Power distribution network resource dispatching method and apparatus, and device and storage medium
Patent Information
- Application Number
- PCT/CN2025/127581
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-03-25
- Filing Date
- 2025-10-14
- Publication Date
- 2026-10-01
Smart Images
Figure CN2025127581_01102026_PF_FP_ABST
Abstract
Description
A method, apparatus, equipment and storage medium for power distribution network resource scheduling Technical Field
[0001] This invention relates to the field of power application technology, and in particular to a method, apparatus, equipment and storage medium for power distribution network resource scheduling. Background Technology
[0002] With the sustainable development of society, building a new power distribution network system based on clean energy is a future trend. The power industry is actively transforming its energy production and consumption patterns, optimizing its energy structure, and increasing the development of renewable energy. However, renewable energy (such as wind power and photovoltaic power) generation is greatly affected by weather, exhibiting intermittent, fluctuating, and random characteristics. When large-scale renewable energy is integrated into the power distribution network system, the demand for the network's dispatching capacity increases significantly.
[0003] Traditional power generation resource scheduling methods are slow to solve problems when faced with large-scale power grids and complex network structures, making it impossible to obtain better scheduling schemes in a timely manner to meet the real-time scheduling needs of the distribution network system. Summary of the Invention
[0004] This invention provides a distribution network resource scheduling method, apparatus, equipment, and storage medium to solve the problem that traditional power generation resource scheduling methods are slow to solve when facing large-scale power grids and complex network structures, and cannot meet the needs of real-time scheduling.
[0005] In a first aspect, embodiments of the present invention provide a method for scheduling resources in a power distribution network, the method comprising:
[0006] A distribution network resource scheduling model is constructed, which includes: a resource scheduling function and a set of scheduling constraints.
[0007] Construct a hierarchical partitioning problem of the scheduling constraint set, and solve the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set;
[0008] Based on the hierarchical partitioning results, the scheduling constraint set is hierarchically partitioned to obtain multiple scheduling constraint subsets.
[0009] Obtain current power data information, and solve the resource scheduling function in parallel based on each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information;
[0010] The schedulable resources of the distribution network are scheduled according to the distribution network resource scheduling information.
[0011] In a second aspect, embodiments of the present invention provide a power distribution network resource scheduling device, the device comprising:
[0012] The model building module is used to build a distribution network resource scheduling model, which includes: a resource scheduling function and a set of scheduling constraints.
[0013] The problem construction and solution module is used to construct the hierarchical partitioning problem of the scheduling constraint set, and solve the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set.
[0014] The hierarchical partitioning module is used to hierarchically partition the set of scheduling constraints according to the hierarchical partitioning result, thereby obtaining multiple subsets of scheduling constraints.
[0015] The information determination module is used to acquire current power data information, and to solve the resource scheduling function in parallel according to each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information.
[0016] The resource scheduling module is used to schedule the schedulable resources of the distribution network according to the distribution network resource scheduling information.
[0017] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising:
[0018] At least one processor;
[0019] and a memory communicatively connected to the at least one processor;
[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the power distribution network resource scheduling method according to any embodiment of the present invention.
[0021] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute the power distribution network resource scheduling method described in any embodiment of the present invention.
[0022] The technical solution of this invention involves constructing a distribution network resource scheduling model, which includes a resource scheduling function and a set of scheduling constraints. The method constructs a hierarchical partitioning problem of the scheduling constraint set, solves the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set, and further partitions the scheduling constraint set hierarchically according to the hierarchical partitioning result to obtain multiple subsets of scheduling constraints. It acquires current power data information, solves the resource scheduling function in parallel based on each subset of scheduling constraints and the current power data information, and obtains distribution network resource scheduling information. Finally, it schedules the schedulable resources of the distribution network according to the distribution network resource scheduling information. This method, by solving the hierarchical partitioning problem to hierarchically partition the scheduling constraint set into multiple subsets of scheduling constraints, and then solves the resource scheduling function in parallel based on each subset of scheduling constraints, decomposes the complex distribution network resource scheduling problem into multiple simple sub-problems for parallel solving. This improves the solution speed of the distribution network resource scheduling problem, shortens the time to obtain a better scheduling scheme, meets the real-time scheduling requirements of the distribution network system, and provides strong support for the subsequent implementation of large-scale renewable energy access to the distribution network system.
[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0025] Figure 1 is a flowchart of a power distribution network resource scheduling method provided in an embodiment of the present invention;
[0026] Figure 2 is a schematic diagram of an example of power node system resource configuration;
[0027] Figure 3 is a schematic diagram of the structure of a power distribution network resource scheduling device provided in an embodiment of the present invention;
[0028] Figure 4 shows a schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention. Detailed Implementation
[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0031] It should be noted that with the sustainable development of society, building a new type of distribution network system based on renewable energy (clean energy) is the future development trend. However, renewable energy has the characteristics of intermittency, volatility, and randomness. When a large number of renewable energy sources are connected to the distribution network system, the traditional power grid dispatching method is slow to solve problems when faced with large-scale power grids and complex network structures. This makes it impossible to obtain better dispatching schemes in a timely manner to meet the needs of real-time dispatching, thus bringing potential risks to the reliability and safety of power grid operation.
[0032] Based on this, the present invention provides a distribution network resource scheduling method. Figure 1 is a flowchart of a distribution network resource scheduling method provided by the present invention. The present invention can be applied to scenarios where various complex situations and changes occur in the power grid, and a better scheduling scheme can be quickly obtained. The method can be executed by a distribution network resource scheduling device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, preferably a mobile terminal, desktop computer, laptop computer, or server.
