CN113708493B - Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment - Google Patents

Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment Download PDF

Info

Publication number
CN113708493B
CN113708493B CN202110987962.0A CN202110987962A CN113708493B CN 113708493 B CN113708493 B CN 113708493B CN 202110987962 A CN202110987962 A CN 202110987962A CN 113708493 B CN113708493 B CN 113708493B
Authority
CN
China
Prior art keywords
processed
information
power distribution
target
distribution terminal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110987962.0A
Other languages
Chinese (zh)
Other versions
CN113708493A (en
Inventor
侯祖锋
郭宗宝
郭文鑫
肖鸣晖
赵瑞锋
徐春华
梁苑
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Power Grid Co Ltd
Zhuhai Power Supply Bureau of Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Zhuhai Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Power Grid Co Ltd, Zhuhai Power Supply Bureau of Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN202110987962.0A priority Critical patent/CN113708493B/en
Publication of CN113708493A publication Critical patent/CN113708493A/en
Application granted granted Critical
Publication of CN113708493B publication Critical patent/CN113708493B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
    • H02J13/00016—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using a wired telecommunication network or a data transmission bus
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
    • Y04S40/124—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wired telecommunication networks or data transmission busses

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The application relates to a cloud edge cooperation-based power distribution terminal operation and maintenance method, a cloud edge cooperation-based power distribution terminal operation and maintenance device, computer equipment and a storage medium. The method comprises the steps of obtaining to-be-processed equipment information and to-be-processed operation information of to-be-processed power distribution terminals from a data center, inputting the to-be-processed operation information into a target state evaluation model, obtaining predicted fault information of the to-be-processed power distribution terminals output by the target state evaluation model, determining target to-be-processed power distribution terminals to be maintained according to the predicted fault information, forming a corresponding to-be-processed distribution list, determining a target operation and maintenance strategy of the list, and controlling the target to-be-processed power distribution terminals to execute the target operation and maintenance strategy. Compared with the traditional operation and maintenance of the power distribution terminal through manual work, the cloud server and the state evaluation model are utilized in the scheme, the state detection and the operation and maintenance of the power distribution terminal on the edge side are carried out, and therefore the operation and maintenance efficiency of the power distribution terminal is improved.

Description

Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment
Technical Field
The application relates to the technical field of power distribution automation, in particular to a cloud-edge cooperation-based power distribution terminal operation and maintenance method, a cloud-edge cooperation-based power distribution terminal operation and maintenance device, computer equipment and storage media.
Background
Electric power is one of important resources for maintaining daily work and life of people, one of important equipment in an electric power system is a power distribution terminal, and the power distribution terminal serves as data acquisition equipment in an automatic power distribution network system and plays an important role in the automatic power distribution system. Therefore, the operation and maintenance of the power distribution terminal is one of the most important work of operation and management of the power distribution network, and the operation and maintenance level of the power distribution terminal directly influences the operation reliability of the power distribution automation system.
The operation and maintenance mode of the power distribution terminal is usually carried out by personnel inspection, however, with the comprehensive popularization of power distribution automation construction, the power distribution terminal has the characteristics of large quantity, wide distribution and the like, and the quantity and coverage area are rapidly increased. The conventional operation and maintenance modes such as regular inspection, field fault processing and the like are low in operation and maintenance efficiency by personnel, and the requirement of power distribution automation operation and maintenance management and control is difficult to meet.
Therefore, the existing operation and maintenance method of the power distribution terminal has the defect of low efficiency.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a cloud-edge collaboration-based power distribution terminal operation and maintenance method, apparatus, computer device, and storage medium that can improve operation and maintenance efficiency.
A cloud-edge cooperation-based power distribution terminal operation and maintenance method is applied to a cloud server and comprises the following steps:
acquiring to-be-processed equipment information and to-be-processed running information of a to-be-processed power distribution terminal from a data center; the data center is arranged on the cloud server and is used for receiving and storing the to-be-processed equipment information and the to-be-processed running information sent by the to-be-processed power distribution terminal;
inputting the equipment information to be processed and the operation information to be processed into a target state evaluation model, and obtaining the predicted fault information of the power distribution terminal to be processed, which is output by the target state evaluation model; the target state evaluation model is obtained by training based on a plurality of pieces of sample equipment information, a plurality of pieces of sample operation information and a plurality of pieces of historical fault information; each of the historical fault information corresponds to a set of sample equipment information and sample operation information;
and determining a target to-be-maintained power distribution terminal according to the predicted fault information, forming a target to-be-maintained power distribution terminal list, determining a target operation and maintenance strategy of the target to-be-maintained power distribution terminal list, and controlling the target to-be-maintained power distribution terminal in the target to-be-maintained power distribution terminal list to execute the target operation and maintenance strategy.
In one embodiment, the method further comprises:
acquiring a plurality of sample equipment information, a plurality of sample operation information and a plurality of historical fault information corresponding to a sample power distribution terminal;
inputting the sample equipment information and the sample operation information into a state evaluation model to be trained, and obtaining sample prediction fault information output by the state evaluation model to be trained;
judging whether the similarity value of the sample prediction fault information and the historical fault information corresponding to the sample equipment information and the sample operation information is smaller than a preset similarity threshold value or not;
if not, the state evaluation model to be trained is adjusted according to the similarity value, and the step of inputting the sample equipment information and the sample operation information into the state evaluation model to be trained is returned;
if yes, ending the circulation, and taking the current state evaluation model to be trained as a target state evaluation model.
In one embodiment, after the obtaining the to-be-processed equipment information and the to-be-processed operation information of the to-be-processed power distribution terminal from the data center, the method further includes:
acquiring historical inspection information corresponding to the power distribution terminal to be processed;
determining inspection parameters corresponding to the power distribution terminal to be processed according to the historical inspection information;
And detecting whether abnormal operation information exists in the to-be-processed operation information of the to-be-processed power distribution terminal according to the inspection parameters and a preset period, if so, generating corresponding alarm information and a target operation and maintenance strategy according to the abnormal operation information, and controlling the to-be-processed power distribution terminal to execute the target operation and maintenance strategy.
4. The method of claim 1, the predicted fault information comprising a predicted fault probability; the determining the target to-be-processed power distribution terminal to be maintained according to the predicted fault information to form a target to-be-processed power distribution terminal list comprises the following steps:
if the predicted fault probability is greater than or equal to a preset fault threshold value, determining the power distribution terminal to be processed corresponding to the predicted fault information as a target power distribution terminal to be processed;
and generating a target to-be-processed power distribution terminal list according to the to-be-processed equipment information of the target to-be-processed power distribution terminal.
