Distributed collaborative optimization control method, system and equipment for power distribution network and medium

Abstract

The invention relates to the field of intelligent optimization operation of a power distribution network, and discloses a distributed collaborative optimization control method, system, equipment and medium for the power distribution network. The power distribution network is partitioned and an edge intelligent agent is configured to monitor network loss data of the power distribution network in real time; triggering an optimization control process: taking the network active loss as a target function, constraining the line power flow, the distributed power supply power and the node voltage, and reconstructing through semi-definite programming to construct an optimization control model of a convex quadratic programming model; decomposing the constructed model into a plurality of distributed optimization control sub-models based on partition coordination on the basis of coupling branch states among the regions, and solving each sub-model by adopting a synchronous alternating direction multiplier algorithm which introduces historical iteration results and increments of each edge agent to obtain a distributed collaborative optimization strategy and execute the distributed collaborative optimization strategy; through partition management, distributed optimization and cooperative control, efficient operation and optimization of the power distribution network are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent optimal operation of distribution networks, and particularly to a distributed collaborative optimization control method, system, device and medium for a distribution network. Background Art

[0002] As the end link of power transmission, the operation stability and loss situation of the distribution network are directly related to the economy and reliability of the entire power grid.

[0003] Traditional distribution network operation optimization methods often rely on centralized control systems, which collect, analyze and process global data through a central processor to formulate optimization strategies. However, with the continuous expansion of the scale and increasing complexity of the distribution network, centralized control methods gradually expose problems such as large data communication volume, heavy calculation burden, slow response speed, etc., making it difficult to meet the high requirements of modern distribution networks for real-time performance and reliability, resulting in the increasingly poor operation stability of the distribution network.

[0004] Therefore, how to effectively improve the operation stability of the distribution network has become a technical problem urgently to be solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a distributed collaborative optimization control method, system, device and medium for a distribution network, to solve the problem of how to effectively improve the operation stability of the distribution network.

[0006] To solve the above technical problems, the present invention provides a distributed collaborative optimization control method for a distribution network, including: Real-time monitoring of the network loss data of the distribution network; When the network loss data exceeds a preset network loss threshold, taking the network active power loss of the distribution network as the objective function, respectively constraining the line power flow, distributed power source power and node voltage in the distribution network, and performing semidefinite programming reconstruction on the formed constraint conditions, and constructing an optimization control model for the distribution network with the reconstruction result and the objective function; Obtaining the coupling branch states among multiple edge regions in the distribution network, and decomposing the optimization control model into several distributed optimization control submodels based on partition coordination according to the coupling branch states; Controlling the edge agents deployed in each edge region to solve each distributed optimization control submodel by using a preset distributed optimization algorithm to obtain a distributed collaborative optimization strategy; the preset distributed optimization algorithm is a synchronous alternating direction multiplier algorithm introducing the historical iteration results and increments of each edge agent.

[0007] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: (1) By means of real-time monitoring of network loss data by edge agents, abnormal network losses can be quickly detected and optimization control can be triggered, improving the stability and reliability of the distribution network; through semidefinite programming reconstruction, the optimization control model is transformed into a convex quadratic programming model, ensuring the global optimality of the solution and computational efficiency, and improving the accuracy and efficiency of network loss calculation. (2) The global optimization problem is decomposed into multiple sub-problems and solved by a distributed optimization algorithm, reducing the computational complexity and improving the computational efficiency; based on the partition coordination mechanism of the coupled branch states, the interaction between edge regions can be effectively processed, ensuring global consistency; historical iteration results and incremental information are introduced during the solution process to accelerate the algorithm convergence and improve the optimization performance; through partition management, distributed optimization and cooperative control, the present invention realizes the efficient operation and optimization of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for implementation will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 is a flowchart of a distributed cooperative optimization control method for a distribution network provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the division of the edge region of the distribution network provided by an embodiment of the present invention; Figure 3 is a flowchart of the solution of each distributed optimization control sub-model provided by an embodiment of the present invention; Figure 4 is a schematic diagram of the topology and edge division of the IEEE 33-node system provided by an embodiment of the present invention; Figure 5 is a comparison chart of voltages before and after optimization of the IEEE 33-node system provided by an embodiment of the present invention; Figure 6 is a diagram of the iterative change of the boundary residuals of each edge of the IEEE 33-node system provided by an embodiment of the present invention; Figure 7 is a diagram of the iterative change of the reactive power output of distributed power sources in the IEEE 33-node system provided by an embodiment of the present invention; Figure 8 is a daily load curve diagram of the IEEE 33-node system provided by an embodiment of the present invention; Figure 9 is a comparison chart of network losses before and after optimization of the IEEE 33-node system provided by an embodiment of the present invention; Figure 10It is a structural diagram of a distributed collaborative optimization control system for a distribution network provided by an embodiment of the present invention; Figure 11 It is a structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0010] Next, in combination with the accompanying drawings and embodiments, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0011] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0012] In the description of the present application, it should be noted that unless otherwise clearly defined and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration, and do not indicate or imply that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0013] In the description of the present application, it should be noted that unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those of ordinary skill in the technical field of the present invention. The terms used in the specification of the present invention are only for describing specific embodiments, and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0014] In one embodiment, as Figure 1As shown in the figure, the first aspect of the present invention provides a distributed collaborative optimization control method for a distribution network, including: S1. Real-time monitor the network loss data of the distribution network; In one embodiment, before the real-time monitoring of the network loss data of the distribution network, it further includes: Regarding the stable connection areas in the distribution network as the network edges to divide the distribution network into several edge areas; the stable connection areas are configured such that within the area is statically connected, between areas are not directly connected, the power supply of the area is the upper-level substation, and the boundary between adjacent areas is the normally open tie switch in the distribution network; Model the electrical equipment in each of the edge areas to describe the equipment parameters, operating states, installation locations, and control or adjustment methods of each of the edge areas, and generate a basic attribute model; Configure an edge agent for each of the edge areas, use each of the basic attribute models as the static structure of each of the edge agents, collect the real-time operation data in each of the edge areas and store it through each of the basic attribute models to construct the operating states of each of the edge agents.

