Distribution network feeder automation system distribution terminal arrangement method and device

Abstract

The application provides a power distribution terminal arrangement method and device for a power distribution network feeder automation system, which can be used in the technical field of power distribution automation. The method comprises the following steps: generating at least two power distribution terminal arrangement schemes of a power distribution network feeder automation system to be arranged by using electromagnetic transient simulation software; inputting each power distribution terminal arrangement scheme into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each power distribution terminal arrangement scheme; and determining a final power distribution terminal arrangement scheme of the power distribution network feeder automation system according to the classification result corresponding to each power distribution terminal arrangement scheme. The power distribution terminal arrangement method and device for the power distribution network feeder automation system provided in the application embodiment greatly accelerate the speed of solving the final power distribution terminal arrangement scheme in online application, and the machine learning algorithm has stronger robustness for complex working conditions.

Description

Technical Field

[0001] The present application relates to the field of power distribution automation technology, and in particular to a method and device for arranging power distribution terminals in a power distribution network feeder automation system. Background Art

[0002] The distribution network directly impacts the daily electricity consumption of residents. Sudden power outages caused by faults can severely disrupt normal production and daily life. Distribution automation is a crucial component of smart distribution networks and a key means of improving power supply reliability, enhancing power quality, and ensuring safe and reliable operation. As a key function in distribution automation systems, feeder automation can quickly locate and isolate faults and restore power to non-faulty areas.

[0003] For feeder automation systems, deploying terminals at every tower node and branch is neither economical nor necessary. During distribution network operation, terminals are often located at key tower nodes and branches to ensure rapid restoration of power to critical loads and minimize the economic and social impact of power outages. In distribution networks, feeder structures and operating conditions vary significantly, and the load size, number of branches, and load types connected to different feeders are highly diverse. Therefore, properly configuring terminals within feeders is a fundamental issue during the planning and design phases.

[0004] Traditionally, distribution terminal placement in feeder automation systems relied on manual experience combined with simple calculations to determine the final terminal location. In recent years, optimization algorithms such as genetic algorithms have also been adopted for automated selection. However, these optimization algorithms consume significant computational time, and the smaller the model granularity, the longer the computational time. Summary of the Invention

[0005] In response to the problems in the prior art, the embodiments of the present application provide a method and device for arranging distribution terminals in a distribution network feeder automation system, which can at least partially solve the problems in the prior art.

[0006] On the one hand, the present application proposes a method for arranging distribution terminals of a distribution network feeder automation system, comprising:

[0007] Generate at least two distribution terminal layout schemes for the distribution network feeder automation system to be deployed using electromagnetic transient simulation software;

[0008] Input each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes;

[0009] According to the classification results corresponding to each distribution terminal layout scheme, a final distribution terminal layout scheme of the distribution network feeder automation system is determined.

[0010] In some embodiments, the method further comprises:

[0011] For a distribution network feeder automation system used as a training sample, using electromagnetic transient simulation software, at least two distribution terminal layout schemes for the distribution network feeder automation system are generated;

[0012] Using an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes, and generating a labeled power distribution terminal layout scheme sample set;

[0013] The machine learning model is trained according to each distribution terminal layout plan and the label of the distribution terminal layout plan in the distribution terminal layout plan sample set to obtain a trained machine learning model.

[0014] In some embodiments, the step of using an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes and generating a labeled power distribution terminal layout scheme sample set includes:

[0015] With the goal of minimizing the importance of power loss loads, a grey wolf algorithm is used to solve the optimal distribution terminal layout scheme among the at least two distribution terminal layout schemes;

[0016] Different types of labels are set for the optimal distribution terminal layout scheme and other distribution terminal layout schemes to obtain a sample set of distribution terminal layout schemes with labels.

[0017] In some embodiments, generating at least two distribution terminal layout schemes of a distribution network feeder automation system for terminal layout using electromagnetic transient simulation software includes:

[0018] Use electromagnetic transient simulation software to establish a simulation model of the distribution network feeder automation system where terminals are to be deployed;

[0019] Fault simulation is performed based on the simulation model to generate at least two distribution terminal layout schemes for the distribution network feeder automation system.

[0020] In some embodiments, the simulation model established using electromagnetic transient simulation software includes the primary side equipment of the distribution network feeder automation system, and the primary side equipment includes distribution network feeders, distribution transformers, circuit breakers, branch switches, loads, tower nodes, external power grid models and / or distributed power sources.

[0021] In some embodiments, the simulation model established using electromagnetic transient simulation software further includes a busbar circuit breaker action logic sub-model, a distribution terminal action logic sub-model, and a tie switch action logic sub-model.

[0022] In some embodiments, the busbar circuit breaker action logic sub-model enables the circuit breaker in the simulation model to perform switching actions, thereby realizing current quick-break protection, overcurrent protection and automatic reclosing functions in the low-voltage feeder;

[0023] The power distribution terminal action logic sub-model enables the power distribution terminal in the simulation model to have the functions of immediate opening when voltage is lost, delayed closing when power is received, and switch locking;

[0024] The tie switch action logic sub-model enables the tie switch in the simulation model to have instantaneous pressure locking and load transfer functions.

[0025] In some embodiments, each distribution terminal layout scheme generated by fault simulation based on the simulation model includes the feeder structure of the distribution network feeder automation system, the feeder rated load, the feeder load under the current working conditions, the proportion of designed important loads, the proportion of important loads under the current working conditions, the proportion of the number of feeder distribution terminals, the load size covered by the feeder distribution terminal, the load size not covered by the feeder distribution terminal, the feeder distribution terminal type and / or the distribution of distribution terminals in the feeder.

[0026] In some embodiments, inputting each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes includes:

[0027] Using multiple rows of heat maps to graphically represent each of the power distribution terminal layout schemes, generating multiple rows of heat maps corresponding to each power distribution terminal layout scheme;

[0028] Multiple rows of heat maps corresponding to each distribution terminal layout scheme are respectively input into a pre-trained machine learning model to obtain the classification results output by the machine learning model for each distribution terminal layout scheme.

