CN116596183A - Multi-layer distribution network information convergence analysis and collaborative filtering maintenance system and application method - Google Patents

Abstract

The invention relates to the technical field of distribution network data analysis, in particular to a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system and method, comprising the following steps: the service core control layer completes system scheduling and operation control; the resource control layer performs resource management; the data acquisition and transmission layer acquires distribution network equipment sensing data and power grid business resource data, and monitors data quality and transmission process; the anomaly analysis processing layer utilizes various algorithms to identify and screen anomaly data in the sensing data of the distribution network equipment and the power grid business resource data, performs anomaly business research and judgment according to the anomaly data, and generates an overhaul work order. The invention carries out hierarchical comprehensive calculation based on equipment infrared data of a distribution network sensing layer, transformer temperature and humidity, cable voltage and current data, distribution network lines, variable-voltage load, voltage, current, platform area information and other data, and solves the problems of inaccurate and untimely abnormal information judgment caused by single monitoring dimension of the traditional distribution network information.

Description

Multi-layer distribution network information convergence analysis and collaborative filtering maintenance system and application method

Technical Field

The invention relates to the technical field of distribution network data analysis, in particular to a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system and a use method.

Background

In recent years, the data size of the distribution network is continuously increased, and requirements on the running state and the power supply quality of the distribution network equipment are higher and higher, but the data size of the distribution network is continuously increased to bring more frequent abnormal movement, so that abnormal monitoring needs to be set. The traditional abnormality monitoring and processing mode has the operation processes of multiple acquisition and recording separation, off-line processing, overhaul, data maintenance and the like, the abnormality monitoring process is complicated to process, the requirements of data real-time performance and timeliness cannot be met, a manual work order is required to be initiated in the overhaul process, the service classification is manually carried out, the overhaul plan is declared, the working efficiency is low, the plan declaration is inaccurate, and the abnormal information processing is not timely. Meanwhile, daily work tickets and operation tickets are handled, inspection, defect recording, overhaul plan inputting and the like are all in a production environment, so that the work efficiency of monitoring and overhaul processing of distribution network abnormality is low.

Disclosure of Invention

The invention provides a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system and a use method thereof, which overcome the defects of the prior art, and can effectively solve the problems of low efficiency, weak real-time performance, manual generation of work orders and easy error existing in the existing distribution network anomaly monitoring.

One of the technical schemes of the invention is realized by the following measures: a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system comprises:

the service core control layer is used for completing system scheduling and operation control and realizing distribution network information convergence analysis and collaborative filtering maintenance;

the resource control layer is used for carrying out engine resource management, user authority control and workflow management;

the data acquisition and transmission layer acquires sensing data of distribution network equipment and power grid business resource data and monitors data quality and transmission process;

the abnormality analysis processing layer is used for identifying and screening abnormal data in the network distribution equipment sensing data and the power grid service resource data by utilizing various algorithms, performing abnormal service research and judgment according to the abnormal data and generating an overhaul work order;

and the big data analysis display layer is used for carrying out big data analysis and visual display on the data of the data acquisition and transmission layer and the abnormality analysis processing layer.

The following are further optimizations and/or improvements to the above-described inventive solution:

the data acquisition and transmission layer comprises: the data acquisition layer and the data monitoring layer;

the data acquisition layer acquires and stores distribution network equipment perception data and power grid business resource data;

And the data monitoring layer is used for carrying out quality analysis and data transmission monitoring on the data and displaying and marking the abnormality, wherein the quality analysis comprises data attribute extraction, format conversion, dimension definition and regularity verification.

The data acquisition layer comprises: the system comprises an integrated database, a distribution network equipment sensing data acquisition unit and a power grid business resource data acquisition unit;

distribution network equipment perception data acquisition unit includes: the front-end sensing module collects sensing data of distribution network equipment at the front end according to a collection instruction of the service core control layer, the sensing data are cached to the sensing data caching module, the sensing data conversion processing module extracts the sensing data of the distribution network equipment in the sensing data caching module, and the sensing data of the distribution network equipment are stored in the integrated database after being subjected to marking classification, data protocol conversion and A/D conversion;

the power grid business resource data acquisition unit comprises: the system comprises a front-end acquisition module, a resource data caching module and a resource data conversion processing module, wherein the front-end acquisition module extracts and re-calculates required power grid business resource data in a power grid business resource library, caches the calculated power grid business resource data to the resource data caching module, and the resource data conversion processing module extracts the power grid business resource data in the resource data caching module, performs label classification, data processing and data protocol conversion on the power grid business resource data and stores the power grid business resource data in an integrated database.

The data monitoring layer comprises a quality monitoring unit and a transmission monitoring unit;

the quality monitoring unit comprises a data quality monitoring analysis module, a reference database, a data dimension definition statistics module, a data detection module, a verification module and an analysis result display module, wherein the data quality monitoring analysis module extracts data acquired by the data acquisition layer and reference data in the reference database according to instructions, the data detection module extracts data attributes, the data dimension definition statistics module performs format conversion and dimension definition on the data, the verification module performs regularity verification on the data processed by the data dimension definition statistics module, and the analysis result display module displays the regularity verification result;

the transmission monitoring unit comprises a token bucket data transmission monitoring module, a double-rate three-color marking module, an information rate calculating module, a message analysis and research judging module and a token bucket marking buffer module, wherein the token bucket data transmission monitoring module controls the double-rate three-color marking module to carry out double-rate three-color marking according to instructions, the information rate calculating module calculates the information rate of data, the message analysis and research judging module compares marking information with a calculation result, and researches, judges and separates abnormal transmission data, and buffers the abnormal transmission data in the token bucket marking buffer module.