[0015] Specifically, before the present invention real-time monitors the network loss data of the distribution network, it is necessary to first divide the distribution network into multiple edge areas, and configure a distribution network edge agent for each edge area as the edge computing carrier of the optimization strategy, and execute the tasks of data collection and processing, establishment and optimization solution calculation of the optimization control model, and issuance of control instructions for controllable resource equipment within the scope of its jurisdiction edge area. The area division process is as follows: First, the radial source-network-load-storage distribution network applicable to the present invention connects to the large power grid and consists of power equipment such as the 10 kV busbar of the substation, the 10 kV distribution feeder, the distribution transformer, the switch or the ring main unit, the pole-mounted switch, the cable branch box, the switching station, etc., as well as users, substations, photovoltaics, energy storage, etc. connected to the distribution network. Next, the stable connection area of the distribution network is used as the edge distribution network of the grid edge for edge division. The stable connection area of the distribution network can be generated according to the static topology of the distribution network and meets the following conditions: ① It is statically connected within the area; ② The areas are not directly connected to each other, that is, they are not directly connected through 10 kV lines; ③ The power source of this area is the upper-level substation, that is, the 220 / 110 / 35 kV substation, and the boundary between adjacent edge agents of the distribution network is the normally open tie switch in the distribution network. Then, the electrical equipment in each delimited edge area is modeled to describe the basic attributes of the equipment, such as equipment parameters, operating status, installation location, and control or adjustment methods, and this information is used as the static structure of the edge agent in the corresponding area, becoming the reference data of the agent status, and a basic attribute model of each edge area is generated. Finally, the edge agents collect the real-time operation data and real-time network loss data in the corresponding edge areas, including equipment output, line power, line current, node injection power, node voltage value, and set data such as load, tie switch, and line, and store these data according to the established basic attribute model for constructing the operation status of the agent, providing data support for subsequent event judgment and optimization.

[0016] By dividing the distribution network into several edge areas, with each area as a management unit, the present invention helps to achieve regional management of the distribution network, making the operation and maintenance and management of the distribution network more refined, improving management efficiency, and configuring edge agents for each edge area. These agents can monitor the status of electrical equipment in the area in real time, detect and handle abnormal situations in a timely manner, thereby improving the reliability and safety of the distribution network; by introducing edge agents and basic attribute models, the distribution network can realize functions such as real-time monitoring, early warning, control, and optimization, thereby improving the intelligent level of the distribution network, helping to reduce the operation and maintenance costs of the distribution network, improve energy utilization efficiency, and promote the sustainable development of the power system.

[0017] S2. When the network loss data exceeds the preset network loss threshold, take the network active power loss of the distribution network as the objective function, respectively constrain the line power flow, distributed power source power, and node voltage in the distribution network, and perform semidefinite programming reconstruction on the formed constraint conditions, and construct the optimization control model of the distribution network with the reconstruction result and the objective function; Under normal circumstances, the distribution network operates according to the set planned working mode. However, considering the economy of the distribution network system operation, the present invention takes the system network loss as the condition for the edge agent to trigger an action. When each edge agent monitors an event of excessive system network loss, it starts the optimization service processing flow, optimizes the reactive power of the distribution network system by adjusting devices such as distributed power sources in the system, thereby reducing the network loss and stabilizing the node voltage. Among them, the system network loss refers to the power loss caused by factors such as the resistance, inductance, and capacitance of power equipment such as lines, transformers, and switchgear during the power transmission and distribution processes in the distribution network. The preset network loss threshold of the system refers to a threshold set for controlling and monitoring the system network loss, and this threshold can be determined according to factors such as system capacity, load demand, and economic environment.

[0018] The present invention monitors the network loss data of the distribution network system in real time through each edge agent. When it exceeds the preset network loss threshold, it triggers an event of excessive distribution network loss. Then, an optimization model needs to be constructed based on the data at this time, enabling each edge agent to take optimization control actions to solve the model, and adjusting the line power flow, distributed power source power, and node voltage in this area according to the obtained optimization strategy to ensure that the distribution network operates in an optimal state, thereby eliminating the event and making the distribution network return to a satisfactory operating state.

[0019] The present invention takes the network active power loss of the distribution network as the objective function, which is expressed by the following formula: In the formula, is the network active power loss of the distribution network; n is the total number of nodes; l ij is the square value of the current amplitude of line ij; r ij is the resistance of line ij; P ij , Q ij are the active and reactive powers transmitted at the head end of line ij respectively; V i is the voltage of node i.

[0020] Constraints are formed for the line power flow, distributed power source power, and node voltage in the distribution network respectively. Among them, the line power flow constraint is an equality constraint, and the branch power flow equation is adopted. For a radial source-network-load-storage distribution network, ignoring the influence of line-to-ground capacitance and susceptance, according to Kirchhoff's voltage and current laws, the power flow equation described in the form of branches can be obtained as follows: In the formula, P jk , Q jk are the active and reactive powers transmitted at the head end of line jk respectively, k: j→k represents the set of all line ends with node j as the head end and node k as the end; , The active and reactive powers generated by the distributed power source at node j, respectively; x ij is the reactance of line ij; p c j and q c j are the active and reactive powers of the load at node j, respectively; is the voltage magnitude at node j; and V ref are the voltage magnitude of the slack node and its reference value, respectively.