[0029] In some embodiments, the step of graphically representing each of the power distribution terminal layout schemes using multiple rows of heat maps to generate multiple rows of heat maps corresponding to each of the power distribution terminal layout schemes includes:

[0030] For each of the distribution terminal layout schemes, using the feeder rated load in the distribution terminal layout scheme and the feeder load under the current working condition, draw the first row of the multiple rows of heat maps corresponding to the distribution terminal layout scheme;

[0031] Using the proportion of important loads designed in the distribution terminal layout plan and the proportion of important loads under the current working conditions, draw the second row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0032] Using the feeder structure in the power distribution terminal layout plan, draw the third row of the multi-row heat map corresponding to the power distribution terminal layout plan;

[0033] Using the proportion of the number of feeder distribution terminals in the distribution terminal layout plan, draw the fourth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0034] Using the feeder distribution terminal type in the distribution terminal layout plan, draw the fifth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0035] Using the distribution of distribution terminals in the feeder in the distribution terminal layout plan, the power of the distribution terminals, and the load size covered by the feeder distribution terminals, the sixth row of the multi-row thermal map corresponding to the distribution terminal layout plan is drawn, and the multi-row thermal map corresponding to the distribution terminal layout plan is generated.

[0036] On the other hand, the present application proposes a distribution terminal arrangement device for a distribution network feeder automation system, comprising:

[0037] A first generating module is configured to generate at least two distribution terminal layout schemes for a distribution network feeder automation system to be terminal arranged using electromagnetic transient simulation software;

[0038] An input module, configured to input each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes;

[0039] A determination module is used to determine the final distribution terminal layout plan of the distribution network feeder automation system according to the classification results corresponding to each distribution terminal layout plan.

[0040] In some embodiments, the apparatus further comprises:

[0041] The second generation module is configured to generate at least two distribution terminal layout schemes for a distribution network feeder automation system as a training sample using electromagnetic transient simulation software;

[0042] a third generating module, configured to use an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes, and generate a labeled power distribution terminal layout scheme sample set;

[0043] The training module is used to train the machine learning model according to each distribution terminal layout plan and the label of the distribution terminal layout plan in the distribution terminal layout plan sample set to obtain a trained machine learning model.

[0044] In some embodiments, the third generation module is specifically configured to:

[0045] With the goal of minimizing the importance of power loss loads, a grey wolf algorithm is used to solve the optimal distribution terminal layout scheme among the at least two distribution terminal layout schemes;

[0046] Different types of labels are set for the optimal distribution terminal layout scheme and other distribution terminal layout schemes to obtain a sample set of distribution terminal layout schemes with labels.

[0047] In some embodiments, the first generating module is specifically configured to:

[0048] Use electromagnetic transient simulation software to establish a simulation model of the distribution network feeder automation system where terminals are to be deployed;

[0049] Fault simulation is performed based on the simulation model to generate at least two distribution terminal layout schemes for the distribution network feeder automation system.

[0050] In some embodiments, the simulation model established using electromagnetic transient simulation software includes the primary side equipment of the distribution network feeder automation system, and the primary side equipment includes distribution network feeders, distribution transformers, circuit breakers, branch switches, loads, tower nodes, external power grid models and / or distributed power sources.

[0051] In some embodiments, the simulation model established using electromagnetic transient simulation software further includes a busbar circuit breaker action logic sub-model, a distribution terminal action logic sub-model, and a tie switch action logic sub-model.

[0052] In some embodiments, the busbar circuit breaker action logic sub-model enables the circuit breaker in the simulation model to perform switching actions, thereby realizing current quick-break protection, overcurrent protection and automatic reclosing functions in the low-voltage feeder;

[0053] The power distribution terminal action logic sub-model enables the power distribution terminal in the simulation model to have the functions of immediate opening when voltage is lost, delayed closing when power is received, and switch locking;

[0054] The tie switch action logic sub-model enables the tie switch in the simulation model to have instantaneous pressure locking and load transfer functions.

[0055] In some embodiments, each distribution terminal layout scheme generated by fault simulation based on the simulation model includes the feeder structure of the distribution network feeder automation system, the feeder rated load, the feeder load under the current working conditions, the proportion of designed important loads, the proportion of important loads under the current working conditions, the proportion of the number of feeder distribution terminals, the load size covered by the feeder distribution terminal, the load size not covered by the feeder distribution terminal, the feeder distribution terminal type and / or the distribution of distribution terminals in the feeder.

[0056] In some embodiments, the input module is specifically configured to:

[0057] Using multiple rows of heat maps to graphically represent each of the power distribution terminal layout schemes, generating multiple rows of heat maps corresponding to each power distribution terminal layout scheme;

[0058] Multiple rows of heat maps corresponding to each distribution terminal layout scheme are respectively input into a pre-trained machine learning model to obtain the classification results output by the machine learning model for each distribution terminal layout scheme.

[0059] In some embodiments, the input module graphically represents each of the power distribution terminal layout schemes using multiple rows of heat maps, and generating multiple rows of heat maps corresponding to each power distribution terminal layout scheme includes:

[0060] For each of the distribution terminal layout schemes, using the feeder rated load in the distribution terminal layout scheme and the feeder load under the current working condition, draw the first row of the multiple rows of heat maps corresponding to the distribution terminal layout scheme;

[0061] Using the proportion of important loads designed in the distribution terminal layout plan and the proportion of important loads under the current working conditions, draw the second row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0062] Using the feeder structure in the power distribution terminal layout plan, draw the third row of the multi-row heat map corresponding to the power distribution terminal layout plan;

[0063] Using the proportion of the number of feeder distribution terminals in the distribution terminal layout plan, draw the fourth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0064] Using the feeder distribution terminal type in the distribution terminal layout plan, draw the fifth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0065] Using the distribution of distribution terminals in the feeder in the distribution terminal layout plan, the power of the distribution terminals, and the load size covered by the feeder distribution terminals, the sixth row of the multi-row thermal map corresponding to the distribution terminal layout plan is drawn, and the multi-row thermal map corresponding to the distribution terminal layout plan is generated.