The abnormal analysis processing layer comprises an abnormal data operation layer, an abnormal service research judging layer and a work order triggering layer;

the abnormal data operation layer is used for preprocessing the sensing data of the distribution network equipment and the power grid business resource data, carrying out data fusion after preprocessing, and identifying and screening the abnormal data by utilizing a plurality of algorithms after fusion;

an abnormal business research and judgment layer for carrying out abnormal business research and judgment according to the abnormal data and marking the abnormal business corresponding to the abnormal data;

and the work order triggering layer determines an abnormal service maintenance scheme according to the marked abnormal service, and generates and pushes a maintenance work order after verification.

The abnormal data operation layer includes:

the sensing data preprocessing module and the power grid business resource data preprocessing module respectively clean sensing data of the distribution network equipment and power grid business resource data, the data deviation rectifying operation module performs secondary data cleaning and data structuring verification, the processed data is transmitted to the data fusion module through the BUS BUS to perform data fusion, the data prediction module performs definition and conversion on the data protocol of the fused data, the data is pushed to the secondary data analysis module to perform data matrix arrangement after conversion, the data logic association operation module performs matrix data operation, the data marking module performs business data marking, the data is pushed to the data attribute target identification module to perform data identification and screening after fusion after completion, and the data is pushed to the fusion database;

The data analysis logic control unit extracts the fusion data, and the OCSVM abnormal data detection control module and the Kmeans abnormal data detection control module are used for respectively analyzing the fusion data;

the data output by the OCSVM abnormal data detection control module is subjected to density separation by a density separation module through Gaussian distribution statistics and data distribution variance calculation, data set classification is performed through data high-dimensional detection after the data density separation is completed, abnormal data is scattered, the scattered abnormal data is marked through an abnormal data marking module, and the abnormal data is pushed to a multidimensional abnormal data marking module;

pushing data output by the Kmeans abnormal data detection control module to a clustering operation module for clustering separation, completing convex set intersection operation through a convex data set logic operation module to form a set of n-dimensional semi-positive definite matrixes, converging the convex data set through a KMeans convergence algorithm, sorting out a converged data set, and pushing the converged data set to a multidimensional abnormal data marking module;

the multidimensional abnormal data marking module performs intersection operation to form a multidimensional abnormal data set, and the multidimensional abnormal data set is pushed to the multidimensional abnormal data logic judging module to perform data format and protocol operation and is pushed to the service core control layer in the form of a message.

The abnormal service research judging layer is characterized in that the abnormal data triggering module calls the sharp abnormal service shunting module to separate abnormal data logic attributes, pushes the abnormal data logic attributes to the abnormal service analysis operation module to conduct service logic classification and definition, the thread operation module conducts service classification circulation, flows to the fault report repair plan logic control module, the active rush repair logic control module and the plan power failure logic control module according to different service logic attributes, calls the abnormal service mark display module to complete marks corresponding to the abnormal service attributes, and returns to the service core control layer;

or/and the combination of the two,

the work order logic control unit calls a corresponding fault report work order control module, an active repair work order control module and a plan stop work order control module according to the work order label, pushes work order data and the work order label to the work order data marking unit to carry out logic linkage, the work order data checking module checks the work order data and the work order label with the abnormal data, pushes the work order data and the work order label to the work order data checking cache after the check is successful, and the work order data checking logic judging module carries out logic checking operation on the service label and the work order label to generate an overhaul work order after the completion and returns to the service core control layer.

The resource control layer comprises a Calibrated boosted trees cloud computing module, a logic operation module, a virtualized resource management module, a user authority module and a workflow management module, wherein the Calibrated boosted trees cloud computing module calls the logic operation module to respectively control the virtualized resource management module, the user authority module and the workflow management module to respectively perform engine resource management, user authority control and workflow management;

or/and the combination of the two,

the data preprocessing module pushes marked abnormal service attributes and data to the data preprocessing module for preprocessing, the data preprocessing module pushes the marked abnormal service attributes and the marked data to the metadata management module and the data image conversion module for data definition and data graph conversion respectively, the data management module pushes the data to the BI interaction module after finishing the data analysis from the FFT data operation module and the EM Training data operation module, the data image conversion module pushes the image data to the data visual analysis logic control unit for logically associating the image data with the data attributes, the data image conversion module pushes the image data to the BI interaction module after finishing the data interaction module, the BI interaction module carries out structured and unstructured data application classification and marking, and pushes the data to the visual display control module after finishing the data graph display with the large data through the perception layer data visual model and the power grid service resource data visual model;

Or/and the combination of the two,

and the service core control layer is characterized in that the service center master control unit completes data bidirectional transmission and instruction control through the FCFS scheduling unit and stores data into the center database, and the FCFS scheduling unit calls the logic control units corresponding to all the layers to realize instruction transmission, operation control and data transmission between all the layers and the service core control layer.

The second technical scheme of the invention is realized by the following measures: a multi-layer distribution network information convergence analysis and collaborative filtering maintenance method comprises the following steps:

the service core control layer controls the resource control layer, the data acquisition and transmission layer, the anomaly analysis processing layer and the big data analysis display layer to initialize;

responding to the initialization success instruction, the service core control layer calls the resource control layer to manage engine resources, control user authority and manage workflow;

responding to normal operation of the resource control layer, calling a data acquisition transmission layer by the service core control layer, acquiring network equipment sensing data and power grid service resource data, and monitoring data quality and transmission process;

the service core control layer calls an anomaly analysis processing layer to identify and screen anomaly data in the distribution network equipment sensing data and the power grid service resource data by utilizing various algorithms, and performs anomaly service research and judgment according to the anomaly data;

The service core control layer calls the big data analysis display layer to generate an abnormal service overhaul scheme corresponding to the abnormal service;

the service core control layer calls an abnormal analysis processing layer and generates an overhaul work order based on an abnormal service overhaul scheme;

the service core control layer calls the big data analysis display layer to display the data visually.