[0021] The reactive power of the controllable distributed power source device in the basic attribute model, that is, the power constraint of the distributed power source The adjustment range is limited by its own installed capacity and active power, and is expressed by the following formula: In the formula, s j is the installed capacity of the distributed generation device; q gmax j is the maximum reactive power of the distributed generation device; p g j is the current operating value of the active power of the distributed generation device.

[0022] At the same time, considering the stability and reliability of the operation of the distribution network, it is required that the node voltages of the distribution network meet the safety constraints and remain near the rated voltage during operation, that is, the node voltage constraint is expressed by the following formula: In the formula, is the voltage deviation, generally taken as 0.05 pu.

[0023] It can be seen that the distributed power source power constraint and the node voltage constraint belong to inequality constraints, and the line power flow constraint contains complex quadratic terms, making the optimization problem non-convex. It is difficult for the distributed optimization algorithm to find the global optimal solution for non-convex problems and cannot guarantee convergence. In order to solve the non-convex non-linear programming problem distributedly, first, the branch power flow equation is reasonably simplified, that is, 1) the power loss on the line is much smaller than the power transmitted by the line itself; 2) the voltage deviation between nodes is much smaller than the node voltage itself. Based on the above two assumptions, the quadratic terms in the branch power flow equation can be ignored, and the voltage magnitude V of each node in the objective function can also be approximated as the voltage magnitude V1 of the slack node; then, the constraint conditions are reconstructed by semi-definite programming, so as to convert the original non-convex optimization problem into a convex optimization problem. To further ensure the convexification of the power flow constraint and the safety of the node voltage, the semi-definite programming reconstruction of the formed constraint conditions is carried out by the following formula: In the formula, Ui is the square value of the voltage amplitude of node i; U j is the square value of the voltage amplitude of node j; is the norm.

[0024] The obtained optimal control model of the distribution network is represented by the following formula: In the formula, q g is the reactive power generated by the distributed power source; is the square value of the voltage amplitude of the balancing node; N is the set of nodes in the distribution network; 、 are respectively the minimum and maximum values of the reactive power generated by the distributed power source of node j.

[0025] After reasonably simplifying and reconstructing the original optimization problem, it is transformed into a convex quadratic programming model with a quadratic objective function and linear constraint conditions, that is, the optimal control model. According to the optimization theory, the local optimal solution of the convex optimization problem is equal to the global optimal solution, which makes it easy to find the global optimal solution of the problem by using the distributed algorithm, thereby effectively improving the operation stability of the distribution network.

[0026] S3. Obtain the coupling branch states between multiple edge regions in the distribution network, and decompose the optimal control model into several distributed optimal control sub-models based on partition coordination according to the coupling branch states; In one embodiment, step S3 includes: Obtain the node set and branch set in each of the edge regions, so as to couple the adjacent edge regions through the branches on the edge boundary, obtain the coupling branches between the edge regions, and use the power transmitted on each coupling branch and the square of the voltage of the nodes at both ends of each branch as the corresponding coupling branch states; Based on the principle that the coupling branch states of each edge region are equal to those of its adjacent edge regions, decompose the optimal control model into several distributed optimal control sub-models based on partition coordination; the number of the distributed optimal control sub-models is the same as the number of the edge regions.

[0027] Specifically, for a distribution network system, it can be represented by a graph structure where N is the set of nodes in the whole system, E is the set of branches in the whole system, and e ij ∈E represents a certain branch in the system, where . Suppose the distribution network system is divided into r edge regions, represented by the set R; for a certain edge region a, N a represents the node set of this region, and E a represents the branch set of this region, and eij ∈E a represents a certain branch in this area. The adjacent edge areas are coupled through the branches on the edge boundary, that is, two or more edge areas sharing at least one branch are adjacent edge areas. The set of coupled branches is represented by . The coupled branch e ij 's state variables include the power P ij , Q ij transmitted by the branch, and the squared voltages U i , U j of the nodes at both ends of the branch. Then the state of the coupled branches in the edge area a is represented by the vector . The schematic diagram of the distribution network edge area division is as shown in Figure 2 . Taking the distribution network system shown in the appendix Figure 2 as an example, the node set of edge area 1 is {1, 2, 3, 4, 5}, the node set of edge area 2 is {4, 5, 6, 7, 8}, and the node set of edge area 3 is {7, 8, 9, 10, 11}. Then edge area 1 and edge area 2 are coupled through the branch e 45 , and edge area 2 and edge area 3 are coupled through the branch e 78 , and the set of coupled branches is .

[0028] To make the problem after the edge area division equivalent to the original problem, the state variables of the coupled branches obtained by solving the sub-problems of adjacent edge areas must be equal, that is, the state X a,ij of the coupled branches obtained by the sub-problem of edge area a must be equal to the state X b,ij of the coupled branches obtained by the sub-problem of its adjacent edge area b. Based on this, the optimal control model can be decomposed into several distributed optimal control sub-models based on partition coordination. The number of these sub-models is equal to the number of edge areas and edge agents. Each distributed optimal control sub-model is represented by the following formula: In the formula, r is the total number of edge areas; f a (x a ), h a (x a ), g a (x a ) are the objective function, equality constraint, and inequality constraint of the distributed optimal control sub-model of the a-th edge area respectively; x a is the decision variable of the a-th edge area, that is, the state of the coupled branches ; b is other edge areas adjacent to the a-th edge area. Therefore, b does not refer to a certain fixed area, but all edge areas adjacent to edge area a.

