Optimization method and system for low-voltage distribution-microgrid automatic commutation device

Abstract

The invention relates to a distribution-micro-grid technology, and discloses an optimization method and system for a low-voltage distribution-micro-grid automatic commutation device, and the method comprises the steps: connecting a distribution network with a target region low-voltage distribution-micro-grid through an automatic commutation device, and carrying out the detailed production process description of the target region low-voltage distribution-micro-grid. And obtaining a low-voltage distribution-microgrid node load change corresponding to the low-voltage distribution-microgrid production plan in the target area, and meanwhile, considering the uncertainty of new energy output, and proposing a strategy of the action of the automatic commutation device under the situation of the minimum operation cost of the system and the three-phase unbalance degree. According to the method disclosed by the invention, the three-phase imbalance treatment of the power distribution network can be realized through load phase online switching according to a low-voltage distribution-microgrid production plan.

Description

Technical Field

[0001] This invention relates to distribution-microgrid technology, and more particularly to an optimization method and system for automatic phase commutation devices in low-voltage distribution-microgrids. Background Technology

[0002] With the new round of power system reform, the operation and management structure of the power system has changed. The scale of energy access to the energy internet, such as wind, solar, and energy storage, is gradually expanding. A large number of load resources with regulation potential have emerged on the distribution network side, and the energy consumption patterns of parks covering commercial, industrial, or residential areas are complex and diverse. As the distribution network coupled with the low-voltage distribution-microgrid structure of the parks becomes increasingly complex, covering a wide range of users of various types, and including a large number of single-phase users, the phenomenon of three-phase load imbalance is prone to occur, bringing new challenges to the safe and stable operation of the power system.

[0003] In the existing technology, the main methods for addressing the three-phase imbalance problem in the distribution network are manual phase switching and the use of reactive power compensation devices.

[0004] Manual phase switching involves manually switching the load when a three-phase imbalance is detected, based on the knowledge and experience of power grid workers. This method heavily relies on the professional skills of the personnel and cannot be used for online load switching according to actual conditions, thus the effectiveness of the solution cannot be guaranteed.

[0005] The principle of using reactive power compensation devices is to combine a compensation network consisting of static var compensators (SVCs) with the load, using an asymmetrical compensation network to compensate for phase-to-phase load imbalances and achieve three-phase load balance in the distribution network. However, this method generally only alleviates the three-phase imbalance at the distribution network end and requires high load stability.

[0006] With the introduction of automatic phase-switching devices for low-voltage loads, three-phase imbalance can be mitigated through online load phase switching. Therefore, considering the load changes in the production process of the low-voltage distribution-microgrid in the industrial park, as well as the operation plan and cost of the automatic phase-switching device, it is of great significance to study strategies for mitigating three-phase imbalance in the distribution-low-voltage distribution-microgrid while minimizing the total system operating cost. Summary of the Invention

[0007] This invention addresses the problem that existing low-voltage distribution-microgrid automatic phase-switching devices can only alleviate three-phase imbalance at the distribution network end and have high requirements for load stability. It provides an optimized method and system for low-voltage distribution-microgrid automatic phase-switching devices.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution: An optimization method for automatic phase commutation devices in low-voltage distribution microgrids, the method comprising: A dynamic load model of the low-voltage distribution-microgrid production process is constructed based on the production process of the target area. An operation model for the automatic phase commutation device of the low-voltage distribution-microgrid was established by using a dynamic load model of the low-voltage distribution-microgrid production process in the target area. By using the operation model of the automatic phase commutation device of the low-voltage distribution-microgrid, the optimal scheduling model of the low-voltage distribution-microgrid with Distflow three-phase optimal power flow is improved. Based on the improved Distflow three-phase optimal power flow low-voltage distribution-microgrid optimal scheduling model, the deep neural network method integrating two-stage clustering is used to simulate typical wind and solar operation scenarios, and the planned action strategy and optimal scheduling of automatic phase switching device are obtained.

[0009] As a preferred option: Establishing an operating model for the automatic commutation device of the low-voltage distribution-microgrid using a dynamic load model of the low-voltage distribution-microgrid production process in the target area includes: Based on the production process load dynamic model of the low-voltage distribution-microgrid in the target area, dynamic data of load change of at least one node in the low-voltage distribution-microgrid during the scheduling cycle are obtained. Automatic phase commutation device is used as the connection interface between low-voltage distribution microgrid and low-voltage distribution network. The automatic phase commutation device is configured to dynamically switch the phase sequence connection of its node in response to control commands. Based on dynamic load change data and the line connection structure between the low-voltage distribution network and the low-voltage distribution-microgrid, an operation model of the automatic phase commutation device for the low-voltage distribution-microgrid is constructed.

