A distributed power supply planning method and device, electronic equipment and storage medium

Abstract

The application provides a distributed power supply planning method and device, electronic equipment and storage medium, and belongs to the field of distribution network planning. The method comprises the following steps: screening the optional nodes of the distributed power supply to be planned based on the small world theory to obtain the candidate nodes, and determining the solution space according to the candidate nodes; constructing an optimization objective function and a constraint condition, initializing the to-be-planned variable of the distributed power supply to be planned to obtain an initial Onomarchus population, improving the Onomarchus algorithm of the initial Onomarchus population through an adaptive weight and a Levy flight strategy to obtain a child population, determining the population fitness of the child population according to the optimization objective function and screening to obtain a new round of Onomarchus population, and iteratively optimizing to obtain optimal planning variables. The important node screening through the small world theory can effectively reduce the solution dimension, the adaptive weight and the Levy flight strategy can improve the convergence speed and the global search ability of the algorithm, and the fast and accurate solution of the distributed power supply planning problem is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network planning, and particularly relates to a distributed power supply planning method and device, an electronic device and a storage medium. BACKGROUND

[0002] With the development of low-carbon energy, photovoltaic and wind power and other distributed power supplies as important green energy in the power grid are becoming more and more important. Distributed power supply can effectively supplement the traditional centralized power supply mode and realize the optimal allocation of resources. Distributed power supply planning is a crucial preliminary work in the development planning of power systems, including the planning of the access location and capacity of distributed power supply. A reasonable distributed power supply planning method can make full use of existing resources, technologies and facilities, and improve the power quality and stability of the distribution network.

[0003] In the planning of distributed power supply, the existing technology usually uses a multi-objective genetic algorithm or other heuristic algorithm to solve after establishing a site selection and capacity optimization model. However, due to the large number of optional locations of distributed power supply, the solution space of distributed power supply planning is large, especially as the scale of distributed power supply expands, the number of nodes of distributed power supply planning increases and the network structure becomes complex, the large solution space will significantly increase the difficulty of solving, and thus the existing algorithm performs poorly in terms of solving speed and solving accuracy.

[0004] Therefore, the existing technology has the technical problem that the solution space of distributed power supply planning is too large, and the existing optimization algorithm is difficult to quickly and accurately solve, which needs to be improved. SUMMARY

[0005] Therefore, it is necessary to provide a distributed power supply planning method and device, an electronic device and a storage medium to solve the technical problem that the solution space of distributed power supply planning is too large and the existing optimization algorithm is difficult to quickly and accurately solve in the prior art.

[0006] To solve the above technical problems, on the one hand, the present application provides a distributed power supply planning method, comprising:

[0007] Based on the small world theory, the optional nodes of the distributed power supply to be planned are screened to obtain candidate nodes, and the solution space is determined according to the candidate nodes;

[0008] An optimization objective function and constraint condition of the distributed power supply to be planned are constructed, the initial Onthophagus population of the distributed power supply to be planned is initialized, the Onthophagus algorithm is optimized by self-adaptive weight and Levy flight strategy in the solution space to obtain the offspring population, the population fitness of the offspring population is determined according to the optimization objective function, the new Onthophagus population is screened from the offspring population according to the population fitness, and the optimal planning variable is obtained by iterative optimization.

[0009] In a possible implementation, the important node screening of the optional nodes of the to-be-planned distributed power based on the small-world theory obtains the candidate nodes, including:

[0010] The power loss improvement rate, the betweenness centrality and the closeness centrality of each optional node of the to-be-planned distributed power are sequentially calculated;

[0011] The node screening of the optional nodes is performed according to the power loss improvement rate, the betweenness centrality, the closeness centrality and a preset screening ratio to obtain the screened nodes;

[0012] The adjacent node filtering and the branch node supplement are performed on the screened nodes to obtain the candidate nodes.

[0013] In a possible implementation, the optimization objective function includes a total active power loss objective function, a voltage stability objective function and a total capacity objective function; and the constraint conditions include a power balance constraint, a node voltage constraint, a power supply capacity constraint and a total installed capacity constraint.

[0014] In a possible implementation, the to-be-planned variables of the to-be-planned distributed power are initialized to obtain an initial formica population, including:

[0015] The to-be-planned variables of the to-be-planned distributed power are initialized based on a chaotic mapping to obtain the initial formica population;

[0016] The to-be-planned variables include site selection and capacity determination.