[0029] Thus, the optimization control model of the entire system is decomposed into the collaborative calculation of r distributed optimization control sub-models, and the distributed collaborative optimization control model of the multi-distribution network edge intelligent agents is constructed. By obtaining the node set and branch set of each edge area, the present invention helps to clearly define the boundary and internal composition of each edge area, thereby improving the zoning management ability of the distribution network. Through clear area division, resource allocation, fault location and isolation, and operation strategy formulation can be carried out more effectively; by determining the coupling branches between adjacent edge areas, electrical connection and information interaction between regions are realized, which helps to enhance the coordinated control ability between them while maintaining the relative independence of each edge area. When a fault occurs in a certain area or the operation strategy needs to be adjusted, information can be quickly transmitted through the coupling branches to achieve fast response and collaborative actions between regions; based on the principle that the coupling branch state of each edge area is equal to the coupling branch state of its adjacent edge area, the optimization control model is decomposed into several distributed optimization control sub-models based on partition coordination, which reduces the complexity of the control model and enables each edge area to independently solve its own optimization control sub-model, improving the calculation efficiency and scalability. At the same time, the distributed implementation method also helps to improve the robustness and fault tolerance of the system.

[0030] S4. Control the edge intelligent agents deployed in each of the edge areas to solve each of the distributed optimization control sub-models by using a preset distributed optimization algorithm, and obtain a distributed collaborative optimization strategy; the preset distributed optimization algorithm is a synchronous alternating direction multiplier algorithm that introduces the historical iteration results and increments of each of the edge intelligent agents; In one embodiment, step S4 includes: Based on each of the distributed optimization control sub-models, control each of the edge intelligent agents to construct the augmented Lagrangian objective function and edge constraint conditions of the edge area to which it belongs; Under each of the edge constraint conditions, control each of the edge intelligent agents to iteratively solve each of the augmented Lagrangian objective functions by using the preset distributed optimization algorithm until a preset iteration convergence condition is reached, and output the regional decision variables of each of the edge areas as the distributed collaborative optimization strategy.

[0031] Specifically, since the decomposed distributed optimization control sub-model is a convex programming model with separable objective function and linear boundary coupling constraints, the present invention uses a synchronous alternating direction multiplier algorithm that introduces the historical iteration results of the edge agents and the state increments of the coupling branches to achieve distributed solution. Still taking the edge area a and its adjacent edge area b as an example, the distributed optimization control sub-models corresponding to these two edge areas are the edge a sub-problem and the edge b sub-problem (where the edge b sub-problem corresponds to the distributed optimization control sub-models of all adjacent edge areas of the edge area a). Then, based on these two sub-problems, the augmented Lagrangian objective function corresponding to the objective function of each edge agent is constructed. and , and through appropriate transformation, it is transformed into: In the formula, t is the number of iterations; and are the initial values of the coupling branch states of the edge areas a and b respectively; and are the fixed reference values of the (t + 1)-th iteration of the edge areas a and b respectively; λ a and λ b are the dual variables of the edge areas a and b respectively, and each of them contains 4 elements, such as correspond to the coupling branch state respectively; is the penalty parameter; is the square of the 2-norm.

[0032] Next, the edge constraint conditions of each edge area are determined. The edge constraint conditions of the edge area a can be expressed as: That is, the constraint conditions in the above-mentioned optimization control model of the distribution network are restricted to those within the edge area a. Similarly, the edge constraint conditions of the edge area b also restrict the constraint conditions in the above-mentioned optimization control model of the distribution network to the corresponding edge area, which will not be elaborated here.

[0033] For the solution of each distributed optimization control sub-model, that is, under the edge constraint conditions corresponding to each edge region, with the goal of minimizing the augmented Lagrangian objective function, the edge agents corresponding to this region adopt a synchronous alternating direction multiplier algorithm that introduces the historical iteration results of the edge agents and the state increment of the coupled branch to iteratively solve the augmented Lagrangian objective function of this region until the preset iteration convergence condition is reached. Then, the regional decision variables of each edge region (that is, the finally updated coupled branch state) are output and used as a distributed collaborative optimization strategy to control each edge agent to adjust the line power flow, distributed power generation power, and node voltage in this region to ensure that the distribution network operates in an optimal state. Among them, the preset iteration convergence condition is that the boundary residual tends to zero, and the boundary residual is the square of the two-norm of the difference in the coupled branch states obtained by adjacent edge regions, as shown in the following formula: In the formula, is the convergence accuracy.

[0034] When the regional decision variables output by each edge region satisfy the above formula, the iteration ends. Through distributed optimization control, the present invention decomposes large-scale optimization problems into multiple sub-problems and processes them in parallel by each edge agent, thus significantly improving the optimization efficiency; the distributed optimization strategy enables the system to have a strong tolerance to the failure or malfunction of a single agent, enhancing the robustness and reliability of the system; by constructing an augmented Lagrangian objective function and considering edge constraint conditions, the problem can be more accurately described and optimized, realizing the reasonable allocation and efficient utilization of resources; each edge agent works collaboratively under the distributed optimization control framework to jointly solve the optimization problem, which helps to achieve the global optimal solution or an approximate optimal solution.

[0035] In another embodiment, the solution of each distributed optimization control sub-model can be implemented by combining the distributed stochastic gradient descent algorithm and the federated learning method: still taking the edge region a and its adjacent edge region b as an example, determine the objectives and coupling constraints according to the distributed optimization control sub-models of the edge region a and the edge region b; 1. Initialization stage: Initialize the global model parameters, and distribute the global model parameters to the edge agents a and b, and set the learning rate, communication period, and maximum number of iterations; 2. Local update stage: Stochastic gradient descent update: Each edge agent randomly samples a mini-batch from the local dataset, calculates the stochastic gradient to update the local variables, and local iteration: within each communication period, a and b respectively perform the stochastic gradient descent update process for the number of times of the communication period; 3. Global aggregation: At the end of each communication period, a and b upload the local model parameters to the central server for global aggregation, and the central server receives the model parameters of a and b to calculate the global model parameters and distribute them to a and b; 4. Check for convergence: a and b calculate the boundary residuals according to the obtained parameters. If the convergence condition is met, the algorithm terminates and outputs the coupling branch states of their respective regions; otherwise, continue to iterate the above process. This solution can accelerate model training, protect data privacy, improve the model generalization ability, has flexibility and scalability, can promote efficient resource utilization, and is particularly suitable for processing large-scale datasets and distributed computing environments, providing new ideas and solutions for the training and deployment of machine learning models.

