Distribution network fault handling identification and decision-making system based on cloud platform

Abstract

The present invention discloses a distribution network fault handling identification decision system based on a cloud platform, and specifically relates to the technical field of distribution network fault handling identification decision. By retrieving actual power data corresponding to each effective fault node in an effective fault node set, and determining the specific fault type existing in the effective fault node based on the actual power data, the omission of fault type detection is reduced, so that the specific fault type existing in the effective fault node can be obtained more accurately and comprehensively; in addition, by obtaining the effective fault node's own influence coefficient and combining the fault type and severity corresponding to the fault node, the final influence coefficient of each effective fault node is finally obtained, and different decision instructions are issued according to the importance level corresponding to the final influence coefficient, so that the fault node can be repaired in time to ensure the stability of the power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault handling identification decision-making, and specifically to a distribution network fault handling identification decision-making system based on a cloud platform. Background Art

[0002] The distribution network fault handling identification and decision-making system based on the cloud platform is a system that identifies and locates faults in the power distribution network through the cloud platform, determines the faults in the distribution network, and automatically makes decisions based on the corresponding fault types, promptly reminding relevant personnel to carry out maintenance to ensure the stability and reliability of the power system operation. This automated decision-making process greatly improves the efficiency and accuracy of fault handling, reduces misjudgments and delays that may be caused by human factors, helps power operators optimize distribution network management strategies and equipment maintenance plans, and further improves the reliability and safety of the distribution network.

[0003] Existing distribution network fault handling identification and decision-making methods often determine which nodes are faulty and issue maintenance instructions to the faulty nodes to remind staff to repair them. However, in the actual process, different faulty nodes have different corresponding importance, and the severity and type of faults of different faulty nodes are also different. If maintenance instructions are simply issued to remind staff to repair them, the faulty nodes may not be repaired in a timely manner, resulting in reduced stability of the power grid. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that the maintenance of faulty nodes is not timely enough, resulting in reduced stability of the power grid, and to propose a distribution network fault handling identification decision system based on a cloud platform.

[0005] The present invention proposes a distribution network fault handling identification and decision-making system based on a cloud platform, the system is used to make decisions on a target distribution network, and the system includes:

[0006] Final fault type module: obtains the valid fault node set of the target distribution network, retrieves the actual power data corresponding to each valid fault node in the valid fault node set, and determines the final fault type set of each valid fault node according to the actual power data;

[0007] Self-influence module: constructs the power grid network diagram of the target distribution network, and determines the self-influence index of each effective fault node according to the power grid network diagram and the influence data corresponding to the effective fault node set;

[0008] Final impact module: determines the final impact coefficient of each valid fault node according to its own impact index and the final fault type set of the fault node;

[0009] Decision-making module: Determine the importance level of each valid fault node based on the final impact coefficient of each valid fault node and the preset final impact coefficient level correspondence table, and send a decision instruction to the corresponding terminal according to the importance level of each valid fault node.

[0010] Optionally, the final fault type module includes:

[0011] Comparison module: record the node where the fault alarm in the target distribution network sends out an alarm as the initial fault node, and compare the fault alarm time of each initial fault node with the preset minimum effective alarm time;

[0012] Valid fault node module: When the fault alarm time of the initial fault node is not less than the preset minimum valid alarm time, the initial fault node is regarded as a valid fault node, and all valid fault nodes in the target distribution network are regarded as a valid fault node set;

[0013] Actual power data module: retrieves all power data monitored by each effective fault node in the effective fault node set as the actual power data of the effective fault node.

[0014] Optionally, the final fault type module further includes:

[0015] Preliminary fault type module: inputs the actual power data of each effective fault node into a preset fault type determination model, and outputs a preliminary fault type set of the effective fault node;

[0016] Possible coexisting fault module: querying a preset coexisting fault table according to all fault types in the preliminary fault type set of the valid fault node, and obtaining the remaining possible coexisting fault type sets of the valid fault node;

[0017] Actual existing fault module: extract the fault power data change characteristics of each other possible coexisting fault type in the set of other possible coexisting fault types of the effective fault node, and match the fault power data change characteristics of the other possible coexisting fault types with the actual power data. If the degree of match is greater than the preset match threshold, the other possible coexisting fault types are taken as the actual existing fault types;

[0018] Final fault determination module: merges all actual existing fault types of valid fault nodes with the preliminary fault type set to obtain the final fault type set.

