Power distribution network fault processing method and system based on big data

Abstract

The invention relates to a power distribution network fault processing method and system based on big data, and the method comprises the steps: collecting current fault information, and outputting a predicted fault point according to the current fault information and a database; dividing the fault route into two sections of sub-routes according to the position information of the predicted fault point, and determining a priority patrol route and a patrol starting point according to the environment information within a preset distance around the sub-routes; respectively dispatching patrol personnel and maintenance personnel to the patrol starting point and the predicted fault point, generating a first-aid repair recommendation route according to the position information of the predicted fault point and the position information of the maintenance personnel, and generating a patrol recommendation route according to the patrol starting point and the position information of the patrol personnel; according to the method, the actual fault point can be quickly determined, the fault processing efficiency of the power distribution network is improved, and the safety of personnel in the area near the fault line is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault processing, and in particular to a distribution network fault processing method and system based on big data. Background Art

[0002] A distribution network refers to an electric power network that receives electric energy from a transmission network or a regional power plant and distributes it locally or step by step according to voltage to various types of users through distribution facilities. The existing "binary method" is used to locate distribution network faults. It divides the faulty line or equipment into two parts for trial power transmission or detection, thereby determining the specific location of the fault. The problems existing in the existing distribution network fault handling mainly include inaccurate fault location: due to the complex structure of the distribution network, the fault point is difficult to locate quickly and accurately, resulting in the inability of emergency repair personnel to quickly reach the fault site, which prolongs the fault recovery time. Therefore, the present invention proposes a distribution network fault handling method and system based on big data. Summary of the invention

[0003] The present invention provides a distribution network fault processing method and system based on big data to solve the technical problems mentioned in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A method for handling distribution network faults based on big data, the method comprising the following steps:

[0006] S1. Collect current fault information and predict the fault point according to the current fault information and database output. The current fault information includes the fault line, fault type, fault occurrence time and fault impact range;

[0007] S2, dividing the fault route into two sub-routes according to the location information of the predicted fault point, and determining the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-routes;

[0008] S3. Dispatching inspection personnel and maintenance personnel to the inspection starting point and predicted fault point respectively, generating a recommended repair route according to the location information of the predicted fault point and the location information of the maintenance personnel, and generating a recommended inspection route according to the inspection starting point and the location information of the inspection personnel.

[0009] As a further technical solution of the present invention, the method further includes:

[0010] When the predicted fault point is not the actual fault point, it is determined based on the binary method whether there is an actual fault point in the priority patrol route. When the actual fault point exists in the priority patrol route, the fault route in the current fault information is updated, and the latest predicted fault point is output again based on the method in step S1; the priority patrol sub-route is divided into two sub-routes according to the latest predicted fault point, and the latest priority patrol sub-route is determined again based on the method in step S2 until the location of the actual fault point is determined.

[0011] As a further technical solution of the present invention, the step of collecting current fault information and outputting a predicted fault point according to the current fault information and a database includes:

[0012] Collect current fault information, including fault line, fault type, fault occurrence time, and fault impact range;

[0013] Extracting target historical fault information from a database according to the fault line in the current fault information, wherein the historical fault line in the target historical fault information is the same as the fault line in the current fault information, and the historical fault information includes a historical fault point, a historical fault line, a historical fault type, a historical fault occurrence time, and a historical fault impact range, and the database is used to store a large amount of historical fault information;

[0014] Calculating the similarity between the current fault information and the target historical fault information;

[0015] The similarities are sorted according to their magnitude, and a historical fault point in the target historical fault information with the largest similarity value is obtained as a predicted fault point.

[0016] As a further technical solution of the present invention, the steps of dividing the fault route into two sub-routes according to the location information of the predicted fault point, and determining the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-routes include:

[0017] Acquire location information of a predicted fault point, and divide the fault route into two sub-routes according to the location information of the predicted fault point, wherein the predicted fault point is located between the two sub-routes, and the two sub-routes constitute the fault route;

[0018] respectively obtaining environmental information within a preset distance around the sub-lines, wherein the environmental information includes the number of houses of each type and the type of each house;

[0019] Determine the flow heat of the two sub-routes according to the environmental information. The flow heat is calculated by multiplying the number of houses of each type by the sum of the weights of the house types. Each house type corresponds to a weight value, which is set according to actual needs. The house types include schools, hospitals, office buildings, ordinary houses, residential communities, etc. The house type with a larger flow of people has a larger corresponding weight value;

[0020] Compare the passenger flow heat of the two sub-routes and determine the sub-route with greater passenger flow heat as the priority inspection route;

[0021] Another endpoint of the priority inspection sub-route other than the predicted fault point is determined as the inspection starting point.