[0036] In one embodiment, controlling each of the edge agents to iteratively solve each of the augmented Lagrangian objective functions by using the preset distributed optimization algorithm includes: Initialize the dual variables and penalty parameters of each of the edge agents, and initialize its own coupling branch state and fixed reference value through the historical iteration results and coupling branch state increments of each of the edge agents; According to the dual variables, penalty parameters, and fixed reference values of each of the edge agents after initialization, use the gradient descent method to solve each of the augmented Lagrangian objective functions to obtain the regional decision variables of each of the edge regions; When the regional decision variables do not reach the preset iteration convergence condition, control each of the edge agents to interact with its adjacent edge agents to exchange its own regional decision variables, so that each of the edge agents updates its own fixed reference value and dual variable according to the regional decision variables of each adjacent edge agent; Update the penalty parameter through the adaptive penalty parameter adjustment method, so that each of the edge agents solves each of the augmented Lagrangian objective functions based on the updated fixed reference value, dual variable, and penalty parameter to obtain the updated regional decision variables of each; When the updated regional decision variables in each area do not meet the preset iterative convergence condition, repeat the update steps of the fixed reference value, penalty parameter, and dual variable, as well as the solution steps for each of the augmented Lagrangian objective functions, based on the updated regional decision variables in each area until the updated regional decision variables in each area meet the preset iterative convergence condition.

[0037] Specifically, first initialize each parameter required in the synchronous alternating direction multiplier algorithm, that is, set the initial dual variable and penalty parameter for each edge agent, and these parameters will be continuously updated in the subsequent iterative process; among them, considering that the edge agent can store the previous iterative values, the present invention pre-updates the decision variable value by comprehensively using the historical iterative results and the coupling branch state increment, so as to improve the convergence performance. Then, the coupling branch state of each edge agent is updated by its own historical iterative results and increment, which is expressed by the following formula: In the formula, and are the coupling branch state increments of the edge regions a and b respectively; t is the number of iterations; and are the initialized coupling branch states of the edge regions a and b respectively; is the number of historical iterative values stored by the edge agent; and are the increment coefficients of the edge regions a and b respectively, and they are determined by solving the minimization error; and are the historical increment coefficients corresponding to the edge regions a and b at the i-th historical iteration respectively.

[0038] At the same time, initialize the fixed reference value of each edge agent by using the historical iterative results of each edge agent, which is expressed by the following formula: Then, adopt the gradient descent method to solve the augmented Lagrangian objective function of each edge region based on the initialized dual variable, penalty parameter, and fixed reference value, and obtain the initial regional decision variable, that is: Based on whether the initial regional decision variable obtained by the foregoing boundary residuals and preset number of iterations meets the conditions, if not, control each edge agent to interact with its adjacent edge agents to exchange its own regional decision variable (that is, the coupled branch state obtained from the above formula) and ), and calculate the average value of the coupled branch states of each edge agent respectively as the fixed reference value for the next iteration: Control each edge agent to update the dual variable of its own region respectively: Adopt the adaptive penalty parameter adjustment method to update the penalty parameter, which is represented by the following formula: In the formula, , are the penalty parameters before and after update respectively; and are adjustable parameters, which can be set to v = 2, is 10; is the fixed reference value at the t-th iteration; is the 2-norm, also known as the Euclidean norm. Since the convergence of the synchronous alternating direction multiplier algorithm is related to the global nature of the solution and the penalty parameter, adopting the adaptive penalty parameter adjustment method can satisfy the convergence while maintaining the global nature of the solution.

[0039] Subsequently, control each edge agent to solve each augmented Lagrangian objective function based on the updated fixed reference value, dual variable and penalty parameter through the gradient descent method or other algorithms to obtain the updated regional decision variables; continue to judge whether the updated regional decision variables converge. If not, based on the updated regional decision variables, repeat the update steps of the fixed reference value, penalty parameter and dual variable and the solution steps of each augmented Lagrangian objective function until the updated regional decision variables reach the preset iteration convergence condition. The solution process of each distributed optimization control sub-model is as Figure 3 shown.

[0040] Through the cooperation of edge agents, the present invention realizes the distributed optimization of regional decision variables, improves the computing efficiency and scalability; since the data does not need to be centrally processed, the data privacy of edge agents is protected; through the adaptive penalty parameter adjustment method, the scheme can dynamically adjust the penalty parameter according to the actual situation, improve the convergence speed and optimization effect; through the preset iteration convergence condition, the scheme can ensure that the finally obtained regional decision variables meet certain accuracy requirements.

[0041] In one embodiment, the schematic diagram of the IEEE 33 - node system topology and edge division is as follows Figure 4 shown. Taking the Figure 4 shown distribution network as an example to verify the effectiveness of the proposed method. Among them, the IEEE 33 - node system is divided into 3 edge regions, and each region is managed by an edge agent. According to the zoning method of copying the boundary branches and placing them in two adjacent edge regions at the same time, the sets of nodes representing the edge regions are: Edge Region 1: {1 - 8, 19 - 26}, Edge Region 2: {7 - 18}, Edge Region 3: {6, 26 - 33}. The installation locations of 5 controllable distributed power sources are nodes {8, 12, 16, 21, 30}. The active power output of each distributed power source is set to 400 kW, the maximum reactive power output is 400 kvar, the upper limit of the voltage security constraint is 1.05 pu, and the lower limit is 0.95 pu.