The beneficial effects of the invention include:

the invention carries out hierarchical comprehensive calculation based on equipment infrared data of a distribution network sensing layer, transformer temperature and humidity, cable voltage and current data, distribution network lines, variable-voltage load, voltage, current, platform area information and other data, and solves the problems of inaccurate and untimely abnormal information judgment caused by single monitoring dimension of the traditional distribution network information. And the service core control layer, the resource control layer, the data acquisition and transmission layer, the anomaly analysis processing layer and the big data analysis display layer are utilized to realize data acquisition, processing, research and judgment, work order and display all-round automatic processing, so that the distribution network information convergence analysis and collaborative filtering maintenance are realized efficiently and rapidly, and compared with the existing single anomaly analysis, anomaly service non-research and judgment and maintenance worker single man-initiated mode, the efficiency and accuracy of anomaly analysis and work order generation are effectively improved.

Compared with the traditional business that the data acquisition and analysis process is single, island exists among the data, and the data with different formats cannot be analyzed in a linkage way, the invention carries out technical fusion on the sensing layer data and the business data of the power grid information system through the data fusion process.

In the invention, in the research and judgment of the abnormal service, the abnormal data and the service scene are automatically associated based on the abnormal service through the share algorithm to form the research and judgment of the abnormal service, thereby solving the problems of inaccurate information and positioning error of manually defined abnormal service in the traditional service.

According to the invention, the data monitoring layer is used for monitoring the data acquisition process, the data quality and the data transmission condition in the data operation and analysis process in real time and in the whole process, and the accuracy, the integrity and the timeliness of the data are ensured from the source end.

According to the invention, the dispatching of the instruction and the data is completed through the FCFS dispatching algorithm, so that the independent operability of the whole engine data and transmission is improved, and the whole working efficiency is improved.

When the work order is generated, the accuracy of the work order information can be checked, the problem that the overhaul operation cannot be executed or the delay of the overhaul operation caused by the work order information error in the traditional overhaul service is reissued is effectively avoided, and the loss of further expansion of accidents caused by untimely overhaul is avoided.

Drawings

Fig. 1 is a schematic diagram of the system structure of the present invention.

Fig. 2 is a schematic diagram of a service core control layer according to the present invention.

Fig. 3 is a schematic structural diagram of a resource control layer in the present invention.

Fig. 4 is a schematic structural diagram of a data acquisition and transmission layer according to the present invention.

Fig. 5 is a schematic structural diagram of a data acquisition layer in the present invention.

Fig. 6 is a schematic structural diagram of a data monitoring layer in the present invention.

FIG. 7 is a schematic diagram of an anomaly analysis processing layer according to the present invention.

FIG. 8 is a schematic diagram of the structure of the abnormal data operation layer according to the present invention.

Fig. 9 is a schematic structural diagram of an abnormal service research layer in the present invention.

FIG. 10 is a schematic diagram of the structure of a work order trigger layer according to the present invention.

FIG. 11 is a schematic diagram of the structure of the big data analysis display layer in the present invention.

Fig. 12 is a process flow of the present invention.

Detailed Description

The present invention is not limited by the following examples, and specific embodiments can be determined according to the technical scheme and practical situations of the present invention.

The invention is further described below with reference to examples and figures:

example 1: as shown in fig. 1, the embodiment of the invention discloses a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system, which comprises:

And (I) a service core control layer is used for completing system scheduling and operation control and realizing distribution network information convergence analysis and collaborative filtering maintenance.

Specifically, as shown in fig. 2, a service center master control unit in a service core control layer completes data bidirectional transmission and instruction control through an FCFS scheduling unit, and stores data into a center database, and the FCFS scheduling unit calls a logic control unit corresponding to each layer to realize instruction transmission, operation control and data transmission between each layer and the service core control layer.

It should be noted that, the logic control unit corresponding to each layer of the service core control layer includes:

the FCFS scheduling unit is used for calling the resource control unit according to the instruction of the service center control unit to complete the internal operation control of the resource control layer;

the FCFS scheduling unit calls the big data analysis control unit according to the instruction of the service center control unit to complete the internal operation of the big data analysis display layer;

the FCFS dispatching unit calls the data acquisition logic control unit, the XPDL data interaction unit and the data monitoring logic control unit according to the instruction of the service center control unit to complete the internal operation control of the data acquisition transmission layer;

The FCFS dispatching unit calls the data operation logic control unit, the service research judgment logic control unit and the work order logic control unit according to the instruction of the service center control unit to complete the internal operation control of the abnormality analysis processing layer.

And (II) a resource control layer for performing engine resource management, user authority control and workflow management.

Specifically, as shown in fig. 3, the resource control layer includes a Calibrated boosted trees cloud computing module, a logic operation module, a virtualized resource management module, a user authority module, and a workflow management module, where the Calibrated boosted trees cloud computing module invokes the logic operation module to respectively control the virtualized resource management module, the user authority module, and the workflow management module, and respectively perform engine resource management, user authority control, and workflow management.

And thirdly, a data acquisition and transmission layer is used for acquiring sensing data of distribution network equipment and power grid business resource data and monitoring data quality and transmission process.

Specifically, as shown in fig. 4, the data acquisition and transmission layer comprises a data acquisition layer and a data monitoring layer;

(1) And the data acquisition layer acquires and stores the network distribution equipment perception data and the power grid business resource data.