[0019] Optionally, the self-influence module includes:

[0020] Influencing data corresponding module: the influencing data includes degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient;

[0021] Target network diagram module: construct a power network diagram of a target distribution network to obtain a target network diagram, wherein the target network diagram includes a plurality of nodes, each of which corresponds to a node of the target distribution network;

[0022] Degree centrality module: obtain the node corresponding to each valid fault node in the power grid network diagram, obtain the target fault node set, and obtain the total number of nodes connected to each fault node in the target fault node set, and record the total number of connected nodes as the degree centrality of the fault node;

[0023] Cable usage time module: obtains the commissioning time of the cable used by each effective fault node and the corresponding preset service life of the cable, and divides the commissioning time by the preset service life to obtain the cable usage time coefficient of the fault node;

[0024] Cable load module: retrieves the average load current value of the cable used by each effective fault node during the period of time when it is put into use according to historical records, and divides the average load current value by the preset maximum tolerable load current value to obtain the cable load factor of the fault node;

[0025] Cable quality module: The cable usage time coefficient and cable load coefficient of each effective fault node are weighted and summed to obtain the cable quality coefficient.

[0026] Optionally, the self-influence module further includes:

[0027] Environmental impact module: obtains the ambient temperature and humidity of the fault point at different times within a fixed time period after the failure of each effective fault node, and obtains the environmental impact coefficient of the effective fault node based on the ambient temperature and humidity. The specific formula is: In the formula, Gdx is the environmental impact coefficient, T i Indicates the temperature at different times, S i represents the humidity at different times, i represents the order of temperature and humidity at different times, i∈[1,n], n is a positive integer, d1 and d2 are the preset proportional coefficients of temperature and humidity respectively, and d1 and d2 are both greater than 0;

[0028] Maintenance interval module: obtains the time interval from the last maintenance of each valid fault node to the current time, obtains the current time interval, and divides the current time interval by the average maintenance time interval of the valid fault node to obtain the maintenance interval coefficient of the valid fault node.

[0029] Optionally, the self-influence module is also applied to:

[0030] The self-influence index of each effective fault node is obtained according to the degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient of each effective fault node. The specific formula is:

[0031] Rfd=f1×Gas+f2×Gvr+f3×Gdx+f4×Gdy

[0032] Where Rfd is the self-influence index, Gas, Gvr, Gdx, and Gdy represent degree centrality, cable quality coefficient, environmental impact coefficient, and maintenance interval coefficient, respectively; f1, f2, f3, and f4 are proportional coefficients of degree centrality, cable quality coefficient, environmental impact coefficient, and maintenance interval coefficient, respectively; and f1, f2, f3, and f4 are all greater than 0.

[0033] Optionally, the final impact module includes:

[0034] Fault importance module: determine all final fault types in the final fault type set of each valid fault node, and query the corresponding preset fault type importance value table according to each fault type, determine the importance value corresponding to each fault type, add the importance values ​​corresponding to all fault types, and obtain the fault importance coefficient of each valid fault node of the valid fault node;

[0035] Final influence coefficient module: The fault importance coefficient and the self-influence index of each effective fault node are weighted and summed to obtain the final influence coefficient of the effective fault node.

[0036] Optionally, the decision module is applied to:

[0037] The final impact coefficient of each effective fault node is matched with the preset final impact coefficient level correspondence table to determine the importance level of each effective fault node;

[0038] A corresponding decision instruction is generated according to the importance level of each valid fault node, and the decision instruction is sent to the corresponding terminal.

[0039] Beneficial effects of the present invention:

[0040] The present invention proposes a distribution network fault handling identification decision system based on a cloud platform. By retrieving the actual power data corresponding to each effective fault node in the effective fault node set, the specific fault type existing in the fault node can be determined according to the actual power data, thereby reducing the omissions in fault type detection, so that the specific fault type existing in the fault node can be obtained more accurately and comprehensively; in addition, different decision instructions can be issued according to the importance corresponding to different fault nodes, the severity and type of the fault, so that the fault node can be repaired in time to ensure the stability of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described below in conjunction with the accompanying drawings.