[0033] As shown in Figure 1, the power distribution network resource scheduling method provided in this embodiment of the invention may specifically include:
[0034] S101. Construct a distribution network resource scheduling model, which includes: resource scheduling function and scheduling constraint set.
[0035] The distribution network resource scheduling model can be understood as a model used to analyze and schedule the output of each generating unit in the distribution network. The resource scheduling function can be understood as a function used to determine the optimal resource scheduling scheme. This function can be guided by one or more optimization objectives, such as minimizing operating costs, maximizing resource utilization, minimizing voltage deviation, and / or minimizing active power loss. The scheduling constraint set can be understood as a series of restrictions that the scheduling scheme must satisfy to ensure the feasibility, safety, and / or economy of the scheduling scheme. These constraints may include line power flow constraints, voltage constraints, and power constraints of generating units.
[0036] In this embodiment, a resource scheduling function is constructed by determining the optimization objective of the current scenario and the decision variables involved, and a suitable set of scheduling constraints is set. Based on the resource scheduling function and the set of scheduling constraints, a distribution network resource scheduling model is built. For example, to ensure the safe operation of the distribution network system and simultaneously respond to the dual-carbon objective, the optimization objective can be defined as minimizing voltage deviation, maximizing distributed generation output, and minimizing active power loss. The decision variables can be defined as distributed generation output, stable generation output, and reactive power compensation. The set of scheduling constraints can be defined to include voltage constraints, power flow constraints, security constraints, and adjustable resource output constraints.
[0037] It is understandable that distributed power sources can use new energy sources such as photovoltaics and wind power, and reactive power compensation devices can use static var compensators (SVCs), switched capacitor banks (CBs), etc.
[0038] S102. Construct a hierarchical partitioning problem of the scheduling constraint set, and solve the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set.
[0039] The hierarchical partitioning problem can be understood as the problem of rationally dividing the set of scheduling constraints to achieve a specific goal. This specific goal could be minimizing the execution time, resource consumption, and / or execution complexity of the scheduling constraints. The hierarchical partitioning result can be understood as a scheme for hierarchically partitioning the set of scheduling constraints, such as dividing constraints containing upper and lower bounds of parameters into one layer, or dividing constraints involving squared terms into another layer, etc.
[0040] In this embodiment, the specific implementation of constructing the hierarchical partitioning problem of the scheduling constraint set can be as follows: Based on the optimization objective corresponding to the scheduling constraint set, such as the shortest execution time, the least execution resource consumption, and / or the lowest execution complexity, the objective function corresponding to the scheduling constraint set is determined. Based on the objective function and the set constraint information (such as the upper and lower limits of execution time, the upper and lower limits of execution resource consumption, the upper and lower limits of execution complexity, and the limitations of the performance requirements of the distribution network system), the hierarchical partitioning problem of the scheduling constraint set is constructed. The hierarchical partitioning result is obtained by solving the hierarchical partitioning problem. In an optional embodiment, the hierarchical partitioning problem can be solved by an optimization algorithm.
[0041] S103. Based on the hierarchical partitioning results, the scheduling constraint set is hierarchically partitioned to obtain multiple subsets of scheduling constraints.
[0042] The scheduling constraint subset can be understood as the result of dividing the scheduling constraint set. The sum of all scheduling constraint subsets can constitute the complete scheduling constraint set, and each scheduling constraint subset contains at least one constraint.
[0043] In this embodiment, the scheduling constraint set is divided according to the hierarchical division result, resulting in multiple scheduling constraint subsets.
[0044] S104. Obtain current power data information, and solve the resource scheduling function in parallel based on each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information.
[0045] Among them, distribution network resource scheduling information can be understood as information used to provide a reference for scheduling the output of each schedulable resource in the distribution network.
[0046] In this embodiment, current power data information is acquired. This current power data information may include the number of distributed generation sources in the distribution network, the number of power nodes, the voltage of each power node, the active power injected into each power node by the distributed generation sources, the voltage phase angle difference between each power node, and the conductance, etc. Based on the current power data information and various subsets of scheduling constraints, the resource scheduling function is solved in parallel to obtain distribution network resource scheduling information relative to the current power data information.
[0047] S105. Schedule the schedulable resources of the distribution network according to the distribution network resource scheduling information.
[0048] In this embodiment, dispatchable resources and their reasonable output are determined based on distribution network resource scheduling information, thereby scheduling the actual output of the dispatchable resources. The dispatchable resources may include distributed power sources, stable power sources, and reactive power compensation devices.
[0049] This invention provides a distribution network resource scheduling method. The method involves constructing a distribution network resource scheduling model, which includes a resource scheduling function and a set of scheduling constraints. It then constructs a hierarchical partitioning problem of the scheduling constraint set, solves this problem to obtain the hierarchical partitioning result, and further partitions the scheduling constraint set hierarchically based on the result, resulting in multiple subsets of scheduling constraints. Next, it acquires current power data information and solves the resource scheduling function in parallel based on each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information. Finally, it schedules the schedulable resources of the distribution network based on this information. This method decomposes the complex distribution network resource scheduling problem into multiple simpler subproblems for parallel solving, thereby improving the solution speed, shortening the time to obtain a better scheduling scheme, meeting the real-time scheduling requirements of the distribution network system, and providing strong support for the subsequent integration of large-scale renewable energy into the distribution network system.
[0050] As a first optional embodiment of this example, based on the above embodiment, the construction of the distribution network resource scheduling model can be specified as the following steps:
[0051] a1) Obtain historical electrical data of the distribution network, and construct the resource scheduling function based on the historical electrical data.