[0010] As a preferred option, the operating model of the automatic phase commutator for low-voltage distribution-microgrids includes state variables representing the connection status of the automatic phase commutator with each phase line at different times and constraints that limit the operation logic of the automatic phase commutator.

[0011] As a preferred option, the improved low-voltage distribution-microgrid optimal scheduling model for three-phase optimal power flow, based on the operation model of the low-voltage distribution-microgrid automatic phase commutation device, includes: Based on the operation model of the automatic phase commutation device of low-voltage distribution-microgrid, a multi-objective optimization scheduling model is constructed. Solve the multi-objective optimization scheduling model to generate the action strategy of the automatic commutation device and the output plan of each unit in the system.

[0012] As a preferred option, multi-objective optimization scheduling models include: The first objective function is used to minimize the total operating cost of the system. The second objective function is used to minimize the three-phase current imbalance at at least one critical node in the low-voltage distribution-microgrid; Three-phase power flow constraint functions are used to study the electrical and physical laws of distribution networks and low-voltage distribution-microgrids under three-phase asymmetrical operation.

[0013] As a preferred option, the Distflow three-phase optimal power flow low-voltage distribution-microgrid optimization scheduling model includes a three-phase distribution network operation model, a photovoltaic unit operation model, a wind turbine unit operation model, and an energy storage operation model.

[0014] As a preferred approach, constructing a low-voltage distribution-microgrid production process load dynamic model based on the production process of the target area includes: Determine the production process for the target area, which includes multiple production stages that are sequential in time and logically dependent. Establish a correspondence between multiple production stages and at least one node in the low-voltage distribution-microgrid of the target area, with one production stage corresponding to one or more nodes; Based on the correspondence between production stages and nodes, as well as the operating logic and energy consumption characteristics of each production stage, a dynamic model of production process load is constructed. The dynamic model of production process load is used to dynamically predict the load change of at least one node over time.

[0015] As a preferred option, the production process includes raw material production, first-stage warehousing and transportation, sorting and packaging, and second-stage warehousing and transportation.

[0016] As a preferred option: Based on the improved Distflow three-phase optimal power flow low-voltage distribution-microgrid optimal scheduling model, and incorporating a deep neural network method with two-stage clustering to simulate typical wind and solar operation scenarios, the planned action strategy and optimized scheduling of the automatic phase commutation device are obtained, including: The generation of typical daily photovoltaic and wind power output samples in different seasons is based on historical processed data of the target area. Through scene clustering analysis and deep neural network learning, typical daily photovoltaic and wind power output samples in different seasons are generated. By using typical daytime photovoltaic and wind power output samples from different seasons, the production plan and dynamic changes of nodal loads of the low-voltage distribution-microgrid in the target area under the corresponding scenarios are determined. By analyzing the production plans and dynamic changes in node loads of the low-voltage distribution-microgrid in the target area under corresponding scenarios, and taking the total system operating cost and the three-phase imbalance of key nodes in the distribution network as optimization objectives, a mixed-integer linear programming model is constructed. The decision variables of the mixed-integer linear programming model include the operating state of the automatic commutation device. Solve the mixed-integer linear programming model to generate the planned action strategy and optimized scheduling of the automatic phase commutation device within the scheduling cycle.

[0017] To address the aforementioned technical problems, the present invention also provides an optimization system for an automatic phase-commutation device in a low-voltage distribution-microgrid, which implements an optimization method for such a device, comprising: The module for constructing the dynamic model of microgrid production process load builds a dynamic model of microgrid production process load based on the production process of the target area. The module for establishing the operation model of the low-voltage distribution-microgrid automatic phase commutation device establishes the operation model of the low-voltage distribution-microgrid automatic phase commutation device through the dynamic load model of the microgrid production process in the target area. An improved module of the Distflow three-phase optimal power flow low-voltage distribution-microgrid optimal scheduling model is provided. This module improves the Distflow three-phase optimal power flow low-voltage distribution-microgrid optimal scheduling model by using the low-voltage distribution-microgrid automatic phase commutation device operation model. The module for determining the planned action strategy and optimal scheduling of the automatic phase commutation device is based on the improved Distflow three-phase optimal power flow low-voltage distribution-microgrid optimal scheduling model. It integrates a deep neural network method with two-stage clustering to simulate typical wind and solar operation scenarios, thereby obtaining the planned action strategy and optimal scheduling of the automatic phase commutation device.