[0042] Figure 1 This is a framework diagram of the cloud platform-based distribution network fault handling identification and decision-making system proposed by the present invention;

[0043] Figure 2 This is a specific processing flow chart of the final fault type module proposed by the present invention. 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] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0046] The embodiment of the present invention provides a distribution network fault handling identification and decision-making system based on a cloud platform. Figure 1 , Figure 1 A framework diagram of a cloud-based distribution network fault handling identification and decision-making system provided in an embodiment of the present invention. The system is used to make decisions on a target distribution network, and the system includes:

[0047] Final fault type module: obtains the valid fault node set of the target distribution network, retrieves the actual power data corresponding to each valid fault node in the valid fault node set, and determines the final fault type set of each valid fault node according to the actual power data;

[0048] Self-influence module: constructs the power grid network diagram of the target distribution network, and determines the self-influence index of each effective fault node according to the power grid network diagram and the influence data corresponding to the effective fault node set;

[0049] Final impact module: determines the final impact coefficient of each valid fault node according to its own impact index and the final fault type set of the fault node;

[0050] Decision-making module: Determine the importance level of each valid fault node based on the final impact coefficient of each valid fault node and the preset final impact coefficient level correspondence table, and issue a decision instruction to the corresponding terminal according to the importance level of each valid fault node.

[0051] Based on the cloud platform-based distribution network fault handling identification decision system provided by the embodiment of the present invention, the above-mentioned method can determine the specific fault type of the fault node, reduce the omissions in fault type detection, and make it possible to obtain the specific fault type of the fault node more accurately and comprehensively; and issue different decision instructions according to the importance, severity and type of the fault corresponding to different fault nodes, so that the fault node can be repaired in time to ensure the stability of the power grid.

[0052] In one embodiment, the final fault type module includes:

[0053] Comparison module: record the node where the fault alarm in the target distribution network sends out an alarm as the initial fault node, and compare the fault alarm time of each initial fault node with the preset minimum effective alarm time;

[0054] Valid fault node module: When the fault alarm time of the initial fault node is not less than the preset minimum valid alarm time, the initial fault node is regarded as a valid fault node, and all valid fault nodes in the target distribution network are regarded as a valid fault node set;

[0055] Actual power data module: retrieves all power data monitored by each effective fault node in the effective fault node set as the actual power data of the effective fault node.

[0056] In one implementation, the preset minimum effective alarm time is set by professional technicians according to actual conditions, and is not specifically limited.

[0057] In one implementation method, by comparing the fault alarm time of the initial fault node with the preset minimum valid alarm time through the above method, those situations that are only short-term alarms or false alarms can be filtered out. Only nodes whose duration reaches the preset standard are confirmed as valid fault nodes, ensuring the accuracy and reliability of fault diagnosis.

[0058] In one embodiment, the final fault type module further includes:

[0059] Preliminary fault type module: inputs the actual power data of each effective fault node into a preset fault type determination model, and outputs a preliminary fault type set of the effective fault node;

[0060] Possible coexisting fault module: querying a preset coexisting fault table according to all fault types in the preliminary fault type set of the valid fault node, and obtaining the remaining possible coexisting fault type sets of the valid fault node;

[0061] Actual existing fault module: extract the fault power data change characteristics of each other possible coexisting fault type in the set of other possible coexisting fault types of the effective fault node, and match the fault power data change characteristics of the other possible coexisting fault types with the actual power data. If the degree of match is greater than the preset match threshold, the other possible coexisting fault types are taken as the actual existing fault types;

[0062] Final fault determination module: merges all actual existing fault types of valid fault nodes with the preliminary fault type set to obtain the final fault type set.

[0063] It should be noted that the preset fault type determination model is set by professionals based on the historical power data of the target distribution network and the corresponding power fault type, and is not specifically limited. The preset matching degree threshold is set by professionals based on the actual situation, and the specific value is not limited.

[0064] In one implementation, through the above method, through multi-level analysis and comparison, the misjudgment that may be caused by a single analysis method is reduced, the accuracy of fault diagnosis is improved, and at the same time, the coexistence of faults is taken into account to ensure that the diagnosis results can reflect the complex situation of multiple coexisting faults and avoid missed diagnosis.