[0017] In a possible implementation, the initial formica population is optimized in a solution space by using a self-adaptive weight and Levy flight strategy improved formica algorithm to obtain a child population, including:

[0018] The initial formica population is sequentially updated by using a self-adaptive weight rolling ball behavior simulation population update, a breeding behavior simulation population update and a Levy flight strategy stealing behavior simulation population update in the solution space to obtain the child population.

[0019] In a possible implementation, the self-adaptive weight rolling ball behavior simulation population update includes:

[0020] A position update weight is determined based on a current iteration number and a preset maximum iteration number;

[0021] The initial formica population is weighted and updated by using the rolling ball behavior simulation according to the position update weight to update the individual positions of the initial formica population.

[0022] In a possible implementation, the Levy flight strategy stealing behavior simulation population update includes:

[0023] generate a first random direction vector and a second random direction vector in a preset parameter range, and determine a Levy disturbance step length according to the first random direction vector and the second random direction vector;

[0024] perform a Levy disturbance foraging behavior simulation on the initial formicidae population according to the disturbance step length, and update individual positions of the initial formicidae population.

[0025] In another aspect, the present application also provides a distributed power supply planning device, comprising:

[0026] A node screening unit is configured to perform important node screening on selectable nodes of the distributed power supply to be planned based on a small-world theory to obtain candidate nodes, and determine a solution space according to the candidate nodes.

[0027] A formicidae algorithm optimization unit is configured to construct an optimization objective function and constraint conditions of the distributed power supply to be planned, initialize to-be-planned variables of the distributed power supply to be planned to obtain an initial formicidae population, perform adaptive weight and Levy flight strategy improvement on the initial formicidae population in the solution space to obtain a child population, determine population fitness of the child population according to the optimization objective function, screen the child population according to the population fitness to obtain a new round of formicidae population, and iteratively optimize to obtain optimal planning variables.

[0028] In another aspect, the present application also provides an electronic device, comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the distributed power supply planning method described above when executing the program.

[0029] In another aspect, the present application also provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the distributed power supply planning method described above.

[0030] The present application has the following beneficial effects: in the distributed power supply planning method provided by the present application, first, important node screening is performed on selectable nodes of the distributed power supply to be planned based on a small-world theory to obtain candidate nodes, and a solution space is determined according to the candidate nodes; then, an optimization objective function and constraint conditions of the distributed power supply to be planned are constructed, to-be-planned variables of the distributed power supply to be planned are initialized to obtain an initial formicidae population, adaptive weight and Levy flight strategy improvement are performed on the initial formicidae population in the solution space to obtain a child population, population fitness of the child population is determined according to the optimization objective function, a new round of formicidae population is obtained by screening the child population according to the population fitness, and optimal planning variables are obtained by iteratively optimizing. The present application can effectively reduce the solution dimension by performing important node screening on the selectable nodes based on the small-world theory, and can improve the convergence speed and global search ability of the algorithm by adaptive weight and Levy flight strategy, thereby realizing fast and accurate solution of the distributed power supply planning problem. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description only represent some of the embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0032] Figure 1 A flowchart of an embodiment of the distributed power supply planning method provided by the present application;

[0033] Figure 2 A flowchart of the important node screening of the small world theory in the embodiment of the present application;

[0034] Figure 3 A flowchart of the self-adaptive weight rolling ball simulation population updating in the embodiment of the present application;

[0035] Figure 4 A flowchart of the Lévy flight strategy stealing behavior simulation population updating in the embodiment of the present application;

[0036] Figure 5 A voltage distribution diagram of a distribution network node;

[0037] Figure 6 An active power loss improvement result diagram of a distribution network;

[0038] Figure 7 A structural diagram of an embodiment of the distributed power supply planning device provided by the present application;

[0039] Figure 8 A structural diagram of an embodiment of the electronic device provided by the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only represent some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without any creative effort belong to the scope of protection of the present application.

[0041] In the description of the embodiments of the present application, unless otherwise specified, the meaning of “a plurality of” is two or more. The association relationship of the associated objects is described by “and / or”, which means that there can be three kinds of relationships, for example: A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone.

