Distributed power distribution fault processing method and system based on edge calculation

Abstract

The invention relates to a distributed power distribution fault processing method and system based on edge computing, and the system comprises a sensing layer which comprises a fault sensing unit and an edge computing node which are disposed at a low-voltage power distribution system terminal, and the fault sensing unit is used for collecting the operation data and environment data of power distribution equipment, the edge computing node processes and analyzes the data; the network layer is used for realizing data transmission between the sensing layer and the platform layer; the platform layer is used for storing, managing, analyzing, processing and applying the data uploaded by the sensing layer; the application layer is an application which is developed and deployed on the platform layer and is related to fault processing; the system has the advantages that through localized data processing and real-time analysis, the response speed and reliability of the power distribution system are remarkably improved; the system can detect and respond to abnormal conditions within millisecond-level time, loss caused by faults is greatly reduced, fault reasons are accurately positioned through a comprehensive scoring model and contribution degree analysis, and the accuracy of fault diagnosis is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, and particularly relates to a distributed power distribution fault processing method and system based on edge computing. BACKGROUND

[0002] With the continuous improvement of the intelligent level of power systems, the safety, stability and real-time response capability of the power distribution network have become key concerns for operation and maintenance management. Traditional power distribution fault monitoring methods mostly rely on centralized data collection and analysis systems, that is, through remote monitoring centers to process and judge the field data. However, this mode has problems such as high response delay, large communication bandwidth occupation, strong dependence on the center node, etc., and when facing sudden faults or local power failure scenes, it is often difficult to achieve fast and effective fault identification and positioning.

[0003] In recent years, edge computing technology has been widely applied in industrial Internet of Things, intelligent manufacturing, smart city and other fields. Edge computing can significantly reduce data transmission delay, improve system response speed, and enhance local autonomy by sinking data processing tasks from the cloud to edge nodes close to the data source. Its application in power distribution systems helps to realize real-time perception, on-site analysis and rapid alarm of the running state of power distribution equipment, and improves the reliability and intelligent level of the overall system.

[0004] At present, some researches have tried to introduce edge computing into the field of power distribution network fault monitoring. For example, some systems deploy terminal devices with preliminary computing capabilities at key locations such as ring network cabinets and power distribution rooms to collect and analyze current, voltage, temperature and other parameters. However, due to the lack of a unified scoring mechanism and abnormal judgment model, it is difficult to effectively integrate different sensor data, affecting the accuracy and timeliness of fault identification.

[0005] In addition, most existing systems do not have a perfect fault contribution analysis mechanism, which cannot clearly distinguish the primary and secondary relationships of various abnormal factors, making it difficult for operation and maintenance personnel to quickly lock the problem source when facing complex fault scenes, reducing the repair efficiency and system maintenance quality.

[0006] Based on this, the present application is proposed. SUMMARY

[0007] One of the purposes of the present application is to provide a distributed power distribution fault processing system based on edge computing, which realizes efficient identification, accurate positioning and intelligent decision support of power distribution faults.

[0008] In order to achieve the above purpose, the technical scheme of the present application is as follows: A distributed power distribution fault processing system based on edge computing, comprising: The perception layer includes a fault perception unit deployed at the terminal of a low-voltage power distribution system and an edge computing node, the fault perception unit is used to collect operation data and environmental data of power distribution equipment in real time, and the edge computing node is used to receive data from the fault perception unit and process and analyze the data; The network layer is used to realize data transmission between the perception layer and the platform layer; The platform layer is a cloud service platform under a commercial public cloud and / or a private cloud system, which is used to store, manage, analyze and process data uploaded by the perception layer and apply the data; The application layer is an application related to fault processing developed and deployed on the platform layer.

[0009] Further, the fault perception unit includes but is not limited to the following sensors: A current sensor is used to monitor the current value of the power distribution equipment; A voltage sensor is used to monitor the voltage value of the power distribution equipment; A temperature sensor is used to monitor the temperature change of the power distribution equipment; An environmental sensor is used to monitor the external environmental state of the power distribution equipment.

[0010] Further, the edge computing node includes a composite scoring model, which is used to quantify the influence degree of environmental factors, current, voltage, current change rate and voltage change rate on the power distribution equipment at each time point. The cloud platform determines whether the influence degree exceeds the set threshold value according to the quantification result uploaded by the edge computing node, and if the threshold value is exceeded, an alarm is issued and a corresponding fault report is generated.