In one embodiment, the controlling the target to-be-processed power distribution terminal in the target to-be-processed power distribution terminal list to execute the target operation and maintenance policy includes:
controlling the target to-be-processed power distribution terminals in the target to-be-processed power distribution terminal list to perform self-checking self-recovery and/or software upgrading so as to enable the target to-be-processed power distribution terminals to recover normal operation;
After the target operation and maintenance strategy is executed by the target to-be-processed power distribution terminal in the target to-be-processed power distribution terminal list, the method further comprises the following steps:
acquiring target to-be-processed equipment information of the target to-be-processed power distribution terminal after executing the target operation and maintenance strategy, and target to-be-processed operation information;
inputting the target to-be-processed equipment information and the target to-be-processed running information into a target state evaluation model, and obtaining target prediction fault information output by the target state evaluation model;
and if the target predicted fault information has preset high-risk fault information, generating corresponding fault early warning information so that a worker can check the target power distribution terminal to be processed based on the fault early warning information.
In one embodiment, after obtaining the predicted fault information of the power distribution terminal to be processed output by the target state evaluation model, the method further includes:
clustering the predicted fault information according to the type of the to-be-processed equipment information of the to-be-processed power distribution terminal to obtain a predicted fault information cluster corresponding to the to-be-processed equipment information;
and if the number of the same type of predictive fault information in the predictive fault information cluster is larger than a preset value, generating a corresponding operation and maintenance strategy according to the to-be-processed equipment information.
In one embodiment, the obtaining the to-be-processed equipment information and the to-be-processed operation information of the to-be-processed power distribution terminal from the data center includes:
acquiring at least one of equipment type, manufacturer, model, operation time, channel type and affiliated power distribution area of the power distribution terminal to be processed from a data center, and taking the at least one of equipment type, manufacturer, model, operation time, channel type and affiliated power distribution area as the information of the equipment to be processed;
and acquiring at least one of the running state, the battery state, the communication state and the alarm information of the power distribution terminal to be processed from the data center as the running information to be processed.
A power distribution terminal operation and maintenance device based on cloud edge cooperation, which is applied to a cloud server, the device comprises:
the acquisition module is used for acquiring to-be-processed equipment information and to-be-processed running information of the to-be-processed power distribution terminal from the data center; the data center is arranged on the cloud server and is used for receiving and storing the to-be-processed equipment information and the to-be-processed running information sent by the to-be-processed power distribution terminal;
the prediction module is used for inputting the equipment information to be processed and the operation information to be processed into a target state evaluation model and obtaining the predicted fault information of the power distribution terminal to be processed, which is output by the target state evaluation model; the target state evaluation model is obtained by training based on a plurality of pieces of sample equipment information, a plurality of pieces of sample operation information and a plurality of pieces of historical fault information; each of the historical fault information corresponds to a set of sample equipment information and sample operation information;
And the operation and maintenance module is used for determining a target to-be-maintained power distribution terminal according to the predicted fault information, forming a target to-be-processed power distribution terminal list, determining a target operation and maintenance strategy of the target to-be-processed power distribution terminal list, and controlling the target to-be-processed power distribution terminal in the target to-be-processed power distribution terminal list to execute the target operation and maintenance strategy.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method described above.
According to the cloud edge cooperation-based power distribution terminal operation and maintenance method, device, computer equipment and storage medium, the information of the equipment to be processed and the operation information to be processed of the power distribution terminal are obtained from the data center, the target state evaluation model is input, the predicted fault information of the power distribution terminal to be processed, which is output by the target state evaluation model, is obtained, the target power distribution terminal to be maintained is determined according to the predicted fault information, a corresponding list of the power distribution terminals to be processed is formed, and the target operation and maintenance strategy of the list is determined, so that the target power distribution terminal to be processed is controlled to execute the target operation and maintenance strategy. Compared with the traditional operation and maintenance of the power distribution terminal through manual work, the cloud server and the state evaluation model are utilized in the scheme, the state detection and the operation and maintenance of the power distribution terminal on the edge side are carried out, and therefore the operation and maintenance efficiency of the power distribution terminal is improved.
Drawings
Fig. 1 is an application environment diagram of a cloud-edge collaboration-based operation and maintenance method of a power distribution terminal in an embodiment;
fig. 2 is a schematic flow chart of a cloud-edge collaboration-based operation and maintenance method for a power distribution terminal in an embodiment;
fig. 3 is a flow chart of a power distribution terminal operation and maintenance method based on Yun Bian cooperation in another embodiment;
fig. 4 is a block diagram of a power distribution terminal operation and maintenance device based on cloud edge collaboration in an embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The power distribution terminal operation and maintenance method based on cloud edge cooperation can be applied to an application environment shown in fig. 1. The power distribution terminal 102 communicates with the cloud server 104 through a network. The power distribution terminal 102 can be arranged in a power distribution network system, the power distribution terminal 102 can send collected data to a data center in the cloud server 104 for storage, and an operation and maintenance application and a distribution network main station application can be further arranged in the cloud server 104, so that the cloud server 104 can evaluate the state of the power distribution terminal 102 according to relevant information of the power distribution terminal 102 stored in the data center based on the application, and the cloud server 104 can remotely operate and maintain the corresponding power distribution terminal 102 according to the result of the state evaluation, thereby realizing cloud-edge collaborative operation and maintenance of the power distribution terminal. The cloud server 104 may be implemented as an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a cloud-edge collaboration-based power distribution terminal operation and maintenance method is provided, and the method is applied to the cloud server in fig. 1 for illustration, and includes the following steps:
step S202, obtaining to-be-processed equipment information and to-be-processed running information of a to-be-processed power distribution terminal from a data center; the data center is arranged on the cloud server and used for receiving and storing the information of the equipment to be processed and the operation information to be processed, which are sent by the power distribution terminal to be processed.