[0042] The terms "first", "second", and the like in the description of embodiments herein do not necessarily mean or imply that the corresponding parts are either the first or the second in importance or imply the number of the corresponding parts. Therefore, the technical features defined with "first" and "second" can explicitly or implicitly include at least one of the features.

[0043] Reference herein to "embodiments" means that a particular feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive or alternative embodiments. It is explicitly and implicitly understood that the embodiments described herein can be combined with each other.

[0044] The application provides a distributed power supply planning method and device, electronic equipment and storage medium, which are described below.

[0045] Figure 1 An embodiment of the distributed power supply planning method provided by the application is shown in the flowchart as shown in the figure. Figure 1 The distributed power supply planning method comprises the following steps.

[0046] S101, selecting an important node from the optional nodes of the distributed power supply to be planned based on the small world theory to obtain a candidate node, determining a solution space according to the candidate node;

[0047] S102, constructing an optimization objective function and a constraint condition of the distributed power supply to be planned, initializing a to-be-planned variable of the distributed power supply to be planned to obtain an initial Onthophagus population, optimizing the initial Onthophagus population in the solution space by using an improved Onthophagus algorithm with adaptive weight and Levy flight strategy to obtain a child population, determining a population fitness of the child population according to the optimization objective function, screening the child population according to the population fitness to obtain a new round of Onthophagus population, and iteratively optimizing to obtain an optimal planning variable.

[0048] Compared with the prior art, the distributed power supply planning method provided by the embodiment of the application firstly screens the optional nodes of the distributed power supply to be planned based on the small world theory to obtain the optional nodes, and determines the solution space according to the optional nodes; then, the optimization objective function and the constraint condition of the distributed power supply to be planned are constructed, the variable to be planned of the distributed power supply to be planned is initialized to obtain the initial Onomarchus population, the initial Onomarchus population is optimized in the solution space by using the self-adaptive weight and the Levy flight strategy to improve the Onomarchus algorithm to obtain the offspring population, the population fitness of the offspring population is determined according to the optimization objective function, the offspring population is screened according to the population fitness to obtain a new round of Onomarchus population, and the optimal planning variable is obtained by iterative optimization. The small world theory is used to screen the important nodes of the optional nodes, so that the solution dimension can be effectively reduced. The self-adaptive weight and the Levy flight strategy are used to improve the convergence speed and the global search ability of the algorithm, so that the distributed power supply planning problem can be quickly and accurately solved.

[0049] In some embodiments of the application, Figure 2 The flowchart of the important node screening of the small world theory of the embodiment of the application is shown in Figure 2 The small world theory is used to screen the important nodes of the optional nodes of the distributed power supply to be planned to obtain the optional nodes, which includes:

[0050] S201, the power loss improvement rate, the betweenness centrality and the closeness centrality of each optional node of the distributed power supply to be planned are calculated in sequence;

[0051] S202, the optional nodes are screened according to the power loss improvement rate, the betweenness centrality, the closeness centrality and the preset screening ratio to obtain the screened nodes;

[0052] S203, the screened nodes are filtered by the adjacent nodes and supplemented by the branch nodes to obtain the optional nodes.

[0053] Specifically, considering that there are many optional positions of the distributed power supply in the distributed power supply planning problem, the solution space of the distributed power supply planning is large, and the solution difficulty is high, the embodiment first screens the optional access nodes from the two angles of the active power loss improvement effect of the distribution network and the importance of the nodes in the distribution network, determines the optional node positions, and thus reduces the solution dimension.

[0054] The active power loss improvement rate formula is expressed as:

[0055]

[0056] Wherein, P represents the original active power loss of the distribution network, P represents the active power loss after the distributed power supply is connected to the i th node, P represents the active power loss after the distributed power supply is connected to the i th node, The smaller the value is, the better the improvement effect of the node accessing the distributed power supply is.

[0057] According to the small-world theory concept, there is a correlation between the clustering coefficient and the average path length of a network, and the distribution network has a high clustering coefficient and a short average path length at the same time. Therefore, embodiments utilize the betweenness centrality and closeness centrality in the small-world theory to evaluate the importance of a node in the distribution network. The betweenness centrality measures the frequency of a node as an intermediate node in the shortest path between other node pairs, and the node with high betweenness centrality plays a bridge role in the distribution network, improving connectivity and energy transmission efficiency; the closeness centrality measures the average shortest path length of a node to all other nodes in the network, and the node with high closeness centrality is located at the center position of the distribution network and is more easily connected to other nodes, promoting rapid energy transmission.

