solutions, the first quantum rotation gate adjustment coefficient is expressed by the following formula:

[0029]

[0030] In the formula, λ(t) is the first quantum rotation gate adjustment coefficient; λ0 is the initial quantum gate rotation coefficient after initial value assignment; λ max is the maximum value of the first quantum rotation gate adjustment coefficient in the global search phase; t is the iteration times; T1 is the iteration times of the global search phase;

[0031] The first pheromone evaporation coefficient is expressed by the following formula:

[0032]

[0033] In the formula, ρ(t) is the first pheromone evaporation coefficient; ρ0 is the initial pheromone evaporation coefficient after initial value assignment; ρ max is the maximum value of the first pheromone evaporation coefficient in the global search stage.

[0034] As one of the preferred solutions, the second quantum rotation gate adjustment coefficient is expressed by the following formula:

[0035]

[0036] In the formula, λ * (t) is the second quantum rotation gate adjustment coefficient; λ max , λ min are respectively the maximum value and the minimum value of the second quantum rotation gate adjustment coefficient in the local search stage;

[0037] The second pheromone evaporation coefficient is expressed by the following formula:

[0038]

[0039] In the formula, ρ * (t) is the second pheromone evaporation coefficient; ρ max , ρ min are respectively the maximum value and the minimum value of the second pheromone evaporation coefficient in the local search stage.

[0040] As one of the preferred solutions, optimizing each of the global optimal solutions through the simulated annealing algorithm to obtain several new solutions for updating each of the global optimal solutions includes:

[0041] Performing neighborhood perturbation on each of the global optimal solutions to obtain several neighborhood solutions;

[0042] Quantifying the difference between the fitness value of each of the global optimal solutions and the fitness value of each of the neighborhood solutions based on the fitness function;

[0043] Deciding whether to accept the neighborhood solution according to the difference through the Metropolis criterion to update each of the global optimal solutions.

[0044] The second aspect of the present invention provides a substation area load adjustment planning system for a distribution network, including:

[0045] A model construction module for constructing a load adjustment planning model for a distribution network area and determining the objective function and constraint conditions of the load adjustment planning model for the distribution network area;

[0046] A strategy solving module for solving the load adjustment planning model for the distribution network area based on the objective function and the constraint conditions by using an optimized improvement algorithm to obtain a load adjustment planning strategy for all areas in the distribution network for execution; the optimized improvement algorithm is configured to be formed by combining a quantum ant colony algorithm with a simulated annealing algorithm introducing a multi-stage search strategy.

[0047] A third aspect of the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the method for load adjustment planning for a distribution network area as described above is implemented.

[0048] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a stored computer program. When the device where the computer-readable storage medium is located executes the computer program, the method for load adjustment planning for a distribution network area as described above is implemented.

[0049] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0050] (1) Through the load adjustment planning model for the distribution network area, factors such as the load distribution of each area can be comprehensively considered to formulate a reasonable load adjustment strategy, and the load distribution of the area after load adjustment is more balanced, which helps to reduce power grid losses and improve the operation efficiency of the power grid;

[0051] (2) By combining the quantum ant colony algorithm with the simulated annealing algorithm introducing a multi-stage search strategy, the parallelism of quantum computing and the distributed search ability of the ant colony algorithm are fully utilized to improve the operation efficiency of the algorithm, and the multi-stage search strategy helps the algorithm to gradually approach the optimal solution in complex problems, enhancing the robustness of the algorithm, thereby improving the load adjustment planning effect and planning efficiency for the distribution network area. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] To more clearly illustrate the technical solutions of the present invention, the drawings required for implementation will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0053] Figure 1 is a flowchart of a method for load adjustment planning for a distribution network area provided by an embodiment of the present invention;

[0054] Figure 2 It is a structural diagram of a substation load adjustment planning system for a distribution network provided by an embodiment of the present invention;

[0055] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0056] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0057] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0058] In the description of the present application, it should be noted that, unless otherwise clearly defined and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the internal communication of two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration and do not indicate or imply that the system or component referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0059] In the description of the present application, it should be noted that unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0060] In one embodiment, as Figure 1 shown, the first aspect of the present invention provides a method for planning the load adjustment of a substation area in a distribution network, including:

[0061] S1. Construct a load adjustment planning model for the substation area of the distribution network, and determine the objective function and constraint conditions of the load adjustment planning model for the substation area;

[0062] Specifically, the present invention constructs a load adjustment planning model for the substation area by obtaining relevant data such as the transformer capacity, line carrying capacity, substation area topology, power supply amount, current and voltage of each substation area in the distribution network, and based on these data, comprehensively considering the cost, load rate, power supply distance and line end voltage of the substation area in the distribution network. It is represented by the following formula:

[0063]

[0064] In the formula, F(X) is the load adjustment planning model for the substation area; r i is the load rate after adjustment of the i-th substation area in the distribution network; r target is the target load rate; n is the total number of substation areas in the distribution network; C i is the adjustment cost of the i-th substation area in the distribution network; C max is the total cost after adjustment of all substation areas in the distribution network; D i is the change in the power supply distance after adjustment of the i-th substation area in the distribution network; D max is the maximum change in the power supply distance after adjustment of all substation areas in the distribution network; v i is the voltage value at the end of the line after adjustment of the i-th substation area in the distribution network; v target is the target voltage value; w1, w2, w3, w4 are weight coefficients, w1 + w2 + w3 + w4 = 1, and these coefficients can be adjusted according to actual needs. For example, w1 = 0.4, w2 = 0.3, w3 = 0.1, w4 = 0.2, etc., to balance factors such as load rate, cost, power supply distance and voltage.