The data center may be a database disposed in the cloud server 104, and may be used to store related data sent by the power distribution terminal 102. The cloud server 104 may be disposed at the cloud and communicate with the plurality of power distribution terminals 102 on the edge side, for example, the power distribution terminals 102 may send acquired data to a data center in the cloud server 104, and the data sent by the power distribution terminals 102 may be information of to-be-processed devices and to-be-processed operation information of the power distribution terminals 102. The cloud server 104 may obtain information on equipment to be processed and operation information on operation to be processed of the power distribution terminal to be processed from the data center. For example, the intelligent operation and maintenance application and the distribution network host application in the cloud server 104 each acquire the above-mentioned to-be-processed device information and to-be-processed operation information from the data center, and the intelligent operation and maintenance application and the distribution network host application may also issue respective control instructions to the distribution terminal 102 respectively.
The to-be-processed device information and the to-be-processed operation information of the power distribution terminal 102 stored in the data center of the cloud server 104 may be various. For example, in one embodiment, obtaining, from a data center, to-be-processed equipment information and to-be-processed operation information of a to-be-processed power distribution terminal includes: acquiring at least one of equipment type, manufacturer, model, operation time, channel type and affiliated power distribution area of a power distribution terminal to be processed from a data center as information of the equipment to be processed; and acquiring at least one of the running state, the battery state, the communication state and the alarm information of the power distribution terminal to be processed from the data center as the running information to be processed. In this embodiment, the to-be-processed device information sent by the power distribution terminal 102 to the data center may include, but is not limited to, static information such as a device type, a manufacturer, a model, a commissioning time, a channel type, a region to which the to-be-processed device information belongs; the operation information to be processed can include, but is not limited to, real-time information such as operation state, battery state, communication state, alarm information and the like; the data sent from the power distribution terminal 102 to the data center may also include history information such as operation records, inspection records, and maintenance records of the power distribution terminal 102. The data center of the cloud server 104 may receive and store the above information, so that the cloud server 104 may perform operation and maintenance on the power distribution terminal 102 based on relevant data in the data center.
In addition, it should be noted that, the cloud server 104 may be configured with a corresponding distribution network operation manager, and the distribution network operation manager may perform the operation of the power distribution terminal and the management of the distribution network host station by accessing the cloud server 104 in the cloud platform.
Step S204, inputting the information of the equipment to be processed and the operation information to be processed into a target state evaluation model, and obtaining the predicted fault information of the power distribution terminal to be processed, which is output by the target state evaluation model; the target state evaluation model is obtained based on training of a plurality of sample equipment information, a plurality of sample operation information and a plurality of historical fault information; each of the historical fault information corresponds to a set of sample device information and sample run information.
The target state evaluation model may be a neural network model for evaluating the health state and the operation state of the power distribution terminal 102, and may be trained based on a plurality of sample device information, a plurality of sample operation information, and a plurality of historical fault information of the plurality of power distribution terminals 102, and each of the historical fault information corresponds to a set of sample device information and sample operation information. The cloud server 104 may utilize the target state model to predict the operational state and health state of the power distribution terminal 102. For example, the cloud server 104 may input the obtained to-be-processed device information and to-be-processed operation information into a target state evaluation model, where the target state evaluation model may output the device information of the input model and the predicted fault information of the to-be-processed power distribution terminal 102 corresponding to the operation information, where the predicted fault information may include a predicted fault type that may occur in the power distribution terminal 102 and an occurrence probability of the predicted fault type. The target state evaluation model may be trained by mining an association relationship among sample equipment information, sample operation information, and historical fault information. For example, when a fault occurs, the device information of the power distribution terminal 102 and the operation information thereof are necessarily in a certain state, and the cloud server 104 may mine the association relationship therein; the cloud server 104 can perform statistics processing on the historical data of the power distribution terminal, so as to identify the problems of long-time non-refreshing, frequent jitter of remote signaling, long-time continuous offline, frequent disconnection, remote control failure and the like of the power distribution terminal, and provide data support for judging the running state of the terminal; therefore, the cloud server 104 can utilize a data mining algorithm to deeply mine the association relationship between the fault history information of the power distribution terminal and the running state information of the power distribution terminal 102, the equipment information of the power distribution terminal 102, and the measured information such as long-time unrefreshing, frequent jitter of remote signaling, long-time continuous offline, frequent disconnection, remote control failure and the like, so as to provide support for the evaluation of the health state of the power distribution terminal.
Step S206, determining a target to-be-maintained power distribution terminal according to the predicted fault information, forming a target to-be-maintained power distribution terminal list, determining a target operation and maintenance strategy of the target to-be-maintained power distribution terminal list, and controlling the target to-be-maintained power distribution terminal in the target to-be-maintained power distribution terminal list to execute the target operation and maintenance strategy.
The predicted fault information may be fault information that may occur in the power distribution terminal 102 to be processed output by the target state evaluation model. The cloud server 104 may determine the target to-be-processed power distribution terminals 102 that need to be maintained based on the predicted fault information, and form a corresponding target to-be-processed power distribution terminal list. For example, the predicted fault information of each power distribution terminal 102 does not necessarily represent that the power distribution terminal 102 will fail, the cloud server 104 may take the power distribution terminal 102 that may fail as a target power distribution terminal to be processed 102 and add the power distribution terminal to a target power distribution terminal list to be processed, and the cloud server 104 may determine a corresponding target operation and maintenance policy based on the predicted fault information of each target power distribution terminal to be processed 102 in the target power distribution terminal list to be processed, and the cloud server 104 may remotely control the target power distribution terminals to be processed 102 in the target power distribution terminal list to execute the target operation and maintenance policy, so that cloud-side coordinated operation of operating and maintaining the power distribution terminals 102 on the edge side in the cloud may be realized.
According to the cloud edge cooperation-based power distribution terminal operation and maintenance method, the to-be-processed equipment information and the to-be-processed operation information of the to-be-processed power distribution terminal are obtained from the data center, the to-be-processed operation information is input into the target state evaluation model, the predicted fault information of the to-be-processed power distribution terminal output by the target state evaluation model is obtained, the target to-be-processed power distribution terminal needing to be maintained is determined according to the predicted fault information, a corresponding to-be-processed distribution list is formed, the target operation and maintenance strategy of the list is determined, and therefore the target to-be-processed power distribution terminal is controlled to execute the target operation and maintenance strategy. Compared with the traditional operation and maintenance of the power distribution terminal through manual work, the cloud server and the state evaluation model are utilized in the scheme, the state detection and the operation and maintenance of the power distribution terminal on the edge side are carried out, and therefore the operation and maintenance efficiency of the power distribution terminal is improved.