[0052] In this embodiment, historical electrical data of the power distribution network within a certain period or time is obtained, and the resource scheduling function is constructed based on the historical electrical data.
[0053] As one implementation method, the historical electrical data includes the current voltage of each power node in the distribution network, the active power injected by the power source into each power node in the current period, the voltage phase angle difference and conductance between power nodes;
[0054] Correspondingly, this optional embodiment can further specify the construction of the resource scheduling function based on the historical electrical data as follows:
[0055] a11) Based on the current voltage and the corresponding ideal voltage of each power node, construct a first resource scheduling subfunction with the goal of minimizing voltage deviation.
[0056] a12) Based on the active power injected by the power source into each power node during the current period, construct a second resource scheduling subfunction with the goal of maximizing the output of the distributed power source.
[0057] a13) Based on the voltage phase angle difference, conductance, voltage amplitude of the power nodes and time interval, construct a third resource scheduling subfunction with the goal of minimizing the active power loss of the distribution network.
[0058] a14) The resource scheduling function is constructed based on the first resource scheduling sub-function, the second resource scheduling sub-function, and the third resource scheduling sub-function.
[0059] In this embodiment, the resource scheduling function composed of the first resource scheduling subfunction, the second resource scheduling subfunction, and the third resource scheduling subfunction can be specifically expressed as follows:
[0060] In the formula, f1, f2, and f3 are the first resource scheduling subfunction, the second resource scheduling subfunction, and the third resource scheduling subfunction, respectively; i is the power node number; N is the number of remaining power nodes excluding those connected to the schedulable resources; U i,t U represents the actual voltage of power node i at time t. i,ref N represents the ideal voltage at voltage node i at time t; G The number of distributed power sources in the distribution network; Let θ be the active power injected by the distributed generation at power node i at time t; T is the number of cycles; θ ij and G ij These represent the voltage phase angle difference and conductance between power node i and power node j, respectively; n is the total number of power nodes; U i and U j Δt represents the voltage magnitudes at nodes i and j, respectively; Δt represents the time interval.
[0061] The above-described technical solution in this embodiment constructs a first resource scheduling sub-function with the goal of minimizing voltage deviation, a second resource scheduling sub-function with the goal of maximizing distributed power generation output, and a third resource scheduling sub-function with the goal of minimizing active power loss in the distribution network. Based on the first, second, and third resource scheduling sub-functions, the resource scheduling function is constructed. This achieves better optimization of the energy structure of the distribution network while ensuring the safe operation of the distribution network system, realizing diversified energy supply, and reducing active power loss in the distribution network.
[0062] b1) Based on the resource scheduling function and the set of scheduling constraints, the distribution network resource scheduling model is formed, wherein the set of scheduling constraints includes constraints on branch current amplitude, constraints on power node voltage amplitude, constraints on branch active power, constraints on branch apparent power, constraints on the balance between active power injected into power nodes and active power consumed by loads, and constraints on the balance between reactive power injected into power nodes and reactive power consumed by loads.
[0063] In this embodiment, the scheduling constraint set can be specifically represented as:
[0064] In the formula, I ij I represents the current magnitude in branch ij from power node i to power node j. ij,max U represents the upper limit of the current amplitude in branch ij; i U represents the voltage amplitude at power node i. i,max and U i,min P represents the upper and lower limits of the voltage amplitude at the power node. ij With Q ij P represents the active and reactive power of branch ij; ij,min P ij,max These are the upper and lower limits of the active power of branch ij, respectively; S ij,max P represents the maximum apparent power. g,i P is the active power injected by the power source at power node i. L,i Q represents the active power consumed by the load at power node i. g,i Q is the reactive power injected by the power source at power node i. L,i This represents the reactive power consumed by the load at power node i.
[0065] The above-described technical solution in this embodiment forms the power distribution network resource scheduling model based on the resource scheduling function and the set of scheduling constraints, thereby achieving a scheduling scheme that can better optimize the energy structure of the power distribution network while ensuring the safe operation of the power distribution network system.
[0066] As a second optional embodiment of this example, based on the above embodiment, the hierarchical partitioning problem of constructing the scheduling constraint set can be specifically optimized into the following steps:
[0067] a2) Based on the execution time and first weight of each constraint in the scheduling constraint set, construct a first partitioning function with the objective of minimizing the total execution time of the scheduling constraint set.
[0068] The first weight can be understood as the weight relative to each constraint, used to indicate the importance or execution frequency of the constraint.
[0069] In this embodiment, based on the execution time and first weight of each constraint in the scheduling constraint set, the first partitioning function f4(x) constructed with the objective of minimizing the total execution time of the scheduling constraint set can be specifically expressed as:
[0070] In the formula, w ax is the first weight of the a-th constraint in the scheduling constraint set; a Let be the execution time of the a-th constraint; sum is the total number of constraints in the scheduling constraint set.
[0071] b2) Based on the hierarchical complexity of the scheduling constraint set after hierarchical partitioning and the second weight, construct a second partitioning function with the objective of minimizing the total hierarchical complexity of the scheduling constraint set.
[0072] The layered complexity can be understood as the complexity of each layer after the hierarchical division (measured by factors such as lines of code and function call depth). The second weight can be understood as the complexity weight relative to each layer, used to represent the importance of that layer in the power distribution network system.
[0073] In this embodiment, based on the hierarchical complexity of the scheduling constraint set after hierarchical partitioning and the second weight, the constructed second partitioning function f5(y), which aims to minimize the total hierarchical complexity of the scheduling constraint set, can be specifically expressed as:
[0074] In the formula, c b The second weight of layer b; y b Let m be the layer complexity of layer b; m is the total number of layers.