[0065] In one embodiment, the self-influence module includes:

[0066] Influencing data corresponding module: Influencing data include degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient;

[0067] Target network diagram module: construct a power network diagram of the target distribution network to obtain the target network diagram, which contains several nodes, each of which corresponds to a node of the target distribution network;

[0068] Degree centrality module: obtain the node corresponding to each valid fault node in the power grid network diagram, obtain the target fault node set, and obtain the total number of nodes connected to each fault node in the target fault node set, and record the total number of connected nodes as the degree centrality of the fault node;

[0069] Cable usage time module: obtains the commissioning time of the cable used by each effective fault node and the corresponding preset service life of the cable, and divides the commissioning time by the preset service life to obtain the cable usage time coefficient of the fault node;

[0070] Cable load module: retrieves the average load current value of the cable used by each effective fault node during the period of time when it is put into use according to historical records, and divides the average load current value by the preset maximum tolerable load current value to obtain the cable load factor of the fault node;

[0071] Cable quality module: The cable usage time coefficient and cable load coefficient of each effective fault node are weighted and summed to obtain the cable quality coefficient.

[0072] It should be noted that the commissioning time of the cable used by each effective fault node and the average load current value of the cable used by each effective fault node during the period of commissioning can be directly obtained from the historical operation records of the effective fault node, or obtained by other means, without specific limitation; the corresponding preset service life of the cable can be directly obtained by querying the production data of the cable, or by other means, without specific limitation.

[0073] In one implementation method, through the above method, the centrality and cable quality coefficient of each effective fault node can be calculated more accurately, making the self-influence index of each effective fault node more accurate; the degree centrality reflects the number of connections and influence of the node in the power grid network, and the cable quality coefficient comprehensively considers the cable's commissioning time, average load current value and preset maximum tolerable load current value, thereby evaluating the health status and reliability of the cable.

[0074] In one embodiment, the self-influence module further includes:

[0075] Environmental impact module: obtains the ambient temperature and humidity of the fault point at different times within a fixed time period after the failure of each effective fault node, and obtains the environmental impact coefficient of the effective fault node based on the ambient temperature and humidity. The specific formula is: In the formula, Gdx is the environmental impact coefficient, T i Indicates the temperature at different times, S i represents the humidity at different times, i represents the order of temperature and humidity at different times, i∈[1,n], n is a positive integer, d1 and d2 are the preset proportional coefficients of temperature and humidity respectively, and d1 and d2 are both greater than 0;

[0076] Maintenance interval module: obtains the time interval from the last maintenance of each valid fault node to the current time, obtains the current time interval, and divides the current time interval by the average maintenance time interval of the valid fault node to obtain the maintenance interval coefficient of the valid fault node.

[0077] It should be noted that within a fixed time period after the failure of each effective fault node, the ambient temperature and humidity of the fault point at different times can be obtained by using temperature sensors and humidity sensors installed near the distribution network node, or by other methods, which are not specifically limited.

[0078] In one implementation method, the environmental impact coefficient and maintenance interval coefficient of each effective fault node can be calculated more accurately through the above method, so that the self-impact index of each effective fault node is more accurate; the environmental impact coefficient reflects the impact of environmental conditions on node stability and fault probability by recording the changes in ambient temperature and humidity at the time of the fault; and the maintenance interval coefficient is based on the node's maintenance history data, taking into account the impact of maintenance frequency on node operation stability.

[0079] In one embodiment, the self-influence module is also applied to:

[0080] The self-influence index of each effective fault node is obtained according to the degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient of each effective fault node. The specific formula is:

[0081] Rfd=f1×Gas+f2×Gvr+f3×Gdx+f4×Gdy

[0082] Where Rfd is the self-influence index, Gas, Gvr, Gdx, and Gdy represent degree centrality, cable quality coefficient, environmental impact coefficient, and maintenance interval coefficient, respectively; f1, f2, f3, and f4 are proportional coefficients of degree centrality, cable quality coefficient, environmental impact coefficient, and maintenance interval coefficient, respectively; and f1, f2, f3, and f4 are all greater than 0.