In one embodiment, further comprising: acquiring a plurality of sample equipment information, a plurality of sample operation information and a plurality of historical fault information corresponding to a sample power distribution terminal; inputting sample equipment information and sample operation information into a state evaluation model to be trained, and obtaining sample prediction fault information output by the state evaluation model to be trained; judging whether the similarity value of the sample prediction fault information and the historical fault information corresponding to the sample equipment information and the sample operation information is smaller than a preset similarity threshold value or not; if not, adjusting the state evaluation model to be trained according to the similarity value, and returning to the step of inputting the sample equipment information and the sample operation information into the state evaluation model to be trained; if yes, ending the circulation, and taking the current state evaluation model to be trained as a target state evaluation model.
In this embodiment, the cloud server 104 may train the state evaluation model to be trained to obtain the target state evaluation model. The cloud server 104 may obtain sample device information, sample operation information, and historical fault information of a plurality of sample power distribution terminals participating in training, thereby obtaining a plurality of sample device information, a plurality of sample operation information, and a plurality of historical fault information, and each of the historical fault information corresponds to a set of sample device information and sample operation information. The cloud server 104 may input a sample device information and sample operation information into the state evaluation model to be trained, the state evaluation model to be trained may output sample prediction fault information obtained based on the sample device information and the sample operation information prediction, and output the sample prediction fault information, the cloud server 104 may obtain the sample prediction fault information, and the cloud server 104 may determine a similarity value of the sample prediction fault information and historical fault information corresponding to the set of sample device information and the sample operation information input into the state evaluation model to be trained, if the similarity value is greater than or equal to a preset similarity threshold, the cloud server 104 may determine that the state evaluation model to be trained is not trained, adjust relevant parameters in the state evaluation model to be trained according to the similarity value, and return a step of inputting the sample device information and the sample operation information into the state evaluation model to be trained, so that the cloud server 104 may perform next training on the state evaluation model to be trained by using a new set of sample device information and sample operation information. When the similarity value is smaller than the preset similarity threshold, the cloud server 104 may determine that the training is completed, end the training, and use the state evaluation model obtained by the current training as the target state evaluation model.
The device information, the operation information, and the historical fault information may all include multiple types of information, and the cloud server 104 may mine the relationship between them by training the target state evaluation model. For example, the cloud server 104 may utilize a big data analysis algorithm to study association rules and evolution rules between faults of the power distribution terminal device and information such as running state parameters, operation time, manufacturer, model, channel type, measurement, long-time non-refreshing, frequent jitter of remote signaling, long-time continuous offline, frequent disconnection, remote control failure and the like of the power distribution terminal device, and build a power distribution terminal health state evaluation and prediction model, that is, the state evaluation model, and utilize a machine learning and association analysis algorithm to adjust parameters and weights to obtain a target state evaluation model, so that the cloud server 104 may utilize the target state evaluation model to predict fault information of the power distribution terminal 102.
According to the embodiment, the cloud server 104 can train to obtain the target state evaluation model based on the plurality of sample equipment information, the plurality of sample operation information and the plurality of historical fault information, so that the cloud server 104 can utilize the target state evaluation model to operate and maintain the power distribution terminal 102 to be processed, and the operation and maintenance efficiency of the power distribution terminal is improved.
In one embodiment, after obtaining the to-be-processed equipment information and the to-be-processed operation information of the to-be-processed power distribution terminal from the data center, the method further includes: acquiring historical inspection information corresponding to a power distribution terminal to be processed; determining inspection parameters corresponding to the power distribution terminal to be processed according to the historical inspection information; detecting whether abnormal operation information exists in the to-be-processed operation information of the to-be-processed power distribution terminal according to the inspection parameters and a preset period, if so, generating corresponding alarm information and a target operation and maintenance strategy according to the abnormal operation information, and controlling the to-be-processed power distribution terminal to execute the target operation and maintenance strategy.
In this embodiment, the cloud server 104 may automatically patrol the power distribution terminal 102 on the edge side, so as to perform daily monitoring on the state of the power distribution terminal 102 and perform early warning on an abnormal state. The power distribution terminal 102 may determine, based on the historical inspection information, an inspection mode of the power distribution terminal 102, for example, the power distribution terminal 102 may obtain the historical inspection information of the power distribution terminal 102 to be processed, and analyze the historical inspection information to obtain inspection parameters corresponding to the power distribution terminal 102 to be processed, so that the cloud server 104 may detect, according to the inspection parameters, whether abnormal operation information, such as shutdown or disconnection, exists in the operation information of the power distribution terminal 102 to be processed according to a preset period; if so, the cloud server 104 may generate corresponding alarm information and a target operation and maintenance policy according to the abnormal operation information, and control the abnormal power distribution terminal 102 to execute the target operation and maintenance policy.
For example, the cloud server 104 may learn a work record list of manual inspection in the past by using a machine learning method, extract inspection work items, and generate inspection parameters according to the extracted inspection work items, so that the cloud server 104 may check the states of all power distribution terminals at regular time according to the inspection parameters, and early warn abnormal terminals. The cloud server 104 can monitor and daily operation and maintenance the state of the power distribution terminal 102, and the cloud server 104 monitors the operation state of the power distribution terminal in real time, and when abnormal conditions such as shutdown and disconnection occur in the power distribution terminal, an alarm signal is sent, for example, alarm information is sent to the terminal of the related staff, so that the related staff can process the alarm information. In addition, in some embodiments, the cloud server 104 may also perform batch setup and update for the edge-side power distribution terminal 102. The cloud server 104 can set batch parameters of the power distribution terminal at the cloud, and can update batch running programs of the power distribution terminal at the cloud. For example, when the plurality of power distribution terminals 102 are in the abnormal state, the cloud server 104 may perform parameter setting and program updating on the plurality of power distribution terminals 102 in batches, so that the power distribution terminals 102 recover to a normal operation state.
Through the embodiment, the cloud server 104 can perform timing inspection and early warning on the power distribution terminal 102, so that the operation and maintenance efficiency of the power distribution terminal 102 is improved.
In one embodiment, determining a target to-be-processed power distribution terminal to be maintained according to the predicted fault information to form a target to-be-processed power distribution terminal list includes: if the predicted fault probability is greater than or equal to a preset fault threshold value, determining the power distribution terminal to be processed corresponding to the predicted fault information as a target power distribution terminal to be processed; and generating a target to-be-processed power distribution terminal list according to the to-be-processed equipment information of the target to-be-processed power distribution terminal.
