Method and system for detecting and positioning short-circuit fault of alternating-current micro-grid based on multiple agents

Abstract

The invention relates to a multi-agent-based alternating-current micro-grid short-circuit fault detection and positioning method and system, and the method comprises the following steps: setting a plurality of agents in an alternating-current micro-grid, and collecting current signals in real time; the intelligent agent collects a current signal in real time and extracts a wavelet energy spectrum value through a binary wavelet energy spectrum transformation algorithm, and when the wavelet energy spectrum value exceeds a set fault threshold value, it is judged that the alternating-current micro-grid has a short-circuit fault; the intelligent agent which detects the fault confirms the intelligent agent which is responsible for the fault by communicating with the adjacent intelligent agent; and the intelligent agent responsible for the fault confirms the fault type and the fault position according to the AC micro-grid type and the fault detection algorithm.

Description

Technical Field

[0001] The present application relates to the field of power monitoring technology, and more specifically, to a method and system for detecting and locating short-circuit faults in an AC microgrid based on multiple intelligent agents. Background Art

[0002] As the proportion of new energy generation in my country's energy structure continues to increase, the stability of microgrid operation has received increasing attention. In the operation of microgrids, the detection, judgment and location of short-circuit faults are crucial. However, the protection of microgrids faces many challenges. For example, the direction of short-circuit current is bidirectional, which may cause the protection device to bear reverse current; the frequent connection and removal of distributed power sources causes topological changes, which increases the difficulty of setting the protection device. These problems make the traditional short-circuit fault protection scheme no longer effectively applicable to microgrids, so it is urgent to study new short-circuit fault protection methods for microgrids.

[0003] Prior art, such as the Chinese patent with patent number "CN109444667A", discloses a distribution network early fault classification method based on convolutional neural network. This method introduces the relevant theories and methods of wavelet decomposition and convolutional neural network into the classification of early faults in distribution network, and verifies the rationality of the method. Wavelet decomposition can separate the approximation and details of the waveform, and these representations are closely related to early faults. The input of the convolutional neural network is formed by combining these representations. By learning the combination of these representations, the convolutional neural network captures the detailed information about the early faults, and can classify the early faults. This method is much better than traditional detection in terms of required data volume and accuracy. It is of great significance to the classification and processing of early faults in distribution networks.

[0004] The problem with the above-mentioned prior art is that the method can only diagnose the fault information of the distribution network, but cannot locate the fault; and the method only includes the diagnosis method of the three-phase three-wire system, but does not diagnose the three-phase four-wire system. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a multi-agent-based AC microgrid short-circuit fault detection and positioning method and system.

[0006] The technical solution of the present invention is as follows:

[0007] The present invention proposes a multi-agent-based AC microgrid short-circuit fault detection and positioning method, comprising the following steps:

[0008] Step S1, setting a plurality of intelligent agents in the AC microgrid to collect current signals in real time;

[0009] Step S2, the intelligent agent collects the current signal in real time, and extracts the wavelet energy spectrum value through the binary wavelet energy spectrum transformation algorithm. When the wavelet energy spectrum value exceeds the set fault threshold, it is determined that a short circuit fault occurs in the AC microgrid;

[0010] Step S3, the agent that detects the fault identifies the agent responsible for the fault by communicating with neighboring agents;

[0011] In step S4, the agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and the fault detection algorithm.

[0012] As a preferred embodiment, the intelligent agent includes: a detection module, a signal processing module, a fault judgment module, a communication module and a fault area positioning module; wherein the detection module is used to collect current signals in real time; the signal processing module is used to perform wavelet transform on the collected current signals to extract wavelet energy spectrum values; the fault judgment module is used to judge whether a fault has occurred and the type of fault; the communication module is used to communicate with adjacent intelligent agents after the intelligent agent detects a fault, and judge the intelligent agent responsible for locating the fault area; the positioning module determines the fault location based on the BP neural network algorithm.

[0013] As a preferred implementation, the positioning module determines the fault location according to the BP neural network algorithm, wherein the objective function of the BP neural network algorithm is:

[0014] l = tansig (W1*A+B1)*W2+B2;

[0015] Where: l is the location where the short circuit fault occurs; tansig() is the neural network activation function; A is the input of the BP neural network algorithm; W1 is the weight from the input layer to the hidden layer; B1 is the bias of the hidden layer; W2 is the weight from the hidden layer to the output layer; B2 is the bias of the output layer.