[0018] This invention, by adopting the above technical solutions, has significant technical effects: This invention presents an optimized planning method for automatic phase commutation devices in low-voltage distribution-microgrids to address three-phase imbalance. The method connects the distribution network to the target area's low-voltage distribution-microgrid via an automatic phase commutation device. By detailing the production process of the target area's low-voltage distribution-microgrid, the method obtains the load changes at the nodes of the low-voltage distribution-microgrid corresponding to the production plan. Simultaneously, considering the uncertainty of renewable energy output, the method proposes strategies for minimizing system operating costs and optimizing the automatic phase commutation device's operation under three-phase imbalance scenarios.

[0019] The method of the present invention can address the three-phase imbalance of the distribution network by switching the load phase online, according to the production plan of the low-voltage distribution-microgrid. Attached Figure Description

[0020] Figure 1 This invention provides an improved topology diagram for an IEEE 33-node coupled low-voltage distribution-microgrid node system.

[0021] Figure 2 This is a diagram showing the power output characteristics of the three-phase system of the power distribution network-industrial park low-voltage distribution-microgrid of the present invention.

[0022] Figure 3 This is a characteristic diagram of the change of the three-phase unbalance index of the key three-phase lines in the power distribution network according to the present invention.

[0023] Figure 4This is a feature diagram of the planned operation strategy of the low-voltage distribution-microgrid automatic phase commutation device of the present invention.

[0024] Among them, Distflow (Distributed Flow); IEEE (Institute of Electrical and Electronics Engineers); K-means (K-means clustering algorithm); SOC (State of Charge); MILP (Mixed-Integer Linear Programming); DNN (Deep Neural Network); and ESS (Energy Storage System). Detailed Implementation

[0025] To better understand the technical content of the present invention, specific embodiments are described below in conjunction with the accompanying drawings.

[0026] Various aspects of the invention are described in this disclosure with reference to the accompanying drawings, which illustrate numerous illustrative embodiments. The embodiments of this disclosure are not necessarily intended to encompass all aspects of the invention. It should be understood that the various concepts and embodiments described above, as well as those described in more detail below, can be implemented in any of many ways, because the concepts and embodiments disclosed herein are not limited to any particular implementation. Furthermore, some aspects of the invention disclosed may be used alone or in any suitable combination with other aspects of the invention disclosed.

[0027] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0028] Example An optimization planning method for automatic phase commutation devices for managing three-phase imbalance in low-voltage distribution microgrids, such as... Figure 1 The example topology diagram of the improved IEEE 33-node coupled low-voltage distribution-microgrid node system shown illustrates an improved IEEE 33-node power distribution test system, including: a low-voltage distribution network and a target area low-voltage distribution-microgrid. The improvement over the original IEEE 33-node system lies in that nodes 7 and 12 are respectively connected to the park's low-voltage distribution-microgrid, with an automatic phase-commutation device serving as the connection interface between the low-voltage distribution-microgrid and the low-voltage distribution network. The park's production process corresponds to the park's low-voltage distribution-microgrid node, including four processes: raw material production stage, first-stage warehousing and transportation, classification and packaging stage, and second-stage warehousing and transportation. A dynamic load model of the park's low-voltage distribution-microgrid production process is constructed. Construct a dynamic load model of the low-voltage distribution-microgrid production process in the industrial park, including four stages: raw material production, primary warehousing and transportation, sorting and packaging, and secondary warehousing and transportation. The raw material production stage includes: ; ; In the formula, For production line Constant load; This refers to the production line power coefficient. Indicates production line The stopping variable at time; Indicates production line The initial variable at time; Indicates production line The runtime variables at any given moment; Indicates production line The runtime variables at any given moment; and These represent the minimum and maximum operating times of the production line, respectively. Indicates the minimum downtime of the production line; This indicates the output of the production line per unit of time. This indicates the total amount of work that needs to be completed during the production phase. This represents any point in the optimization cycle; Indicates the number of raw material production lines; Indicates the scheduling period; This represents any point in time within the scheduling period.