In this embodiment, the predicted fault information may include a predicted fault probability of the power distribution terminal 102 to be processed. The cloud server 104 may determine a target pending distribution terminal list based on the predicted fault probability. The cloud server 104 may detect whether the predicted fault probability output by the target state evaluation model is greater than or equal to a preset fault threshold, if yes, the cloud server 104 may determine that the to-be-processed power distribution terminal 102 corresponding to the predicted fault probability is the target to-be-processed power distribution terminal 102, and the target to-be-processed power distribution terminal 102 may be multiple, and the cloud server 104 may generate a target to-be-processed power distribution terminal list based on to-be-processed equipment information of the target to-be-processed power distribution terminal 102, that is, the cloud server 104 adds the equipment identifier of the target to-be-processed power distribution terminal 102 into the target to-be-processed power distribution terminal list.
The target state evaluation model may include a health state evaluation and a fault prediction process for the power distribution terminal 102. For example, the cloud server 104 may utilize the power distribution terminal health status evaluation model, i.e., the target status evaluation model described above, to evaluate the current health status of the power distribution terminal 102 according to the current operating status parameters of the power distribution terminal 102 and other related information. And predicting the probability of faults and what faults occur in a period of time in the future of the terminal by using a power distribution terminal health prediction model, namely the target state evaluation model. Therefore, the cloud server 104 can perform active operation and maintenance on the power distribution terminal 102 based on the probability of the fault, that is, the cloud server 104 lists the power distribution terminal 102 that may have the fault into a focused attention list according to the state evaluation and the fault prediction, so as to form the target to-be-processed power distribution terminal list.
Through the embodiment, the cloud server 104 can determine the target to-be-processed power distribution terminal 102 needing active operation and maintenance based on the predicted fault probability, so that the operation and maintenance efficiency of the power distribution terminal 102 is improved.
In one embodiment, controlling a target pending power distribution terminal in a target pending power distribution terminal list to execute a target operation and maintenance policy includes: and controlling the target to-be-processed power distribution terminals in the target to-be-processed power distribution terminal list to perform self-checking and self-recovery and/or software upgrading so as to enable the target to-be-processed power distribution terminals to recover normal operation.
In this embodiment, the cloud server 104 may perform active operation and maintenance on each target to-be-processed power distribution terminal 102 in the target to-be-processed power distribution terminal list, for example, the cloud server 104 may remotely control the target to-be-processed power distribution terminal 102 to perform self-checking and self-recovering operations, and the cloud server 104 may also remotely control the target to-be-processed power distribution terminal 102 to perform operation software upgrade, so that the target to-be-processed power distribution terminal 102 is restored to a normal operation state.
In addition, after controlling the target to-be-processed power distribution terminal 102 to execute the corresponding target operation and maintenance policy, the cloud server 104 may further perform state evaluation and fault prediction on the target to-be-processed power distribution terminal 102 after executing the target operation and maintenance policy based on the target state evaluation model. For example, in one embodiment, after the target pending distribution terminal in the target pending distribution terminal list is controlled to execute the target operation and maintenance policy, the method further includes: acquiring target to-be-processed equipment information and target to-be-processed operation information of a target to-be-processed power distribution terminal after executing a target operation and maintenance strategy; inputting the target equipment information to be processed and the target operation information to be processed into a target state evaluation model, and obtaining target prediction fault information output by the target state evaluation model; if the target prediction fault information has preset high-risk fault information, generating corresponding fault early warning information and sending the corresponding fault early warning information to a terminal of a worker, so that the worker can check the target power distribution terminal to be processed based on the fault early warning information.
In this embodiment, the predicted fault information may further include a predicted fault type, after the target to-be-processed power distribution terminal 102 executes the target operation and maintenance policy, the cloud server 104 may obtain the target to-be-processed equipment information and the target to-be-processed operation information of the executed target to-be-processed power distribution terminal 102, and input the target to-be-processed equipment information and the target to-be-processed operation information into the target state evaluation model, where the target state evaluation model may perform state evaluation and fault prediction on the target to-be-processed operation information and the target to-be-processed equipment information, so that the cloud server 104 may obtain the target predicted fault information output by the target state evaluation model, and detect whether the preset high risk fault information exists therein, where the high risk fault information may be preset, and if so, the cloud server 104 may generate corresponding fault early warning information and send the fault early warning information to the terminal of the staff, so that the relevant staff may check the target to-be-processed power distribution terminal 102 based on the fault early warning information. For example, the server 102 may add the power distribution terminal 102 having an abnormal state in the automatic inspection and the power distribution terminal 102 having a possible fault predicted by the target state evaluation model to the target to-be-processed power distribution terminal list, and remotely perform a self-inspection and self-recovery operation on the terminals in the target to-be-processed power distribution terminal list, and continue to evaluate and predict by using the target state evaluation model. The cloud server 104 can also remotely upgrade the running software of the terminals in the target to-be-processed power distribution terminal list, and continuously evaluate and predict the terminals by adopting a target state evaluation model. When the cloud server 104 maintains the terminal with high risk after the active operation, personnel can be scheduled to perform on-site inspection and maintenance.
Through the above embodiment, the cloud server 104 may remotely perform operation and maintenance on the target to-be-processed power distribution terminal 102 on the edge side based on the target operation and maintenance policy, so that the efficiency of operation and maintenance of the power distribution terminal is improved.
In one embodiment, after obtaining the predicted fault information of the power distribution terminal to be processed output by the target state evaluation model, the method further includes: clustering the predicted fault information according to the type of the to-be-processed equipment information of the to-be-processed power distribution terminal to obtain a predicted fault information cluster corresponding to the to-be-processed equipment information; if the number of the same type of predictive fault information in the predictive fault information cluster is larger than a preset value, generating a corresponding operation and maintenance strategy according to the to-be-processed equipment information.
