Method for recording power supply service log based on power gap system

Abstract

The invention relates to a method for recording a power supply service log based on an electric power gap system, and the method comprises the following steps: collecting the power supply information of a corresponding region through each edge node of the electric power gap system in a self-adaptive manner, generating a power supply service log, and carrying out the preprocessing of the power supply service log in the edge node; the edge node uploads the preprocessed power supply service log to a power gap system, and constructs a graph database for storing the power supply service log; constructing an event association analysis model, and analyzing the connection weight of each node in the graph database through the event association analysis model; and generating a fault propagation chain based on the connection weight of each node in the graph database.

Description

Technical Field

[0001] The present invention relates to a method for recording power supply service logs based on the power Hongmeng system, which belongs to the technical field of power monitoring. Background Art

[0002] In the power supply system, fault monitoring and logging are important components to ensure the safe, reliable and efficient operation of the power system. Traditional fault recording and analysis methods usually rely on centralized data processing and manual recording, facing the following challenges:

[0003] Data inconsistency: The log formats and contents generated by different devices and systems vary, making data integration difficult.

[0004] Lack of real-time performance: Fault monitoring systems often respond slowly and are unable to capture and record fault information in a timely manner, resulting in delayed decision-making.

[0005] Difficulty in fault tracing: Existing fault analysis technologies mostly rely on experience and lack a systematic root cause analysis method, making it difficult to trace the fault propagation path.

[0006] Low collaboration efficiency: Due to data dispersion and system silos, the collaborative processing capabilities between departments are insufficient, affecting the speed of fault response. Summary of the invention

[0007] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a method for recording power supply service logs based on the power Hongmeng system.

[0008] The technical solution of the present invention is as follows:

[0009] On the one hand, the present invention provides a method for recording a power supply service log based on the power Hongmeng system, comprising the following steps:

[0010] Through the power Hongmeng system, each edge node adaptively collects the power supply information of its corresponding area and generates a power supply service log, and pre-processes the power supply service log in the edge node;

[0011] The edge node uploads the pre-processed power supply service log to the power Hongmeng system and builds a graph database to store the power supply service log;

[0012] Construct an event correlation analysis model, and use it to analyze the connection weights of each node in the graph database;

[0013] Generate a fault propagation chain based on the connection weights of each node in the graph database.

[0014] As a preferred embodiment of the present invention, the edge node adaptively collects the power supply information of its corresponding area, which is specifically shown in the following formula:

[0015]

[0016] Where: f(t) represents the sampling frequency at time t; represents the reference sampling frequency; α represents the sensitivity factor; V(t) represents the voltage value at time t; Indicates the reference voltage value.

[0017] As a preferred implementation manner of the present invention, the power supply service log includes a timestamp, a power equipment ID, a power equipment parameter type, a power equipment parameter value, and geographic information.

[0018] As a preferred embodiment of the present invention, the preprocessing steps of the power supply service log are:

[0019] The power supply service log is smoothed by the sliding average method, as shown in the following formula:

[0020]

[0021] in: represents the smoothed power supply service log; k represents the total number of samples in the power supply service log; x i represents the i-th sample in the power supply service log;

[0022] The smoothed data is compressed as shown in the following formula:

[0023]

[0024] Where: X t represents the compressed power supply service log; μ represents the compression factor.

[0025] As a preferred embodiment of the present invention, the graph database constructs the devices and device connection relationships of each edge node in the power supply service log into a graph;

[0026] Each node in the graph represents an electric device, and the connecting edges between the nodes in the graph represent the association relationship between the electric devices. At the same time, each node also has attribute parameters.