[0083] In one implementation, through the above method, a more accurate self-influence index of each effective fault node can be obtained. The degree centrality reflects the importance and connection degree of the node in the network, the cable quality coefficient takes into account the usage and load capacity of the cable, and the environmental impact coefficient reflects the impact of external conditions on node stability through changes in ambient temperature and humidity. The maintenance interval coefficient takes into account the maintenance frequency and historical maintenance of the node. The comprehensive consideration of these factors provides a comprehensive self-influence assessment for each effective fault node.

[0084] In one embodiment, the final impact module includes:

[0085] Fault importance module: determine all final fault types in the final fault type set of each valid fault node, and query the corresponding preset fault type importance value table according to each fault type, determine the importance value corresponding to each fault type, add the importance values ​​corresponding to all fault types, and obtain the fault importance coefficient of each valid fault node of the valid fault node;

[0086] Final influence coefficient module: The fault importance coefficient and the self-influence index of each effective fault node are weighted and summed to obtain the final influence coefficient of the effective fault node.

[0087] In one implementation method, the preset fault type importance value table is set by professionals based on actual conditions and is not specifically limited; in addition, through the above method, the self-influence index of each effective fault node and the final fault type set of the fault node are combined to determine the final influence coefficient of each effective fault node, which can comprehensively and accurately consider the importance of the effective fault node when a fault occurs and its possible impact.

[0088] In one embodiment, the decision module further includes:

[0089] Importance level module: The final impact coefficient of each effective fault node is matched with the preset final impact coefficient level correspondence table to determine the importance level of each effective fault node;

[0090] Decision sending module: generates corresponding decision instructions according to the importance level of each valid fault node, and sends the decision instructions to the corresponding terminal.

[0091] In one implementation, the maintenance personnel corresponding to the preset importance level are determined by professionals based on the actual ability, qualification and maintenance experience of the maintenance personnel, and are not specifically limited.

[0092] In one implementation, the importance level of each fault node is determined according to the final influence coefficient of each effective fault node and the preset final influence coefficient level correspondence table. The level reflects the importance and influence of the fault node in the operation of the distribution network. By comparing the mapping relationship between the final influence coefficient and the preset level, the specific importance level of each node can be determined.

[0093] Based on the importance level of each valid fault node, a corresponding decision instruction is generated and sent to the terminal equipment of the maintenance personnel corresponding to the same importance level, reminding the corresponding maintenance personnel to handle the fault of the corresponding distribution network node. This approach ensures the effective allocation of resources, which not only improves the response speed and accuracy of fault handling, but also orderly dispatches and allocates maintenance resources through the preset importance level system, so that the faulty nodes can be repaired in time, ensuring the stability of the power grid and ensuring the stable operation and reliability of the distribution network.

[0094] It should be noted that, for example, if a node in a distribution network is determined to be a high-importance node, this usually means that the failure of the node will have a significant impact on the entire distribution network, and may cause a large-scale power outage or affect the operation of important equipment. In this case, the system immediately responds with a decision instruction and sends it to the terminal device corresponding to the maintenance personnel of the high-importance level, reminding the staff to repair the faulty node;

[0095] For example, suppose a node in a distribution network is determined to be a medium-important node. In this case, the failure of the node may have an impact on the local area, but will not pose a serious threat to the operation of the entire distribution network. In this case, the system immediately responds with a decision instruction and sends it to the terminal device corresponding to the maintenance personnel of the medium-important level, reminding the staff to repair the faulty node.

[0096] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A distribution network fault handling identification and decision-making system based on a cloud platform, characterized in that: The system is used to make decisions on a target distribution network, and the system includes: Final fault type module: obtains the valid fault node set of the target distribution network, retrieves the actual power data corresponding to each valid fault node in the valid fault node set, and determines the final fault type set of each valid fault node according to the actual power data; Self-influence module: constructs the power grid network diagram of the target distribution network, and determines the self-influence index of each effective fault node according to the power grid network diagram and the influence data corresponding to the effective fault node set; Final impact module: determines the final impact coefficient of each valid fault node according to its own impact index and the final fault type set of the fault node; Decision-making module: Determine the importance level of each valid fault node by using the final impact coefficient of each valid fault node and the preset final impact coefficient level correspondence table, and send a decision instruction to the corresponding terminal according to the importance level of each valid fault node; The self-influence module is also used for: The self-influence index of each effective fault node is obtained according to the degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient of each effective fault node. The specific formula is: ； In the formula, is its own impact index, They represent degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient respectively. are the proportionality coefficients of degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient, respectively, and , , , All are greater than 0; The final impact module includes: Fault importance module: determine all final fault types in the final fault type set of each valid fault node, and query the corresponding preset fault type importance value table according to each fault type, determine the importance value corresponding to each fault type, add the importance values ​​corresponding to all fault types, and obtain the fault importance coefficient of each valid fault node of the valid fault node; Final influence coefficient module: The fault importance coefficient and the self-influence index of each effective fault node are weighted and summed to obtain the final influence coefficient of the effective fault node.