[0022] Another object of the present invention is to provide a distribution network fault processing system based on big data, the system comprising:

[0023] A fault point prediction module, which is used to collect current fault information and output a predicted fault point based on the current fault information and a database. The current fault information includes a fault line, a fault type, a fault occurrence time, and a fault impact range;

[0024] A patrol route determination module, used to divide the fault route into two sub-routes according to the location information of the predicted fault point, and determine a priority patrol route and a patrol starting point according to environmental information within a preset distance around the sub-routes;

[0025] The task dispatching module is used to dispatch inspection personnel and maintenance personnel to the inspection starting point and the predicted fault point respectively, generate a recommended repair route according to the location information of the predicted fault point and the location information of the maintenance personnel, and generate a recommended inspection route according to the inspection starting point and the location information of the inspection personnel.

[0026] As a further technical solution of the present invention, the system also includes a loop determination module, which includes: when the predicted fault point is not the actual fault point, based on the binary method, it is prioritized to determine whether there is an actual fault point in the priority patrol route; when the actual fault point exists in the priority patrol route, the fault route in the current fault information is updated, and the latest predicted fault point is output again based on the method in the fault point prediction module; the priority patrol sub-route is divided into two sub-routes according to the latest predicted fault point, and the latest priority patrol sub-route is determined again based on the method in the patrol route determination module until the location of the actual fault point is determined.

[0027] As a further technical solution of the present invention, the fault point prediction module includes:

[0028] A fault information collection unit, used to collect current fault information, wherein the current fault information includes the fault line, fault type, fault occurrence time, and fault impact range;

[0029] a target information matching unit, configured to extract target historical fault information from a database according to the fault line in the current fault information, wherein the historical fault line in the target historical fault information is the same as the fault line in the current fault information, and the historical fault information includes a historical fault point, a historical fault line, a historical fault type, a historical fault occurrence time, and a historical fault impact range, and the database is configured to store a large amount of historical fault information;

[0030] A similarity determination unit, used to calculate the similarity between the current fault information and the target historical fault information;

[0031] The fault point prediction unit is used to sort the target historical fault information according to the similarity value, and obtain the historical fault point with the largest similarity value as the predicted fault point.

[0032] As a further technical solution of the present invention, the inspection route determination module includes:

[0033] a route division unit, configured to obtain location information of a predicted fault point, and divide the fault route into two sub-routes according to the location information of the predicted fault point, wherein the predicted fault point is located between the two sub-routes, and the two sub-routes constitute the fault route;

[0034] An environmental information acquisition unit, used to respectively acquire environmental information within a preset distance around the sub-lines, wherein the environmental information includes the number of houses of each type and the type of each house;

[0035] A crowd flow calculation unit, used to determine crowd flow heat of the two sub-routes according to the environmental information, where the crowd flow heat is calculated by multiplying the number of houses of each type by the sum of the weights of the house types;

[0036] A patrol route determination unit is used to compare the passenger flow heat of two sub-routes and determine the sub-route with greater passenger flow heat as a priority patrol route;

[0037] The inspection starting point determination unit is used to determine another end point of the priority inspection sub-route other than the predicted fault point as the inspection starting point.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a distribution network fault processing method and system based on big data, in which the current fault information and the database output predict the fault point, so as to achieve early prediction of the fault point and improve the fault processing efficiency. On this basis, the present invention divides the fault route into two sub-routes according to the location information of the predicted fault point, and determines the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-route, wherein the priority inspection route and the inspection starting point are determined according to the corresponding pedestrian flow heat of the sub-route, so as to achieve priority processing of the area with large pedestrian flow in the fault route, and at the same time, the actual fault point can be quickly determined through the cyclic coordination of the inspection starting point and the predicted fault point, so as to improve the processing efficiency of the distribution network fault and effectively ensure the safety of the personnel in the area near the fault route. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The figure is a flowchart of a distribution network fault handling method based on big data.

[0040] Figure 2 This is a flowchart of the fault point prediction step in a distribution network fault handling method based on big data.

[0041] Figure 3 This is a flowchart of the steps for determining the inspection starting point in a distribution network fault handling method based on big data.

[0042] Figure 4 This is a structural block diagram of a distribution network fault processing system based on big data. DETAILED DESCRIPTION

[0043] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a distribution network fault processing method based on big data, and the method includes the following steps:

[0045] S1. Collect current fault information and predict the fault point according to the current fault information and database output. The current fault information includes the fault line, fault type, fault occurrence time and fault impact range. The fault line includes line name and line number, etc. The fault type includes: disconnection, short circuit, grounding, overload, etc. The database is used to store a large amount of historical fault information;

[0046] S2, dividing the fault route into two sub-routes according to the location information of the predicted fault point, and determining the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-routes;

[0047] S3. Dispatching inspection personnel and maintenance personnel to the inspection starting point and predicted fault point respectively, generating a recommended repair route according to the location information of the predicted fault point and the location information of the maintenance personnel, and generating a recommended inspection route according to the inspection starting point and the location information of the inspection personnel.