[0016] As a preferred implementation, A is the input of the BP neural network algorithm, including wavelet energy spectrum value, fault phase angle and distributed power supply capacity; the expression of input quantity A is as follows:

[0017] A=(S GD ,θ c ,E 4max1 );

[0018] Where: S GD is the capacity of distributed power supply; θ c is the fault phase angle; E 4max1 It is the first peak value of the fault current wavelet energy spectrum waveform.

[0019] As a preferred implementation, the intelligent agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and the fault detection algorithm. The specific AC microgrid types include three-phase three-wire system and three-phase four-wire system.

[0020] For a three-phase three-wire system, the agent determines the fault type by detecting the zero-sequence current. The zero-sequence current formula is as follows:

[0021]

[0022] Where: I is the zero-sequence current of the three-phase three-wire system, I a ,I b ,I c They are the three-phase currents A, B and C of the three-phase three-wire system;

[0023] For a three-phase four-wire system, the agent distinguishes between ground faults and non-ground faults by detecting residual current. The residual current formula is as follows:

[0024]

[0025] Where: I d is the residual current; I a ,I b ,I c ,I n Represent the current vectors of phase a, phase b, phase c and phase n respectively.

[0026] On the other hand, the present invention also provides an AC microgrid short-circuit fault detection and positioning system based on multi-agents, comprising:

[0027] The intelligent agent signal collection part is used to collect current signals in real time by setting up multiple intelligent agents in the AC microgrid;

[0028] Short-circuit fault judgment part: The intelligent agent of the short-circuit fault judgment part extracts the wavelet energy spectrum value according to the real-time collected current signal through the binary wavelet energy spectrum transformation algorithm. If the wavelet energy spectrum value exceeds the set fault threshold, it is determined that a short-circuit fault occurs in the AC microgrid;

[0029] In the responsible agent determination part, the agent that detects the fault confirms the agent responsible for the fault by communicating with neighboring agents;

[0030] In the fault diagnosis and location part, the agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and fault detection algorithm.

[0031] As a preferred implementation, the intelligent agent in the intelligent agent signal acquisition part includes: a detection module, a signal processing module, a fault judgment module, a communication module and a fault area positioning module; wherein the detection module is used to sample the current signal in real time; the signal processing module performs wavelet transform to extract the wavelet energy spectrum value; the fault judgment module is used to judge whether a fault has occurred and the type of fault; the communication module is used to communicate with adjacent intelligent agents after the intelligent agent detects a fault, and judge the intelligent agent responsible for locating the fault area; the positioning module calculates and determines the fault location according to the BP neural network algorithm.

[0032] As a preferred implementation, the positioning module determines the fault location according to the BP neural network algorithm, wherein the objective function of the BP neural network algorithm is:

[0033] l = tansig (W1*A+B1)*W2+B2;

[0034] Where: l is the location where the short circuit fault occurs; tansig() is the neural network activation function; A is the input of the BP neural network algorithm; W1 is the weight from the input layer to the hidden layer; B1 is the bias of the hidden layer; W2 is the weight from the hidden layer to the output layer; B2 is the bias of the output layer.

[0035] On the other hand, the present invention further provides an electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for detecting and locating short-circuit faults in an AC microgrid based on multiple agents as described in any embodiment of the present invention is implemented.

[0036] On the other hand, the present invention also provides a computer-readable medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement a multi-agent-based AC microgrid short-circuit fault detection and positioning method as described in any embodiment of the present invention.

[0037] The present invention has the following beneficial effects:

[0038] 1. The present invention can also achieve regional positioning for different types of cables, such as replacing copper core cables with aluminum core cables, and has good versatility.

[0039] 2. The present invention can adapt to topology and capacity changes, realize the regional positioning of AC microgrid short-circuit faults in all modes, and is not affected by line distance.

[0040] 3. The present invention is applicable to various types of AC microgrids including: three-phase three-wire system and three-phase four-wire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 This is a schematic diagram of the method flow of Example 1;

[0043] Figure 2 This is the structure diagram of the microgrid simulation model. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0046] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0047] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0048] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0049] Embodiment 1:

[0050] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be combined with the specific embodiments of the present application and refer to the attached Figure 1 , clearly and completely describe the technical solution of the present invention.