[0065] The objective function of the load adjustment planning model for the substation area is to minimize the load adjustment planning model for the substation area, that is, minF(X); the constraint conditions include the substation area load rate constraint: 30% < r i < 80%, and the substation area line end voltage constraint: 198V < vi <235.4V.

[0066] S2. Based on the objective function and the constraint conditions, use an optimized improved algorithm to solve the load adjustment planning model of the substation area, and obtain the load adjustment planning strategies for all substation areas in the distribution network for execution; the optimized improved algorithm is configured to be formed by combining a quantum ant colony algorithm introducing a multi-stage search strategy with a simulated annealing algorithm;

[0067] In one embodiment, step S2 includes:

[0068] Initialize the algorithm parameters, and based on the initialized algorithm parameters, use the objective function as the fitness function. Under the constraint conditions, use a quantum ant colony algorithm introducing a multi-stage search strategy to search for the global optimal solution of each substation area;

[0069] Optimize each of the global optimal solutions through a simulated annealing algorithm to obtain several new solutions to update each of the global optimal solutions, and feedback the updated global optimal solutions to the quantum ant colony algorithm introducing a multi-stage search strategy to adjust the pheromone;

[0070] Iteratively execute the global optimal solution search step of the quantum ant colony algorithm introducing a multi-stage search strategy and the global optimal solution optimization step of the simulated annealing algorithm based on each updated global optimal solution until a preset iteration condition is reached, and use the finally output global optimal solutions as the load adjustment planning strategies for all substation areas in the distribution network for execution.

[0071] Specifically, based on the objective function and the constraint conditions, the present invention uses an optimized improved algorithm formed by combining a quantum ant colony algorithm introducing a multi-stage search strategy with a simulated annealing algorithm to solve the load adjustment planning model of the substation area, and obtains the load adjustment planning strategies for all substation areas in the distribution network, including:

[0072] First, initialize the algorithm parameters, such as setting the basic parameters of the improved quantum ant colony algorithm: the number of ants, the pheromone evaporation coefficient, the quantum rotation angle, the pheromone, etc., and randomly generate the initial quantum bit state to form the initial population, so that each individual represents a possible load adjustment planning strategy for the substation area; then determine the initial temperature, the cooling rate, and the temperature drop strategy of the simulated annealing algorithm, set the initial solution, which can be the same as a certain individual in the initial population of the improved quantum ant colony algorithm, or randomly generate a solution that meets the problem constraints; and it is also necessary to determine parameters such as the number of substation areas and the quantum bit coding length of the load adjustment plan. The present invention uses quantum bit coding to represent the load adjustment planning strategy of the substation area. For each pair of substations (transfer out - transfer in), use a quantum bit q to represent whether to perform a load adjustment operation, and the state of the quantum bit can be expressed as:

[0073] q = α|0> + β|1>

[0074] |α| 2 + |β| 2 = 1

[0075] where α and β are the probability amplitudes of the qubit; |0> represents no charge adjustment operation; |1> represents the charge adjustment operation. At the same time, constraints on the amount of charge adjustment need to be imposed, and L can be determined according to factors such as the transformer capacity and line carrying capacity of the substation area max，i is the maximum allowable load adjustment amount for the i-th substation area, then the amount of charge adjustment in the load adjustment planning strategy for each substation area cannot exceed L max，i .

[0076] Then, the objective function is used as the fitness function, and under the constraint conditions, a quantum ant colony algorithm introducing a multi-stage search strategy is used to search for the global optimal solution of each substation area. That is, in each iteration, a path (i.e., the load adjustment planning strategy) is selected according to the pheromone concentration, and the advantages of quantum computing are utilized to perform parallel search through the superposition and entanglement characteristics of qubits, improving the search efficiency. A multi-stage search strategy is adopted to gradually narrow the search range and improve the convergence speed, so as to search for the global optimal solution for each substation area using the improved quantum ant colony algorithm

[0077] Then, the simulated annealing algorithm is applied to further optimize the global optimal solution of each substation area, and according to the acceptance probability criterion of the simulated annealing algorithm, new solutions are accepted or rejected to jump out of the local optimum, and then the global optimal solution is updated, so as to feedback the updated global optimal solution to the quantum ant colony algorithm introducing the multi-stage search strategy to update the pheromone and guide subsequent searches