[0066] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for arranging distribution terminals of a distribution network feeder automation system described in any of the above embodiments are implemented.

[0067] The embodiment of the application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the power distribution terminal arrangement method of the power distribution feeder automation system according to any one of the above embodiments.

[0068] The power distribution terminal arrangement method and device of the power distribution feeder automation system provided by the embodiment of the application perform feeder automation working condition simulation on the power distribution feeder automation system to be arranged by using electromagnetic transient simulation software, obtain at least two power distribution terminal arrangement schemes of the system, and perform power distribution terminal arrangement scheme determination by using a trained machine learning model. Since the main calculation workload can be implemented in simulation optimization and model training, the speed of solving the final power distribution terminal arrangement scheme in online application is greatly accelerated, and the machine learning algorithm has stronger robustness for complex working conditions. BRIEF DESCRIPTION OF DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without any creative effort. In the drawings:

[0070] Figure 1 is a flowchart of the power distribution terminal arrangement method of the power distribution feeder automation system provided by an embodiment of the application.

[0071] Figure 2 is a partial flowchart of the power distribution terminal arrangement method of the power distribution feeder automation system provided by an embodiment of the application.

[0072] Figure 3 is a partial flowchart of the power distribution terminal arrangement method of the power distribution feeder automation system provided by an embodiment of the application.

[0073] Figure 4 is a partial flowchart of the power distribution terminal arrangement method of the power distribution feeder automation system provided by an embodiment of the application.

[0074] Figure 5 is a partial flowchart of the power distribution terminal arrangement method of the power distribution feeder automation system provided by an embodiment of the application.

[0075] Figure 6 is a partial flowchart of the power distribution terminal arrangement method of the power distribution feeder automation system provided by an embodiment of the application.

[0076] Figure 7 is a schematic diagram of a multi-row heat map provided by an embodiment of the application.

[0077] Figure 8 Schematic diagram of a multi-row heat map provided in an embodiment of the present application.

[0078] Figure 9 It is a structural diagram of a simulation model of a distribution network feeder automation system provided in one embodiment of the present application.

[0079] Figure 10 It is a structural diagram of a busbar circuit breaker action logic sub-model provided in an embodiment of the present application.

[0080] Figure 11 It is a structural diagram of the distribution terminal action logic sub-model provided in one embodiment of the present application.

[0081] Figure 12 It is a structural diagram of the tie switch action logic sub-model provided in one embodiment of the present application.

[0082] Figure 13 It is a structural diagram of a convolutional neural network model provided in one embodiment of the present application.

[0083] Figure 14 It is a structural diagram of a distribution terminal arrangement device of a distribution network feeder automation system provided in one embodiment of the present application.

[0084] Figure 15 This is a schematic diagram of the physical structure of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0085] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clearly understood, the embodiments of the present application are further described in detail below with reference to the accompanying drawings. The illustrative embodiments of the present application and their descriptions are used to explain the present application but are not intended to limit the present application. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present application can be arranged in any order.

[0086] The terms “first,” “second,” etc. used herein do not specifically refer to an order or sequence, nor are they intended to limit this application. They are merely used to distinguish elements or operations described with the same technical terms.

[0087] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0088] As used herein, "and / or" includes any and all permutations of the items described.

[0089] The execution subject of the distribution terminal arrangement method of the distribution network feeder automation system provided in the embodiment of the present application includes but is not limited to a computer.

[0090] Figure 1 FIG. 1 is a flow chart of a method for arranging power distribution terminals in a feeder automation system of a distribution network according to an embodiment of the present application. Figure 1 As shown, the distribution terminal arrangement method of the distribution network feeder automation system provided in the embodiment of the present application includes:

[0091] S101. Generate at least two distribution terminal layout schemes for a distribution network feeder automation system to be deployed using electromagnetic transient simulation software;

[0092] S102: Input each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes;

[0093] S103: Determine a final distribution terminal layout plan for the distribution network feeder automation system according to the classification results corresponding to each distribution terminal layout plan.

[0094] The present application provides a method for arranging distribution terminals in a distribution network feeder automation system. This method uses electromagnetic transient simulation software to simulate the operating conditions of the distribution network feeder automation system undergoing terminal arrangement, obtaining at least two distribution terminal arrangement schemes for the system. This scheme is then determined using a trained machine learning model. Because the majority of computational workload can be handled through simulation optimization and model training, the speed of solving the final distribution terminal arrangement scheme in online applications is greatly accelerated, and the use of machine learning algorithms provides greater robustness for complex operating conditions.

[0095] like Figure 2 As shown, in some embodiments, the method further includes:

[0096] S201. For a distribution network feeder automation system used as a training sample, generate at least two distribution terminal layout schemes for the distribution network feeder automation system using electromagnetic transient simulation software;

[0097] S202: using an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes, and generating a labeled power distribution terminal layout scheme sample set;

[0098] S203. Train the machine learning model according to each power distribution terminal layout plan and the label of the power distribution terminal layout plan in the power distribution terminal layout plan sample set to obtain a trained machine learning model.

[0099] Specifically, the above steps S201 to S203 are the training process of the machine learning model used in step S102. The process of using electromagnetic transient simulation software to generate a distribution terminal layout plan for the distribution network feeder automation system as a training sample in step S201 is similar to the process of using electromagnetic transient simulation software to generate a distribution terminal layout plan for the distribution network feeder automation system to be terminal arranged in step S101; after obtaining at least two distribution terminal layout plans, the optimization algorithm is used to screen the optimal distribution terminal layout plan among the at least two distribution terminal layout plans, and the optimal distribution terminal layout plan and other distribution terminal layout plans are labeled respectively. Finally, each labeled distribution terminal layout plan is used to train the machine learning model to obtain a trained machine learning model.