[0027] As a preferred embodiment of the present invention, the event association analysis model is constructed based on a graph convolutional network. The graph convolutional network is used to aggregate and weight the fault events of neighboring nodes in the graph database to determine whether there are associated events and evaluate the strength of the association, as shown in the following formula:

[0028]

[0029] Where: H l represents the feature matrix of the lth layer; W lrepresents the weight matrix of the lth layer; D represents the degree matrix; σ represents the activation function; H l+1 Represents the feature matrix of the l+1th layer;

[0030] The final feature matrix output by the model is used to identify the association weights of the nodes, and the nodes whose sum of adjacent association weights is greater than the threshold are regarded as key nodes.

[0031] As a preferred embodiment of the present invention, the steps of generating a fault propagation chain are:

[0032] Set the key node as the initial failure node;

[0033] Use depth-first search to find fault propagation paths in the graph:

[0034] Starting from the initial fault node, traverse the adjacent nodes, record the access path and the associated weight of each step, until all fault propagation paths are found;

[0035] Set a fault propagation path threshold, calculate the sum of the weights of each fault propagation path, and remove fault propagation paths that are less than the fault propagation path threshold.

[0036] On the other hand, the present invention further provides 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 program, the method described in any embodiment of the present invention is implemented.

[0037] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0038] The present invention has the following beneficial effects:

[0039] 1. The present invention utilizes the distributed characteristics of the power Hongmeng system to build a flexible network architecture and reduce the risk of single point failure; each node (device, sensor, etc.) can operate independently and achieve efficient interconnection through the soft bus of the Hongmeng system.

[0040] 2. The present invention uses graph convolutional networks (GCN) to analyze the correlation between nodes, automatically identify the fault propagation chain, and provide data support for subsequent root cause analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0047] Embodiment 1:

[0048] See also Figure 1 , a method for recording power supply service logs based on the power Hongmeng system, comprising the following steps:

[0049] Through the power Hongmeng system, each edge node adaptively collects the power supply information of its corresponding area and generates a power supply service log, and pre-processes the power supply service log in the edge node;

[0050] The edge node uploads the pre-processed power supply service log to the power Hongmeng system and builds a graph database to store the power supply service log;

[0051] Construct an event correlation analysis model, and use it to analyze the connection weights of each node in the graph database;

[0052] Generate a fault propagation chain based on the connection weights of each node in the graph database.

[0053] As a preferred implementation of this embodiment, the edge node adaptively collects the power supply information of its corresponding area, as shown in the following formula:

[0054]

[0055] Where: f(t) represents the sampling frequency at time t; represents the reference sampling frequency; α represents the sensitivity factor; V(t) represents the voltage value at time t; Indicates the reference voltage value.

[0056] As a preferred implementation manner of this embodiment, the power supply service log includes a timestamp, a power equipment ID, a power equipment parameter type, a power equipment parameter value, and geographic information.

[0057] As a preferred implementation of this embodiment, the preprocessing steps of the power supply service log are:

[0058] The power supply service log is smoothed by the sliding average method, as shown in the following formula:

[0059]

[0060] in: represents the smoothed power supply service log; k represents the total number of samples in the power supply service log; x i represents the i-th sample in the power supply service log;

[0061] The smoothed data is compressed as shown in the following formula:

[0062]

[0063] Where: X t represents the compressed power supply service log; μ represents the compression factor.

[0064] As a preferred implementation of this embodiment, the graph database constructs the devices and device connection relationships of each edge node in the power supply service log into a graph;

[0065] Each node in the graph represents an electric device, and the connecting edges between the nodes in the graph represent the association relationship between the electric devices. At the same time, each node also has attribute parameters.

[0066] As a preferred implementation of this embodiment, the event association analysis model is constructed based on a graph convolutional network. The graph convolutional network is used to aggregate and weight the fault events of adjacent nodes in the graph database to determine whether there are associated events and evaluate the strength of the association, as shown in the following formula:

[0067]

[0068] Where: H l represents the feature matrix of the lth layer; W l represents the weight matrix of the lth layer; D represents the degree matrix; σ represents the activation function; H l+1Represents the feature matrix of the l+1th layer;

[0069] The final feature matrix output by the model is used to identify the association weights of the nodes, and the nodes whose sum of adjacent association weights is greater than the threshold are regarded as key nodes.