2. The cloud platform-based distribution network fault handling identification and decision-making system according to claim 1 is characterized in that: The final fault type module includes: Comparison module: record the node where the fault alarm in the target distribution network sends out an alarm as the initial fault node, and compare the fault alarm time of each initial fault node with the preset minimum effective alarm time; Valid fault node module: When the fault alarm time of the initial fault node is not less than the preset minimum valid alarm time, the initial fault node is regarded as a valid fault node, and all valid fault nodes in the target distribution network are regarded as a valid fault node set; Actual power data module: retrieves all power data monitored by each effective fault node in the effective fault node set as the actual power data of the effective fault node.

3. The cloud platform-based distribution network fault handling identification and decision-making system according to claim 2 is characterized in that: The final fault type module also includes: Preliminary fault type module: inputs the actual power data of each effective fault node into a preset fault type determination model, and outputs a preliminary fault type set of the effective fault node; Possible coexisting fault module: querying a preset coexisting fault table according to all fault types in the preliminary fault type set of the valid fault node, and obtaining the remaining possible coexisting fault type sets of the valid fault node; Actual existing fault module: extract the fault power data change characteristics of each other possible coexisting fault type in the set of other possible coexisting fault types of the effective fault node, and match the fault power data change characteristics of the other possible coexisting fault types with the actual power data. If the degree of match is greater than the preset match threshold, the other possible coexisting fault types are taken as the actual existing fault types; Final fault determination module: merges all actual existing fault types of valid fault nodes with the preliminary fault type set to obtain the final fault type set.

4. The cloud platform-based distribution network fault handling identification and decision-making system according to claim 1, characterized in that: The self-influence module includes: Influencing data corresponding module: the influencing data includes degree centrality, cable quality coefficient, environmental impact coefficient and maintenance interval coefficient; Target network diagram module: construct a power network diagram of a target distribution network to obtain a target network diagram, wherein the target network diagram includes a plurality of nodes, each of which corresponds to a node of the target distribution network; Degree centrality module: obtain the node corresponding to each valid fault node in the power grid network diagram, obtain the target fault node set, and obtain the total number of nodes connected to each fault node in the target fault node set, and record the total number of connected nodes as the degree centrality of the fault node; Cable usage time module: obtains the commissioning time of the cable used by each effective fault node and the corresponding preset service life of the cable, and divides the commissioning time by the preset service life to obtain the cable usage time coefficient of the fault node; Cable load module: retrieves the average load current value of the cable used by each effective fault node during the period of time when it is put into use according to historical records, and divides the average load current value by the preset maximum tolerable load current value to obtain the cable load factor of the fault node; Cable quality module: The cable usage time coefficient and cable load coefficient of each effective fault node are weighted and summed to obtain the cable quality coefficient.

5. The cloud platform-based distribution network fault handling identification and decision-making system according to claim 4 is characterized in that: The self-influence module also includes: Environmental impact module: obtains the ambient temperature and humidity of the fault point at different times within a fixed time period after each effective fault node fails, and obtains the environmental impact coefficient of the effective fault node based on the ambient temperature and humidity. The specific formula is: , where is the environmental impact coefficient, Indicates the temperature at different times, Indicates the humidity at different times. Indicates the order of temperature and humidity at different times. , is a positive integer, and are the preset proportional coefficients for temperature and humidity, respectively, and and All are greater than 0; Maintenance interval module: obtains the time interval from the last maintenance of each valid fault node to the current time, obtains the current time interval, and divides the current time interval by the average maintenance time interval of the valid fault node to obtain the maintenance interval coefficient of the valid fault node.

Images