[0011] Further, the composite scoring model is as follows: ; Wherein, represents the total influence degree at time point t; is a scoring function, which represents the influence degree of the i-th scoring item at time point t, the first scoring item is an environmental factor, the second scoring item is a current, the third scoring item is a voltage, the fourth scoring item is a current change rate, and the fifth scoring item is a voltage change rate; n represents the total number of scoring items; represents the weight coefficient of the i-th scoring item; For the environmental scoring item, ; Wherein represents the reading of the j-th environmental sensor at time point t, represents the expected value within the normal range of the j-th environmental sensor, and m represents the number of environmental sensors; For the current score item, ; wherein I represents the current reading, I min and I max represent the safe upper and lower limits of the current; For the voltage score item, ; wherein V represents the voltage reading, V min and V max represent the safe upper and lower limits of the voltage; For the current rate of change score item, ; wherein, represents the current rate of change at time t, represents the safe threshold of the current rate of change; For the voltage rate of change score, ; wherein, represents the voltage rate of change at time t, represents the safe threshold of the voltage rate of change.

[0012] Further, the platform layer comprises: a database management module for storing data uploaded by the perception layer; a data analysis module for processing received data, identifying abnormal situations and generating fault reports; a security protection module for ensuring the security and privacy of data; an open API interface module supporting integration with other systems or third-party applications.

[0013] Further, in the data analysis module, a contribution calculation unit is included for evaluating the contribution of environmental factors, current, voltage, current rate of change and voltage rate of change at each time point to the impact of power distribution equipment, determining the main factors causing the fault, and facilitating the data analysis module to generate fault reports; The contribution calculation unit includes the following calculation model: ; wherein, represents the contribution of the i-th score item at time point t; is the normalized score of , wherein s i,max represents the maximum evaluation value of the i-th score item.

[0014] Further, the application layer comprises: a fault monitoring and alarm module that receives fault reports in real time and generates alarm information according to preset rules; an operation and maintenance management and scheduling module that provides operation and maintenance management tools, supports device inspection plan development, task allocation and progress tracking; The visualization and reporting module provides a rich visualization interface to display the operating status and health status of the power distribution system; The decision support module provides decision suggestions based on data analysis results and preset rules.

[0015] The second objective of this invention is to provide a distributed power distribution fault handling method based on edge computing, characterized in that, based on the aforementioned distributed power distribution fault handling system based on edge computing, it includes the following steps: S10. Collect operating data and environmental data of power distribution equipment through the fault sensing unit; S20. The edge computing node receives data from the fault perception unit and uses a composite scoring model to quantify the impact of environmental factors, current, voltage and current change rate, and voltage change rate on the power distribution equipment at each time point. The cloud platform determines whether the impact exceeds the set threshold based on the quantification results uploaded by the edge computing node. At the same time, it evaluates the contribution of environmental factors, current, voltage and current change rate, and voltage change rate to the impact on the power distribution equipment at each time point, determines the main factors causing the fault, and finally generates a corresponding fault report. S30. Based on the fault report, the application layer notifies relevant personnel to take measures and provides fault location and diagnostic information.

[0016] The advantages of this invention are as follows: The edge computing-based distributed power distribution fault handling system significantly improves the response speed and reliability of the power distribution system through localized data processing and real-time analysis; the system can detect and respond to anomalies within milliseconds, greatly reducing losses caused by faults, and accurately locates the cause of faults through a comprehensive scoring model and contribution analysis, improving the accuracy of fault diagnosis; furthermore, by reducing unnecessary data transmission, the system not only lowers bandwidth requirements and operating costs but also enhances the overall architecture's security and privacy protection. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the architecture of the distributed power distribution fault handling system based on edge computing in the embodiment. Detailed Implementation

[0018] The present invention will be further described in detail below with reference to embodiments. It should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., used in this document indicate the orientation or positional relationship based on the coordinate system shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the present invention.

[0019] likeFigure 1 As shown in the figure, this embodiment proposes a distributed power distribution fault handling system based on edge computing, including a perception layer, a network layer, a platform layer and an application layer.

[0020] The perception layer includes fault perception units and edge computing nodes deployed at the terminals of the low-voltage power distribution system. The fault perception units are used to collect real-time operating data and environmental data of the power distribution equipment, and the edge computing nodes are used to receive data from the fault perception units and process and analyze the data.

[0021] The fault detection unit includes, but is not limited to, current sensors, voltage sensors, temperature sensors, and environmental sensors. Current sensors monitor the current value of the power distribution equipment; voltage sensors monitor the voltage value; temperature sensors monitor temperature changes; and environmental sensors monitor the external environmental conditions. Through these sensors, the fault detection unit can collect real-time data on the current, voltage, temperature, and other environmental parameters of the power distribution equipment.

[0022] The edge computing node includes a composite scoring model to quantify the impact of environmental factors, current, voltage, current change rate, and voltage change rate on the power distribution equipment at each time point. Based on the quantification results uploaded by the edge computing node, the cloud platform determines whether the impact exceeds a set threshold. If it does, an alarm is issued and a corresponding fault report is generated. In this embodiment, the composite scoring model is as follows: ; in, This indicates the total degree of influence at time point t; Let be the scoring function, representing the degree of influence of the i-th scoring item at time point t. The first scoring item is environmental factors, the second is current, the third is voltage, the fourth is the rate of change of current, and the fifth is the rate of change of voltage; n represents the total number of scoring items. This represents the weight coefficient of the i-th rating item.