[0042] The power flow calculation uses per - unit values. The base power of the system is 1.0 MVA, the voltage base is selected as 12.66 kV, the slack node is node 1, and the voltage is 1.0 pu. At this time, the voltage deviation of the end - node 33 in the IEEE 33 - node system reaches 0.052 pu, and the network loss is 202.7 kW, triggering an event of excessive network loss in the distribution network (assuming that the allowable threshold of network loss set by the edge agent is 180 kW). The edge agent needs to take actions to eliminate the event.

[0043] Using the distributed cooperative optimization control method of the distribution network described in the present invention to optimize the control of distributed power sources in the system, the penalty parameter is taken as 0.05, and the convergence accuracy is taken as , and the voltage comparison diagram of the IEEE 33 - node system before and after optimization can be obtained as follows Figure 5 shown. From the Figure 5 figure, it can be seen that after the optimization control, the voltage distributions of the 3 edge systems have been significantly improved. The voltages of all nodes meet the requirements of safe operation, the voltage deviation is significantly reduced. After the optimization control, the network loss of the IEEE 33 - node system is reduced to 36.454 kW, which is within the allowable threshold set by the edge agent, eliminating the event of excessive network loss in the distribution network and improving the economic efficiency of the distribution network operation.

[0044] In order to verify the correctness and effectiveness of the distributed cooperative optimization control method of the distribution network described in the present invention, its control effect is compared with that of the centralized optimization control method. Among them, the centralized optimization method uses the primal - dual interior - point method for solution. Then, the comparison of the reactive power outputs of the distributed power sources in the system calculated by the distributed method and the centralized method is shown in the following table: As can be seen from the above table, the output of the distributed power source under distributed optimization control is the same as that under centralized optimization control, which indicates the correctness of the result obtained by using the improved synchronous alternating direction multiplier algorithm to solve the optimization control model distributively.

[0045] Distributed solution is an iterative optimization process, which requires each edge agent to interact with the state information of the coupled branch in each iteration. Therefore, the fewer the number of iterations required for the solution to converge, the fewer the number of communications required to obtain the convergent cooperative control strategy, and the smaller the communication burden. The iterative variation diagram of the boundary residuals of each edge obtained by applying the distributed cooperative optimization control method proposed in the present invention and the conventional ADMM algorithm is as Figure 6 shown. The method proposed in the present invention converges after 13 iterations, while the conventional ADMM algorithm needs 20 iterations to complete the iterative convergence. It can be seen from this that the method proposed in the present invention has a faster convergence speed.

[0046] The iterative variation diagram of the reactive power output of the distributed power source in the IEEE 33-node system is as Figure 7 shown, which shows the change of the reactive power output of the distributed power source optimized by 3 edges with the iterative process. It can be seen that among the 3 edges, the distributed optimization control method described in the present invention can quickly reach convergence, requires fewer iterations, has a small communication burden between adjacent edge agents, and the agent can obtain the control strategy of its own edge area quickly. Because the optimization sub-problems established by each edge agent are simple convex quadratic programming problems, the global optimal solution can be obtained in each iteration, which is conducive to quickly converging to the consistent control strategy of each area; and the speed of each edge agent to solve the sub-optimization problem is also relatively fast.

[0047] In order to analyze the adaptability of the distributed method proposed in the present invention to the change of the system operation state, the daily load curve diagram of the IEEE 33-node system is as Figure 8 shown, and each load power changes according to the 96-point normalized daily load curve shown in Figure 8 . The active power values of each load in the previous analysis correspond to the load values corresponding to the normalized load of 1.0 at the 68th moment in Figure 8 , and the load power factor remains unchanged at each moment. Distributed optimization control is performed under the system state at each moment point, and the comparison of the network losses of the IEEE 33-node system before and after optimization is shown in the appendix Figure 9 shown. As can be seen from the appendix Figure 9 , in the 3 edge subsystems, with the continuous change of the load, the method of edge agent autonomy and multi-party cooperation can achieve distributed optimization control of the system at each moment point, the network loss is significantly reduced, the business goal of network loss optimization is achieved, and at the same time it also shows that the proposed method has good adaptability to the change of the system operation state.

[0048] In the embodiments of the present application, in view of the problem of how to effectively improve the operation stability of the distribution network, a distributed collaborative optimization control method for the distribution network is designed. By dividing the global distribution network into multiple regions and constructing distribution network edge agents as the edge computing carriers of the optimization strategy, the local execution of data collection, processing, and optimization control is realized, which not only improves the data processing efficiency, but also reduces the dependence on the central control system, enhancing the reliability and flexibility of the system. When the monitoring system detects that the network loss is too high, the edge agent can quickly start the network loss optimization service processing flow, and effectively reduce the system network loss and improve the node voltage stability by adjusting devices such as distributed power sources. This real-time and automated optimization control strategy helps to improve the safe and economic operation level of the power system and reduce energy waste. By reasonable simplification, convexification, and iterative processing, the non-convex optimization problem is transformed into a convex optimization problem to construct the optimization control model, ensuring the convergence and global optimality of the distributed algorithm solution, which not only simplifies the solution process of the optimization problem, but also improves the accuracy and reliability of the optimization results. In terms of distributed collaborative control, the present invention realizes information sharing and collaborative optimization between adjacent edge agents by constructing multiple distributed collaborative optimization sub-models, which helps to balance the power supply and demand in each region and improve the stability and economy of the entire power system.

[0049] It should be noted that although the steps in the above flowcharts are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders.