As shown in fig. 5, the data acquisition layer includes: the system comprises an integrated database, a distribution network equipment sensing data acquisition unit and a power grid business resource data acquisition unit;

distribution network equipment perception data acquisition unit includes: the front-end sensing module acquires sensing data (data is expressed in a serial code form) of distribution network equipment at the front end according to an acquisition instruction of a service core control layer, pushes the acquired serial code into the sensing data caching module for caching, and the sensing data conversion processing module comprises a sensing data marking module, a sensing data marking module and a sensing acquisition logic operation module; it should be further noted that the front-end sensing module may include an infrared data acquisition module of the distribution network device, a temperature and humidity data acquisition module of the transformer, a voltage data acquisition module of the cable, and a current data acquisition module of the cable, where the collected sensing data of the distribution network device includes infrared data of the distribution network device, temperature and humidity data of the transformer, voltage data of the cable, and current data of the cable, where the number of sensing data buffer modules is the same as and one-to-one corresponding to the acquisition modules in the front-end sensing module.

The power grid business resource data acquisition unit comprises: the system comprises a front-end acquisition module, a resource data caching module and a resource data conversion processing module, wherein the front-end acquisition module comprises a load rate logic operation module, an overload logic operation module, a low-voltage logic operation module, a three-phase unbalanced logic operation module and an openable capacity logic operation module, and the resource data caching module corresponds to the load rate logic operation module; the overload logic operation module extracts data such as line load, equipment type, station area and the like, calculates an overload value according to logic algorithms of different dimensions, and pushes a result to an overload data cache; the low voltage logic operation module calculates the low voltage according to logic algorithms of different dimensions such as line voltage, bus balance, load, platform area information and the like, and pushes the result to a low voltage data cache; calculating three-phase voltages by a three-phase unbalanced logic operation module according to logic algorithms of different dimensions, such as phase voltages, currents, loads, platform area information and the like, and pushing results to a three-phase unbalanced voltage data cache; calculating openable capacity data by an openable capacity logic operation module according to logic algorithms of different dimensions, such as line rated capacity, load coefficient, power load, station area information and the like, and pushing a result to an openable capacity data cache; the method comprises the steps of pushing the power grid business data to a resource data conversion processing unit after resource extraction is completed, wherein the resource data conversion processing module comprises a power grid business resource data marking module, a power grid business resource data protocol conversion module and a power grid business resource data logic operation module, marking and classifying corresponding business data are carried out by the power grid business resource data marking module, pushing the power grid business resource data protocol conversion module after the power grid business data marking module is completed, pushing the power grid business resource data protocol conversion module to the power grid business resource data logic operation module after data protocol conversion is completed, carrying out load rate, overload, low voltage, three-phase imbalance and openable capacity value operation, and pushing the power grid business resource data to an integrated database after the power grid business resource data protocol conversion module is completed.

(2) And the data monitoring layer is used for carrying out quality analysis and data transmission monitoring on the data and displaying and marking the abnormality, wherein the quality analysis comprises data attribute extraction, format conversion, dimension definition and regularity verification.

Specifically, as shown in fig. 6, the data monitoring layer includes a quality monitoring unit and a transmission monitoring unit;

the quality monitoring unit comprises a data quality monitoring analysis module, a reference database, a data dimension definition statistics module, a data detection module, a verification module and an analysis result display module, wherein the data quality monitoring analysis module extracts data acquired by the data acquisition layer and reference data in the reference database according to instructions, the data detection module extracts data attributes including non-empty quantity, non-repeated value quantity, maximum value, minimum value, top5 value and the like, the data dimension definition statistics module performs format conversion and dimension definition on the data, the verification module performs regularity verification on the data processed by the data dimension definition statistics module, the integrity, correctness, current and consistency of the data are included, and the analysis result display module displays the regularity verification result.

Here, the quality monitoring unit may monitor the abnormal data identified by the abnormal analysis processing layer, and the monitoring method is the same.

The transmission monitoring unit comprises a token bucket data transmission monitoring module, a double-rate three-color marking module, an information rate calculating module, a message analysis and research judging module and a token bucket marking buffer module, wherein the token bucket data transmission monitoring module controls the double-rate three-color marking module to carry out double-rate three-color marking according to instructions, the information rate calculating module calculates the information rate of data, the message analysis and research judging module compares marking information with a calculation result, and researches, judges and separates abnormal transmission data, and buffers the abnormal transmission data in the token bucket marking buffer module.

The information rate calculation module includes a CIR calculation module, a CBS calculation module, a PIR calculation module, and a PBS calculation module.

And (IV) an anomaly analysis processing layer, which utilizes a plurality of algorithms to identify and screen anomaly data in the sensing data of the distribution network equipment and the power grid business resource data, performs anomaly business research and judgment according to the anomaly data, and generates an overhaul work order.

Specifically, as shown in fig. 7, the exception analysis processing layer includes an exception data operation layer, an exception service research judging layer and a work-sheet triggering layer;

the abnormal data operation layer is used for preprocessing the sensing data of the distribution network equipment and the power grid business resource data, carrying out data fusion after preprocessing, and identifying and screening the abnormal data by utilizing a plurality of algorithms after fusion;

An abnormal business research and judgment layer for carrying out abnormal business research and judgment according to the abnormal data and marking the abnormal business corresponding to the abnormal data;

and the work order triggering layer determines an abnormal service maintenance scheme according to the marked abnormal service, and generates and pushes a maintenance work order after verification.