[0023] For the environmental scoring item, ; in This represents the reading of the j-th environmental sensor at time point t. Let m represent the expected value within the normal range of the j-th environmental sensor, and m represent the number of environmental sensors. For the current rating item, In the formula, I represents the current reading, I min and I max Indicates the upper and lower safety limits of the current; For the voltage rating item, In the formula, V represents the voltage reading.min and V max Indicates the upper and lower safety limits of the voltage; For the current change rate scoring item In the formula, This represents the rate of change of current over time t. The safety threshold representing the rate of change of current; For voltage change rate scoring In the formula, This represents the rate of change of voltage over time t. This represents the safety threshold for the rate of voltage change.

[0024] The platform layer includes a database management module, a data analysis module, a security protection module, and an open API interface module. The database management module stores data uploaded from the perception layer; the data analysis module processes the received data, identifies anomalies, and generates fault reports; the security protection module ensures data security and privacy; and the open API interface module supports integration with other systems or third-party applications.

[0025] The data analysis module includes a contribution calculation unit, used to evaluate the contribution of environmental factors, current, voltage, current change rate, and voltage change rate to the impact on power distribution equipment at each time point, identifying the main factors causing the fault and facilitating the generation of fault reports by the data analysis module. The contribution calculation unit includes the following calculation model: ; In the formula, This represents the contribution of the i-th rating item at time point t; yes The standardized score, i.e. In the formula s i,max This represents the maximum evaluation value of the i-th rating item.

[0026] The application layer includes a fault monitoring and alarm module, an operation and maintenance management and scheduling module, a visualization and reporting module, and a decision support module. The fault monitoring and alarm module receives fault reports in real time and generates alarm information according to preset rules; the operation and maintenance management and scheduling module provides operation and maintenance management tools, supporting equipment inspection plan formulation, task allocation, and progress tracking; the visualization and reporting module provides a rich visualization interface to display the operating status and health status of the power distribution system; and the decision support module can provide decision suggestions based on data analysis results and preset rules.

[0027] The distributed power distribution fault handling method based on the above system includes the following steps: S10. Collect operating data and environmental data of power distribution equipment through the fault sensing unit; S20. The edge computing node receives data from the fault perception unit and uses a composite scoring model to quantify the impact of environmental factors, current, voltage and current change rate, and voltage change rate on the power distribution equipment at each time point. The cloud platform determines whether the impact exceeds the set threshold based on the quantification results uploaded by the edge computing node. At the same time, it evaluates the contribution of environmental factors, current, voltage and current change rate, and voltage change rate to the impact on the power distribution equipment at each time point, determines the main factors causing the fault, and finally generates a corresponding fault report. S30. Based on the fault report, the application layer notifies relevant personnel to take measures and provides fault location and diagnostic information.

[0028] The above system has the following technical effects: 1. With strong real-time performance and fast response speed, the perception layer monitors the operating status of power distribution equipment in real time through sensors (such as current, voltage, temperature, and environmental sensors) deployed in low-voltage power distribution terminals; combined with the local data processing capabilities of edge computing nodes, it realizes rapid data analysis and preliminary judgment, reduces the latency caused by data uploading to the cloud, and improves the system's response speed. 2. Multi-dimensional quantitative assessment to improve fault identification accuracy: A composite scoring model is adopted, comprehensively considering the influence of multiple dimensions such as environmental factors, current, voltage, current change rate, and voltage change rate, and assigning different weights to achieve a comprehensive quantitative assessment of the operating status of power distribution equipment. Further analysis of the relative impact of each factor through a contribution calculation unit helps to accurately identify the main causes of faults, thereby improving the accuracy of fault identification. 3. Enhanced intelligent alarm and fault location capabilities: When the scoring result exceeds the set threshold, the system automatically triggers the alarm mechanism and generates a fault report. At the same time, combined with the fault location algorithm (contribution calculation) in the data analysis module, the specific location or equipment where the fault occurred can be quickly located, shortening the fault investigation time and improving operation and maintenance efficiency. 4. Supports decision support and visual management. The application layer provides a visual display interface to intuitively present the operating status, health status and historical trends of the power distribution system. The decision support module can provide targeted operation and maintenance suggestions or preventive measures based on historical data and current scoring results to help managers make scientific decisions. 5. Safe, reliable, and easy to expand and integrate: The platform layer has a security protection module to ensure the security and privacy of data during collection, transmission, storage and use; the open API interface module supports integration with other management systems (such as SCADA, EMS, etc.) or third-party applications, and has good compatibility and scalability.