[0048] In this embodiment, the method further includes:

[0049] When the predicted fault point is not the actual fault point, it is determined based on the binary method whether there is an actual fault point in the priority patrol route. When there is an actual fault point in the priority patrol route, the fault route in the current fault information is updated, and the priority patrol route is used as the latest fault route. The latest predicted fault point is output again based on the method in step S1; the priority patrol sub-route is divided into two sub-routes according to the latest predicted fault point, and the latest priority patrol sub-route is determined again based on the method in step S2 until the location of the actual fault point is determined.

[0050] In an embodiment of the present invention, the present invention predicts the fault point through the current fault information and the database output, so as to realize the advance prediction of the fault point and improve the fault handling efficiency. On this basis, the present invention divides the fault route into two sub-routes according to the location information of the predicted fault point, and determines the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-route, wherein the priority inspection route and the inspection starting point are determined according to the corresponding pedestrian flow heat of the sub-route, so as to realize the priority processing of the area with large pedestrian flow in the fault route, and at the same time, the actual fault point can be quickly determined through the cyclic coordination of the inspection starting point and the predicted fault point, so as to improve the handling efficiency of the distribution network fault and effectively ensure the safety of the personnel in the area near the fault route.

[0051] See also Figure 2 As another preferred embodiment of the present invention, the step of collecting current fault information and outputting a predicted fault point according to the current fault information and a database comprises:

[0052] S11, collecting current fault information, wherein the current fault information includes fault line, fault type, fault occurrence time, and fault impact range;

[0053] S12, extracting target historical fault information from a database according to the fault line in the current fault information, wherein the historical fault line in the target historical fault information is the same as the fault line in the current fault information, and the historical fault information includes historical fault points, historical fault lines, historical fault types, historical fault occurrence times, and historical fault impact ranges, and the database is used to store a large amount of historical fault information;

[0054] S13, calculating the similarity between the current fault information and the target historical fault information; the specific steps include: comparing the current fault information with the target historical fault information, respectively calculating the similarity of the fault type, the similarity of the fault occurrence time and the similarity of the fault impact range, calculating the sum of the similarity of the fault type, the similarity of the fault occurrence time and the similarity of the fault impact range to obtain the final similarity, wherein the method for determining the similarity of the fault type is: when the fault types are the same, the similarity of the fault type is A, and the specific value of A is set according to actual needs. When they are different, the similarity of the fault type is determined to be 0; the method for determining the similarity of the fault occurrence time is: when the time difference is smaller, the similarity of the fault occurrence time is greater, and the time difference is positively correlated with the similarity of the fault occurrence time. Only the time difference under the 24-hour system is determined, and the time difference of the date is not determined, that is, the change of the date is not considered; the method for determining the similarity of the fault impact range is: calculated according to the overlap between the fault impact range and the historical fault impact range,

[0055] S14. Sort by similarity, and obtain a historical fault point in the target historical fault information with the largest similarity value as a predicted fault point.

[0056] See also Figure 3 As another preferred embodiment of the present invention, the step of dividing the fault route into two sub-routes according to the location information of the predicted fault point, and determining the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-routes includes:

[0057] S21, obtaining location information of a predicted fault point, and dividing the fault route into two sub-routes according to the location information of the predicted fault point, wherein the predicted fault point is located between the two sub-routes, and the two sub-routes constitute the fault route;

[0058] S22, respectively obtaining environmental information within a preset distance around the sub-lines, wherein the environmental information includes the number of houses of each type and the type of each house;

[0059] S23, determining the flow heat of the two sub-routes respectively according to the environmental information, the flow heat is calculated by multiplying the number of houses of each type by the sum of the weights of the house types, each house type corresponds to a weight value, which is set according to actual needs, and the house types include schools, hospitals, office buildings, ordinary houses, residential communities, etc., and the house type with a larger flow of people has a larger corresponding weight value;

[0060] S24, comparing the passenger flow heat of the two sub-routes, and determining the sub-route with the larger passenger flow heat as the priority inspection route;

[0061] S25: Determine another endpoint of the priority inspection sub-route other than the predicted fault point as the inspection starting point.