[0078] Finally, the global optimal solution search step and the simulated annealing algorithm optimization step are repeatedly executed until the preset iteration conditions are reached (such as reaching the maximum number of iterations, convergence of the objective function value, etc.). The global optimal solutions of each substation area finally output are used as the load adjustment planning strategy and this strategy is executed to adjust the load in the distribution network; or the solution with the optimal fitness value can be selected from all the solutions obtained in the optimization and improvement algorithm search process as the final load adjustment planning strategy output for the substation area. In addition, a detailed analysis can be carried out on the output optimal strategy, including the load adjustment situation, load factor, cost, power supply distance, voltage and other index improvement situations of each substation area, and the results are presented in the form of charts, data tables, etc., providing a decision-making basis for the actual load adjustment work of the substation area

[0079] The present invention uses an optimized and improved algorithm formed by combining a quantum ant colony algorithm with a simulated annealing algorithm that introduces a multi-stage search strategy to solve the load adjustment planning model for each substation area, that is, the simulated annealing algorithm is executed after each iteration of the quantum ant colony algorithm. Through the random perturbation and probability acceptance mechanism of simulated annealing, it helps the quantum ant colony algorithm jump out of the local optimal solution. As the number of iterations increases, the temperature gradually decreases, and the randomness of simulated annealing weakens, making the algorithm gradually converge to the global optimal solution. It combines the advantages of quantum computing and the ant colony algorithm to achieve parallel search and intelligent optimization, significantly improving the search efficiency; by introducing the multi-stage search strategy and the simulated annealing algorithm, it effectively avoids falling into the local optimum and enhances the global optimization ability; and this method can handle complex constraint conditions and multi-objective optimization problems, is applicable to different types of distribution networks and load adjustment requirements, and speeds up the convergence rate of the algorithm by gradually narrowing the search range and dynamically adjusting the pheromone concentration.

[0080] In one embodiment, an optimized and improved algorithm formed by combining a wolf pack algorithm, fuzzy logic, and a neural network can also be used to solve the load adjustment planning model for the substation area under the objective function and constraint conditions, specifically including:

[0081] Initialization: Set parameters such as the size of the wolf pack, the dimension of the search space, and the maximum number of iterations. Initialize the positions of each artificial wolf in the wolf pack, as well as the structure and parameters of the fuzzy neural network. Fuzzy logic dynamic parameter adjustment: Use the iteration number ratio (reflecting the optimization process) and population diversity (measured by the entropy value of the distance between solutions) as input variables, and the search step size (controlling the movement range of the wolf pack) and siege threshold (determining when to switch from the wandering phase to the siege phase) as output variables, and design fuzzy rules: If the iteration number ratio is low and the diversity is high, increase the step size (enhancing global exploration); if the iteration number ratio is high and the diversity is low, decrease the step size and lower the siege threshold, etc. Neural network fitness prediction: Design the structure of the neural network, including the input layer, hidden layer, and output layer, as well as the connection weights and biases between layers. Use a number of solutions randomly generated in the initial stage to calculate the true fitness to construct a training set for training. During the optimization process, use the neural network to predict the newly generated solutions, and only calculate the true fitness for the solutions with better predictions to update the neural network regularly, add newly calculated true fitness data, and improve the prediction accuracy. The improved wolf pack search mechanism includes 1. Wandering phase: Adopt fuzzy step size control, so that each wolf randomly wanders in the solution space according to the current step size to generate candidate solutions, and then use the neural network to predict the fitness of the candidate solutions, and only retain the solutions with better predictions for true evaluation. 2. Summoning phase: When a wolf discovers a better solution (fitness lower than the threshold), trigger the summoning behavior, and other wolves gather towards this position, and dynamically adjust the siege radius according to the voltage deviation and the degree of load rate balance. 3. Siege phase: Select several wolves with the best fitness as the "lead wolves", and other wolves conduct fine search in their neighborhoods, apply quantum rotation gate perturbation to the lead wolf solutions to generate diverse solutions to avoid premature convergence. 4. Wolf pack update: According to the principle of "survival of the fittest", remove the artificial wolf with the worst fitness and randomly generate new artificial wolves, and update the parameters of the fuzzy neural network to adapt to the new search space and solution distribution. Iteration and convergence: Repeat the above neural network fitness prediction steps and the improved wolf pack search mechanism until the maximum number of iterations is reached or the convergence condition is satisfied, and output the final load adjustment planning strategy for the distribution area.

[0082] The present invention uses fuzzy rules to dynamically control search parameters, enhancing the adaptability of the algorithm to complex constraints; processes uncertain factors through a neural network, improving the robustness and global optimization ability of the search, and accelerating fitness evaluation to reduce computational overhead; and uses an improved wolf pack search mechanism to balance global exploration and local exploitation.

[0083] In addition, for the substation area load adjustment planning model, algorithms such as the chaotic adaptive differential bee colony algorithm can also be used for solution. It uses the Logistic chaotic mapping to generate the initial population, enhances the diversity of solutions, adopts an adaptive differential strategy to dynamically adjust the mutation factor and crossover probability of differential evolution, and combines the employed bee - observing bee division of labor mechanism of the artificial bee colony algorithm to balance global exploration and local exploitation, so as to solve the problem that the traditional adaptive differential strategy is prone to falling into local optima, and thus effectively improve the effect and efficiency of the substation area load adjustment planning for the distribution network.