As shown in fig. 8, the abnormal data operation layer includes:

the sensing data preprocessing module and the power grid business resource data preprocessing module respectively perform data cleaning on sensing data of the distribution network equipment and power grid business resource data (the data cleaning uses the existing conventional data preprocessing methods, such as a missing value, an outlier, inconsistent preprocessing methods and the like), the data correction operation module performs secondary data cleaning and data structuring verification, the processed data is transmitted to the data fusion module through the BUS BUS for data fusion, the data prediction module defines and converts a data protocol of the fused data, the data is pushed to the secondary data analysis module for data matrix arrangement after conversion after completion, the data logic association operation module performs matrix data operation, the data marking module performs business data marking, and the data is pushed to the data attribute target recognition module for fused data recognition and screening after completion and then is pushed to the fusion database;

The data analysis logic control unit extracts the fusion data, and the OCSVM abnormal data detection control module and the Kmeans abnormal data detection control module are used for respectively analyzing the fusion data;

specifically, data output by the OCSVM abnormal data detection control module are subjected to density separation through a density separation module by means of Gaussian distribution statistics and data distribution variance calculation, data set classification is carried out through data high-dimensional detection after the data density separation is completed, abnormal vectors are calculated through different parameter adjustment of a base detector based on sample feature sampling, normalized value conversion is formed, abnormal data are scattered, and the scattered abnormal data are marked through an abnormal data marking module and are pushed to a multidimensional abnormal data marking module; pushing data output by the Kmeans abnormal data detection control module to a clustering operation module for clustering separation, completing convex set intersection operation through a convex data set logic operation module to form a set of n-dimensional semi-positive definite matrixes, converging the convex data set through a KMeans convergence algorithm, sorting out a converged data set, and pushing the converged data set to a multidimensional abnormal data marking module;

the multidimensional abnormal data marking module performs intersection operation to form a multidimensional abnormal data set, and the multidimensional abnormal data set is pushed to the multidimensional abnormal data logic judging module to perform data format and protocol operation and is pushed to the data operation logic control module of the service core control layer in the form of a message.

As shown in fig. 9, the abnormal service research and judgment layer includes an abnormal data triggering module, a sharp abnormal service distribution module, an abnormal service analysis operation module, a service classification and definition module, a service classification circulation module, a fault report and repair plan logic control module, an active rush repair logic control module and a plan power failure logic control module, a related service logic calculation module, an abnormal service mark display module, a service research and judgment logic control unit, a service core control layer and a service core control layer, wherein the abnormal service analysis layer includes an abnormal data triggering module, a sharp abnormal service distribution module, a service logic classification and definition module, a service classification circulation module, a fault report and repair plan logic control module, an active rush repair logic control module and a plan power failure logic control module, and an abnormal service mark display module.

The work order layer includes a work order triggering module for calling a Jbpm work order control module, pre-generating a business work order label according to an abnormal business overhaul scheme, calling a corresponding fault report work order control module, an active rush-repair work order control module and a planned stop work order control module according to the work order label to examine corresponding work order data, pushing the work order data and the work order label to a work order data marking module for logic linkage, checking the abnormal data extracted by the work order data and work order label and a service center main control unit by the work order data checking module, pushing the work order data and the work order label to a work order data checking cache after the check is successful, performing logic check operation on the business label and the work order label by the work order data checking logic judging module, generating an overhaul work order after the completion, and returning to the work order logic control unit in the service core control layer.

And fifthly, carrying out big data analysis and visual display on the data of the data acquisition and transmission layer and the abnormality analysis and processing layer.

Specifically, as shown in fig. 11, the big data analysis and display layer includes a data preprocessing module, a metadata management module, a data image conversion module, a data definition and data graph conversion module, a data image conversion module, a data interaction module, a data image conversion module, a data visualization analysis logic control module, a BI interaction module, a visual display control module, a perception layer data visualization model and a power grid service resource data visualization model.

The invention discloses a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system, which is used for carrying out hierarchical comprehensive calculation based on equipment infrared data of a distribution network sensing layer, transformer temperature and humidity, cable voltage and current data, distribution network line, variable-voltage load, voltage, current, platform area information and other data, and solves the problems of inaccurate and untimely abnormal information judgment caused by single monitoring dimension of traditional distribution network information. Furthermore, the invention utilizes the service core control layer, the resource control layer, the data acquisition and transmission layer, the anomaly analysis processing layer and the big data analysis display layer to realize the data acquisition, processing, studying and judging, worksheet and display all-round automatic processing, efficiently and quickly realize the distribution network information convergence analysis and collaborative filtering maintenance, and effectively improves the efficiency and the accuracy of anomaly analysis and worksheet generation compared with the existing single anomaly analysis, no studying and judging of anomaly service and single operator initiation mode of maintenance workers.

Example 2: as shown in fig. 12, the embodiment of the invention discloses a method for using a multi-layer distribution network information convergence analysis and collaborative filtering maintenance system, which comprises the following steps:

step S101, a service core control layer controls a resource control layer, a data acquisition transmission layer, an anomaly analysis processing layer and a big data analysis display layer to initialize.

Specifically, the service center general control unit sends an instruction to the FCFS scheduling unit, and the FCFS scheduling unit sends an initialization instruction to the resource control layer, the data acquisition and transmission layer, the exception analysis processing layer and the big data analysis display layer, and the resource control layer, the data acquisition and transmission layer, the exception analysis processing layer and the big data analysis display layer execute the initialization instruction.

Step S102, in response to the initialization success instruction, the service core control layer calls the resource control layer to perform engine resource management, user authority control and workflow management.

Specifically, the service center general control unit may determine whether the initialization is completed according to the feedback information of the initialization execution result, and in response to the completion of the initialization, reinitialize the initialization, and in response to the completion, the service center control unit invokes the resource control unit through the FCFS scheduling unit to control Calibrated boosted trees cloud computing module, logic operation module, virtualized resource management module, user authority module, and workflow management module to perform virtualized resource management, user authority management, and workflow management.