[0051] To solve the problems in the prior art, the present invention provides a method for detecting and locating short-circuit faults in an AC microgrid based on a multi-agent system, comprising the following steps:

[0052] Step S1, setting a plurality of intelligent agents in the AC microgrid to collect current signals in real time;

[0053] In this embodiment, Figure 2 As shown, Figure 2 It is a microgrid simulation model. The setting method of the agent takes two agents A and B as an example. Agent A is responsible for the regional positioning tasks of area 1, area 2, and area 3, and agent B is responsible for the regional positioning tasks of area 4, area 5, and area 6. If new areas are added, the tasks will be divided and assigned in this mode.

[0054] The intelligent agent includes: a detection module, a signal processing module, a fault judgment module, a communication module and a fault area positioning module; wherein the detection module is used to collect current signals in real time; the signal processing module is used to perform wavelet transform on the collected current signals to extract wavelet energy spectrum values; the fault judgment module is used to judge whether a fault has occurred and the type of fault; the communication module is used to communicate with adjacent intelligent agents after the intelligent agent detects a fault, and judge the intelligent agent responsible for locating the fault area; the positioning module calculates and determines the fault location according to the BP neural network algorithm.

[0055] The positioning module determines the fault location according to the BP neural network algorithm, wherein the objective function of the BP neural network algorithm is:

[0056] l = tansig (W*A+B1)*W2+B2

[0057] Where: l is the location where the short circuit fault occurs, tansig() is the neural network activation function; A is the input of the BP neural network algorithm; W1 is the weight from the input layer to the hidden layer; B1 is the bias of the hidden layer; W2 is the weight from the hidden layer to the output layer; B2 is the bias of the output layer.

[0058] in:

[0059] A=(S GD ,θ c ,E 4max1 );

[0060]

[0061] Where: S GD is the capacity of distributed power supply; θ c is the fault phase angle; E 4max1 is the first peak value of the fault current wavelet energy spectrum waveform; x is the input value of tansig.

[0062] Step S2, the intelligent agent collects the current signal in real time, and extracts the wavelet energy spectrum value through the binary wavelet energy spectrum transformation algorithm. When the wavelet energy spectrum value exceeds the set fault threshold, it is determined that a short circuit fault occurs in the AC microgrid;

[0063] In this embodiment, during the operation of the agent, each agent collects the current waveform through the current sensor and extracts the wavelet energy spectrum value using the binary wavelet energy spectrum transformation algorithm. If an agent detects that the wavelet energy spectrum value exceeds the set fault threshold (generally, it should be greater than 5 times the wavelet energy spectrum value during normal operation), it means that a short circuit fault has occurred in the microgrid.

[0064] Step S3, the agent that detects the fault identifies the agent responsible for the fault by communicating with neighboring agents;

[0065] In this embodiment, the agent that detects the fault transmits the fault information to the rear agent through the RS485 communication module. If the rear agent also detects the fault, it means that the fault point is not in the area between the two agents; if the front agent detects the fault signal, but the rear agent does not, the rear agent can determine that the fault is located in the area between the two agents, and feed this information back to the front agent through the RS485 communication module, and determine that the front agent is the agent responsible for the fault. For example, in Figure 2 A fault occurs in area 1 in the system, agent A detects the fault and sends the fault information to agent B. Since agent B does not detect the fault, it can be determined that the fault area is between agent A and agent B, and agent A is the agent responsible for the fault.

[0066] In step S4, the agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and the fault detection algorithm.

[0067] The intelligent agent responsible for the fault determines the fault type and fault location according to the AC microgrid type and the fault detection algorithm. The specific AC microgrid types include three-phase three-wire system and three-phase four-wire system.

[0068] For a three-phase three-wire system, the agent determines the fault type by detecting the zero-sequence current. The zero-sequence current formula is as follows:

[0069]

[0070] Where: I is the zero-sequence current of the three-phase three-wire system, I a ,I b ,I c They are the three-phase currents A, B and C of the three-phase three-wire system;

[0071] For a three-phase four-wire system, the agent distinguishes between ground faults and non-ground faults by detecting residual current. The residual current formula is as follows:

[0072]

[0073] Where: I d is the residual current; I a ,I b ,I c ,I n Represent the current vectors of phase a, phase b, phase c and phase n respectively.

[0074] In this embodiment, after the fault area is determined, the intelligent agent in front of the fault area will be responsible for determining the fault type and accurately locating the fault. In this example, intelligent agent A is responsible for determining the fault type and locating the area.