In this embodiment, the cloud server 104 may perform cluster analysis on the power distribution terminal 102 that may have a fault, and after obtaining the predicted fault information of the power distribution terminal 102 to be processed, the power distribution terminal 102 may perform cluster processing on the predicted fault information according to the type of the to-be-processed device information of the power distribution terminal 102 to be processed, so as to obtain a predicted fault information cluster corresponding to the to-be-processed device information. The types of the device information to be processed may include a plurality of types, for example, the device information to be processed may be a model number of the power distribution terminal 102, and since the model number may include a plurality of types, the above-mentioned predictive failure information cluster may also be a plurality of types. Each predicted fault information cluster may include multiple types of predicted fault information, and when the cloud server 104 detects that the number of the predicted fault information of the same type in the predicted fault information cluster is greater than a preset value, the cloud server 104 may determine that the fault information is a common defect of the type of power distribution terminal 102, so that the cloud server 104 may generate a corresponding operation and maintenance policy according to the to-be-processed equipment information, thereby performing unified upgrade maintenance on the power distribution terminal 102 corresponding to the to-be-processed equipment information. For example, the cluster analysis may be a familial feature analysis, where the cloud server 104 identifies familial features by performing cluster and association analysis on defects of the devices of the power distribution terminal 102, and proposes an operation maintenance policy and plan based on the familial features. If the defect familiarity analysis finds that the number of times that a certain type of fault occurs on a certain version or lot number of power distribution terminals 102 of a certain manufacturer is too high, a batch unified upgrade maintenance plan can be proposed for the same type of terminals.
Through the embodiment, the cloud server 104 can determine a fault possibly occurring in common with equipment information based on the equipment information of the power distribution terminal 102, so that uniform maintenance is performed on the same type of power distribution terminal 102, and the operation and maintenance efficiency of the power distribution terminal is improved.
In one embodiment, as shown in fig. 3, fig. 3 is a flow chart of a power distribution terminal operation and maintenance method based on Yun Bian cooperation in another embodiment. The method comprises the following steps: the server 102 may obtain status data of the power distribution terminal from the data center, including static information such as a device type, a manufacturer, a model, a commissioning time, a channel type, a region to which the power distribution terminal belongs, real-time information such as an operation status, a battery status, a communication status, and alarm information, and historical information such as an operation record, a patrol record, and a maintenance record. The cloud server 104 may also perform preprocessing and statistical analysis on the data using big data techniques. For example, when the cloud server 104 finds that a batch of terminals are disconnected, analyzing network characteristics of the disconnected power distribution terminals, judging whether the reason of the disconnection is a terminal fault or a communication network fault, and generating equipment defect alarm information; and monitoring the collected terminal running state, and generating an alarm when abnormality occurs. The cloud server 104 can also identify the problems of long-time non-refreshing, frequent jitter of remote signaling, long-time continuous offline, frequent disconnection, remote control failure and the like of the power distribution terminal by carrying out statistics processing on the historical data of the power distribution terminal, so as to provide data support for judging the running state of the terminal. The cloud server 104 can further utilize a data mining algorithm to deeply mine the association relationship between the power distribution terminal fault history information and the terminal operation state information and the information such as long-time unrefreshing, frequent jitter of remote signaling, long-time continuous offline, frequent offline, remote control failure and the like, so as to provide support for the evaluation of the health state of the power distribution terminal.
The cloud server 104 may perform intelligent operation and maintenance on the power distribution terminal 102. For example, the cloud server 104 may perform state monitoring and daily operation and maintenance on the power distribution terminal 102, specifically includes monitoring an operation state of the power distribution terminal in real time, and sending an alarm signal when an abnormal situation such as shutdown or disconnection occurs in the power distribution terminal. The cloud server 104 can set batch parameters of the power distribution terminals at the cloud; and the cloud server 104 can update the batch running program of the power distribution terminal at the cloud. The cloud server 104 may also perform automatic inspection on the power distribution terminal 102, specifically including learning a work record list of manual inspection in the past by using a machine learning method, and extracting inspection work items. And generating inspection parameters according to the extracted inspection work items. And then checking the states of all the power distribution terminals at regular time according to the inspection parameters. And early warning is carried out on the abnormal terminal. The cloud server 104 may further perform health status evaluation on the power distribution terminal 102, and specifically includes researching association rules and evolution rules between information such as failure and self-running status parameters, operation time, manufacturer, model, channel type, and measurement of long-time non-refreshing, frequent jitter of remote signaling, long-time continuous offline, frequent disconnection, and remote control failure of the power distribution terminal by using a big data analysis algorithm. The cloud server 104 may also establish a power distribution terminal health status evaluation and prediction model, that is, the target status evaluation model, and adjust parameters and weights by using a machine learning and association analysis algorithm. And evaluating the current health state of the terminal according to the current running state parameters and other related information by using the power distribution terminal health state evaluation model. And predicting the probability of faults and what faults occur in a period of time in the future by using the power distribution terminal health prediction model.
The cloud server 104 may also perform active operation and maintenance on the power distribution terminal 102, specifically including listing the terminal that may fail into a focused attention list, that is, the target to-be-processed power distribution terminal list, according to the fault early warning in the automatic inspection and the state evaluation and the fault prediction in the target state evaluation model. The cloud server 104 remotely performs self-checking and self-recovering operation on the terminals in the key attention list, and continues to evaluate and predict by adopting the target state evaluation model. The cloud server 104 can remotely upgrade the running software of the terminal in the key attention list, continuously evaluate and predict the terminal with the target state evaluation model, and schedule personnel to carry out on-site inspection and maintenance on the terminal with high risk. The cloud server 104 can also identify familial characteristics in the defects of the terminal equipment by clustering and association analysis, and propose an operation maintenance strategy and a plan on the basis of the familial characteristics. If the defect familiarity analysis finds that the number of times that a certain type of faults occur at a certain type of terminals of a certain model or lot number of a certain manufacturer is too large, a batch unified upgrading maintenance plan can be provided for the same type of terminals.
Through the embodiment, the centralized operation and maintenance are performed on the power distribution terminal by adopting the cloud edge cooperative technology, the remote operation and maintenance application of the power distribution terminal is deployed at the cloud end, the unified data base of the cloud end is utilized, the information interaction links are reduced, and the consistency and the accuracy of data are ensured; the operation and maintenance application is used as one of application functions of the cloud master station, so that the workload of switching among a plurality of systems of a distribution network operation manager is reduced. Meanwhile, an intelligent operation and maintenance technology is adopted to automatically patrol the power distribution terminal, a health state evaluation model of the power distribution terminal is built, operation and maintenance are carried out on demand, an overhaul strategy is optimized, operation and maintenance workload is reduced, failure rate of the power distribution terminal is reduced, and therefore operation and maintenance efficiency of the power distribution terminal 102 is improved.