[0029] 6. Promote the transformation of power distribution system to intelligent operation and maintenance. The system has realized the transformation from traditional manual inspection to automated and intelligent operation and maintenance, which has significantly improved the reliability, stability and operation and maintenance efficiency of the power distribution system, and provided strong support for the construction of smart grid and smart energy management system.

[0030] The above embodiments are only used to explain the concept of the present invention, and are not intended to limit the protection of the present invention. Any non-substantial modifications made to the present invention using this concept should fall within the protection scope of the present invention.

Claims

1. A distributed power distribution fault handling system based on edge computing, characterized in that, include: The perception layer includes fault perception units and edge computing nodes deployed at the terminals of the low-voltage power distribution system. The fault perception units are used to collect real-time operating data and environmental data of the power distribution equipment, and the edge computing nodes are used to receive data from the fault perception units and process and analyze the data. The network layer is used to enable data transmission between the perception layer and the platform layer. The platform layer is a cloud service platform under a commercial public cloud and / or private cloud system, used to store, manage, analyze and process, and apply the data uploaded by the perception layer; The application layer consists of applications developed and deployed on top of the platform layer that are related to fault handling.

2. The distributed power distribution fault handling system based on edge computing as described in claim 1, characterized in that, The fault detection unit includes, but is not limited to, the following sensors: Current sensors are used to monitor the current value of power distribution equipment; Voltage sensors are used to monitor the voltage values ​​of power distribution equipment; Temperature sensors are used to monitor temperature changes in power distribution equipment; Environmental sensors are used to monitor the external environmental conditions of power distribution equipment.

3. The distributed power distribution fault handling system based on edge computing as described in claim 2, characterized in that, The edge computing node includes a composite scoring model, which is used to quantify the impact of environmental factors, current, voltage, current change rate and voltage change rate on power distribution equipment at each time point. The cloud platform determines whether the impact exceeds a set threshold based on the quantification results uploaded by the edge computing node. If the threshold is exceeded, an alarm is issued and a corresponding fault report is generated.

4. The distributed power distribution fault handling system based on edge computing as described in claim 3, characterized in that, The composite scoring model is as follows: ； in, This indicates the total degree of influence at time point t; Let be the scoring function, representing the degree of influence of the i-th scoring item at time point t. The first scoring item is environmental factors, the second scoring item is current, the third scoring item is voltage, the fourth scoring item is the rate of change of current, and the fifth scoring item is the rate of change of voltage. n represents the total number of rating items; This represents the weight coefficient of the i-th rating item.

5. A distributed power distribution fault handling system based on edge computing as described in claim 4, characterized in that, The platform layer includes: The database management module is used to store the data uploaded by the perception layer; The data analysis module is used to process the received data, identify anomalies, and generate fault reports. A security protection module is used to ensure the security and privacy of data; An open API interface module supports integration with other systems or third-party applications.

6. The distributed power distribution fault handling system based on edge computing as described in claim 5, characterized in that, The data analysis module includes a contribution calculation unit, which is used to evaluate the contribution of environmental factors, current, voltage, current change rate and voltage change rate to the degree of influence of power distribution equipment at each time point, to determine the main factors causing the fault, and to facilitate the generation of fault reports by the data analysis module. The contribution calculation unit includes the following calculation model: ； In the formula, This represents the contribution of the i-th rating item at time point t; yes The standardized score, i.e. In the formula s i,max This represents the maximum evaluation value of the i-th rating item.

7. A distributed power distribution fault handling system based on edge computing as described in claim 5, characterized in that, The application layer includes: The fault monitoring and alarm module receives fault reports in real time and generates alarm information according to preset rules; The operation and maintenance management and scheduling module provides operation and maintenance management tools to support equipment inspection plan formulation, task allocation and progress tracking; The visualization and reporting module provides a rich visualization interface to display the operating status and health status of the power distribution system; The decision support module provides decision suggestions based on data analysis results and preset rules.

8. A distributed power distribution fault handling method based on edge computing, characterized in that, The distributed power distribution fault handling system based on edge computing as described in any one of claims 1 to 7 includes the following steps: S10. Collect operating data and environmental data of power distribution equipment through the fault sensing unit; S20. The edge computing node receives data from the fault perception unit and uses a composite scoring model to quantify the impact of environmental factors, current, voltage and current change rate, and voltage change rate on the power distribution equipment at each time point. The cloud platform determines whether the impact exceeds the set threshold based on the quantification results uploaded by the edge computing node. At the same time, it evaluates the contribution of environmental factors, current, voltage and current change rate, and voltage change rate to the impact on the power distribution equipment at each time point, determines the main factors causing the fault, and finally generates a corresponding fault report. S30. Based on the fault report, the application layer notifies relevant personnel to take measures and provides fault location and diagnostic information.

Images