[0029] During the sorting and packaging stage, products need to be transferred from the upstream production line to the downstream packaging production line through the warehousing process. Therefore, warehouse waiting time needs to be considered, including: ; In the formula, For packaging production line Constant load; The power factor of the packaging production line; and These represent the number of products per hour produced through the production line and the packaging production line, respectively. Indicates packaging production line The runtime variables at any given moment; This indicates the number of products consumed per hour on the packaging production line; This represents the minimum sum of production time and warehouse waiting time.

[0030] The first and second stages of warehousing and transportation include: ; ; In the formula, , They represent Time and Warehouse status during the warehousing and transportation phase between the production line and the packaging production line; , They represent Time and Warehouse status during the second stage of warehousing; , Indicates the maximum capacity of the warehouse; , Indicates the minimum capacity of the warehouse; This indicates the number of products consumed per hour on the packaging production line; , Warehouses Constant load; , These are the warehouse power coefficients.

[0031] Based on the dynamic load model of the production process of the low-voltage distribution-microgrid in the park, dynamic data of node load changes under the production plan are obtained. The low-voltage distribution-microgrid in the park is connected to the distribution network through an automatic phase-switching device that can automatically change the phase sequence. Taking into account the symmetrical three-phase lines of the distribution network, the single-phase lines of the distribution network and the single-phase lines of the low-voltage distribution-microgrid in the park, an operation model of the low-voltage three-phase distribution network-park low-voltage distribution-microgrid automatic phase-switching device is constructed. The operation model of the automatic phase-switching device for low-voltage three-phase distribution network - industrial park low-voltage distribution - microgrid includes: ; ; ; ; In the formula, and A 0-1 state variable, representing Time and Automatic phase commutation device at all times Phase state; For auxiliary 0-1 variables; and For automatic phase commutation device in Time and A 0-1 variable indicating whether a commutation action was performed at any given time; This represents the maximum number of commutations allowed within the scheduling cycle. This is the minimum commutation holding time for the commutation device.

[0032] Based on the operation model of the automatic phase-switching device of low-voltage three-phase distribution network-park low-voltage distribution-microgrid, a three-phase imbalance index of current at key nodes of low-voltage distribution network is constructed. With the goal of minimizing the total system operating cost and alleviating the three-phase imbalance at key nodes, an optimized scheduling model of low-voltage three-phase distribution network-park low-voltage distribution-microgrid with improved Distflow three-phase optimal power flow is constructed. like Figure 2 As shown, the power output characteristic diagram of the three-phase system of distribution network-park low-voltage distribution-microgrid represents the power output characteristics of different phases of the upper-level power grid and gas turbine units under the optimization objective. This aims to alleviate the three-phase current imbalance index at key nodes and reduce the total operating cost of the system.

[0033] The three-phase current imbalance index at key nodes of the low-voltage distribution network is taken into account, including: ; In the formula, for Total phase current; , , These represent the total current of the three phases.

[0034] An improved optimal dispatch model for low-voltage three-phase distribution network-industrial park low-voltage distribution-microgrid based on Distflow three-phase optimal power flow is proposed, including a three-phase distribution network operation model, a photovoltaic unit operation model, a wind turbine unit operation model, and an energy storage operation model. The expression for the three-phase distribution network operation model is: ; ; ; In the formula, , for Time Node , between Active and reactive power of a phase line; , for Time Node , between Active and reactive power of a phase line; , for Time Node Active and reactive loads; for Time Node , between The square of the phase line current; for Time Node , between The square of the node voltage of a phase line; , They are nodes The limit for the square of voltage; , The lines are respectively Current and transmission power limits; A set of nodes; , They are nodes , Inter-line resistance and reactance.

[0035] The expression for the photovoltaic unit operation model is: ; In the formula, for Photovoltaics are always contributing power; Forecast value of photovoltaic power output; To output reactive power to the photovoltaic inverter; This refers to the rated capacity of the photovoltaic inverter. Let be the minimum power factor of the photovoltaic inverter, and be a given constant.

[0036] The expression for the wind turbine operation model is: ; ; In the formula, For wind speed, To cut into wind speed, To cut off the wind speed, The rated wind speed of the wind turbine unit. This refers to the rated output power of the wind turbine generator set. This represents the actual output of wind power. This represents the predicted wind power output.