Step S103, responding to the normal operation of the resource control layer, the service core control layer calls the data acquisition transmission layer, acquires the sensing data of the distribution network equipment and the power grid service resource data, and monitors the data quality and the transmission process.

Specifically, the service center general control unit can judge whether resource management is normal according to feedback information, and in response to the judgment, the resource inspection is resumed, and in response to the judgment, the service center control unit invokes the data acquisition logic control unit through the FCFS scheduling unit to control the data acquisition transmission layer to perform data acquisition and data monitoring.

The specific data acquisition is as follows:

step S311, the data acquisition logic unit sends an instruction through the XPDL data interaction module;

step S312, the distribution network equipment sensing data acquired by the distribution network equipment infrared data acquisition module, the transformer temperature and humidity data acquisition module, the cable voltage data acquisition module and the cable current data acquisition module comprise distribution network equipment infrared data, transformer temperature and humidity data, cable voltage data and cable current data;

step S313, the acquired sensing data of the distribution network equipment is pushed to a sensing data caching module for caching, a sensing data marking module marks and sorts the sensing data of the distribution network equipment, the sensing data marking module pushes the sensing data to a sensing data protocol conversion module after finishing, the acquired analog data is converted into digital data, the digital data is pushed to a sensing acquisition logic operation unit for A/D conversion after finishing, and the digital data is stored in an integrated database;

Step S314, the load factor logic operation module, the overload logic operation module, the low-voltage logic operation module, the three-phase unbalanced logic operation module and the openable capacity logic operation module extract the load factor, the overload factor, the low-voltage, the three-phase unbalanced data and the openable capacity related data from the power grid service resource library through the API interface module;

step S315, the power grid business resource data marking module marks and classifies corresponding business data, the business data is pushed to the power grid business resource data protocol conversion module after finishing data protocol conversion, the business data is pushed to the power grid business resource data logic operation unit to carry out load rate, overload, low voltage, three-phase imbalance and openable capacity value operation, and the business data is pushed to the integrated database after finishing data protocol conversion.

Specific data monitoring is as follows:

step S321, a service center control unit calls a data monitoring logic control unit through an FCFS scheduling unit to monitor the overall data quality and the transmission process;

step S322, the data quality monitoring analysis module extracts data acquired by the data acquisition layer and reference data in a reference database according to the instruction, the data detection module extracts data attributes including the number of non-empty, the number of non-repeated values, the maximum value, the minimum value, the number of top5 values and the like, the data dimension definition statistics module performs format conversion and dimension definition on the data, the verification module performs regularity verification on the data processed by the data dimension definition statistics module, the integrity, the correctness, the current property and the consistency of the data are included, and the analysis result display module displays the regularity verification result;

Step S323, the token bucket data transmission monitoring module controls the dual-rate three-color marking module to carry out dual-rate three-color marking according to the instruction, the information rate calculation module calculates the information rate of the data, the message analysis and judgment module compares the marking information with the calculation result, judges and separates abnormal transmission data, and caches the abnormal transmission data in the token bucket marking cache module;

step S324, judging whether the data transmission monitoring is abnormal, if so, performing the cyclic monitoring, and if so, pushing the network distribution equipment perception data and the power grid business resource data to the service center general control unit through the XPDL data interaction module.

Step S104, the service core control layer calls an anomaly analysis processing layer to identify and screen anomaly data in the network distribution equipment sensing data and the power grid service resource data by utilizing various algorithms, and performs anomaly service research and judgment according to the anomaly data.

Specifically, the service center general control unit pushes data to the data logic operation unit, controls the abnormal data operation layer to identify and screen abnormal data, namely, performs data operation, prediction, secondary analysis, logic association, marking and attribute identification, completes fusion of the sensing layer and service resource data, performs two ways of abnormal monitoring on the fused data by the data analysis logic control unit, performs OCSVM abnormal monitoring, performs data density separation and high-dimensional detection, marks the abnormal data, performs Kmeans abnormal monitoring, performs clustering operation and convex data set operation, and forms a bracelet data set. And carrying out multidimensional data intersection logic operation on the two abnormal detection results, carrying out abnormal marking, and carrying out final logic judgment on the abnormal data.

Specifically, the service center master control unit invokes the service research and judgment logic control unit by using the FCFS scheduling unit, controls the abnormal service research and judgment layer to classify the abnormal data service, classifies the abnormal service scene by using the sharp abnormal shunting module, carries out instruction control on the scene service research and judgment by using the thread operation unit, correspondingly carries out fault repair planning, active repair and planned power failure, completes the abnormal service scene research and judgment, marks and displays the abnormal data and the abnormal service, returns the result to the service research and judgment logic control unit, and returns the result to the service center master control unit by using the service center master control unit.

Step S105, the service core control layer calls the big data analysis display layer to generate an abnormal service maintenance scheme corresponding to the abnormal service.

Specifically, the data management module in the big data analysis display layer can pre-store abnormal service overhaul schemes corresponding to various abnormal services, and can directly match and search the corresponding abnormal service overhaul schemes after the abnormal services are received.

And S106, the service core control layer calls an exception analysis processing layer and generates an overhaul work order based on an exception service overhaul scheme.

Specifically, the service center control layer utilizes the FCFS scheduling unit to call the work order logic control unit to control the work order triggering layer, namely, the work order logic control unit controls the work order triggering module, based on an abnormal service maintenance scheme, the corresponding fault report maintenance, active rush-repair and planned stop work order information generation are completed through the jbpm work order control module, data verification is carried out according to abnormal data and abnormal service, whether the work order is abnormal or not is judged, if so, the last step is carried out, and if so, the service abnormal maintenance work order is generated.