[0100] like Figure 3 As shown, in some embodiments, the using an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes and generating a labeled power distribution terminal layout scheme sample set includes:

[0101] S2021. With the goal of minimizing the importance of power loss loads, use the Grey Wolf Algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes;

[0102] S2022. Set different types of labels for the optimal distribution terminal layout scheme and other distribution terminal layout schemes to obtain a sample set of distribution terminal layout schemes with labels.

[0103] Specifically, under different distribution terminal layout schemes, after the distribution network feeder automation system is activated, the gray wolf algorithm is used to search for the optimal solution with the minimum importance of the power-off load as the objective function to determine the optimal solution. The number of optimal solutions is at least one; the optimal solution and the non-optimal solution are labeled, for example, the label of the optimal solution is marked with 1, and the label of the non-optimal solution is marked with 0, forming a sample set.

[0104] Minimizing the importance of lost loads means minimizing the power outage loss per unit investment. This is calculated by dividing the load size restored after a power outage during the distribution terminal operation by the terminal investment. Specifically, a weighted calculation method can be used to determine the distribution terminal layout plan that minimizes the importance of lost loads.

[0105] like Figure 4 As shown, in some embodiments, generating at least two distribution terminal layout schemes of the distribution network feeder automation system to be arranged using electromagnetic transient simulation software includes:

[0106] S1011. Using electromagnetic transient simulation software, establish a simulation model of the distribution network feeder automation system for which terminal arrangement is to be performed;

[0107] S1012: Perform fault simulation based on the simulation model to generate at least two distribution terminal layout plans for the distribution network feeder automation system.

[0108] Specifically, a simulation model of the distribution network feeder automation system to be terminal-arranged is established in the electromagnetic transient simulation software, and the actual data of each device in the distribution network feeder automation system is input into the parameters to be set of the model. Based on the simulation model with set parameters, fault simulation is performed to form fault cases. Each fault case can form a distribution terminal layout plan.

[0109] In some embodiments, the simulation model established using electromagnetic transient simulation software includes primary-side equipment of the distribution network feeder automation system, including distribution network feeders, distribution transformers, circuit breakers, branch switches, loads, tower nodes, an external power grid model, and / or distributed power sources. The simulation model may also include secondary-side equipment, such as secondary-side equipment types.

[0110] In some embodiments, the simulation model established using electromagnetic transient simulation software further includes a busbar circuit breaker action logic sub-model, a distribution terminal action logic sub-model, and a tie switch action logic sub-model.

[0111] In some embodiments, the busbar circuit breaker action logic sub-model enables the circuit breaker in the simulation model to perform switching actions, thereby realizing current quick-break protection, overcurrent protection and automatic reclosing functions in the low-voltage feeder;

[0112] The power distribution terminal action logic sub-model enables the power distribution terminal in the simulation model to have the functions of immediate opening when voltage is lost, delayed closing when power is received, and switch locking;

[0113] The tie switch action logic sub-model enables the tie switch in the simulation model to have instantaneous pressure locking and load transfer functions.

[0114] In some embodiments, each distribution terminal layout scheme generated by fault simulation based on the simulation model includes the feeder structure of the distribution network feeder automation system, the feeder rated load, the feeder load under the current working conditions, the proportion of designed important loads, the proportion of important loads under the current working conditions, the proportion of the number of feeder distribution terminals, the load size covered by the feeder distribution terminal, the load size not covered by the feeder distribution terminal, the feeder distribution terminal type and / or the distribution of distribution terminals in the feeder.

[0115] like Figure 5 As shown, in some embodiments, inputting each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes includes:

[0116] S1021. Graphically represent each of the power distribution terminal layout schemes using multiple rows of heat maps to generate multiple rows of heat maps corresponding to each of the power distribution terminal layout schemes;

[0117] S1022. Input multiple rows of heat maps corresponding to each distribution terminal layout scheme into a pre-trained machine learning model to obtain the classification results output by the machine learning model for each distribution terminal layout scheme.

[0118] Specifically, the feeder structure, feeder rated load, feeder load under current working conditions and other characteristics of each distribution terminal layout scheme are quantified, and the quantified features are graphed to generate multiple rows of heat maps corresponding to each distribution terminal layout scheme. The multiple rows of heat maps are used as input to the machine learning model.

[0119] like Figure 6 As shown, in some embodiments, the use of multiple rows of heat maps to graphically represent each of the power distribution terminal layout schemes, and generating multiple rows of heat maps corresponding to each power distribution terminal layout scheme includes:

[0120] S10211. For each distribution terminal layout scheme, using the feeder rated load in the distribution terminal layout scheme and the feeder load under the current working condition, draw the first row of the multiple rows of heat maps corresponding to the distribution terminal layout scheme;

[0121] S10212. Using the designed important load proportion in the distribution terminal layout plan and the important load proportion under the current working condition, draw the second row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0122] S10213. Using the feeder structure in the power distribution terminal layout plan, draw the third row of the multi-row heat map corresponding to the power distribution terminal layout plan;

[0123] S10214. Using the proportion of the number of feeder distribution terminals in the distribution terminal layout plan, draw the fourth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0124] S10215. Using the feeder distribution terminal type in the distribution terminal layout plan, draw the fifth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0125] S10216. Using the distribution of distribution terminals in the feeder in the distribution terminal layout plan, the power of the distribution terminals, and the load size covered by the feeder distribution terminals, draw the sixth row of the multi-row thermal map corresponding to the distribution terminal layout plan, thereby generating a multi-row thermal map corresponding to the distribution terminal layout plan.

[0126] For example, a multi-row heat map such as Figure 7As shown, the construction process of each multi-row heat map is as follows:

[0127] The first line shows the feeder load and feeder rated load under the current working condition. First, the feeder load p under the current working condition is calculated. s The feeder load is normalized with the feeder rated load p, using the maximum feeder load among all samples as the benchmark. The normalized feeder load under the current operating condition and the feeder rated load are then plotted with a horizontal size of 500 pixels, forming a horizontal histogram with a pixel size of 500 × 10.