[0075] Since for different fault initial phase angles θ c , the first peak value E of the fault current wavelet energy spectrum waveform 4max1 As the distance d from the short-circuit point to the detection point increases, it decreases. After research, it is found that for different short-circuit fault types and different capacity conditions, the conclusion is consistent with the above. Therefore, E can be measured by the intelligent agent. 4max1 And the fault phase angle θ c , Distributed power capacity S GD Realize regional positioning of short-circuit faults.

[0076] Taking the area that agent A is responsible for (i.e., area 1, area 2, and area 3) as an example, the short-circuit fault occurs at l∈{1,2,3}. To ensure the accuracy of the model, the capacity of the distributed generation is S GD ∈{80,85,90,95,100,105,110,115,120}, θ c ∈{0,30,60,90,120,150}, it is measured that when a single-phase ground short circuit fault occurs in area 1, area 2, and area 3, the E detected by agent A 4max1 , we get a total of 9×6×3=162 E detected by agent A when single-phase ground short circuit occurs in area 1, area 2, and area 3 4max1The value is 162, that is, the total number of sample points is 150. 150 sample points are randomly selected as the training set of the BP neural network algorithm, and the remaining 12 sample points are the test set. The precise positioning formula obtained by BP neural network training is that l is the location of the fault area, W1 is the weight from the input layer to the hidden layer, B1 is the bias of the hidden layer, W2 is the weight from the hidden layer to the output layer, B2 is the bias of the output layer, A is the input, and tansig is the neural network activation function. When a fault occurs, the agent responsible for locating the fault area is first determined by the cooperation between multiple agents, and then the S detected by the agent is used as the GD ,θ c 、E 4max1 Substitute into the BP neural network algorithm to calculate the fault area. Figure 2 This is a flow chart for locating the area when a short circuit fault occurs.

[0077] Since the invention has taken into account capacity changes, including the switching of distributed power sources, changes in topology, such as the removal of distributed power sources, will not affect the detection results of each intelligent agent. In addition, the method can also achieve regional positioning for different types of cables, such as replacing copper core cables with aluminum core cables, and has good versatility.

[0078] Embodiment 2:

[0079] This embodiment provides an AC microgrid short-circuit fault detection and positioning system based on multi-agents, including:

[0080] The intelligent agent signal collection part is used to collect current signals in real time by setting up multiple intelligent agents in the AC microgrid;

[0081] Short-circuit fault judgment part: The intelligent agent of the short-circuit fault judgment part extracts the wavelet energy spectrum value according to the real-time collected current signal through the binary wavelet energy spectrum transformation algorithm. If the wavelet energy spectrum value exceeds the set fault threshold, it is determined that a short-circuit fault occurs in the AC microgrid;

[0082] In the responsible agent determination part, the agent that detects the fault confirms the agent responsible for the fault by communicating with neighboring agents;

[0083] In the fault diagnosis and location part, the agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and fault detection algorithm.

[0084] Embodiment three:

[0085] This embodiment provides an electronic device having a computer program stored thereon. When the computer program is executed by a processor, a multi-agent-based AC microgrid short-circuit fault detection and positioning method as described in any embodiment of the present invention is implemented.

[0086] Embodiment 4:

[0087] This embodiment provides a computer-readable medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement a multi-agent-based AC microgrid short-circuit fault detection and positioning method as described in any embodiment of the present invention.

[0088] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0089] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, 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, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0092] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multi-agent-based AC microgrid short-circuit fault detection and positioning method, characterized in that: The following steps are involved: Step S1, setting a plurality of intelligent agents in the AC microgrid to collect current signals in real time; Step S2, the intelligent agent collects the current signal in real time, and extracts the wavelet energy spectrum value through the binary wavelet energy spectrum transformation algorithm. When the wavelet energy spectrum value exceeds the set fault threshold, it is determined that a short circuit fault occurs in the AC microgrid; Step S3, the agent that detects the fault identifies the agent responsible for the fault by communicating with neighboring agents; In step S4, the agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and the fault detection algorithm.

2. According to the multi-agent-based AC microgrid short-circuit fault detection and positioning method of claim 1, it is characterized by: The intelligent agent includes: a detection module, a signal processing module, a fault judgment module, a communication module and a fault area positioning module; wherein the detection module is used to collect current signals in real time; the signal processing module is used to perform wavelet transform on the collected current signals to extract wavelet energy spectrum values; the fault judgment module is used to judge whether a fault has occurred and the type of fault; the communication module is used to communicate with adjacent intelligent agents after the intelligent agent detects a fault, and judge the intelligent agent responsible for locating the fault area; the positioning module calculates and determines the fault location according to the BP neural network algorithm.