[0075] c2) Based on the first partitioning function, the second partitioning function, and the hierarchical partitioning constraints, determine the hierarchical partitioning problem with the objective of minimizing the sum of the total execution time and the total hierarchical complexity, wherein the hierarchical partitioning constraints include constraints on the execution time of each constraint, constraints on each hierarchical complexity, and constraints on the performance of the distribution network system.
[0076] In this embodiment, to ensure that the execution time of the partitioned constraints meets the requirements of the distribution network system, the number of partitions and the layer complexity of each layer conform to the actual situation of the distribution network. Simultaneously, to ensure that the performance under the current constraint partitioning and layered structure meets the performance requirements of the distribution network system, the layer partitioning constraints can be specifically expressed as follows: D(x,y)≥D req ;
[0077] In the formula, x max x min Let y be the maximum and minimum execution times of the a-th constraint, respectively. max y min Let be the maximum and minimum values of the layer complexity of layer b, respectively, and let D(x,y) be the performance of the distribution network system under the current constraints and layer structure. req This represents the minimum performance required by the system.
[0078] As described above, based on the first partitioning function, the second partitioning function, and the hierarchical partitioning constraints, the hierarchical partitioning problem with the objective of minimizing the sum of the total execution time and the total hierarchical complexity can be specifically expressed as: min[λ1f4(x)+λ2f5(y)];
[0079] st D(x,y)≥D req ;
[0080] In the formula, λ1 and λ2 are the weights corresponding to the first partition function and the second partition function, respectively, determined by the analytic hierarchy process, where λ1 + λ2 = 1.
[0081] The above-described technical solution in this embodiment determines the hierarchical partitioning problem with the goal of minimizing the sum of the total execution time and the total hierarchical complexity by using the first partitioning function, the second partitioning function, and the hierarchical partitioning constraints. This enables the complex set of scheduling constraints in the distribution network to be divided into multiple smaller and easier-to-process subsets of scheduling constraints. In this way, while ensuring the safe operation of the distribution network system, the solution speed of the distribution network resource scheduling model is accelerated, providing strong support for the subsequent promotion of related businesses such as distributed power source access.
[0082] As a third optional embodiment of this example, based on the above embodiments, the hierarchical partitioning result of the scheduling constraint set can be obtained by solving the hierarchical partitioning problem, specifically optimized as follows:
[0083] a3) Initialize the parameters and initialize the population using the chaotic mapping Bernoulli method. The parameters include the population size, maximum number of iterations, external archive size, and access table. The population is a set of hierarchical partitioning results for the hierarchical partitioning problem.
[0084] In this embodiment, the chaotic mapping Bernoulli method is used to initialize the population, resulting in a more diverse and uniform population, thereby improving the ability to solve complex optimization models. The Bernoulli equation can be specifically expressed as:
[0085] In the formula, x(t) is the state variable at time t, and x(t+1) is the state variable at time t+1; λ3 is a constant parameter, where 0≤λ3≤1, used as the threshold and scaling factor of the piecewise function.
[0086] b3) Adjust the weights based on the current iteration count and the maximum iteration count.
[0087] It should be noted that while adjusting the weights, the initial fitness can be calculated based on the position of each individual in the population after initialization, and the individual can be a hummingbird.
[0088] c3) Execute the guided foraging process, the territory foraging process, and the migration search process; in the guided foraging process, a target individual is selected for each individual in the population based on the access table, the current position is updated according to the non-linearly increased adaptive weight and the position of the target individual, and the fitness is updated.
[0089] The position of the target individual can be understood as the position corresponding to the current optimal solution.
[0090] In this embodiment, the nonlinear increase of adaptive weights can be specifically expressed as:
[0091] In the formula, w is the current weight value; w max w min The maximum and minimum values of the weights; T' max t' is the maximum number of iterations; t' is the current number of iterations; e is the natural constant, approximately equal to 2.718; k is the adjustment exponent, controlling the rate of exponential growth.
[0092] d3) Perform non-dominant sorting on the population and select non-dominant solutions; store the non-dominant solutions in an external archive and adjust the crowding distance.
[0093] e3) If the maximum number of iterations is reached or the fitness no longer improves, then stop iterating and obtain the hierarchical partitioning result of the scheduling constraint set.
[0094] In this embodiment, if the maximum number of iterations is reached or the fitness no longer improves, the iteration stops and the current optimal solution is output as the hierarchical partitioning result of the scheduling constraint set.
[0095] The technical solution described in this embodiment accelerates the solution of the hierarchical partitioning problem by optimizing the algorithm. The resulting hierarchical partitioning is superior and better meets actual operational needs, enabling more flexible responses to various complex situations and changes that may occur in the distribution network (such as load fluctuations and distributed power source integration), thereby improving the stability and reliability of the distribution network operation. Furthermore, the use of the chaotic mapping Bernoulli method to initialize the population generates a more diverse and uniform population. The introduction of a nonlinear adaptive weighting method balances the global and local optimization capabilities of the algorithm, improving its ability to solve complex hierarchical partitioning problems and enabling faster and better hierarchical partitioning results.
[0096] As a fourth optional embodiment of this example, it also includes:
[0097] a4) Construct a directed graph of the power distribution network resource scheduling model, wherein the graph nodes of the directed graph represent the power nodes in the power distribution network resource scheduling model, and the directed edges represent the power transmission relationships between the power nodes.