[0070] As a preferred implementation of this embodiment, the steps for generating a fault propagation chain are:

[0071] Set the key node as the initial failure node;

[0072] Use depth-first search to find fault propagation paths in the graph:

[0073] Starting from the initial fault node, traverse the adjacent nodes, record the access path and the associated weight of each step, until all fault propagation paths are found;

[0074] Set a fault propagation path threshold, calculate the sum of the weights of each fault propagation path, and remove fault propagation paths that are less than the fault propagation path threshold.

[0075] Embodiment 2:

[0076] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0077] Embodiment three:

[0078] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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 method for recording power supply service logs based on the power Hongmeng system, characterized in that: The following steps are involved: Through the power Hongmeng system, each edge node adaptively collects the power supply information of its corresponding area and generates a power supply service log, and pre-processes the power supply service log in the edge node; The edge node uploads the pre-processed power supply service log to the power Hongmeng system and builds a graph database to store the power supply service log; Construct an event correlation analysis model, and use it to analyze the connection weights of each node in the graph database; Generate a fault propagation chain based on the connection weights of each node in the graph database.

2. According to claim 1, a method for recording power supply service logs based on the power Hongmeng system is characterized in that: The edge node adaptively collects the power supply information of its corresponding area, as shown in the following formula: Where: f(t) represents the sampling frequency at time t; represents the reference sampling frequency; α represents the sensitivity factor; V(t) represents the voltage value at time t; Indicates the reference voltage value.

3. According to a method for recording power supply service logs based on the power Hongmeng system according to claim 1, it is characterized in that: The power supply service log includes a timestamp, a power equipment ID, a power equipment parameter type, a power equipment parameter value, and geographic information.

4. According to claim 1, a method for recording power supply service logs based on the power Hongmeng system is characterized in that: The preprocessing steps of the power supply service log are: The power supply service log is smoothed by the sliding average method, as shown in the following formula: in: represents the smoothed power supply service log; k represents the total number of samples in the power supply service log; x i represents the i-th sample in the power supply service log; The smoothed data is compressed as shown in the following formula: Where: X t represents the compressed power supply service log; μ represents the compression factor.

5. According to a method for recording power supply service logs based on the power Hongmeng system according to claim 1, it is characterized in that: The graph database constructs the devices and device connection relationships of each edge node in the power supply service log into a graph; Each node in the graph represents an electric device, and the connecting edges between the nodes in the graph represent the association relationship between the electric devices. At the same time, each node also has attribute parameters.

6. According to claim 5, a method for recording power supply service logs based on the power Hongmeng system is characterized in that: The event association analysis model is built based on a graph convolutional network. The graph convolutional network aggregates and calculates the weights of fault events of neighboring nodes in the graph database to determine whether there are associated events and evaluate the strength of the association, as shown in the following formula: Where: H l represents the feature matrix of the lth layer; W l represents the weight matrix of the lth layer; D represents the degree matrix; σ represents the activation function; H l+1 Represents the feature matrix of the l+1th layer; The final feature matrix output by the model is used to identify the association weights of the nodes, and the nodes whose sum of adjacent association weights is greater than the threshold are regarded as key nodes.

7. According to claim 6, a method for recording power supply service logs based on the power Hongmeng system is characterized in that: The steps for generating a fault propagation chain are: Set the key node as the initial failure node; Use depth-first search to find fault propagation paths in the graph: Starting from the initial fault node, traverse the adjacent nodes, record the access path and the associated weight of each step, until all fault propagation paths are found; Set a fault propagation path threshold, calculate the sum of the weights of each fault propagation path, and remove fault propagation paths that are less than the fault propagation path threshold.

8. 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, the method according to any one of claims 1 to 7 is implemented.

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

Images