Step S107, the service core control layer calls the big data analysis display layer to display the data visually.

Specifically, the service center control layer invokes the big data analysis control unit by using the FCFS scheduling unit, the service center master control unit pushes data to the big data analysis control module for data display, namely, the data preprocessing module pushes marked abnormal service attributes and data to the data preprocessing module for preprocessing, the data preprocessing module pushes the marked abnormal service attributes and the marked data to the metadata management module and the data image conversion module for data definition and data graph conversion respectively after the marked abnormal service attributes and the marked data are completed, the data management module pushes the data to the BI interaction module after the data analysis is completed, the data image conversion module pushes the image data to the data visualization analysis logic control unit for logically associating the image data with the data attributes, the BI interaction module for structured and unstructured data application classification and marking, the data preprocessing module pushes the marked abnormal service attributes and the marked data to the visual display control module after the marked abnormal service attributes and the data, and the data and the big data graph display are performed through the perception layer data visualization model and the power grid service resource data visualization model.

Example 3: the embodiment of the application discloses electronic equipment, which comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to realize the use method of the multi-layer distribution network information convergence analysis and collaborative filtering overhaul system.

The processor may be a Central Processing Unit (CPU), a general purpose processor, a digital signal processor DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware components, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Combinations of computing functions may also be implemented, for example, as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, or the like. The memory may include, but is not limited to: various media capable of storing computer programs, such as a USB flash disk, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

The technical characteristics form the optimal embodiment of the invention, have stronger adaptability and optimal implementation effect, and can increase or decrease unnecessary technical characteristics according to actual needs so as to meet the requirements of different situations.

Claims (10)

1. The utility model provides a multilayer distribution network information convergence analysis and collaborative filtering maintenance system which characterized in that includes:

the service core control layer is used for completing system scheduling and operation control and realizing distribution network information convergence analysis and collaborative filtering maintenance;

the resource control layer is used for carrying out engine resource management, user authority control and workflow management;

the data acquisition and transmission layer acquires sensing data of distribution network equipment and power grid business resource data and monitors data quality and transmission process;

the abnormality analysis processing layer is used for identifying and screening abnormal data in the network distribution equipment sensing data and the power grid service resource data by utilizing various algorithms, performing abnormal service research and judgment according to the abnormal data and generating an overhaul work order;

and the big data analysis display layer is used for carrying out big data analysis and visual display on the data of the data acquisition and transmission layer and the abnormality analysis processing layer.

2. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to claim 1, wherein the data acquisition and transmission layer comprises: the data acquisition layer and the data monitoring layer;

The data acquisition layer acquires and stores distribution network equipment perception data and power grid business resource data;

and the data monitoring layer is used for carrying out quality analysis and data transmission monitoring on the data and displaying and marking the abnormality, wherein the quality analysis comprises data attribute extraction, format conversion, dimension definition and regularity verification.

3. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to claim 2, wherein the data acquisition layer comprises: the system comprises an integrated database, a distribution network equipment sensing data acquisition unit and a power grid business resource data acquisition unit;

distribution network equipment perception data acquisition unit includes: the front-end sensing module collects sensing data of distribution network equipment at the front end according to a collection instruction of the service core control layer, the sensing data are cached to the sensing data caching module, the sensing data conversion processing module extracts the sensing data of the distribution network equipment in the sensing data caching module, and the sensing data of the distribution network equipment are stored in the integrated database after being subjected to marking classification, data protocol conversion and A/D conversion;

The power grid business resource data acquisition unit comprises: the system comprises a front-end acquisition module, a resource data caching module and a resource data conversion processing module, wherein the front-end acquisition module extracts and re-calculates required power grid business resource data in a power grid business resource library, caches the calculated power grid business resource data to the resource data caching module, and the resource data conversion processing module extracts the power grid business resource data in the resource data caching module, performs label classification, data processing and data protocol conversion on the power grid business resource data and stores the power grid business resource data in an integrated database.

4. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to claim 2 or 3, wherein the data monitoring layer comprises a quality monitoring unit and a transmission monitoring unit;

the quality monitoring unit comprises a data quality monitoring analysis module, a reference database, a data dimension definition statistics module, a data detection module, a verification module and an analysis result display module, wherein the data quality monitoring analysis module extracts data acquired by the data acquisition layer and reference data in the reference database according to instructions, the data detection module extracts data attributes, the data dimension definition statistics module performs format conversion and dimension definition on the data, the verification module performs regularity verification on the data processed by the data dimension definition statistics module, and the analysis result display module displays the regularity verification result;

The transmission monitoring unit comprises a token bucket data transmission monitoring module, a double-rate three-color marking module, an information rate calculating module, a message analysis and research judging module and a token bucket marking buffer module, wherein the token bucket data transmission monitoring module controls the double-rate three-color marking module to carry out double-rate three-color marking according to instructions, the information rate calculating module calculates the information rate of data, the message analysis and research judging module compares marking information with a calculation result, and researches, judges and separates abnormal transmission data, and buffers the abnormal transmission data in the token bucket marking buffer module.

5. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to any one of claims 1-4, wherein the anomaly analysis processing layer comprises an anomaly data operation layer, an anomaly service research and judgment layer and a work order triggering layer;

the abnormal data operation layer is used for preprocessing the sensing data of the distribution network equipment and the power grid business resource data, carrying out data fusion after preprocessing, and identifying and screening the abnormal data by utilizing a plurality of algorithms after fusion;

an abnormal business research and judgment layer for carrying out abnormal business research and judgment according to the abnormal data and marking the abnormal business corresponding to the abnormal data;

And the work order triggering layer determines an abnormal service maintenance scheme according to the marked abnormal service, and generates and pushes a maintenance work order after verification.

6. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to claim 5, wherein the anomaly data operation layer comprises:

the sensing data preprocessing module and the power grid business resource data preprocessing module respectively clean sensing data of the distribution network equipment and power grid business resource data, the data deviation rectifying operation module performs secondary data cleaning and data structuring verification, the processed data is transmitted to the data fusion module through the BUS BUS to perform data fusion, the data prediction module performs definition and conversion on the data protocol of the fused data, the data is pushed to the secondary data analysis module to perform data matrix arrangement after conversion, the data logic association operation module performs matrix data operation, the data marking module performs business data marking, the data is pushed to the data attribute target identification module to perform data identification and screening after fusion after completion, and the data is pushed to the fusion database;

the data analysis logic control unit extracts the fusion data, and the OCSVM abnormal data detection control module and the Kmeans abnormal data detection control module are used for respectively analyzing the fusion data;

The data output by the OCSVM abnormal data detection control module is subjected to density separation by a density separation module through Gaussian distribution statistics and data distribution variance calculation, data set classification is performed through data high-dimensional detection after the data density separation is completed, abnormal data is scattered, the scattered abnormal data is marked through an abnormal data marking module, and the abnormal data is pushed to a multidimensional abnormal data marking module;

pushing data output by the Kmeans abnormal data detection control module to a clustering operation module for clustering separation, completing convex set intersection operation through a convex data set logic operation module to form a set of n-dimensional semi-positive definite matrixes, converging the convex data set through a KMeans convergence algorithm, sorting out a converged data set, and pushing the converged data set to a multidimensional abnormal data marking module;

the multidimensional abnormal data marking module performs intersection operation to form a multidimensional abnormal data set, and the multidimensional abnormal data set is pushed to the multidimensional abnormal data logic judging module to perform data format and protocol operation and is pushed to the service core control layer in the form of a message.

7. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to claim 5, wherein,

the abnormal service research judging layer is characterized in that the abnormal data triggering module calls the sharp abnormal service shunting module to separate abnormal data logic attributes, pushes the abnormal data logic attributes to the abnormal service analysis operation module to conduct service logic classification and definition, the thread operation module conducts service classification circulation, flows to the fault report repair plan logic control module, the active rush repair logic control module and the plan power failure logic control module according to different service logic attributes, calls the abnormal service mark display module to complete marks corresponding to the abnormal service attributes, and returns to the service core control layer;

Or/and the combination of the two,

the work order logic control unit calls a corresponding fault report work order control module, an active repair work order control module and a plan stop work order control module according to the work order label, pushes work order data and the work order label to the work order data marking unit to carry out logic linkage, the work order data checking module checks the work order data and the work order label with the abnormal data, pushes the work order data and the work order label to the work order data checking cache after the check is successful, and the work order data checking logic judging module carries out logic checking operation on the service label and the work order label to generate an overhaul work order after the completion and returns to the service core control layer.

8. The multi-layer distribution network information convergence analysis and collaborative filtering maintenance system according to any one of claims 1-7, wherein,

the resource control layer comprises a Calibrated boosted trees cloud computing module, a logic operation module, a virtualized resource management module, a user authority module and a workflow management module, wherein the Calibrated boosted trees cloud computing module calls the logic operation module to respectively control the virtualized resource management module, the user authority module and the workflow management module to respectively perform engine resource management, user authority control and workflow management;

Or/and the combination of the two,

the data preprocessing module pushes marked abnormal service attributes and data to the data preprocessing module for preprocessing, the data preprocessing module pushes the marked abnormal service attributes and the marked data to the metadata management module and the data image conversion module for data definition and data graph conversion respectively, the data management module pushes the data to the BI interaction module after finishing the data analysis from the FFT data operation module and the EM Training data operation module, the data image conversion module pushes the image data to the data visual analysis logic control unit for logically associating the image data with the data attributes, the data image conversion module pushes the image data to the BI interaction module after finishing the data interaction module, the BI interaction module carries out structured and unstructured data application classification and marking, and pushes the data to the visual display control module after finishing the data graph display with the large data through the perception layer data visual model and the power grid service resource data visual model;

or/and the combination of the two,

and the service core control layer is characterized in that the service center master control unit completes data bidirectional transmission and instruction control through the FCFS scheduling unit and stores data into the center database, and the FCFS scheduling unit calls the logic control units corresponding to all the layers to realize instruction transmission, operation control and data transmission between all the layers and the service core control layer.

9. A method of use for a system as claimed in any one of claims 1 to 8, comprising:

the service core control layer controls the resource control layer, the data acquisition and transmission layer, the anomaly analysis processing layer and the big data analysis display layer to initialize;

responding to the initialization success instruction, the service core control layer calls the resource control layer to manage engine resources, control user authority and manage workflow;

responding to normal operation of the resource control layer, calling a data acquisition transmission layer by the service core control layer, acquiring network equipment sensing data and power grid service resource data, and monitoring data quality and transmission process;

the service core control layer calls an anomaly analysis processing layer to identify and screen anomaly data in the distribution network equipment sensing data and the power grid service resource data by utilizing various algorithms, and performs anomaly service research and judgment according to the anomaly data;

the service core control layer calls the big data analysis display layer to generate an abnormal service overhaul scheme corresponding to the abnormal service;

the service core control layer calls an abnormal analysis processing layer and generates an overhaul work order based on an abnormal service overhaul scheme;

the service core control layer calls the big data analysis display layer to display the data visually.

10. An electronic device comprising a processor and a memory, the memory having stored therein a computer program that is loaded and executed by the processor to implement the method of claim 9.