[0098] In this embodiment, the specific implementation of the directed graph for constructing the distribution network resource scheduling model can be to abstract each element in the distribution network as a power node in the directed graph; and to abstract the power transmission relationship between elements as a directed edge in the directed graph.
[0099] A directed graph can be represented by (V,E), where V={v1,v2,…,v... k} represents all power nodes, E = {e ij} represents all directed edges connecting power nodes. It can be understood that the attributes of each power node and the weight of each directed edge are set according to the actual operation of the distribution network and the scheduling objectives.
[0100] b4) Convert the directed graph into a directed acyclic graph.
[0101] In this embodiment, the specific implementation process of converting the directed graph into a directed acyclic graph (DAG) can be achieved through a delay step, using the calculation result from the previous time step as feedback to convert the directed graph into a DAG. The update rule for the delay variable in the delay step can be specifically expressed as: d η (t+1)=f η (d η (t),R(η,t));
[0102] In the formula, the delay variable d η (t) and d η (t+1) represent the delayed outputs of power node η at time steps t and t+1, respectively, f η R(η,t) is the calculation function for power node η; R(η,t) is all the directly related input data of power node η at time step t, including real-time measurement data of the distribution network resources (such as distributed power sources, energy storage devices, loads, etc.) represented by the power node, such as power, voltage, current, etc. These input data reflect the current status and operation of the distribution network resources.
[0103] It should be noted that the directed graph must not contain any closed loops of any kind, that is, for any power node η, there is no path that starts from η, goes through a series of directed edges, and finally returns to η.
[0104] c4) Based on the hierarchical partitioning results, determine the sub-flowcharts corresponding to each subset of scheduling constraints in the directed acyclic graph.
[0105] In this embodiment, the corresponding scheduling constraint subset is determined based on the hierarchical partitioning result, and the sub-flowchart (i.e., partial directed acyclic graph) corresponding to each scheduling constraint subset is determined based on the directed acyclic graph.
[0106] The above-described technical solution in this embodiment uses a directed acyclic graph to represent the distribution network resource scheduling model, which can more clearly show the association and dependency relationships between nodes in the distribution network; based on the hierarchical division results, the sub-flowcharts corresponding to each subset of scheduling constraints in the directed acyclic graph are determined, providing strong support for subsequent thread allocation.
[0107] As a fifth optional embodiment of this example, based on the above optional embodiments, the resource scheduling function can be solved in parallel according to each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information. Specifically, the optimization is as follows:
[0108] a5) Determine thread allocation information based on the attribute information of the sub-flowchart corresponding to the subset of scheduling constraints; thread allocation information includes: number of thread blocks and thread number.
[0109] The thread allocation information can be understood as guidance for allocating threads to each subset of scheduling constraints. The sub-flowchart's attribute information includes the total number of sub-flowcharts, the sub-flowchart's number, and the number of constraints defined within each sub-flowchart.
[0110] In this embodiment, the specific implementation method for determining the number of thread blocks and thread numbers based on the attribute information of the sub-flowchart corresponding to the subset of scheduling constraints can be expressed as follows:
[0111] In the formula, N bq To calculate the required number of thread blocks; q is the total number of sub-flowcharts; G is the sub-flowchart number; s is the number of multiple scenarios; N ag The number of core array groups required to handle the relevant operations; N k The number of constraints defined for the sub-flowchart.
[0112] In the formula, bid represents the thread block number; tid represents the thread number within the block; mod(A,B) represents the remainder when integer A is divided by integer B; σ is the maximum number of threads in a single thread block; r is the number of levels; and z is the number of executable constraints in a thread.
[0113] b5) Assign threads to the solution tasks of each resource scheduling function according to the thread allocation information; the solution tasks of the resource scheduling functions include: solving the resource scheduling functions according to the subset of scheduling constraints and the current power data information.
[0114] In this embodiment, threads are allocated on processors with parallel computing capabilities, such as GPUs, according to thread allocation information, for solving the resource scheduling functions corresponding to each subset of scheduling constraints, so that the resource scheduling functions can be solved in parallel based on each subset of scheduling constraints and the current power data information.
[0115] c5) Based on the allocated thread, solve the task of solving the resource scheduling function to obtain alternative resource scheduling information that satisfies the subset of scheduling constraints.
[0116] Among them, alternative resource scheduling information can be understood as data information that satisfies a subset of scheduling constraints and can be used as possible solutions to the resource scheduling function, and is used as alternatives for distribution network resource scheduling information.
[0117] In this embodiment, based on the allocated thread, the resource scheduling function is solved by using data from the current power data information that satisfy each subset of scheduling constraints, thereby obtaining the alternative resource scheduling information corresponding to each subset of scheduling constraints.
[0118] d5) Determine the distribution network resource scheduling information based on the alternative resource scheduling information that respectively satisfy each subset of the scheduling constraints.
[0119] In this embodiment, the specific method for determining the distribution network resource scheduling information based on the candidate resource scheduling information that satisfies each of the aforementioned scheduling constraint subsets can be as follows: First, find the intersection of all candidate resource scheduling information to obtain candidate resource scheduling information that satisfies all scheduling constraint subsets as the distribution network resource scheduling information. Second, verify each candidate resource scheduling information by inputting it into other scheduling constraint subsets besides the one corresponding to the candidate resource scheduling information, and obtain candidate resource scheduling information that satisfies all scheduling constraint subsets as the distribution network resource scheduling information. It is understood that there is no single candidate resource scheduling information that satisfies all scheduling constraint subsets. If resource scheduling information is selected, new alternative resource scheduling information that satisfies each of the aforementioned subsets of scheduling constraints is determined, and the verification is performed again until alternative resource scheduling information that satisfies all subsets of scheduling constraints is obtained. This alternative resource scheduling information is then used as the distribution network resource scheduling information. Alternatively, the intersection of each alternative resource scheduling information can be found first. If no alternative resource scheduling information exists in the intersection, each alternative resource scheduling information is input into other subsets of scheduling constraints besides the subset corresponding to the alternative resource scheduling information for verification. Alternative resource scheduling information that satisfies all subsets of scheduling constraints is then used as the distribution network resource scheduling information.