[0062] See also Figure 4 Another object of the present invention is to provide a distribution network fault processing system based on big data, the system comprising:

[0063] A fault point prediction module 100 is used to collect current fault information and predict the fault point according to the current fault information and database output, wherein the current fault information includes the fault line, fault type, fault occurrence time and fault impact range;

[0064] A patrol route determination module 200 is used to divide the fault route into two sub-routes according to the location information of the predicted fault point, and determine a priority patrol route and a patrol starting point according to environmental information within a preset distance around the sub-routes;

[0065] The task dispatch module 300 is used to dispatch inspection personnel and maintenance personnel to the inspection starting point and predicted fault point respectively, generate a recommended repair route based on the location information of the predicted fault point and the location information of the maintenance personnel, and generate a recommended inspection route based on the inspection starting point and the location information of the inspection personnel.

[0066] See also Figure 4 As another preferred embodiment of the present invention, the system further includes a loop determination module 400, which includes: when the predicted fault point is not the actual fault point, first determining whether there is an actual fault point in the priority patrol route based on the binary method; when there is an actual fault point in the priority patrol route, updating the fault route in the current fault information, and outputting the latest predicted fault point again based on the method in the fault point prediction module; dividing the priority patrol sub-route into two sub-routes according to the latest predicted fault point, and determining the latest priority patrol sub-route again based on the method in the patrol route determination module until the location of the actual fault point is determined.

[0067] As another preferred embodiment of the present invention, the fault point prediction module 100 includes:

[0068] A fault information collection unit, used to collect current fault information, wherein the current fault information includes the fault line, fault type, fault occurrence time, and fault impact range;

[0069] a target information matching unit, configured to extract target historical fault information from a database according to the fault line in the current fault information, wherein the historical fault line in the target historical fault information is the same as the fault line in the current fault information, and the historical fault information includes a historical fault point, a historical fault line, a historical fault type, a historical fault occurrence time, and a historical fault impact range, and the database is configured to store a large amount of historical fault information;

[0070] A similarity determination unit, used to calculate the similarity between the current fault information and the target historical fault information;

[0071] The fault point prediction unit is used to sort the target historical fault information according to the similarity value, and obtain the historical fault point with the largest similarity value as the predicted fault point.

[0072] As another preferred embodiment of the present invention, the inspection route determination module 200 includes:

[0073] a route division unit, configured to obtain location information of a predicted fault point, and divide the fault route into two sub-routes according to the location information of the predicted fault point, wherein the predicted fault point is located between the two sub-routes, and the two sub-routes constitute the fault route;

[0074] An environmental information acquisition unit, used to respectively acquire environmental information within a preset distance around the sub-lines, wherein the environmental information includes the number of houses of each type and the type of each house;

[0075] A crowd flow calculation unit is used to determine the crowd flow heat of the two sub-routes according to the environmental information. The crowd flow heat is calculated by multiplying the number of houses of each type by the sum of the weights of the house types. Each house type corresponds to a weight value, which is set according to actual needs. The house types include schools, hospitals, office buildings, ordinary houses, residential communities, etc. The house type with a larger crowd flow has a larger corresponding weight value;

[0076] A patrol route determination unit is used to compare the passenger flow heat of two sub-routes and determine the sub-route with greater passenger flow heat as a priority patrol route;

[0077] The inspection starting point determination unit is used to determine another end point of the priority inspection sub-route other than the predicted fault point as the inspection starting point.

[0078] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0079] The above are only preferred 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 distribution network fault processing method based on big data, characterized in that: The method comprises the following steps: S1. Collect current fault information and predict the fault point according to the current fault information and database output. The current fault information includes the fault line, fault type, fault occurrence time and fault impact range; S2, dividing the fault route into two sub-routes according to the location information of the predicted fault point, and determining the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-routes; S3. Dispatching inspection personnel and maintenance personnel to the inspection starting point and predicted fault point respectively, generating a recommended repair route according to the location information of the predicted fault point and the location information of the maintenance personnel, and generating a recommended inspection route according to the inspection starting point and the location information of the inspection personnel.

2. A distribution network fault processing method based on big data according to claim 1, characterized in that: The method further comprises: When the predicted fault point is not the actual fault point, it is determined based on the binary method whether there is an actual fault point in the priority patrol route. When the actual fault point exists in the priority patrol route, the fault route in the current fault information is updated, and the latest predicted fault point is output again based on the method in step S1; the priority patrol sub-route is divided into two sub-routes according to the latest predicted fault point, and the latest priority patrol sub-route is determined again based on the method in step S2 until the location of the actual fault point is determined.