[0058] In the screening process, embodiments first arrange all the nodes in the distribution network in ascending order according to the active loss improvement rate , and set a screening ratio according to the scale of the distribution network, select a certain node according to the screening ratio, and take the top 50% in the embodiments. Then the betweenness centrality and the closeness centrality are calculated in these selected nodes, and are arranged in descending order respectively, and then screened according to the screening ratio, and the union of the top 50% of each is taken in the embodiments. Then embodiments supplement the nodes with a higher proportion of load in the distribution network on this basis, and considering the influence of the access of the distributed power supply on the adjacent load nodes, the distributed power supply layout should not be too concentrated, so in the adjacent nodes of the candidate nodes, embodiments only select nodes with lower values. Finally, check whether all branches in the distribution network have candidate nodes. For the branches without distributed power supply candidate nodes, calculate the proportion of the load of the branch to the total load, and if the proportion exceeds the inverse of the number of the distributed power supply to be accessed, supplement the node with the smallest value in the branch.

[0059] In some embodiments of the application, the optimization objective function includes a total active loss objective function, a voltage stability objective function and a total capacity objective function; the constraint conditions include power balance constraints, node voltage constraints, power supply capacity constraints and total installed capacity constraints.

[0060] Specifically, in the distributed power supply planning, the total active loss, voltage stability and total capacity of the distribution network need to be considered comprehensively, and embodiments take these three indexes as optimization objectives to construct an optimization objective function, wherein:

[0061] The total active loss objective function of the distribution network is expressed by the formula as follows:

[0062]

[0063] wherein, denotes the total number of branches of the power distribution network, denotes the current of the th branch, denotes the resistance of the th branch.

[0064] Power flow calculation is a fundamental and important calculation in power system analysis, which is based on the principle of solving the steady-state operating state parameters of the power system by mathematical method under given power grid structure and operating conditions. In power flow calculation, Newton-Raphson method is one of the most commonly used methods, which is embodied in the solution of power imbalance and Jacobian matrix, and its expression is:

[0065]

[0066] wherein, and respectively represent the partial derivative of active power with respect to voltage phase angle and voltage amplitude, and respectively represent the partial derivative of reactive power with respect to voltage phase angle and voltage amplitude, and respectively represent the phase angle change and voltage change, and respectively represent the node active and reactive power imbalance.

[0067] In order to eliminate the phase angle change and only study the relationship between voltage stability and node power, the Jacobian matrix is simplified, and the simplified Jacobian matrix is:

[0068]

[0069] Eigenvalue analysis can evaluate the stability of the system, and the larger the eigenvalue derivative is, the closer the system is to an unstable state. Therefore, the embodiments can reflect the voltage stability of the power distribution network under different distributed power access conditions by constructing a voltage stability objective function combined with eigenvalue information and node power change, the smaller the value of the voltage stability objective function is, the higher the voltage stability of the power distribution network is. The formula of the voltage stability objective function is:

[0070]

[0071] wherein, is the eigenvalue of the simplified Jacobian matrix , and is the absolute value of the node reactive power imbalance.

[0072] The total capacity objective function of the distributed power source is expressed as:

[0073]

[0074] in, represents the total number of nodes in the distribution network, Representation node Distributed power capacity.

[0075] Then, the constraints of the distributed power planning problem are established, including power balance constraints, node voltage constraints, power capacity constraints and total installed capacity constraints, where:

[0076] The power balance constraint formula is expressed as:

[0077]

[0078] in, and Represents nodes respectively The active injection power and reactive injection power of Representation node The voltage amplitude, Representation and Node The number of directly connected nodes, Representation and Node directly connected nodes, 、 and Representation node and nodes The conductance, susceptance and phase angle difference between them.

[0079] The node voltage constraint formula is expressed as:

[0080]

[0081] in, represents the total number of nodes in the distribution network, and Representation node The upper and lower voltage limits at the .

[0082] The power capacity constraint formula of a single distributed power source is expressed as:

[0083]

[0084] in, Representation node The distributed power capacity, Indicates the maximum capacity of distributed power generation.