[0120] The above-described technical solution in this embodiment determines the thread allocation information corresponding to each subset of scheduling constraints based on the attribute information of the sub-flowcharts corresponding to each subset of scheduling constraints. Threads are then allocated to the solution tasks of each resource scheduling function based on the thread allocation information. Based on the allocated threads, the solution tasks of the resource scheduling functions are solved, achieving rapid solution of the distribution network resource scheduling model. This fully utilizes the parallel computing capabilities of processors such as GPUs, reducing computational costs and resource consumption. It enables the acquisition of better distribution network resource scheduling information in a shorter time to meet the real-time scheduling needs of the distribution network system, providing strong support for the advancement of subsequent related businesses.
[0121] To better understand the power distribution network resource scheduling method provided in this embodiment of the invention, a specific example is given here.
[0122] Figure 2 is a schematic diagram of an example power node system resource configuration. As shown in Figure 2, the IEEE 33 power node system is used for simulation analysis. The voltage is selected as 12.66kV, the total active power of the load is 3715kW, and the total reactive power is 2547kvar. The baseline capacity of the example is set to 10MVA, and the voltage constraint of the power nodes is 0.98pu-1.02pu. The total capacity of distributed power sources is 3MW. Power nodes 10, 13, and 24 are connected to photovoltaic cells with a capacity of 0.5MW each, and power nodes 16, 17, and 32 are connected to wind turbines with a capacity of 0.5MW each.
[0123] Add one static var compensator to the system, connected to power node 25, with a capacity of 1 Mvar; 10 capacitor banks CB, installed at power node 22, with a capacity of 0.5 Mvar; and 2 battery energy storage (ESS) units, connected to power nodes 16 and 32, with an active power capacity of 0.5 MW and a reactive power capacity of 0.5 Mvar.
[0124] With the high penetration of distributed generation, the risk of voltage exceeding limits in the distribution network has increased dramatically. Traditional methods have large voltage deviations, posing a risk of exceeding limits. The average voltage deviations of the traditional method and the method of this invention are 0.4998 and 0.4403, respectively. Compared with the traditional method, the average voltage deviation of the method of this invention is reduced by about 11.90%. Therefore, the method proposed in this invention can minimize voltage deviation while ensuring the safe operation of the distribution network.
[0125] The optimization effect is particularly significant between 14:00 and 22:00, with network loss reduced by 18.69 kW at 20:00. The network losses of the traditional method and the method of the present invention are 542.24 kW·h and 452.58 kW·h, respectively. Compared with the traditional method, the network loss of the method of the present invention is reduced by about 16.53%. Therefore, the method of the present invention performs better in reducing network loss.
[0126] To study the utilization rates of photovoltaic and wind power under different methods, the DG utilization rates of the traditional method and the method of this invention are 32.19% and 36.28%, respectively. Compared with the traditional method, the DG utilization rate of the method of this invention is improved by about 4.09%. The method of this invention is relatively conservative in terms of renewable energy output to ensure the safe and reliable operation of power distribution.
[0127] Figure 3 is a schematic diagram of a power distribution network resource scheduling device provided in an embodiment of the present invention. As shown in Figure 3, the device includes: a model building module 21, a problem building and solving module 22, a hierarchy partitioning module 23, an information determination module 24, and a resource scheduling module 25, wherein...
[0128] Model building module 21 is used to build a distribution network resource scheduling model, which includes: resource scheduling function and scheduling constraint set;
[0129] The problem construction and solution module 22 is used to construct the hierarchical partitioning problem of the scheduling constraint set, and solve the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set.
[0130] The hierarchical partitioning module 23 is used to hierarchically partition the set of scheduling constraints according to the hierarchical partitioning result, so as to obtain multiple subsets of scheduling constraints.
[0131] Information determination module 24 is used to acquire current power data information, and to solve the resource scheduling function in parallel according to each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information;
[0132] The resource scheduling module 25 is used to schedule the schedulable resources of the distribution network according to the distribution network resource scheduling information.
[0133] This invention provides a distribution network resource scheduling device. It constructs a distribution network resource scheduling model, which includes a resource scheduling function and a set of scheduling constraints. The device then constructs a hierarchical partitioning problem of the scheduling constraint set, solves the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set, and further partitions the scheduling constraint set hierarchically according to the hierarchical partitioning result to obtain multiple subsets of scheduling constraints. It acquires current power data information, solves the resource scheduling function in parallel based on each subset of scheduling constraints and the current power data information, and obtains distribution network resource scheduling information. Finally, it schedules the schedulable resources of the distribution network according to the distribution network resource scheduling information. This method, by solving the hierarchical partitioning problem to hierarchically partition the scheduling constraint set into multiple subsets of scheduling constraints, and then solves the resource scheduling function in parallel based on each subset of scheduling constraints, decomposes the complex distribution network resource scheduling problem into multiple simple sub-problems for parallel solving. This improves the solution speed of the distribution network resource scheduling problem, shortens the time to obtain a better scheduling scheme, meets the real-time scheduling requirements of the distribution network system, and provides strong support for the subsequent implementation of large-scale renewable energy access to the distribution network system.