3. A distribution network fault processing method based on big data according to claim 1, characterized in that: The step of collecting current fault information and outputting a predicted fault point according to the current fault information and a database comprises: Collect current fault information, including fault line, fault type, fault occurrence time, and fault impact range; Extracting target historical fault information from a database according to the fault line in the current fault information, wherein the historical fault line in the target historical fault information is the same as the fault line in the current fault information, and the historical fault information includes a historical fault point, a historical fault line, a historical fault type, a historical fault occurrence time, and a historical fault impact range, and the database is used to store a large amount of historical fault information; Calculating the similarity between the current fault information and the target historical fault information; The similarities are sorted according to their magnitude, and a historical fault point in the target historical fault information with the largest similarity value is obtained as a predicted fault point.

4. A distribution network fault processing method based on big data according to claim 1, characterized in that: The step of dividing the fault route into two sub-routes according to the location information of the predicted fault point, and determining the priority inspection route and the inspection starting point according to the environmental information within a preset distance around the sub-routes includes: Acquire location information of a predicted fault point, and divide the fault route into two sub-routes according to the location information of the predicted fault point, wherein the predicted fault point is located between the two sub-routes, and the two sub-routes constitute the fault route; respectively obtaining environmental information within a preset distance around the sub-lines, wherein the environmental information includes the number of houses of each type and the type of each house; Determine the flow heat of the two sub-routes according to the environmental information, where the flow heat is calculated by multiplying the number of houses of each type by the sum of the weights of the house types; Compare the passenger flow heat of the two sub-routes and determine the sub-route with greater passenger flow heat as the priority inspection route; Another endpoint of the priority inspection sub-route other than the predicted fault point is determined as the inspection starting point.

5. A distribution network fault processing system based on big data, characterized in that: The system comprises: A fault point prediction module, which is used to collect current fault information and output a predicted fault point based on the current fault information and a database. The current fault information includes a fault line, a fault type, a fault occurrence time, and a fault impact range; A patrol route determination module, used to divide the fault route into two sub-routes according to the location information of the predicted fault point, and determine a priority patrol route and a patrol starting point according to environmental information within a preset distance around the sub-routes; The task dispatching module is used to dispatch inspection personnel and maintenance personnel to the inspection starting point and the predicted fault point respectively, generate a recommended repair route according to the location information of the predicted fault point and the location information of the maintenance personnel, and generate a recommended inspection route according to the inspection starting point and the location information of the inspection personnel.

6. A distribution network fault processing system based on big data according to claim 5, characterized in that: The system also includes a loop determination module, which includes: when the predicted fault point is not the actual fault point, first determining whether there is an actual fault point in the priority patrol route based on the dichotomy method; when the actual fault point exists in the priority patrol route, updating the fault route in the current fault information, and outputting the latest predicted fault point again based on the method in the fault point prediction module; dividing the priority patrol sub-route into two sub-routes according to the latest predicted fault point, and determining the latest priority patrol sub-route again based on the method in the patrol route determination module until the location of the actual fault point is determined.

7. A distribution network fault processing system based on big data according to claim 5, characterized in that: The fault point prediction module includes: A fault information collection unit, used to collect current fault information, wherein the current fault information includes the fault line, fault type, fault occurrence time, and fault impact range; a target information matching unit, configured to extract target historical fault information from a database according to the fault line in the current fault information, wherein the historical fault line in the target historical fault information is the same as the fault line in the current fault information, and the historical fault information includes a historical fault point, a historical fault line, a historical fault type, a historical fault occurrence time, and a historical fault impact range, and the database is configured to store a large amount of historical fault information; A similarity determination unit, used to calculate the similarity between the current fault information and the target historical fault information; The fault point prediction unit is used to sort the target historical fault information according to the similarity value, and obtain the historical fault point with the largest similarity value as the predicted fault point.

8. A distribution network fault processing system based on big data according to claim 5, characterized in that: The inspection route determination module includes: a route division unit, configured to obtain location information of a predicted fault point, and divide the fault route into two sub-routes according to the location information of the predicted fault point, wherein the predicted fault point is located between the two sub-routes, and the two sub-routes constitute the fault route; An environmental information acquisition unit, used to respectively acquire environmental information within a preset distance around the sub-lines, wherein the environmental information includes the number of houses of each type and the type of each house; A crowd flow calculation unit, used to determine crowd flow heat of the two sub-routes according to the environmental information, where the crowd flow heat is calculated by multiplying the number of houses of each type by the sum of the weights of the house types; A patrol route determination unit is used to compare the passenger flow heat of two sub-routes and determine the sub-route with greater passenger flow heat as a priority patrol route; The inspection starting point determination unit is used to determine another end point of the priority inspection sub-route other than the predicted fault point as the inspection starting point.

Images