It should be understood that, although the steps in the flowcharts of fig. 2-3 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps of fig. 2-3 may include multiple steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the steps or stages are performed necessarily occur sequentially, but may be performed alternately or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 4, a cloud edge collaboration-based operation and maintenance device for a power distribution terminal is provided, including: an acquisition module 500, a prediction module 502, and an operation and maintenance module 504, wherein:
the acquiring module 500 is configured to acquire to-be-processed equipment information and to-be-processed operation information of the to-be-processed power distribution terminal from the data center; the data center is arranged on the cloud server and is used for receiving and storing the to-be-processed equipment information and the to-be-processed running information sent by the to-be-processed power distribution terminal.
The prediction module 502 is configured to input the to-be-processed equipment information and the to-be-processed operation information into a target state evaluation model, and obtain predicted fault information of the to-be-processed power distribution terminal output by the target state evaluation model; the target state evaluation model is obtained by training based on a plurality of pieces of sample equipment information, a plurality of pieces of sample operation information and a plurality of pieces of historical fault information; each of the historical fault information corresponds to a set of sample device information and sample operation information.
And the operation and maintenance module 504 is configured to determine a target to-be-processed power distribution terminal to be maintained according to the predicted fault information, form a target to-be-processed power distribution terminal list, determine a target operation and maintenance policy of the target to-be-processed power distribution terminal list, and control the target to-be-processed power distribution terminal in the target to-be-processed power distribution terminal list to execute the target operation and maintenance policy.
In one embodiment, the apparatus further comprises: the training module is used for acquiring a plurality of sample equipment information, a plurality of sample operation information and a plurality of historical fault information corresponding to the sample power distribution terminal; inputting the sample equipment information and the sample operation information into a state evaluation model to be trained, and obtaining sample prediction fault information output by the state evaluation model to be trained; judging whether the similarity value of the sample prediction fault information and the historical fault information corresponding to the sample equipment information and the sample operation information is smaller than a preset similarity threshold value or not; if not, the state evaluation model to be trained is adjusted according to the similarity value, and the step of inputting the sample equipment information and the sample operation information into the state evaluation model to be trained is returned; if yes, ending the circulation, and taking the current state evaluation model to be trained as a target state evaluation model.
In one embodiment, the apparatus further comprises: the inspection module is used for acquiring historical inspection information corresponding to the power distribution terminal to be processed; determining inspection parameters corresponding to the power distribution terminal to be processed according to the historical inspection information; and detecting whether abnormal operation information exists in the to-be-processed operation information of the to-be-processed power distribution terminal according to the inspection parameters and a preset period, if so, generating corresponding alarm information and a target operation and maintenance strategy according to the abnormal operation information, and controlling the to-be-processed power distribution terminal to execute the target operation and maintenance strategy.
In one embodiment, the operation and maintenance module 504 is specifically configured to determine the to-be-processed power distribution terminal corresponding to the predicted fault information as the target to-be-processed power distribution terminal if the predicted fault probability is greater than or equal to a preset fault threshold; and generating a target to-be-processed power distribution terminal list according to the to-be-processed equipment information of the target to-be-processed power distribution terminal.
In one embodiment, the operation and maintenance module 504 is specifically configured to control the target to-be-processed power distribution terminal in the target to-be-processed power distribution terminal list to perform self-checking and self-recovery and/or software upgrading, so that the target to-be-processed power distribution terminal resumes normal operation.
In one embodiment, the apparatus further comprises: the checking module is used for acquiring the target to-be-processed equipment information and the target to-be-processed running information of the target to-be-processed power distribution terminal after the target operation and maintenance strategy is executed; inputting the target to-be-processed equipment information and the target to-be-processed running information into a target state evaluation model, and obtaining target prediction fault information output by the target state evaluation model; if the target prediction fault information has preset high-risk fault information, generating corresponding fault early warning information and sending the corresponding fault early warning information to a terminal of a worker, so that the worker can check the target power distribution terminal to be processed based on the fault early warning information.
In one embodiment, the apparatus further comprises: the clustering module is used for carrying out clustering processing on the predicted fault information according to the type of the to-be-processed equipment information of the to-be-processed power distribution terminal to obtain a predicted fault information cluster corresponding to the to-be-processed equipment information; and if the number of the same type of predictive fault information in the predictive fault information cluster is larger than a preset value, generating a corresponding operation and maintenance strategy according to the to-be-processed equipment information.
In one embodiment, the obtaining module 500 is specifically configured to obtain, from a data center, at least one of a device type, a manufacturer, a model, a commissioning time, a channel type, and an affiliated power distribution area of the power distribution terminal to be processed, as the information of the device to be processed; and acquiring at least one of the running state, the battery state, the communication state and the alarm information of the power distribution terminal to be processed from the data center as the running information to be processed.
For specific limitation of the operation and maintenance device of the power distribution terminal based on cloud edge cooperation, reference may be made to the limitation of the operation and maintenance method of the power distribution terminal based on cloud edge cooperation hereinabove, and the description thereof will not be repeated here. All or part of each module in the cloud-edge cooperation-based power distribution terminal operation and maintenance device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing operation and maintenance related data based on the power distribution terminal. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a cloud edge cooperation-based power distribution terminal operation and maintenance method.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, including a memory and a processor, where the memory stores a computer program, and the processor implements the above-mentioned cloud-edge collaboration-based power distribution terminal operation and maintenance method when executing the computer program.
In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the above-mentioned cloud-edge collaboration-based power distribution terminal operation and maintenance method.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims (10)

1. The utility model provides a distribution terminal operation and maintenance method based on cloud limit cooperation which is characterized in that is applied to cloud server, the method includes:
acquiring to-be-processed equipment information and to-be-processed running information of a to-be-processed power distribution terminal from a data center; the data center is arranged on the cloud server and is used for receiving and storing the to-be-processed equipment information and the to-be-processed running information sent by the to-be-processed power distribution terminal;
Inputting the equipment information to be processed and the operation information to be processed into a target state evaluation model, and obtaining the predicted fault information of the power distribution terminal to be processed, which is output by the target state evaluation model; the target state evaluation model is obtained by training based on a plurality of pieces of sample equipment information, a plurality of pieces of sample operation information and a plurality of pieces of historical fault information; each of the historical fault information corresponds to a set of sample equipment information and sample operation information;
determining a target to-be-maintained power distribution terminal according to the predicted fault information to form a target to-be-maintained power distribution terminal list, determining a target operation and maintenance strategy of the target to-be-maintained power distribution terminal list, and controlling the target to-be-maintained power distribution terminal in the target to-be-maintained power distribution terminal list to execute the target operation and maintenance strategy, wherein the method comprises the following steps: controlling the target to-be-processed power distribution terminals in the target to-be-processed power distribution terminal list to perform self-checking self-recovery and/or software upgrading so as to enable the target to-be-processed power distribution terminals to recover normal operation;
further comprises: acquiring target to-be-processed equipment information of the target to-be-processed power distribution terminal after executing the target operation and maintenance strategy, and target to-be-processed operation information; inputting the target to-be-processed equipment information and the target to-be-processed running information into a target state evaluation model, and obtaining target prediction fault information output by the target state evaluation model; if the target prediction fault information has preset high-risk fault information, generating corresponding fault early warning information and sending the corresponding fault early warning information to a terminal of a worker, so that the worker can check the target power distribution terminal to be processed based on the fault early warning information.