[0134] Furthermore, the model building module 21 may specifically include:
[0135] A resource scheduling function construction unit is used to acquire historical electrical data of the distribution network and construct the resource scheduling function based on the historical electrical data.
[0136] The resource scheduling model determination unit is used to form the distribution network resource scheduling model based on the resource scheduling function and the set of scheduling constraints.
[0137] The scheduling constraint set includes constraints on branch current amplitude, constraints on power node voltage amplitude, constraints on branch active power, constraints on branch apparent power, constraints on the balance between active power injected into power nodes and active power consumed by loads, and constraints on the balance between reactive power injected into power nodes and reactive power consumed by loads.
[0138] Furthermore, the historical electrical data includes the current voltage of each power node in the distribution network, the active power injected by the power source into each power node in the current period, the voltage phase angle difference and conductance between power nodes;
[0139] Correspondingly, the resource scheduling function building unit can be specifically used for:
[0140] Based on the current voltage and corresponding ideal voltage of each power node, a first resource scheduling subfunction is constructed with the goal of minimizing voltage deviation.
[0141] Based on the active power injected by the power source into each power node during the current period, a second resource scheduling subfunction is constructed with the goal of maximizing the output of the distributed power source.
[0142] Based on the voltage phase angle difference, conductance, voltage amplitude of the power nodes, and time interval, a third resource scheduling sub-function is constructed with the goal of minimizing the active power loss of the distribution network.
[0143] The resource scheduling function is constructed based on the first resource scheduling sub-function, the second resource scheduling sub-function, and the third resource scheduling sub-function.
[0144] Furthermore, the problem construction and solution module 22 may specifically include a problem construction unit and a problem solution unit, wherein the problem construction unit may be used for:
[0145] Based on the execution time and first weight of each constraint in the scheduling constraint set, a first partitioning function is constructed with the goal of minimizing the total execution time of the scheduling constraint set.
[0146] Based on the hierarchical complexity of the scheduling constraint set after hierarchical partitioning and the second weight, a second partitioning function is constructed with the goal of minimizing the total hierarchical complexity of the scheduling constraint set.
[0147] Based on the first partitioning function, the second partitioning function, and the hierarchical partitioning constraints, a hierarchical partitioning problem is determined with the goal of minimizing the sum of the total execution time and the total hierarchical complexity.
[0148] The hierarchical partitioning constraints include constraints on the execution time of each constraint, constraints on the complexity of each layer, and constraints on the performance of the power distribution network system.
[0149] Furthermore, the problem-solving unit can specifically be used for:
[0150] Initialize parameters and use the chaotic mapping Bernoulli method to initialize the population. The parameters include population size, maximum number of iterations, external archive size, and access table. The population is a set of hierarchical partitioning results for the hierarchical partitioning problem.
[0151] Adjust the weights based on the current iteration count and the maximum iteration count;
[0152] The process involves guiding foraging, territorial foraging, and migration search. During guiding foraging, a target individual is selected for each individual in the population based on the access table. The current position is updated based on the nonlinearly increasing adaptive weight and the position of the target individual, and the fitness is also updated.
[0153] The population is sorted into non-dominant groups to select non-dominant solutions; the non-dominant solutions are stored in an external archive and the crowding distance is adjusted.
[0154] If the maximum number of iterations is reached or the fitness no longer improves, the iteration stops, and the hierarchical partitioning result of the scheduling constraint set is obtained.
[0155] Furthermore, the device also includes a graphical representation module, which can be specifically used for:
[0156] Construct a directed graph of the power distribution network resource scheduling model, wherein the graph nodes of the directed graph represent the power nodes in the power distribution network resource scheduling model, and the directed edges represent the power transmission relationships between the power nodes;
[0157] The directed graph is converted into a directed acyclic graph;
[0158] Based on the hierarchical partitioning results, determine the sub-flowcharts corresponding to each subset of scheduling constraints in the directed acyclic graph.
[0159] Furthermore, the information determination module 24 can specifically be used for:
[0160] The thread allocation information is determined based on the attribute information of the sub-flowchart corresponding to the subset of scheduling constraints; the thread allocation information includes: the number of thread blocks and the thread number;
[0161] Threads are allocated to the solution tasks of each resource scheduling function according to the thread allocation information; the solution tasks of the resource scheduling functions include: solving the resource scheduling functions according to the subset of scheduling constraints and the current power data information;
[0162] Based on the allocated thread, the task of solving the resource scheduling function is solved to obtain alternative resource scheduling information that satisfies the subset of scheduling constraints.
[0163] The distribution network resource scheduling information is determined based on the alternative resource scheduling information that satisfies each of the aforementioned scheduling constraint subsets.
[0164] The power distribution network resource scheduling device provided in this embodiment of the invention can execute the power distribution network resource scheduling method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.
[0165] Figure 4 illustrates a schematic diagram of an electronic device 30 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0166] As shown in Figure 4, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 and a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.
[0167] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0168] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 31 performs the various methods and processes described above, such as power distribution network resource scheduling methods.
[0169] In some embodiments, the distribution network resource scheduling method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the distribution network resource scheduling method described above may be performed. Alternatively, in other embodiments, processor 31 may be configured to execute the distribution network resource scheduling method by any other suitable means (e.g., by means of firmware).
[0170] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0171] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0172] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0173] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).