[0050] In another embodiment, as Figure 10 shown, the second aspect of the present invention provides a distributed collaborative optimization control system for a distribution network, including: A network loss monitoring module 10 for real-time monitoring of the network loss data of the distribution network; A model construction module 20 for, when the network loss data exceeds a preset network loss threshold, taking the network active power loss of the distribution network as the objective function, respectively constraining the line power flow, distributed power source power, and node voltage in the distribution network, and performing semidefinite programming reconstruction on the formed constraint conditions, and constructing the optimization control model of the distribution network with the reconstruction result and the objective function; A model decomposition module 30 for obtaining the coupling branch states between multiple edge regions in the distribution network, and decomposing the optimization control model into several distributed optimization control sub-models based on partition coordination based on the coupling branch states; The policy solving module 40 is configured to control the edge agents deployed in each of the edge regions to solve each of the distributed optimization control sub-models by using a preset distributed optimization algorithm, so as to obtain a distributed collaborative optimization policy; the preset distributed optimization algorithm is a synchronous alternating direction multiplier algorithm that introduces the historical iteration results and increments of each of the edge agents.

[0051] It should be noted that each module in the above-mentioned distributed collaborative optimization control system of a distribution network can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. For the specific limitations of a distributed collaborative optimization control system of a distribution network, refer to the limitations of a distributed collaborative optimization control method of a distribution network in the above text. The two have the same functions and effects, and will not be elaborated here.

[0052] A third aspect of the present invention provides an electronic device, which includes: A processor, a memory, and a bus; The bus is used to connect the processor and the memory; The memory is used to store operation instructions; The processor is configured to execute, by calling the operation instructions, instructions to cause the processor to execute the operations corresponding to a distributed collaborative optimization control method of a distribution network as shown in the first aspect of the present application.

[0053] In an alternative embodiment, an electronic device is provided, as Figure 11 shown, Figure 11 The electronic device 5000 shown includes a processor 5001 and a memory 5003. Among them, the processor 5001 and the memory 5003 are connected, such as connected by a bus 5002. Optionally, the electronic device 5000 may further include a transceiver 5004. It should be noted that in actual applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation to the embodiments of the present application.

[0054] The processor 5001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of the present application. The processor 5001 may also be a combination that implements computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0055] The bus 5002 may include a path for transmitting information between the above components. The bus 5002 can be a PCI bus, an EISA bus, or the like. The bus 5002 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 11 only a thick line is used to represent it in Figure 11 , but it does not mean that there is only one bus or one type of bus.

[0056] The memory 5003 can be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM, a CD-ROM, or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0057] The memory 5003 is used to store the application program code for implementing the solution of this application, and is controlled by the processor 5001 to execute. The processor 5001 is used to execute the application program code stored in the memory 5003 to implement the content shown in any of the foregoing method embodiments.

[0058] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0059] The fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements a distributed collaborative optimization control method for a distribution network shown in the first aspect of this application.

[0060] Another embodiment of this application provides a computer-readable storage medium, on which a computer program is stored, and when it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0061] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the above method.

[0062] In summary, the present invention relates to the field of intelligent optimized operation of distribution networks, and discloses a distributed collaborative optimization control method, system, device and medium for a distribution network. By partitioning the distribution network and configuring edge agents to monitor the network loss data of the distribution network in real time, when the network loss exceeds a preset threshold, an optimization control process is triggered: taking the active power loss of the network as the objective function, constraining the line power flow, distributed power source power and node voltage, and reconstructing through semidefinite programming to construct an optimization control model that is a convex quadratic programming model; based on the coupling branch states between regions, the constructed model is decomposed into several distributed optimization control submodels based on partition coordination, and a synchronous alternating direction multiplier algorithm introducing the historical iteration results and increments of each edge agent is used to solve each submodel to obtain a distributed collaborative optimization strategy and execute it; through partition management, distributed optimization and collaborative control, the efficient operation and optimization of the distribution network are realized.

[0063] Each embodiment in this specification is described in a progressive manner. For parts that are the same or similar in each embodiment, they can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0064] The above embodiments only represent several preferred implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and substitutions can be made, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the protection scope of the claimed rights.

Claims

1. A distributed collaborative optimization control method for a distribution network, characterized in that: include: Real-time monitoring of distribution network loss data; When the network loss data exceeds a preset network loss threshold, the network active loss of the distribution network is used as the objective function, the line flow, distributed power source power and node voltage in the distribution network are constrained respectively, and the formed constraint conditions are reconstructed by semi-definite programming, and the optimization control model of the distribution network is constructed with the reconstruction result and the objective function; Acquire coupling branch states between a plurality of edge areas in the distribution network, and decompose the optimization control model into a plurality of distributed optimization control sub-models based on partition coordination based on the coupling branch states; Controlling the edge agents deployed in each of the edge areas to solve each of the distributed optimization control sub-models using a preset distributed optimization algorithm to obtain a distributed collaborative optimization strategy; The preset distributed optimization algorithm is a synchronous alternating direction multiplier algorithm that introduces the historical iteration results and increments of each edge agent.

2. A distributed collaborative optimization control method for a distribution network according to claim 1, characterized in that: Before the real-time monitoring of the network loss data of the distribution network, the method further includes: The stable connection area in the distribution network is used as the edge of the power grid to divide the distribution network into regions, and a plurality of edge regions are obtained; the stable connection area is configured as static interconnection within the region, the regions are not directly connected, the power supply of the region is the upper level substation, and the boundary between adjacent regions is the normally open tie switch in the distribution network; Modeling the electrical equipment in each of the edge areas to describe the equipment parameters, operating status, installation location, and control or adjustment methods of each edge area to generate a basic attribute model; An edge agent is configured for each edge area, and each basic attribute model is used as the static structure of each edge agent. Real-time operation data in each edge area is collected and stored through each basic attribute model to construct the operation status of each edge agent.