3. The method for detecting and locating short-circuit faults in an AC microgrid based on multi-agent according to claim 2, characterized in that: The positioning module determines the fault location according to the BP neural network algorithm, wherein the objective function of the BP neural network algorithm is: l = tansig (W1*A+B1)*W2+B2; Where: l is the location where the short circuit fault occurs; tansig() is the neural network activation function; A is the input of the BP neural network algorithm; W1 is the weight from the input layer to the hidden layer; B1 is the bias of the hidden layer; W2 is the weight from the hidden layer to the output layer; B2 is the bias of the output layer.

4. The method for detecting and locating short-circuit faults in an AC microgrid based on multi-agent according to claim 3, characterized in that: A is the input of the BP neural network algorithm, including wavelet energy spectrum value, fault phase angle and distributed power capacity; the expression of input quantity A is as follows: A=(S GD ,i c ,E 4max1 ); Where: S GD is the capacity of distributed power supply; θ c is the fault phase angle; E 4max1 It is the first peak value of the fault current wavelet energy spectrum waveform.

5. The method for detecting and locating short-circuit faults in an AC microgrid based on multi-agent according to claim 1, characterized in that: The intelligent agent responsible for the fault determines the fault type and fault location according to the AC microgrid type and the fault detection algorithm. The specific AC microgrid types include three-phase three-wire system and three-phase four-wire system. For a three-phase three-wire system, the agent determines the fault type by detecting the zero-sequence current. The zero-sequence current formula is as follows: Where: I is the zero-sequence current of the three-phase three-wire system, I a ,I b ,I c They are the three-phase currents A, B and C of the three-phase three-wire system; For a three-phase four-wire system, the agent distinguishes between ground faults and non-ground faults by detecting residual current. The residual current formula is as follows: Where: I d is the residual current; I a ,I b ,I c ,I n Represent the current vectors of phase a, phase b, phase c and phase n respectively.

6. A multi-agent-based AC microgrid short-circuit fault detection and positioning system, characterized in that: include: The intelligent agent signal collection part is used to collect current signals in real time by setting up multiple intelligent agents in the AC microgrid; Short-circuit fault judgment part: The intelligent agent of the short-circuit fault judgment part extracts the wavelet energy spectrum value according to the real-time collected current signal through the binary wavelet energy spectrum transformation algorithm. If the wavelet energy spectrum value exceeds the set fault threshold, it is determined that a short-circuit fault occurs in the AC microgrid; In the responsible agent determination part, the agent that detects the fault confirms the agent responsible for the fault by communicating with neighboring agents; In the fault diagnosis and location part, the agent responsible for the fault confirms the fault type and fault location according to the AC microgrid type and fault detection algorithm.

7. The multi-agent-based AC microgrid short-circuit fault detection and positioning system according to claim 6, characterized in that: The intelligent agent in the intelligent agent signal acquisition part includes: a detection module, a signal processing module, a fault judgment module, a communication module and a fault area positioning module; wherein the detection module is used to sample the current signal in real time; the signal processing module performs wavelet transform to extract the wavelet energy spectrum value; the fault judgment module is used to judge whether a fault occurs and the type of fault; the communication module is used to communicate with adjacent intelligent agents after the intelligent agent detects a fault, and judge the intelligent agent responsible for locating the fault area; the positioning module calculates and determines the fault location according to the BP neural network algorithm.

8. The multi-agent-based AC microgrid short-circuit fault detection and positioning system according to claim 7, characterized in that: The positioning module determines the fault location according to the BP neural network algorithm, wherein the objective function of the BP neural network algorithm is: l = tansig (W1*A+B1)*W2+B2; Where: l is the location where the short circuit fault occurs; tansig() is the neural network activation function; A is the input of the BP neural network algorithm; W1 is the weight from the input layer to the hidden layer; B1 is the bias of the hidden layer; W2 is the weight from the hidden layer to the output layer; B2 is the bias of the output layer.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the multi-agent-based AC microgrid short-circuit fault detection and positioning as described in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, it realizes the short-circuit fault detection and positioning of the AC microgrid based on multi-agent as described in any one of claims 1 to 5.

Images