[0128] The second line indicates the proportion of important loads R under the current working condition psc R p , no normalization is required, and the graph is directly drawn with a horizontal size of 500 pixels to form a horizontal histogram of 500×10 pixels.

[0129] The third row shows the feeder structure, with 500×10 pixel horizontal histograms representing overhead lines and 250×10 pixel horizontal histograms representing cables.

[0130] The fourth row shows the ratio of feeder distribution terminals to the number of tower nodes, expressed as the number of feeder distribution terminals × 5 / the number of tower nodes.

[0131] The fifth line indicates the distribution terminal type.

[0132] The sixth row shows the distribution of distribution terminals in the feeder, where the power size between terminals is normalized. The load size covered by the feeder distribution terminal / feeder load size is represented by a grayscale heat map.

[0133] In order to better understand the present application, the distribution terminal layout method of the distribution network feeder automation system provided by the present application is described below using an actual 10kV distribution network in a certain area as a specific example.

[0134] Step 1: Establish a simulation model of the distribution network feeder automation system in the electromagnetic transient simulation software. The primary side equipment includes the distribution network feeder, distribution transformer, circuit breaker, branch switch, load, tower node, distributed power supply (optional), and external power grid model. Figure 9 A simulation model was established, including 40 nodes, 40 loads, a circuit breaker CB arranged on the line between nodes 0 and 1, and a tie switch LS arranged on the line connecting node 11 to the external power grid. In addition, Figure 10 The busbar circuit breaker action logic sub-model shown in Figure 11 The distribution terminal action logic sub-model shown in Figure 12The tie switch action logic sub-model shown in the figure has preliminarily completed the construction of the simulation model of the distribution network feeder automation system.

[0135] Step 2: Input the actual data of each device in the distribution network into the parameters to be set in the simulation model to complete the simulation model input; some of the main device parameters are shown in Table 1 below:

[0136] Table 1: Main equipment parameters

[0137]

[0138] Step 3: Perform fault simulation based on the input simulation model to generate fault cases. Each case can be used as a training sample. The basic data format of each sample is as follows:

[0139] 1) Feeder structure:

[0140]

[0141] 2) Feeder rated load size:

[0142]

[0143] Where, P i is the rated load size of the i-th branch.

[0144] 3) The size of the load under the current working conditions

[0145]

[0146] Where, P si is the load size of the i-th branch under the current working condition.

[0147] 4) Design important load proportion

[0148]

[0149] Where, P fs It is the size of the first and second category loads in the total power.

[0150] 5) The proportion of important loads under current working conditions

[0151]

[0152] Where, P fssc It is the size of the first and second category loads in the total power under the current working conditions.

[0153] 6) Number of feeder distribution terminals N

[0154] 7) Load size covered by feeder distribution terminal:

[0155]

[0156] Where, P ij is the size of the total load between nodes i and j, where nodes i and j are two adjacent nodes with distribution terminals.

[0157] 8) Load size not covered by feeder automation terminal:

[0158]

[0159] Where, P nosl is the size of the total load between nodes n and m, where nodes n and m are the substation outlet circuit breaker and the first node where the feeder terminal is arranged.

[0160] 9) Feeder automation terminal type

[0161] Based on the above data definition, a graphical data representation method using multiple rows of graphs is designed to establish a single sample representation method. Figure 7 The graphical display is as follows:

[0162] The first line shows the feeder load and feeder rated load under the current working condition. First, the feeder load p under the current working condition is calculated. s The feeder load is normalized with the feeder rated load p, using the maximum feeder load among all samples as the benchmark. The normalized feeder load under the current operating condition and the feeder rated load are then plotted with a horizontal size of 500 pixels, forming a horizontal histogram with a pixel size of 500 × 10.

[0163] The second line indicates the proportion of important loads R under the current working condition psc R p , no normalization is required, and the graph is directly drawn with a horizontal size of 500 pixels to form a horizontal histogram of 500×10 pixels.

[0164] The third row shows the feeder structure, with 500×10 pixel horizontal histograms representing overhead lines and 250×10 pixel horizontal histograms representing cables.

[0165] The fourth row shows the ratio of feeder distribution terminals to the number of tower nodes, expressed as the number of feeder distribution terminals × 5 / the number of tower nodes.

[0166] The fifth line indicates the distribution terminal type.

[0167] The sixth row shows the distribution of distribution terminals in the feeder, where the power size between terminals is normalized. The load size covered by the feeder distribution terminal / feeder load size is represented by a grayscale heat map.

[0168] For example, in one instance, (i≠0, 1, 11), (i≠0, 1, 11), R psc :R p =1:1, all feeders are overhead lines, the number of distribution terminals is 4, and the number of tower nodes is 40, so the number of feeder distribution terminals × 5 / the number of tower nodes = 1 / 2, and the distribution terminal type is adaptive integrated. The load size covered by the feeder distribution terminal is expressed as P x-y , P y-z , P z-q , where x, y, z, q represent the node locations of the distribution terminals. The graphical display result of the distribution terminal layout scheme of this example is as follows Figure 8 shown.

[0169] Step 4: Use the grey wolf algorithm to determine the optimal terminal solution for the simulation model including the distribution terminal to form a fault sample.

[0170] The objective function of the gray wolf algorithm is to minimize the power outage loss per unit investment, that is, the load size restored after power outage during the operation of the automated terminal / terminal investment.

[0171] When the Grey Wolf Algorithm is calculated based on the electromagnetic transient simulation software for the simulation model of the feeder operating conditions and distribution terminals, each optimization calculation (each layout scheme) will form a sample. If the current calculation is determined to be the optimal scheme, the sample of the scheme is labeled as 1, otherwise it is labeled as 0.