[0084] In one embodiment, the quantum ant colony algorithm introducing a multi - stage search strategy includes:

[0085] Initialize the quantum bit probability amplitude, pheromone, maximum number of iterations, and the number of iterations in the global search stage, and assign initial values to the number of ants, the initial pheromone evaporation coefficient, and the initial quantum gate rotation gate coefficient;

[0086] In the global search stage, dynamically adjust the initial pheromone evaporation coefficient after assigning the initial value and the initial quantum gate rotation gate coefficient after assigning the initial value to obtain the first pheromone evaporation coefficient and the first quantum rotation gate adjustment coefficient;

[0087] Control each ant to construct a load adjustment planning strategy for the corresponding substation area according to the initialized quantum bit probability amplitude and the initialized pheromone to form a number of first global optimal solutions;

[0088] Calculate the fitness value of each of the first global optimal solutions based on the fitness function, and adaptively adjust the probability amplitude of the quantum bit through the quantum rotation gate according to the first quantum rotation gate adjustment coefficient;

[0089] Update the initialized pheromone based on the fitness values of each of the first global optimal solutions and the updated global optimal solutions feedback by the simulated annealing algorithm at the corresponding number of iterations through the first pheromone evaporation coefficient;

[0090] Iteratively execute the generation steps of each of the first global optimal solutions in the global search stage through the adjusted probability amplitude of the quantum bit and the updated pheromone until the number of iterations in the global search stage is reached, obtain a number of first global optimal target solutions and perform local search;

[0091] In the local search stage, dynamically adjust the first pheromone evaporation coefficient and the first quantum rotation gate adjustment coefficient to obtain the second pheromone evaporation coefficient and the second quantum rotation gate adjustment coefficient;

[0092] Randomly select two load adjustment planning strategies of the substation area from each of the first global optimal target solutions to exchange the load adjustment states to form a number of second global optimal solutions;

[0093] Calculate the fitness values of each of the second global optimal solutions based on the fitness function, and adaptively adjust the probability amplitudes of the qubits through the quantum rotation gates according to the adjustment coefficients of the second quantum rotation gates;

[0094] Based on the fitness values of each of the second global optimal solutions and the updated global optimal solutions feedback by the simulated annealing algorithm at the corresponding iteration times, update the updated pheromone through the second pheromone evaporation coefficient;

[0095] Iteratively execute the generation steps of each of the second global optimal solutions in the local search stage through the adjusted probability amplitudes of the qubits and the updated pheromone until the maximum number of iterations is reached, and obtain several second global optimal target solutions to be output as each of the global optimal solutions searched by the quantum ant colony algorithm introducing the multi-stage search strategy.

[0096] Specifically, the improved quantum ant colony algorithm adopted by the present invention is a quantum ant colony algorithm introducing a multi-stage search strategy, which divides the search process of the original quantum ant colony algorithm into a global search stage and a local search stage. In the global search stage, by increasing the pheromone evaporation coefficient ρ and the quantum rotation gate adjustment coefficient λ, the search range is expanded; in the local search stage, ρ and λ are decreased, focusing on fine search near the current better solution to improve the global search ability and accelerate the convergence speed of the algorithm. Among them, the improved quantum ant colony algorithm includes:

[0097] Initialization stage: Initialize the superposition state probability amplitude of each qubit (such as ), to represent the diversity of solutions, and initialize the pheromone matrix, global optimal solution and optimal fitness value, and assign initial values to the number of ants, maximum number of iterations, pheromone evaporation coefficient, pheromone enhancement coefficient Q, quantum rotation gate adjustment coefficient, number of iterations in the global search stage, etc.

[0098] Global search stage: Dynamically adjust the pheromone evaporation coefficient and the quantum rotation gate coefficient according to the current iteration times to obtain the first pheromone evaporation coefficient and the first quantum rotation gate adjustment coefficient, so as to gradually enhance the global exploration ability (reduce pheromone evaporation to retain more paths, increase the quantum rotation angle to accelerate state evolution); among them, the first quantum rotation gate adjustment coefficient is represented by the following formula:

[0099]

[0100] In the formula, λ(t) is the first quantum rotation gate adjustment coefficient; λ0 is the initial quantum gate rotation coefficient after assigning the initial value; λ max is the maximum value of the first quantum rotation gate adjustment coefficient in the global search stage; t is the iteration times; T1 is the number of iterations in the global search stage;

[0101] The first pheromone evaporation coefficient is expressed by the following formula:

[0102]

[0103] In the formula, ρ(t) is the first pheromone evaporation coefficient; ρ0 is the initial pheromone evaporation coefficient after initial value assignment; ρ max is the maximum value of the first pheromone evaporation coefficient in the global search stage.