[0085] The total installed capacity constraint refers to that the total installed capacity of the distributed power supply should not exceed the pre-designed value of the distribution network, and is expressed by a formula as follows:

[0086]

[0087] wherein, is the new energy penetration rate set for the distribution network, represents the total active load in the distribution network.

[0088] In some embodiments of the present application, the initial Mutilon population is obtained by initializing the to-be-planned variables of the to-be-planned distributed power supply, and the initialization includes:

[0089] The initial Mutilon population is obtained by initializing the to-be-planned variables of the to-be-planned distributed power supply based on chaotic mapping;

[0090] The to-be-planned variables include site selection and capacity determination.

[0091] Specifically, to further improve the speed and accuracy of the distributed power supply planning solution, the embodiments use an improved Mutilon optimization algorithm for solution. To improve the diversity of the initial population, the embodiments introduce chaotic mapping to initialize the Mutilon population, and the chaotic mapping formula is expressed as:

[0092]

[0093] wherein, is the population number, is the expansion coefficient of the chaotic mapping, and the value range is In the embodiments, the value is 0.49.

[0094] Based on the chaotic mapping, the expression of the population is:

[0095]

[0096] wherein, and respectively represent the upper and lower boundaries of the to-be-optimized variables. In the embodiments, the to-be-optimized variables include site selection and capacity determination of the distributed power supply.

[0097] In some embodiments of the present application, the initial Mutilon population is optimized in the solution space to obtain a child population by using the self-adaptive weight and Levy flight strategy improved Mutilon algorithm, and the optimization includes:

[0098] The initial Mutilon population is sequentially updated by using the self-adaptive weight, the ball rolling behavior simulation, the breeding behavior simulation and the Levy flight strategy stealing behavior simulation in the solution space to obtain the child population.

[0099] Specifically, the dung beetle optimization algorithm updates the positions of individual dung beetle populations through simulations of rolling ball behavior, reproduction behavior, and stealing behavior. To achieve faster solution speed and higher accuracy, the embodiment improves the rolling ball behavior simulation through adaptive weighting and the stealing behavior simulation through the Lévy flight strategy, thereby increasing the algorithm's convergence speed and global search capabilities.

[0100] In the dung beetle optimization algorithm before the improvement, the rolling ball dung beetle will randomly select a direction in the global search space and move forward in a straight line based on external environmental factors. In the absence of obstacles, the expression for the dung beetle's position update is:

[0101]

[0102] in, is the number of iterations, For the Dung beetle The position at the iteration, and is the weight, and , . It is a state variable. When it takes a value of 1, it means there is no position offset. When it takes a value of -1, it means there is a position offset. represents the global worst position, Used to simulate changes in the external environment.

[0103] When there are obstacles, the expression for updating the dung beetle's position is:

[0104]

[0105] in, is the turning angle of the dung beetle and ,when is 0, and When the dung beetle moves, its position remains unchanged.

[0106] In the simulation of reproductive behavior, dung beetles will roll their dung balls to a safe area during reproduction, providing a better birth environment for their offspring. The boundary update formula for the breeding area is:

[0107]

[0108] in, represents the current local optimal position, and represents the upper and lower bounds of the variable to be optimized, is an inertia weight variable, which is related to the number of iterations. Indicates the maximum number of iterations set.

[0109] In the breeding area, the female dung beetle will produce a new egg in each iteration. The breeding area will also be dynamically updated in each iteration. The expression for updating the position of the breeding ball is:

[0110]

[0111] in, Indicates the The position of the breeding ball after iterations, and For two dimensional row vector, is the number of decision variables in the model to be solved.

[0112] After hatching, the young dung beetles will start to forage on their own. The boundary conditions of the foraging area are:

[0113]

[0114] in, and represent the upper and lower boundaries of the foraging area, respectively. represents the global optimal position.

[0115] The position update expression of the dung beetle is:

[0116]

[0117] in, Indicates the A small dung beetle The position at the iteration, is a normally distributed random number, is a random vector between 0 and 1.

[0118] The stealing behavior simulation means that there are some thieves in the dung beetle group, which will steal the food of the other dung beetles. The expression of their position update is:

[0119]

[0120] in, Indicates the The thief in The position at the iteration, For a normal distribution Random vectors; Is a fixed value. Since the thief's goal is the best food, its position is constantly updated and it will eventually get the optimal position .