[0172] A sample set is formed through models of different working conditions and terminal layout schemes.

[0173] Step 5: Use multiple rows of heat maps as input to the convolutional neural network, such as Figure 13 As shown in the figure, the convolutional neural network uses a three-channel design, with each channel corresponding to a distribution terminal type, such as the adaptive integrated type. The convolutional layer is constructed using a 3×3 convolution kernel. The model is trained and tested using a sample set generated by electromagnetic transient simulation and the Grey Wolf algorithm.

[0174] Step 6: After the model training is completed, it can be used to arrange the distribution terminals of the distribution network feeder automation system. The basic process is: data input - model quantization representation - random arrangement scheme - CNN model judgment - optimal scheme determination.

[0175] This embodiment relates to the local feeder automation category within the feeder automation function of a distribution automation system, and involves the selection of automated distribution terminal layout plans during distribution network feeder design. Circuit breakers and feeder terminals located in the primary grid of the distribution network perform closing, opening, and locking operations according to modularly compiled custom action logic, enabling local feeder automation to locate faults, isolate faults, and provide power to non-faulty areas after a distribution network fault occurs. This embodiment utilizes electromagnetic transient simulation, optimization algorithms, and deep learning methods to determine the layout plan for feeder automation distribution terminals. Specifically, electromagnetic transient simulation is used to simulate feeder automation operating conditions, and an optimization algorithm is used to solve the optimal solution, generating a labeled terminal layout plan sample set. This sample set is then used to train and test a deep learning algorithm to generate a feeder automation distribution terminal layout plan discrimination model. The trained model is then used to determine the feeder automation distribution terminal layout plan. Because the majority of the computational workload can be handled through simulation optimization and model training, the solution speed is greatly accelerated in online applications, and the deep learning method provides greater robustness for complex operating conditions.

[0176] Figure 14 This is a structural diagram of a distribution terminal arrangement device for a distribution network feeder automation system provided by an embodiment of the present application, such as Figure 14 As shown, the distribution terminal arrangement device of the distribution network feeder automation system provided in the embodiment of the present application includes:

[0177] The first generating module 21 is configured to generate at least two distribution terminal layout schemes for a distribution network feeder automation system to be deployed using electromagnetic transient simulation software;

[0178] An input module 22 is configured to input each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes;

[0179] The determination module 23 is configured to determine a final distribution terminal layout scheme of the distribution network feeder automation system according to the classification results corresponding to each distribution terminal layout scheme.

[0180] The present application provides a distribution terminal layout device for a distribution network feeder automation system. This device uses electromagnetic transient simulation software to simulate the operating conditions of the distribution network feeder automation system undergoing terminal layout, obtaining at least two distribution terminal layout schemes for the system. This scheme is then determined using a trained machine learning model. Because the primary computational workload can be handled through simulation optimization and model training, the speed of solving the final distribution terminal layout scheme in online applications is greatly accelerated, and the machine learning algorithm employed provides greater robustness for complex operating conditions.

[0181] In some embodiments, the apparatus further comprises:

[0182] The second generation module is configured to generate at least two distribution terminal layout schemes for a distribution network feeder automation system as a training sample using electromagnetic transient simulation software;

[0183] a third generating module, configured to use an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes, and generate a labeled power distribution terminal layout scheme sample set;

[0184] The training module is used to train the machine learning model according to each distribution terminal layout plan and the label of the distribution terminal layout plan in the distribution terminal layout plan sample set to obtain a trained machine learning model.

[0185] In some embodiments, the third generation module is specifically configured to:

[0186] With the goal of minimizing the importance of power loss loads, a grey wolf algorithm is used to solve the optimal distribution terminal layout scheme among the at least two distribution terminal layout schemes;

[0187] Different types of labels are set for the optimal distribution terminal layout scheme and other distribution terminal layout schemes to obtain a sample set of distribution terminal layout schemes with labels.

[0188] In some embodiments, the first generating module is specifically configured to:

[0189] Use electromagnetic transient simulation software to establish a simulation model of the distribution network feeder automation system where terminals are to be deployed;

[0190] Fault simulation is performed based on the simulation model to generate at least two distribution terminal layout schemes for the distribution network feeder automation system.

[0191] In some embodiments, the simulation model established using electromagnetic transient simulation software includes the primary side equipment of the distribution network feeder automation system, and the primary side equipment includes distribution network feeders, distribution transformers, circuit breakers, branch switches, loads, tower nodes, external power grid models and / or distributed power sources.

[0192] In some embodiments, the simulation model established using electromagnetic transient simulation software further includes a busbar circuit breaker action logic sub-model, a distribution terminal action logic sub-model, and a tie switch action logic sub-model.

[0193] In some embodiments, the busbar circuit breaker action logic sub-model enables the circuit breaker in the simulation model to perform switching actions, thereby realizing current quick-break protection, overcurrent protection and automatic reclosing functions in the low-voltage feeder;

[0194] The power distribution terminal action logic sub-model enables the power distribution terminal in the simulation model to have the functions of immediate opening when voltage is lost, delayed closing when power is received, and switch locking;

[0195] The tie switch action logic sub-model enables the tie switch in the simulation model to have instantaneous pressure locking and load transfer functions.

[0196] In some embodiments, each distribution terminal layout scheme generated by fault simulation based on the simulation model includes the feeder structure of the distribution network feeder automation system, the feeder rated load, the feeder load under the current working conditions, the proportion of designed important loads, the proportion of important loads under the current working conditions, the proportion of the number of feeder distribution terminals, the load size covered by the feeder distribution terminal, the load size not covered by the feeder distribution terminal, the feeder distribution terminal type and / or the distribution of distribution terminals in the feeder.

[0197] In some embodiments, the input module is specifically configured to:

[0198] Using multiple rows of heat maps to graphically represent each of the power distribution terminal layout schemes, generating multiple rows of heat maps corresponding to each power distribution terminal layout scheme;

[0199] Multiple rows of heat maps corresponding to each distribution terminal layout scheme are respectively input into a pre-trained machine learning model to obtain the classification results output by the machine learning model for each distribution terminal layout scheme.