[0104] Then, control each ant to select whether to perform load regulation operations on each substation area pair according to a certain probability based on the initialized qubit probability amplitude and the initialized pheromone, construct its own solution, so as to form a load adjustment planning strategy for the corresponding substation area to form several first global optimal solutions, and check whether the load regulation plan constructed by each ant meets the constraint conditions. If not, adjust it to meet the conditions. Then, calculate the fitness value of the first global optimal solution of each substation area based on the fitness function, and adaptively adjust the probability amplitude of the qubit through the quantum rotation gate according to the first quantum rotation gate adjustment coefficient, which is expressed by the following formula:

[0105]

[0106] In the formula, θ is the rotation angle of the quantum rotation gate; F best is the fitness value of the first global optimal solution; F is the fitness value of the current solution.

[0107] According to the quality of the solution constructed by the ant and the updated global optimal solutions feedback by the simulated annealing algorithm at the corresponding iteration times, update the initialized pheromone through the first pheromone evaporation coefficient, including the pheromone evaporation and pheromone enhancement processes, which is expressed by the following formula:

[0108] τ ij (t + 1) = (1 - ρ)τ ij (t)

[0109]

[0110] In the formula, τ ij is the pheromone matrix, representing the attraction force for performing load regulation operations from substation area i to substation area j; is the pheromone increment left by the k-th ant on the path (i, j); F k is the fitness value of the solution constructed by the k-th ant.

[0111] And in the update process, the simulated annealing algorithm is adopted to assist with the globally optimal solutions updated at the corresponding iteration times: accepting inferior solutions with a probability in the Metropolis criterion to avoid falling into local optima. And in the process of pheromone update, the principle is to increase the pheromone concentration for the path of the distribution area pair passed by the solution with high fitness, so as to guide subsequent ants to select these paths more. The update constraint of pheromone: to avoid over-concentration or dispersion of pheromone, a dynamic range [τ min , τ max is set for the pheromone concentration. After each pheromone update, if τ ij < τ min , then let τ ij = τ min ; if τ ij > τ max , then let τ ij = τ max . τ min and τ max are dynamically adjusted with the iteration times. The range is wider in the early stage to promote global search, and the range becomes narrower in the later stage to strengthen local search; at the same time, according to the pheromone evaporation mechanism, the pheromone concentration gradually evaporates over time to avoid excessive accumulation of pheromone.

[0112] Finally, repeat generating solutions, updating quantum states and pheromones until the iteration times of the global search stage are reached, output the first globally optimal target solution set and start local search.

[0113] Local search stage: First, dynamically adjust the first pheromone evaporation coefficient and the first quantum rotation gate adjustment coefficient respectively to obtain the second pheromone evaporation coefficient and the second quantum rotation gate adjustment coefficient to enhance the local development ability (increasing the pheromone evaporation to accelerate the elimination of obsolete paths and reducing the rotation angle to finely adjust the quantum state); among them, the second quantum rotation gate adjustment coefficient is expressed by the following formula:

[0114]

[0115] In the formula, λ * (t) is the second quantum rotation gate adjustment coefficient; λ max , λ min are respectively the maximum and minimum values of the second quantum rotation gate adjustment coefficient in the local search stage;

[0116] The second pheromone evaporation coefficient is expressed by the following formula:

[0117]

[0118] In the formula, ρ * (t) is the second pheromone evaporation coefficient; ρ max , ρ minThey are the maximum and minimum values of the second pheromone evaporation coefficient in the local search stage, respectively.

[0119] Then, randomly select the load adjustment strategies of two substations from the first global optimal solution, exchange their load adjustment states (for example, the original load adjustment becomes no load adjustment, and the no load adjustment becomes load adjustment, etc.), generate several second global optimal solutions, and calculate the fitness values of these second global optimal solutions based on the fitness function. Update the quantum probability amplitude and pheromone with the updated global optimal solution feedback by the second quantum rotation gate adjustment coefficient, the second pheromone evaporation coefficient, and the simulated annealing algorithm at the corresponding iteration times (the method is the same as that used in the global search process, only the coefficients are different, so it will not be elaborated here), and repeat the local search until the maximum iteration number is reached. Output the final set of second global optimal target solutions as the output of each global optimal solution searched by the quantum ant colony algorithm introducing the multi-stage search strategy.

[0120] The present invention introduces a multi-stage search strategy into the original quantum ant colony algorithm. In the global stage, it quickly locates the potential optimal region through large-scale quantum state evolution and pheromone guidance. In the local stage, it finely mines the local optimal solution through neighborhood perturbation and parameter fine-tuning, which can balance exploration and exploitation and avoid premature convergence. Using the quantum superposition state to represent the diversity of solutions enables multiple candidate solutions to be explored in one iteration. Dynamically adjust the probability amplitude through the quantum rotation gate to accelerate convergence to the high fitness region. Combine simulated annealing to screen high-quality solutions to update the pheromone, which can enhance the guiding nature of path selection. The evaporation coefficient and rotation angle are dynamically adjusted with the iteration times, which can achieve a smooth transition of the search strategy, enhance the global optimization ability, and improve the convergence speed.