[0121] In some embodiments of the present invention,Figure 3 A flowchart of the population update of the adaptive weight rolling ball simulation of an embodiment of the present application is shown in FIG. 3, which includes the following steps: Figure 3 The population update of the adaptive weight rolling ball simulation includes:

[0122] S301, determining a position update weight based on a current iteration number and a preset maximum iteration number;

[0123] S302, performing a weighted rolling ball simulation on the initial melolontha population according to the position update weight to update the individual positions of the initial melolontha population.

[0124] Specifically, in the melolontha optimization algorithm, the update of the melolontha position is greatly affected by the value of the weight The embodiment modifies into a variable that changes with the iteration number, which is expressed by the following formula:

[0125]

[0126] wherein and represent the maximum value and the minimum value of In the embodiment, the maximum value is set to 0.9 and the minimum value is set to 0.1, is the current iteration number, is the preset maximum iteration number.

[0127] Substituting into the melolontha position update formula, a new position formula is obtained:

[0128]

[0129] The embodiment sets the adaptive weight , which can make the position update step of the rolling ball melolontha large at the early stage of iteration, and gradually reduce the step with the increase of the iteration number, so as to balance the global and local search capabilities and improve the speed and accuracy of the model solution.

[0130] In some embodiments of the present application, Figure 4 A flowchart of the population update of the Levy flight strategy theft behavior simulation of an embodiment of the present application is shown in FIG. 4, which includes the following steps: Figure 4 The population update of the Levy flight strategy theft behavior simulation includes:

[0131] S401, generating a first random direction vector and a second random direction vector in a preset parameter range, and determining a Levy disturbance step length according to the first random direction vector and the second random direction vector;

[0132] S402, performing a Levy disturbance theft behavior simulation on the initial melolontha population according to the disturbance step length to update the individual positions of the initial melolontha population.

[0133] Specifically, in the dung beetle algorithm, the thief will update the current local optimal position , but if the algorithm has fallen into a local optimal solution, it will be in a state of stagnation. To this embodiment, the Levy flight strategy is introduced to update the position of the thief, thereby expanding the search space of part of the thieves and jumping out of the local optimal solution. The Levy disturbance step calculation formula is represented as:

[0134]

[0135] wherein, , is a first random direction vector, obeying distribution, is a second random direction vector, obeying distribution. is obtained by the following formula:

[0136]

[0137] wherein, .

[0138] The position expression of the thief finally introduced the Levy flight strategy is:

[0139]

[0140] Finally, in order to verify the effectiveness of the present application, the embodiment compares the IDBO (Improved Dung Beetle Optimizer) of the present application and the DBO (Dung Beetle Optimizer) and the GA (Genetic Algorithms), and obtains Figure 5 and Figure 6 results, wherein Figure 5 is the voltage distribution diagram of the power distribution network under the three algorithms, Figure 6 is the active loss improvement result diagram of the power distribution network under the three algorithms. According to Figure 5 and Figure 6 , it can be seen that compared with the prior art, the present application is obviously superior to the prior art in voltage distribution and active loss improvement.

[0141] In summary, in order to improve the speed and accuracy of distributed power supply planning solution, the application first performs important node screening on the optional nodes of the distributed power supply to be planned based on the small world theory to obtain candidate nodes, and determines the solution space according to the candidate nodes; then constructs the optimization objective function and constraint condition of the distributed power supply to be planned, initializes the to-be-planned variables of the distributed power supply to be planned to obtain an initial Onthophagus population, performs Onthophagus algorithm optimization on the initial Onthophagus population in the solution space by using the adaptive weight and Levy flight strategy to obtain a child population, determines the population fitness of the child population according to the optimization objective function, screens the child population according to the population fitness to obtain a new round of Onthophagus population, and iteratively optimizes to obtain optimal planning variables. The application can effectively reduce the solution dimension by performing important node screening on the optional nodes based on the small world theory, and can improve the convergence speed and global search ability of the algorithm by using the adaptive weight and Levy flight strategy, so as to realize fast and accurate solution of the distributed power supply planning problem.