[0200] In some embodiments, the input module graphically represents each of the power distribution terminal layout schemes using multiple rows of heat maps, and generating multiple rows of heat maps corresponding to each power distribution terminal layout scheme includes:

[0201] For each of the distribution terminal layout schemes, using the feeder rated load in the distribution terminal layout scheme and the feeder load under the current working condition, draw the first row of the multiple rows of heat maps corresponding to the distribution terminal layout scheme;

[0202] Using the proportion of important loads designed in the distribution terminal layout plan and the proportion of important loads under the current working conditions, draw the second row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0203] Using the feeder structure in the power distribution terminal layout plan, draw the third row of the multi-row heat map corresponding to the power distribution terminal layout plan;

[0204] Using the proportion of the number of feeder distribution terminals in the distribution terminal layout plan, draw the fourth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0205] Using the feeder distribution terminal type in the distribution terminal layout plan, draw the fifth row of the multi-row heat map corresponding to the distribution terminal layout plan;

[0206] Using the distribution of distribution terminals in the feeder in the distribution terminal layout plan, the power of the distribution terminals, and the load size covered by the feeder distribution terminals, the sixth row of the multi-row thermal map corresponding to the distribution terminal layout plan is drawn, and the multi-row thermal map corresponding to the distribution terminal layout plan is generated.

[0207] The embodiments of the apparatus provided in the embodiments of the present application can be specifically used to execute the processing flow of the above-mentioned method embodiments. Its functions will not be described in detail here, and reference can be made to the detailed description of the above-mentioned method embodiments.

[0208] Figure 15 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 15 As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other via the communication bus 304. The processor 301 may call the logic instructions in the memory 303 to execute the method described in any of the above embodiments.

[0209] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0210] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0211] This embodiment provides a computer-readable storage medium, which stores a computer program. The computer program enables the computer to execute the methods provided by the above method embodiments.

[0212] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0213] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0214] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0215] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0216] In the description of this specification, reference to the terms "one embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples.

[0217] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for arranging distribution terminals in a distribution network feeder automation system, characterized in that: include: Generate at least two distribution terminal layout schemes for the distribution network feeder automation system to be deployed using electromagnetic transient simulation software; Specifically, the method includes: using electromagnetic transient simulation software to establish a simulation model of a distribution network feeder automation system for which terminal arrangement is to be performed; performing fault simulation based on the simulation model to generate at least two distribution terminal arrangement schemes for the distribution network feeder automation system; Input each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes; Determining a final distribution terminal layout plan of the distribution network feeder automation system according to the classification results corresponding to each distribution terminal layout plan; Inputting each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes includes: graphically representing each of the power distribution terminal layout schemes using multiple rows of heat maps to generate multiple rows of heat maps corresponding to each of the power distribution terminal layout schemes; inputting the multiple rows of heat maps corresponding to each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes; The step of graphically representing each of the power distribution terminal layout schemes using multiple rows of heat maps to generate multiple rows of heat maps corresponding to each of the power distribution terminal layout schemes includes: For each of the distribution terminal layout schemes, using the feeder rated load in the distribution terminal layout scheme and the feeder load under the current working condition, draw the first row of the multiple rows of heat maps corresponding to the distribution terminal layout scheme; Using the proportion of important loads designed in the distribution terminal layout plan and the proportion of important loads under the current working conditions, draw the second row of the multi-row heat map corresponding to the distribution terminal layout plan; Using the feeder structure in the power distribution terminal layout plan, draw the third row of the multi-row heat map corresponding to the power distribution terminal layout plan; Using the proportion of the number of feeder distribution terminals in the distribution terminal layout plan, draw the fourth row of the multi-row heat map corresponding to the distribution terminal layout plan; Using the feeder distribution terminal type in the distribution terminal layout plan, draw the fifth row of the multi-row heat map corresponding to the distribution terminal layout plan; Using the distribution of distribution terminals in the feeder in the distribution terminal layout plan, the power of the distribution terminals, and the load size covered by the feeder distribution terminals, the sixth row of the multi-row thermal map corresponding to the distribution terminal layout plan is drawn, and the multi-row thermal map corresponding to the distribution terminal layout plan is generated.

2. The method according to claim 1, characterized in that The method further comprises: For a distribution network feeder automation system used as a training sample, using electromagnetic transient simulation software, at least two distribution terminal layout schemes for the distribution network feeder automation system are generated; Using an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes, and generating a labeled power distribution terminal layout scheme sample set; The machine learning model is trained according to each distribution terminal layout plan and the label of the distribution terminal layout plan in the distribution terminal layout plan sample set to obtain a trained machine learning model.

3. The method according to claim 2, characterized in that The step of using an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes and generating a labeled power distribution terminal layout scheme sample set includes: With the goal of minimizing the importance of power-loss loads, a gray wolf algorithm is used to solve the optimal distribution terminal layout scheme among the at least two distribution terminal layout schemes, wherein the minimum importance of power-loss loads means the minimum power outage loss per unit investment; Different types of labels are set for the optimal distribution terminal layout scheme and other distribution terminal layout schemes to obtain a sample set of distribution terminal layout schemes with labels.

4. The method according to claim 1, wherein The simulation model established using electromagnetic transient simulation software includes the primary side equipment of the distribution network feeder automation system, and the primary side equipment includes distribution network feeders, distribution transformers, circuit breakers, branch switches, loads, tower nodes, external power grid models and / or distributed power sources.

5. The method according to claim 1, wherein The simulation model established using electromagnetic transient simulation software also includes a busbar circuit breaker action logic sub-model, a distribution terminal action logic sub-model and a tie switch action logic sub-model.