[0121] In one embodiment, optimizing each of the global optimal solutions through the simulated annealing algorithm to obtain several new solutions for updating each of the global optimal solutions includes:

[0122] Perform neighborhood perturbation on each of the global optimal solutions to obtain several neighborhood solutions;

[0123] Based on the fitness function, quantify the difference between the fitness value of each of the global optimal solutions and the fitness value of each of the neighborhood solutions;

[0124] According to the difference, decide whether to accept the neighborhood solution through the Metropolis criterion to update each of the global optimal solutions.

[0125] Specifically, in order to further improve the performance of the improved quantum ant colony algorithm, the present invention introduces the simulated annealing algorithm and utilizes its ability to jump out of the local optimal solution. Combine it with the improved quantum ant colony algorithm to enhance the global search ability, including:

[0126] In each iteration, perform simulated annealing operation on the global optimal solution obtained by the improved quantum ant colony algorithm. Randomly select one or more load regulation decisions for the substation area pairs, make slight changes to them (such as changing the load regulation state or finely tuning the load regulation amount), generate neighborhood solutions, and calculate the difference between the fitness values of each global optimal solution output by the improved quantum ant colony algorithm and the fitness values of each neighborhood solution. Then, according to the Metropolis criterion of simulated annealing, decide whether to accept the neighborhood solution. Generate a random number between [0, 1]. If the random number is less than the acceptance probability calculated according to the current temperature, accept the neighborhood solution as the new global optimal solution. Finally, after each simulated annealing operation, update the temperature according to a certain temperature reduction strategy, and the classical geometric temperature reduction strategy can also be adopted to reduce the randomness of the algorithm and make the search gradually focus on the local optimal solution.

[0127] Feed the new solution accepted by the simulated annealing algorithm back to the quantum ant colony algorithm as the reference information for the next iteration of the quantum ant colony algorithm. For example, according to the load regulation situation of the substation area pairs in the new solution, adjust the pheromone concentration to guide the ants to be more inclined to search for areas related to the new solution; and repeat the search of the quantum ant colony algorithm and the perturbation and acceptance operations of the simulated annealing algorithm to continuously optimize the substation area load adjustment plan until the preset termination conditions are met, such as reaching the maximum number of iterations, convergence of the fitness value, etc. The present invention combines the simulated annealing algorithm with the improved quantum ant colony algorithm, improves the search efficiency and convergence speed of the algorithm, makes the solution process more efficient, and at the same time effectively improves the planning effect and planning efficiency of the substation area load adjustment of the distribution network.

[0128] In the embodiments of the present application, in view of the problem of how to improve the planning effect and efficiency of the substation area load adjustment in the distribution network, a method for the substation area load adjustment planning in the distribution network is designed. First, according to the actual situation and requirements of the distribution network, a substation area load adjustment planning model is constructed, and the objective function and constraint conditions of the model are clarified. Then, an optimized improvement algorithm is used to solve the model. Based on the quantum ant colony algorithm, this algorithm introduces a multi-stage search strategy to gradually narrow the search range and improve the search accuracy. Combining the global search ability and probability jump characteristics of the simulated annealing algorithm, it further enhances the global optimization ability of the algorithm. Finally, the load adjustment planning strategies for all substations in the distribution network are output to guide the actual load adjustment work. By combining the advantages of the quantum ant colony algorithm and the simulated annealing algorithm, the algorithm can perform effective global search in a large solution space, avoid falling into local optimal solutions, and improve the global optimization ability. By introducing a multi-stage search strategy, the algorithm can gradually narrow the search range and improve the search accuracy, thereby accelerating the convergence speed and enhancing the search efficiency. It is applicable to various complex distribution network structures and load adjustment requirements, and has strong versatility and adaptability. Combining the probability jump characteristics of the simulated annealing algorithm, the algorithm can jump out of the local optimum during the search process, further improving the quality and reliability of the load adjustment planning strategy.

[0129] It should be noted that although the steps in the above flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders.

[0130] In another embodiment, as Figure 2 shown, the second aspect of the present invention provides a substation area load adjustment planning system for a distribution network, including:

[0131] A model construction module, configured to construct a substation area load adjustment planning model for the distribution network and determine the objective function and constraint conditions of the substation area load adjustment planning model;

[0132] A strategy solving module, configured to solve the substation area load adjustment planning model based on the objective function and the constraint conditions by using an optimized improvement algorithm to obtain the load adjustment planning strategies for all substations in the distribution network for execution; the optimized improvement algorithm is configured to be formed by combining the quantum ant colony algorithm introducing a multi-stage search strategy and the simulated annealing algorithm.

[0133] It should be noted that each module in the above-mentioned substation load adjustment planning system for a distribution network can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules. For the specific limitations of a substation load adjustment planning system for a distribution network, refer to the limitations of a substation load adjustment planning method for a distribution network in the above text. The two have the same functions and effects and will not be elaborated here.