[0037] The expression for the energy storage operation model is: ; ; In the formula, , For energy storage systems Constant input and output power; , These are 0-1 variables representing the transmission status; for Real-time energy storage system capacity; The attenuation rate; , These refer to the input and output transmission efficiencies, respectively. for Constant energy storage state of charge; This refers to the rated capacity of the energy storage. This represents the maximum number of cycles in the energy storage dispatch cycle. , , , These are the transmission power and state of charge limits, respectively. The scheduling period is [number].

[0038] The objective function of the improved Distflow three-phase optimal power flow low-voltage three-phase distribution network-industrial park low-voltage distribution-microgrid optimal scheduling model is as follows: In the formula, To optimize cost targets; The target is the system operating cost. The target is the three-phase imbalance. and These are the weighting coefficients; , and These are the power generation cost coefficients for the generating unit; for The output of the timing unit; , , They represent different phases; , , These represent the current in different phases of the line.

[0039] like Figure 3 The diagram shows the variation characteristics of the three-phase imbalance index of key three-phase lines in the distribution network. The dashed line represents the change of the three-phase imbalance of the system without considering the three-phase imbalance index, while the solid line represents the change of the three-phase imbalance of the system after optimized scheduling with the three-phase imbalance index in mind. This verifies the effectiveness of the proposed method.

[0040] like Figure 4 The diagram shows the planned action strategy of the automatic phase commutation device for low-voltage distribution-microgrids. The two solid lines represent the action strategies of the automatic phase commutation device controlling different low-voltage distribution-microgrid connections. It can be seen that the automatic phase commutation device operates significantly under the optimization target, which verifies the effectiveness of the proposed method.

[0041] Based on the improved Distflow three-phase optimal power flow optimization scheduling model for low-voltage three-phase distribution networks, industrial parks, and microgrids, a deep neural network method integrating two-stage clustering is used to simulate typical wind and solar operation scenarios. The planned action strategy and optimized scheduling operation scheme of the automatic phase commutation device are obtained, and an optimized planning process for the automatic phase commutation device for the management of three-phase imbalance in low-voltage distribution networks and microgrids is proposed.

[0042] The first phase involves collecting a large amount of historical output data of photovoltaic and wind power from distribution, low-voltage distribution, and microgrids. Then, using an adaptive K-means clustering algorithm, multi-dimensional clustering is performed on output weather, temperature, and light intensity scenarios. Based on the clustering results of the first phase, a deep neural network is trained to generate typical daily photovoltaic and wind power output samples for different seasons. Based on typical daytime photovoltaic and wind power output samples in different seasons, the production plan of the low-voltage distribution-microgrid in the park is planned, and the dynamic changes of the load of the low-voltage distribution-microgrid nodes in the park are obtained. Based on the dynamic changes in load at low-voltage distribution-microgrid nodes in the industrial park, and combined with the objective function and constraints of the three-phase imbalance governance model for low-voltage distribution-microgrid, a mixed integer linear model is constructed for solution to achieve optimized planning of automatic phase commutation devices.

[0043] Specifically, this scheme is based on the low-voltage distribution network-park low-voltage distribution-microgrid optimized scheduling model. The model is transformed into a mixed integer linear model for solution, and the planned action strategy of automatic phase switching device and the optimized scheduling operation scheme of unit output are obtained within the scheduling plan cycle.

[0044] While the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Those skilled in the art can make various modifications and refinements without departing from the spirit and scope of the invention. Therefore, the scope of protection of the present invention shall be determined by the claims.

Claims

1. A method for optimizing low-voltage distribution-microgrid automatic commutation devices, the method comprising: constructing a low-voltage distribution-microgrid production process load dynamic model through a production process of a target area; establishing a low-voltage distribution-microgrid automatic commutation device operation model through the low-voltage distribution-microgrid production process load dynamic model of the target area; improving a low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow through the low-voltage distribution-microgrid automatic commutation device operation model; based on the low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow, simulating a wind-solar typical operation scenario by a deep neural network method of two-stage clustering to obtain an automatic commutation device planned action strategy and optimization scheduling.

2. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 1, characterized in that: establishing a low-voltage distribution-microgrid automatic commutation device operation model through the low-voltage distribution-microgrid production process load dynamic model of the target area comprises: based on the low-voltage distribution-microgrid production process load dynamic model of the target area, obtaining load change dynamic data of at least one node in the low-voltage distribution-microgrid within a scheduling period; taking the automatic commutation device as a connection interface between the low-voltage distribution-microgrid and the low-voltage distribution network, the automatic commutation device being configured to dynamically switch the phase sequence connection of the node where it is located in response to a control instruction; based on the load change dynamic data and the line connection structure of the low-voltage distribution network and the low-voltage distribution-microgrid, constructing a low-voltage distribution-microgrid automatic commutation device operation model.

3. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 2, characterized in that: The low-voltage distribution-microgrid automatic commutation device operation model includes state variables for representing the connection state of the automatic commutation device with each phase line at different times and constraint conditions for defining the action logic of the automatic commutation device.

4. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 1, characterized in that: improving a low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow through the low-voltage distribution-microgrid automatic commutation device operation model comprises: based on the low-voltage distribution-microgrid automatic commutation device operation model, constructing a multi-objective optimization scheduling model; solving the multi-objective optimization scheduling model to generate an action strategy of the automatic commutation device and an output plan of each unit in the system.

5. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 4, characterized in that: The multi-objective optimization scheduling model comprises: a first objective function for minimizing the total operation cost of the system; a second objective function for minimizing the three-phase current unbalance degree of at least one key node in the low-voltage distribution-microgrid; a three-phase power flow constraint function for the electrical physical law of the distribution network and the low-voltage distribution-microgrid under three-phase asymmetric operation state.

6. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 1, characterized in that: The low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow includes a three-phase distribution network operation model, a photovoltaic unit operation model, a wind turbine operation model, and an energy storage operation model.

7. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 1, characterized in that: constructing a low-voltage distribution-microgrid production process load dynamic model through a production process of a target area comprises: determining a production process of the target area, the production process including a plurality of production stages that are continuous in time and have logical dependency relationships; establishing a correspondence between the plurality of production stages and at least one node of the low-voltage distribution-microgrid of the target area, one production stage corresponding to one or more nodes; Based on the correspondence between the production stages and the nodes, and the running logic and energy consumption characteristics of each production stage, a production process load dynamic model is constructed; the production process load dynamic model is used to dynamically predict the load of at least one node over time.

8. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 1, characterized in that: The production process includes raw material production, one-stage warehouse transportation, classification and packaging, and two-stage warehouse transportation.

9. The optimization method for low-voltage grid-connected microgrid automatic commutation device according to claim 1, characterized in that: Based on the improved low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow, the typical operation scenarios of wind and light are simulated by combining the deep neural network method of two-stage clustering, and the automatic commutation device planning action strategy and optimization scheduling are obtained, including: Generation of photovoltaic and wind power output samples under typical days in different seasons, based on historical processing data of the target area, through scene clustering analysis and deep neural network learning, photovoltaic and wind power output samples under typical days in different seasons are generated; Through the photovoltaic and wind power output samples under typical days in different seasons, the production plan and dynamic changes of node load of the target area low-voltage distribution-microgrid under the corresponding scene are determined; Through the production plan and dynamic changes of node load of the target area low-voltage distribution-microgrid under the corresponding scene, a mixed integer linear programming model is constructed with the total system operation cost and the three-phase imbalance degree of the distribution network key node as the optimization objective; wherein the decision variables of the mixed integer linear programming model include the action state of the automatic commutation device; Solving the mixed integer linear programming model generates the automatic commutation device planning action strategy and optimization scheduling within the scheduling period.

10. A low voltage distribution-microgrid automatic commutation device oriented optimization system, characterized in that, An optimization method for low-voltage distribution-microgrid automatic commutation device is used to realize any one of claims 1-9, comprising: A low-voltage distribution-microgrid production process load dynamic model construction module constructs a low-voltage distribution-microgrid production process load dynamic model through the production process of the target area; The low-voltage distribution-microgrid production process load dynamic model module establishes a low-voltage distribution-microgrid automatic commutation device operation model through the low-voltage distribution-microgrid production process load dynamic model of the target area; An improved module of the low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow improves the low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow through the low-voltage distribution-microgrid automatic commutation device operation model; An automatic commutation device planning action strategy and optimization scheduling determination module, based on the improved low-voltage distribution-microgrid optimization scheduling model of Distflow three-phase optimal power flow, simulates the typical operation scenarios of wind and light by combining the deep neural network method of two-stage clustering, and obtains the automatic commutation device planning action strategy and optimization scheduling.

Images