[0142] In order to better implement the distributed power supply planning method in the embodiments of the application, on the basis of the distributed power supply planning method, as shown in Figure 7 the application further provides a distributed power supply planning device. The distributed power supply planning device 700 comprises:

[0143] a node screening unit 701 configured to perform important node screening on the optional nodes of the distributed power supply to be planned based on the small world theory to obtain candidate nodes, and determine the solution space according to the candidate nodes;

[0144] an Onthophagus algorithm optimization unit 702 configured to construct the optimization objective function and constraint condition of the distributed power supply to be planned, initialize the to-be-planned variables of the distributed power supply to be planned to obtain an initial Onthophagus population, perform Onthophagus algorithm optimization on the initial Onthophagus population in the solution space by using the adaptive weight and Levy flight strategy to obtain a child population, determine the population fitness of the child population according to the optimization objective function, screen the child population according to the population fitness to obtain a new round of Onthophagus population, and iteratively optimize to obtain optimal planning variables.

[0145] The distributed power supply planning device 700 provided by the above embodiments can implement the technical solutions described in the distributed power supply planning method embodiments described above, and the principles of implementation of the above modules or units can be referred to the corresponding content in the distributed power supply planning method embodiments described above, which will not be described herein again.

[0146] As shown in Figure 8 the application further correspondingly provides an electronic device 800. The electronic device 800 comprises a processor 801, a memory 802 and a display 803. Figure 8 Only part of the components of the electronic device 800 are shown, but it should be understood that all the shown components are not required, and more or fewer components can be alternatively implemented.

[0147] The processor 801 can be a central processing unit (CPU), a microprocessor, or other data processing chip in some embodiments, for running program codes stored in the memory 802 or processing data, such as the distributed power planning method in the present application.

[0148] In some embodiments, the processor 801 can be a single server or a group of servers. The group of servers can be centralized or distributed. In some embodiments, the processor 801 can be local or remote. In some embodiments, the processor 801 can be implemented in a cloud platform. In an embodiment, the cloud platform can include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0149] The memory 802 can be an internal storage unit of the electronic device 800, such as a hard disk or a memory of the electronic device 800 in some embodiments. The memory 802 can also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 800 in other embodiments.

[0150] Further, the memory 802 can include both the internal storage unit and the external storage device of the electronic device 800. The memory 802 is used to store application software installed on the electronic device 800 and various types of data.

[0151] The display 803 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, etc. in some embodiments. The display 803 is used to display information of the electronic device 800 and to display a visualized user interface. The components 801-803 of the electronic device 800 communicate with each other through a system bus.

[0152] In an embodiment, when the processor 801 executes the distributed power planning program in the memory 802, the following steps can be implemented:

[0153] Based on the small-world theory, the important nodes of the optional nodes of the distributed power to be planned are screened to obtain the candidate nodes, and the solution space is determined according to the candidate nodes;

[0154] The optimization objective function and constraint condition of the to-be-planned distributed power are constructed, the to-be-planned variables of the to-be-planned distributed power are initialized to obtain an initial Onomarchus population, the initial Onomarchus population is optimized in a solution space by using an improved Onomarchus algorithm with adaptive weight and Levy flight strategy to obtain a child population, the population fitness of the child population is determined according to the optimization objective function, the child population is screened according to the population fitness to obtain a new round of Onomarchus population, and the optimal planning variable is obtained through iterative optimization.

[0155] It should be understood that, in addition to the above functions, the processor 801 can also implement other functions when executing the distributed power planning program in the memory 802, which can be specifically understood in the description of the corresponding method embodiments.

[0156] Further, the type of the electronic device 800 is not specifically limited, and the electronic device 800 can be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or the like. Exemplary embodiments of the portable electronic device include, but are not limited to, a portable electronic device running an IOS, android, microsoft, or other operating system. The above-mentioned portable electronic device can also be other portable electronic devices, such as a laptop computer having a touch-sensitive surface (e.g., a touch panel). It should also be understood that, in some other embodiments of the present application, the electronic device 800 can also be a desktop computer having a touch-sensitive surface (e.g., a touch panel).

[0157] Correspondingly, the embodiments of the present application also provide a computer readable storage medium for storing computer readable programs or instructions, which can realize the steps or functions in the distributed power planning method provided by the above method embodiments when the programs or instructions are executed by a processor.