6. The method according to claim 5, characterized in that The busbar circuit breaker action logic sub-model enables the circuit breaker in the simulation model to perform switching actions, thereby realizing current quick-break protection, overcurrent protection and automatic reclosing functions in the low-voltage feeder; The power distribution terminal action logic sub-model enables the power distribution terminal in the simulation model to have the functions of immediate opening when voltage is lost, delayed closing when power is received, and switch locking; The tie switch action logic sub-model enables the tie switch in the simulation model to have instantaneous pressure locking and load transfer functions.

7. The method according to claim 1, characterized in that Each distribution terminal layout scheme generated by fault simulation based on the simulation model includes the feeder structure of the distribution network feeder automation system, the feeder rated load, the feeder load under the current operating conditions, the proportion of designed important loads, the proportion of important loads under the current operating conditions, the proportion of the number of feeder distribution terminals, the load size covered by the feeder distribution terminal, the load size not covered by the feeder distribution terminal, the feeder distribution terminal type and / or the distribution of distribution terminals in the feeder.

8. A distribution terminal layout device for a distribution network feeder automation system, characterized in that: include: A first generating module is configured to generate at least two distribution terminal layout schemes for a distribution network feeder automation system to be terminal arranged using electromagnetic transient simulation software; The first generation module is specifically configured to: establish a simulation model of a distribution network feeder automation system for which terminal arrangement is to be performed using electromagnetic transient simulation software; perform fault simulation based on the simulation model to generate at least two distribution terminal arrangement schemes for the distribution network feeder automation system; An input module, configured to input each of the power distribution terminal layout schemes into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes; A determination module, configured to determine a final distribution terminal layout scheme of the distribution network feeder automation system according to the classification results corresponding to each distribution terminal layout scheme; The input module is specifically configured to: graphically represent each of the power distribution terminal layout schemes using multiple rows of heat maps to generate multiple rows of heat maps corresponding to each power distribution terminal layout scheme; input the multiple rows of heat maps corresponding to each power distribution terminal layout scheme into a pre-trained machine learning model to obtain a classification result output by the machine learning model for each of the power distribution terminal layout schemes; The input module graphically represents each of the power distribution terminal layout schemes using multiple rows of heat maps, and generates multiple rows of heat maps corresponding to each power distribution terminal layout scheme, including: For each of the distribution terminal layout schemes, using the feeder rated load in the distribution terminal layout scheme and the feeder load under the current working condition, draw the first row of the multiple rows of heat maps corresponding to the distribution terminal layout scheme; Using the proportion of important loads designed in the distribution terminal layout plan and the proportion of important loads under the current working conditions, draw the second row of the multi-row heat map corresponding to the distribution terminal layout plan; Using the feeder structure in the power distribution terminal layout plan, draw the third row of the multi-row heat map corresponding to the power distribution terminal layout plan; Using the proportion of the number of feeder distribution terminals in the distribution terminal layout plan, draw the fourth row of the multi-row heat map corresponding to the distribution terminal layout plan; Using the feeder distribution terminal type in the distribution terminal layout plan, draw the fifth row of the multi-row heat map corresponding to the distribution terminal layout plan; Using the distribution of distribution terminals in the feeder in the distribution terminal layout plan, the power of the distribution terminals, and the load size covered by the feeder distribution terminals, the sixth row of the multi-row thermal map corresponding to the distribution terminal layout plan is drawn, and the multi-row thermal map corresponding to the distribution terminal layout plan is generated.

9. The device according to claim 8, characterized in that The device further comprises: The second generation module is configured to generate at least two distribution terminal layout schemes for a distribution network feeder automation system as a training sample using electromagnetic transient simulation software; a third generating module, configured to use an optimization algorithm to solve the optimal power distribution terminal layout scheme among the at least two power distribution terminal layout schemes, and generate a labeled power distribution terminal layout scheme sample set; The training module is used to train the machine learning model according to each distribution terminal layout plan and the label of the distribution terminal layout plan in the distribution terminal layout plan sample set to obtain a trained machine learning model.

10. The device according to claim 9, characterized in that The third generation module is specifically used for: With the goal of minimizing the importance of power-loss loads, a gray wolf algorithm is used to solve the optimal distribution terminal layout scheme among the at least two distribution terminal layout schemes, wherein the minimum importance of power-loss loads means the minimum power outage loss per unit investment; Different types of labels are set for the optimal distribution terminal layout scheme and other distribution terminal layout schemes to obtain a sample set of distribution terminal layout schemes with labels.

11. The device according to claim 8, characterized in that The simulation model established using electromagnetic transient simulation software includes the primary side equipment of the distribution network feeder automation system, and the primary side equipment includes distribution network feeders, distribution transformers, circuit breakers, branch switches, loads, tower nodes, external power grid models and / or distributed power sources.

12. The device according to claim 11, characterized in that The simulation model established using electromagnetic transient simulation software also includes a busbar circuit breaker action logic sub-model, a distribution terminal action logic sub-model and a tie switch action logic sub-model.

13. The device according to claim 12, characterized in that The busbar circuit breaker action logic sub-model enables the circuit breaker in the simulation model to perform switching actions, thereby realizing current quick-break protection, overcurrent protection and automatic reclosing functions in the low-voltage feeder; The power distribution terminal action logic sub-model enables the power distribution terminal in the simulation model to have the functions of immediate opening when voltage is lost, delayed closing when power is received, and switch locking; The tie switch action logic sub-model enables the tie switch in the simulation model to have instantaneous pressure locking and load transfer functions.

14. The device according to claim 8, characterized in that Each distribution terminal layout scheme generated by fault simulation based on the simulation model includes the feeder structure of the distribution network feeder automation system, the feeder rated load, the feeder load under the current operating conditions, the proportion of designed important loads, the proportion of important loads under the current operating conditions, the proportion of the number of feeder distribution terminals, the load size covered by the feeder distribution terminal, the load size not covered by the feeder distribution terminal, the feeder distribution terminal type and / or the distribution of distribution terminals in the feeder.

15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images