[0134] The third aspect of the present invention provides an electronic device, which includes:

[0135] A processor, a memory, and a bus;

[0136] The bus is used to connect the processor and the memory;

[0137] The memory is used to store operation instructions;

[0138] The processor is used to execute instructions by calling the operation instructions, so that the processor executes the operations corresponding to a substation load adjustment planning method as shown in the first aspect of the present application.

[0139] In an optional embodiment, an electronic device is provided, as Figure 3 shown, Figure 3 The electronic device 5000 shown includes a processor 5001 and a memory 5003. Among them, the processor 5001 and the memory 5003 are connected, such as connected through a bus 5002. Optionally, the electronic device 5000 may further include a transceiver 5004. It should be noted that in practical applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation to the embodiments of the present application.

[0140] The processor 5001 can be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in combination with the disclosure of the present application. The processor 5001 can also be a combination that realizes computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0141] The bus 5002 may include a path for transmitting information between the above components. The bus 5002 can be a PCI bus or an EISA bus, etc. The bus 5002 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 3It is represented only by a thick line, but it does not mean that there is only one bus or one type of bus.

[0142] The memory 5003 can be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an EEPROM, a CD-ROM, or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0143] The memory 5003 is used to store the application program code for implementing the solution of this application and is controlled by the processor 5001 to execute. The processor 5001 is used to execute the application program code stored in the memory 5003 to implement the content shown in any of the foregoing method embodiments.

[0144] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0145] The fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements a method for planning the load adjustment of a distribution network area shown in the first aspect of this application.

[0146] Another embodiment of this application provides a computer-readable storage medium, on which a computer program is stored, and when it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0147] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the above method.

[0148] In summary, the present invention relates to the field of computer processing technology, and discloses a method, system, device and medium for load adjustment planning of a distribution network area. The method includes constructing a load adjustment planning model for the distribution network area, and determining the objective function and constraint conditions of the load adjustment planning model for the distribution network area; based on the objective function and the constraint conditions, using an optimized improvement algorithm to solve the load adjustment planning model for the distribution network area, so as to obtain a load adjustment planning strategy for all areas in the distribution network to execute; the optimized improvement algorithm is configured to be formed by combining a quantum ant colony algorithm introducing a multi-stage search strategy with a simulated annealing algorithm. By combining the simulated annealing algorithm with the improved quantum ant colony algorithm, the search efficiency and convergence speed of the algorithm are improved, making the solution process more efficient, and at the same time effectively improving the load adjustment planning effect and planning efficiency of the distribution network area.

[0149] Each embodiment in this specification is described in a progressive manner. For parts that are the same or similar in each embodiment, they can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the above technical features of the embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the above technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0150] The above embodiments only represent several preferred implementation manners of the present application, and the description is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and replacements can still be made, and these improvements and replacements should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the protection scope of the claims.

Claims

1. A method for planning load adjustment in a distribution network, characterized in that: include: Constructing a distribution network load adjustment planning model, and determining the objective function and constraint conditions of the load adjustment planning model; Based on the objective function and the constraints, an optimization and improvement algorithm is used to solve the substation load adjustment planning model to obtain load adjustment planning strategies for all substations in the distribution network for execution; the optimization and improvement algorithm is configured to be formed by combining a quantum ant colony algorithm that introduces a multi-stage search strategy with a simulated annealing algorithm.

2. A method for planning load adjustment in a distribution network according to claim 1, characterized in that: The load adjustment planning model of the substation is expressed by the following formula: Where F(X) is the load adjustment planning model of the substation; i is the load rate of the ith area in the distribution network after adjustment; r target is the target load rate; n is the total number of distribution grids; C i is the adjustment cost of the ith distribution area in the distribution network; C max is the adjusted total cost of all distribution areas in the distribution network; D i is the change in power supply distance after adjustment for the ith substation in the distribution network; D max It is the maximum power supply distance change after adjustment for all substations in the distribution network; v i is the voltage value at the end of the line after adjustment in the ith distribution area in the distribution network; v target is the target voltage value; w1, w2, w3, w4 are weight coefficients.

3. A method for planning load adjustment in a distribution network according to claim 1, characterized in that: The method of solving the load adjustment planning model of the substation using an optimized improved algorithm based on the objective function and the constraint conditions to obtain a load adjustment planning strategy for all substations in the distribution network for execution includes: Initialize the algorithm parameters, and based on the initialized algorithm parameters, use the objective function as the fitness function, and under the constraints, use the quantum ant colony algorithm that introduces a multi-stage search strategy to search for the global optimal solution of each station area; Optimizing each of the global optimal solutions by a simulated annealing algorithm to obtain a number of new solutions to update each of the global optimal solutions, and feeding back the updated global optimal solutions to a quantum ant colony algorithm that introduces a multi-stage search strategy to adjust the pheromone; Based on each updated global optimal solution, the global optimal solution search step of the quantum ant colony algorithm that introduces a multi-stage search strategy and the global optimal solution optimization step of the simulated annealing algorithm are iteratively executed until the preset iteration condition is reached, and the global optimal solutions finally output are used as the load adjustment planning strategy for all substations in the distribution network for execution.