[0158] Those skilled in the art can understand that all or part of the processes of the above-mentioned embodiments can be completed by a computer program to instruct related hardware (such as a processor, a controller, etc.) to complete, and the computer program can be stored in a computer readable storage medium. The computer readable storage medium is a disk, an optical disk, a read-only memory or a random access memory, etc.

[0159] The distributed power supply planning method, device, electronic equipment and storage medium provided by the present application are described in detail above, the principles and implementation modes of the present application are described by applying specific examples in this paper, and the above example is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as a limitation of the present application.

Claims

1. A distributed power planning method, characterized in that: include: Based on the small-world theory, important nodes are screened for optional nodes of the planned distributed power source to obtain candidate nodes, including: sequentially calculating the active loss improvement rate, betweenness centrality, and closeness centrality of each optional node of the planned distributed power source; screening the optional nodes according to the active loss improvement rate, the betweenness centrality, the closeness centrality, and a preset screening ratio to obtain screening nodes; and determining a solution space based on the candidate nodes; An optimization objective function and constraint conditions of the distributed power source to be planned are constructed, the variables to be planned of the distributed power source to be planned are initialized to obtain an initial dung beetle population, the initial dung beetle population is optimized by an improved dung beetle algorithm using adaptive weights and Levy flight strategies in the solution space to obtain an offspring population, the population fitness of the offspring population is determined according to the optimization objective function, the offspring population is screened according to the population fitness to obtain a new round of dung beetle population, and the optimal planning variables are obtained through iterative optimization.

2. The distributed power planning method according to claim 1, characterized in that: The optimization objective function includes a total active power loss objective function, a voltage stability objective function and a total capacity objective function; the constraint conditions include a power balance constraint, a node voltage constraint, a power supply capacity constraint and a total installed capacity constraint.

3. The distributed power planning method according to claim 1, characterized in that: Initializing the variables to be planned of the distributed power source to be planned to obtain an initial dung beetle population includes: Initializing the variables to be planned of the distributed power source to be planned based on the chaotic map to obtain an initial dung beetle population; The variables to be planned include site selection and capacity determination.

4. The distributed power planning method according to claim 1, characterized in that: The step of optimizing the initial dung beetle population by using an adaptive weight and Lévy flight strategy to improve the dung beetle algorithm in the solution space to obtain a progeny population includes: In the solution space, the initial dung beetle population is sequentially updated with adaptive weighted rolling ball behavior simulation population update, reproduction behavior simulation population update and Levy flight strategy stealing behavior simulation population update to obtain an offspring population.

5. The distributed power planning method according to claim 4, characterized in that: The adaptive weighted rolling ball behavior simulates population update, including: Determine a position update weight based on the current number of iterations and a preset maximum number of iterations; A weighted rolling ball behavior simulation is performed on the initial dung beetle population according to the position update weight to update the individual positions of the initial dung beetle population.

6. The distributed power planning method according to claim 4, characterized in that: The Levy flight strategy stealing behavior simulates population update, including: generating a first random direction vector and a second random direction vector within a preset parameter range, and determining a Levy perturbation step length according to the first random direction vector and the second random direction vector; The initial dung beetle population is subjected to a Levy disturbance stealing behavior simulation according to the disturbance step length, and the individual positions of the initial dung beetle population are updated.

7. A distributed power planning device, characterized in that: include: A node screening unit is used to screen important nodes of the optional nodes of the planned distributed power generation based on the small-world theory to obtain candidate nodes, including: sequentially calculating the active loss improvement rate, betweenness centrality and closeness centrality of each optional node of the planned distributed power generation; Screening the optional nodes according to the active power loss improvement rate, the betweenness centrality, the closeness centrality, and a preset screening ratio to obtain screening nodes; and determining a solution space according to the candidate nodes; A dung beetle algorithm optimization unit is used to construct an optimization objective function and constraint conditions for the distributed power source to be planned, initialize the variables to be planned for the distributed power source to be planned to obtain an initial dung beetle population, perform adaptive weight and Levy flight strategy optimization on the initial dung beetle population in the solution space to improve the dung beetle algorithm to obtain an offspring population, determine the population fitness of the offspring population according to the optimization objective function, screen the offspring population according to the population fitness to obtain a new round of dung beetle population, and iteratively optimize to obtain the optimal planning variables.

8. An electronic device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the distributed power supply planning method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the distributed power supply planning method according to any one of claims 1 to 6 is implemented.

Images