3. The distributed collaborative optimization control method of a distribution network according to claim 1, characterized in that: The semidefinite programming reconstruction of the formed constraints is performed by the following formula: Where P ij , Q ij are respectively the active and reactive power transmitted at the head end of line ij; l ij is the square value of the current amplitude of line ij; U i is the square value of the voltage amplitude at node i; is the voltage amplitude at node j; U j is the square value of the voltage amplitude at node j; The optimization control model of the distribution network is expressed by the following formula: In the formula, q g is the reactive power generated by the distributed generation; n is the total number of nodes; rij and xij are the resistance and reactance of line ij respectively; is the square value of the voltage amplitude of the equilibrium node; P jk , Q jk are the active and reactive power transmitted at the head end of line jk, respectively; k:j→k represents the set of all lines with node j as the head end and node k as the end; N is the set of nodes in the distribution network; p c j ,q c j are the active and reactive power of the load at node j respectively; p g j is the active power generated by the distributed power supply at node j; V ref is the reference value of the voltage amplitude of the equilibrium node; , are the minimum and maximum values ​​of reactive power generated by the distributed generation at node j; is the voltage deviation.

4. The distributed collaborative optimization control method of a distribution network according to claim 1, characterized in that: The obtaining of coupling branch states between a plurality of edge areas in the distribution network and decomposing the optimization control model into a plurality of distributed optimization control sub-models based on partition coordination based on the coupling branch states comprises: Acquire a node set and a branch set in each edge region, so as to couple adjacent edge regions through branches on edge boundaries, obtain coupling branches between the edge regions, and use the power transmitted on each coupling branch and the square of the voltage at the nodes at both ends of each branch as the corresponding coupling branch state; Based on the principle that the coupling branch state of each edge region is equal to the coupling branch state of its adjacent edge region, the optimization control model is decomposed into a plurality of distributed optimization control sub-models based on partition coordination; the number of the distributed optimization control sub-models is consistent with the number of the edge regions; the distributed optimization control sub-models are represented by the following formula: Where r is the total number of edge regions; f a (x a ),h a (x a ), g a (x a ) are the objective function, equality constraint, and inequality constraint of the distributed optimization control sub-model of the a-th edge region respectively; x a a is the coupling branch state of the a-th edge region; b is other edge regions adjacent to the a-th edge region.

5. The distributed collaborative optimization control method of a distribution network according to claim 1, characterized in that: The control of the edge agents deployed in the edge areas uses a preset distributed optimization algorithm to solve each of the distributed optimization control sub-models to obtain a distributed collaborative optimization strategy, including: Based on each of the distributed optimization control sub-models, control each of the edge agents to construct an augmented Lagrangian objective function and edge constraint conditions for the edge region to which it belongs; Under each of the edge constraints, each of the edge agents is controlled to use the preset distributed optimization algorithm to iteratively solve each of the augmented Lagrangian objective functions until the preset iterative convergence conditions are reached, and the regional decision variables of each of the edge regions are output as a distributed collaborative optimization strategy.

6. A distributed collaborative optimization control method for a distribution network according to claim 5, characterized in that: The controlling each of the edge agents to adopt the preset distributed optimization algorithm to iteratively solve each of the augmented Lagrangian objective functions includes: Initializing the dual variables and penalty parameters of each edge agent, and initializing the coupling branch state and fixed reference value of itself through the historical iteration results and coupling branch state increments of each edge agent; According to the initialized dual variables, penalty parameters and fixed reference values ​​of each edge agent, the augmented Lagrangian objective function is solved by using the gradient descent method to obtain the regional decision variables of each edge region; When the regional decision variable does not reach the preset iterative convergence condition, controlling each edge agent to interact with its adjacent edge agents to determine its own regional decision variable, so that each edge agent updates its own fixed reference value and dual variable according to the regional decision variables of each adjacent edge agent; The penalty parameter is updated by an adaptive penalty parameter adjustment method, so that each edge agent solves each augmented Lagrangian objective function based on the updated fixed reference value, dual variable and penalty parameter to obtain updated regional decision variables; When the updated regional decision variables do not meet the preset iterative convergence conditions, the updating steps of fixing the reference value, the penalty parameter and the dual variable and the solving steps of the augmented Lagrangian objective functions are repeatedly executed based on the updated regional decision variables until the updated regional decision variables meet the preset iterative convergence conditions.

7. A distributed collaborative optimization control method for a distribution network according to claim 6, characterized in that: The historical iteration results and incremental updates of the coupling branch states of the edge agents are expressed as follows: In the formula, , are the coupling branch state increments of edge regions a and b respectively; t is the number of iterations; , They are the coupling branch states after initialization in edge regions a and b respectively; , are the initial values ​​of the coupling branch states in edge regions a and b, respectively; m is the number of historical iteration values ​​stored by the edge agent; , are the incremental coefficients of edge regions a and b respectively; , are the historical increment coefficients corresponding to the edge areas a and b at the i-th historical iteration respectively; The adaptive penalty parameter adjustment method is expressed by the following formula: In the formula, , are the penalty parameters before and after the update respectively; and is an adjustable parameter; is the fixed reference value at the tth iteration.

8. A distributed collaborative optimization control system for a distribution network, characterized in that: include: Network loss monitoring module, used to monitor network loss data of distribution network in real time; A model building module is used to, when the network loss data exceeds a preset network loss threshold, use the network active loss of the distribution network as an objective function, constrain the line flow, distributed power source power and node voltage in the distribution network respectively, and perform semi-definite programming reconstruction on the formed constraint conditions, and construct an optimization control model of the distribution network with the reconstruction result and the objective function; A model decomposition module, used for obtaining the coupling branch states between multiple edge areas in the distribution network, and decomposing the optimization control model into a plurality of distributed optimization control sub-models based on partition coordination based on the coupling branch states; A strategy solving module, used to control the edge agents deployed in each of the edge areas to solve each of the distributed optimization control sub-models using a preset distributed optimization algorithm to obtain a distributed collaborative optimization strategy; The preset distributed optimization algorithm is a synchronous alternating direction multiplier algorithm that introduces the historical iteration results and increments of each edge agent.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the distributed collaborative optimization control method of the distribution network as described in any one of claims 1 to 7.

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

Images