[0174] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0175] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0176] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0177] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A power distribution network resource scheduling method, characterized in that, include: A distribution network resource scheduling model is constructed, which includes: a resource scheduling function and a set of scheduling constraints. Construct a hierarchical partitioning problem of the scheduling constraint set, and solve the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set; Based on the hierarchical partitioning results, the scheduling constraint set is hierarchically partitioned to obtain multiple scheduling constraint subsets. Obtain current power data information, and solve the resource scheduling function in parallel based on each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information; The schedulable resources of the distribution network are scheduled according to the distribution network resource scheduling information.
2. The method of claim 1, wherein, The construction of the power distribution network resource scheduling model includes: Obtain historical electrical data of the power distribution network, and construct the resource scheduling function based on the historical electrical data; Based on the resource scheduling function and the set of scheduling constraints, the distribution network resource scheduling model is formed. The scheduling constraint set includes constraints on branch current amplitude, constraints on power node voltage amplitude, constraints on branch active power, constraints on branch apparent power, constraints on the balance between active power injected into power nodes and active power consumed by loads, and constraints on the balance between reactive power injected into power nodes and reactive power consumed by loads.
3. The method of claim 2, wherein, The historical electrical data includes the current voltage of each power node in the distribution network, the active power injected by the power source into each power node in the current period, the voltage phase angle difference between power nodes, and the conductance. Correspondingly, constructing the resource scheduling function based on the historical electrical data includes: Based on the current voltage and corresponding ideal voltage of each power node, a first resource scheduling subfunction is constructed with the goal of minimizing voltage deviation. Based on the active power injected by the power source into each power node during the current period, a second resource scheduling subfunction is constructed with the goal of maximizing the output of the distributed power source. Based on the voltage phase angle difference, conductance, voltage amplitude of the power nodes, and time interval, a third resource scheduling sub-function is constructed with the goal of minimizing the active power loss of the distribution network. The resource scheduling function is constructed based on the first resource scheduling sub-function, the second resource scheduling sub-function, and the third resource scheduling sub-function.
4. The method according to any one of claims 1 to 3, characterized in that, The hierarchical partitioning problem for constructing the scheduling constraint set includes: Based on the execution time and first weight of each constraint in the scheduling constraint set, a first partitioning function is constructed with the goal of minimizing the total execution time of the scheduling constraint set. Based on the hierarchical complexity of the scheduling constraint set after hierarchical partitioning and the second weight, a second partitioning function is constructed with the goal of minimizing the total hierarchical complexity of the scheduling constraint set. Based on the first partitioning function, the second partitioning function, and the hierarchical partitioning constraints, a hierarchical partitioning problem is determined with the goal of minimizing the sum of the total execution time and the total hierarchical complexity. The hierarchical partitioning constraints include constraints on the execution time of each constraint, constraints on the complexity of each layer, and constraints on the performance of the power distribution network system.
5. The method according to any one of claims 1-3, characterized in that, The process of solving the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set includes: Initialize parameters and use the chaotic mapping Bernoulli method to initialize the population. The parameters include population size, maximum number of iterations, external archive size, and access table. The population is a set of hierarchical partitioning results for the hierarchical partitioning problem. Adjust the weights based on the current iteration count and the maximum iteration count; The process involves guiding foraging, territorial foraging, and migration search. During guiding foraging, a target individual is selected for each individual in the population based on the access table. The current position is updated based on the nonlinearly increasing adaptive weight and the position of the target individual, and the fitness is also updated. The population is sorted into non-dominant groups to select non-dominant solutions; the non-dominant solutions are stored in an external archive and the crowding distance is adjusted. If the maximum number of iterations is reached or the fitness no longer improves, the iteration stops, and the hierarchical partitioning result of the scheduling constraint set is obtained.
6. The method of claim 1, wherein, Also includes: Construct a directed graph of the power distribution network resource scheduling model, wherein the graph nodes of the directed graph represent the power nodes in the power distribution network resource scheduling model, and the directed edges represent the power transmission relationships between the power nodes; The directed graph is converted into a directed acyclic graph; Based on the hierarchical partitioning results, determine the sub-flowcharts corresponding to each subset of scheduling constraints in the directed acyclic graph.
7. The method of claim 6, wherein, The resource scheduling function is solved in parallel based on each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information, including: The thread allocation information is determined based on the attribute information of the sub-flowchart corresponding to the subset of scheduling constraints; the thread allocation information includes: the number of thread blocks and the thread number; Threads are allocated to the solution tasks of each resource scheduling function according to the thread allocation information; the solution tasks of the resource scheduling functions include: solving the resource scheduling functions according to the subset of scheduling constraints and the current power data information; Based on the allocated thread, the task of solving the resource scheduling function is solved to obtain alternative resource scheduling information that satisfies the subset of scheduling constraints. The distribution network resource scheduling information is determined based on the alternative resource scheduling information that satisfies each of the aforementioned scheduling constraint subsets.
8. A power distribution network resource scheduling apparatus, characterized by, include: The model building module is used to build a distribution network resource scheduling model, which includes: a resource scheduling function and a set of scheduling constraints. The problem construction and solution module is used to construct the hierarchical partitioning problem of the scheduling constraint set, and solve the hierarchical partitioning problem to obtain the hierarchical partitioning result of the scheduling constraint set. The hierarchical partitioning module is used to hierarchically partition the set of scheduling constraints according to the hierarchical partitioning result, thereby obtaining multiple subsets of scheduling constraints. The information determination module is used to acquire current power data information, and to solve the resource scheduling function in parallel according to each subset of scheduling constraints and the current power data information to obtain distribution network resource scheduling information. The resource scheduling module is used to schedule the schedulable resources of the distribution network according to the distribution network resource scheduling information.
9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the power distribution network resource scheduling method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the power distribution network resource scheduling method according to any one of claims 1-7.