4. A method for planning load adjustment in a distribution network according to claim 3, characterized in that: The quantum ant colony algorithm that introduces a multi-stage search strategy includes: Initialize the quantum bit probability amplitude, pheromone, maximum number of iterations, and number of iterations in the global search phase, and assign initial values ​​to the number of ants, initial pheromone volatility coefficient, and initial quantum gate revolving gate coefficient; In the global search phase, the initial pheromone volatility coefficient and the initial quantum gate revolving door coefficient after the initial value are dynamically adjusted to obtain the first pheromone volatility coefficient and the first quantum revolving door adjustment coefficient; Control each ant to construct a load adjustment planning strategy for the corresponding area according to the initialized quantum bit probability amplitude and the initialized pheromone to form several first global optimal solutions; Calculating the fitness value of each of the first global optimal solutions based on the fitness function, so as to adaptively adjust the probability amplitude of the quantum bit through the quantum rotating gate according to the first quantum rotating gate adjustment coefficient; Based on the fitness values ​​of the first global optimal solutions and the updated global optimal solutions fed back by the simulated annealing algorithm at the corresponding number of iterations, the initialized pheromone is updated by the first pheromone volatility coefficient; Iteratively executing the steps of generating each first global optimal solution in the global search phase by using the adjusted probability amplitude of the quantum bit and the updated pheromone until the number of iterations of the global search phase is reached, obtaining several first global optimal target solutions and performing local search; In the local search phase, the first pheromone volatility coefficient and the first quantum revolving door adjustment coefficient are dynamically adjusted to obtain a second pheromone volatility coefficient and a second quantum revolving door adjustment coefficient; Randomly select the load adjustment states of the load adjustment planning strategies of two substations from each of the first global optimal objective solutions and exchange them to form a plurality of second global optimal solutions; Calculating the fitness value of each of the second global optimal solutions based on the fitness function, so as to adaptively adjust the probability amplitude of the quantum bit through the quantum rotating gate according to the second quantum rotating gate adjustment coefficient; Based on the fitness value of each of the second global optimal solutions and the updated global optimal solution fed back by the simulated annealing algorithm at the corresponding number of iterations, the updated pheromone is updated by the second pheromone volatility coefficient; The steps of generating each second global optimal solution in the local search phase are iteratively executed through the adjusted probability amplitude of the quantum bit and the updated pheromone until the maximum number of iterations is reached, and a plurality of second global optimal target solutions are obtained as the outputs of each global optimal solution searched by the quantum ant colony algorithm that introduces a multi-stage search strategy.

5. A method for planning load adjustment in a distribution network according to claim 4, characterized in that: The first quantum rotating gate adjustment coefficient is expressed by the following formula: Where λ(t) is the adjustment coefficient of the first quantum rotating gate; λ0 is the initial quantum gate rotating gate coefficient after initialization; λ max is the maximum value of the adjustment coefficient of the first quantum rotating gate in the global search phase; t is the number of iterations; T1 is the number of iterations in the global search phase; The volatility coefficient of the first pheromone is expressed by the following formula: Where, ρ(t) is the volatility coefficient of the first pheromone; ρ0 is the initial pheromone volatility coefficient after initialization; ρ max is the maximum value of the first pheromone volatility coefficient in the global search stage.

6. A method for planning load adjustment in a distribution network according to claim 4, characterized in that: The second quantum rotating gate adjustment coefficient is expressed by the following formula: In the formula, λ * (t) is the adjustment coefficient of the second quantum rotating gate; λ max , min are the maximum and minimum values ​​of the adjustment coefficient of the second quantum rotating gate in the local search phase respectively; The volatility coefficient of the second pheromone is expressed by the following formula: In the formula, ρ * (t) is the volatility coefficient of the second pheromone; ρ max , min are respectively the maximum and minimum values ​​of the volatility coefficient of the second pheromone in the local search stage.

7. A method for planning load adjustment in a distribution network according to claim 3, characterized in that: The method of optimizing each of the global optimal solutions by a simulated annealing algorithm to obtain a number of new solutions to update each of the global optimal solutions includes: Performing neighborhood perturbations on each of the global optimal solutions to obtain a number of neighborhood solutions; Based on the fitness function, quantify the difference between the fitness value of each of the global optimal solutions and the fitness value of each of the neighborhood solutions; According to the difference, whether to accept the neighborhood solution is determined by the Metropolis criterion, so as to update each of the global optimal solutions.

8. A load adjustment planning system for a distribution network, characterized in that: include: A model building module, used to build a distribution network load adjustment planning model, and determine the objective function and constraint conditions of the load adjustment planning model; A strategy solving module is used to solve the load adjustment planning model of the substation using an optimization and improvement algorithm based on the objective function and the constraints, and obtain the load adjustment planning strategy for all substations in the distribution network for execution; the optimization and improvement algorithm is configured to be formed by combining a quantum ant colony algorithm that introduces a multi-stage search strategy with a simulated annealing algorithm.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for planning load adjustment for a distribution network as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for planning load adjustment for a distribution network as described in any one of claims 1 to 7 is implemented.

Images