2. The method according to claim 1, wherein the method further comprises:
acquiring a plurality of sample equipment information, a plurality of sample operation information and a plurality of historical fault information corresponding to a sample power distribution terminal;
inputting the sample equipment information and the sample operation information into a state evaluation model to be trained, and obtaining sample prediction fault information output by the state evaluation model to be trained;
judging whether the similarity value of the sample prediction fault information and the historical fault information corresponding to the sample equipment information and the sample operation information is smaller than a preset similarity threshold value or not;
if not, the state evaluation model to be trained is adjusted according to the similarity value, and the step of inputting the sample equipment information and the sample operation information into the state evaluation model to be trained is returned;
if yes, ending the circulation, and taking the current state evaluation model to be trained as a target state evaluation model.
3. The method according to claim 1, wherein after obtaining the to-be-processed equipment information and the to-be-processed operation information of the to-be-processed power distribution terminal from the data center, further comprises:
acquiring historical inspection information corresponding to the power distribution terminal to be processed;
Determining inspection parameters corresponding to the power distribution terminal to be processed according to the historical inspection information;
and detecting whether abnormal operation information exists in the to-be-processed operation information of the to-be-processed power distribution terminal according to the inspection parameters and a preset period, if so, generating corresponding alarm information and a target operation and maintenance strategy according to the abnormal operation information, and controlling the to-be-processed power distribution terminal to execute the target operation and maintenance strategy.
4. The method of claim 1, wherein the predicted fault information comprises a predicted fault probability;
the determining the target to-be-processed power distribution terminal to be maintained according to the predicted fault information to form a target to-be-processed power distribution terminal list comprises the following steps:
if the predicted fault probability is greater than or equal to a preset fault threshold value, determining the power distribution terminal to be processed corresponding to the predicted fault information as a target power distribution terminal to be processed;
and generating a target to-be-processed power distribution terminal list according to the to-be-processed equipment information of the target to-be-processed power distribution terminal.
5. The method according to claim 1, wherein after obtaining the predicted fault information of the power distribution terminal to be processed output by the target state evaluation model, further comprises:
Clustering the predicted fault information according to the type of the to-be-processed equipment information of the to-be-processed power distribution terminal to obtain a predicted fault information cluster corresponding to the to-be-processed equipment information;
and if the number of the same type of predictive fault information in the predictive fault information cluster is larger than a preset value, generating a corresponding operation and maintenance strategy according to the to-be-processed equipment information.
6. The method according to claim 1, wherein the obtaining the to-be-processed equipment information and the to-be-processed operation information of the to-be-processed power distribution terminal from the data center includes:
acquiring at least one of equipment type, manufacturer, model, operation time, channel type and affiliated power distribution area of the power distribution terminal to be processed from a data center, and taking the at least one of equipment type, manufacturer, model, operation time, channel type and affiliated power distribution area as the information of the equipment to be processed;
and acquiring at least one of the running state, the battery state, the communication state and the alarm information of the power distribution terminal to be processed from the data center as the running information to be processed.
7. The utility model provides a distribution terminal fortune dimension device based on cloud limit is cooperated which characterized in that is applied to high in the clouds server, the device includes:
the acquisition module is used for acquiring to-be-processed equipment information and to-be-processed running information of the to-be-processed power distribution terminal from the data center; the data center is arranged on the cloud server and is used for receiving and storing the to-be-processed equipment information and the to-be-processed running information sent by the to-be-processed power distribution terminal;
The prediction module is used for inputting the equipment information to be processed and the operation information to be processed into a target state evaluation model and obtaining the predicted fault information of the power distribution terminal to be processed, which is output by the target state evaluation model; the target state evaluation model is obtained by training based on a plurality of pieces of sample equipment information, a plurality of pieces of sample operation information and a plurality of pieces of historical fault information; each of the historical fault information corresponds to a set of sample equipment information and sample operation information;
the operation and maintenance module is used for determining a target to-be-maintained power distribution terminal according to the predicted fault information, forming a target to-be-processed power distribution terminal list, determining a target operation and maintenance strategy of the target to-be-processed power distribution terminal list, and controlling the target to-be-processed power distribution terminal in the target to-be-processed power distribution terminal list to execute the target operation and maintenance strategy, and is specifically used for: controlling the target to-be-processed power distribution terminals in the target to-be-processed power distribution terminal list to perform self-checking self-recovery and/or software upgrading so as to enable the target to-be-processed power distribution terminals to recover normal operation;
further comprises: the checking module is used for acquiring the target to-be-processed equipment information and the target to-be-processed running information of the target to-be-processed power distribution terminal after the target operation and maintenance strategy is executed; inputting the target to-be-processed equipment information and the target to-be-processed running information into a target state evaluation model, and obtaining target prediction fault information output by the target state evaluation model; if the target prediction fault information has preset high-risk fault information, generating corresponding fault early warning information and sending the corresponding fault early warning information to a terminal of a worker, so that the worker can check the target power distribution terminal to be processed based on the fault early warning information.
8. The apparatus of claim 7, wherein the apparatus further comprises: training module for:
acquiring a plurality of sample equipment information, a plurality of sample operation information and a plurality of historical fault information corresponding to a sample power distribution terminal;
inputting the sample equipment information and the sample operation information into a state evaluation model to be trained, and obtaining sample prediction fault information output by the state evaluation model to be trained;
judging whether the similarity value of the sample prediction fault information and the historical fault information corresponding to the sample equipment information and the sample operation information is smaller than a preset similarity threshold value or not;
if not, the state evaluation model to be trained is adjusted according to the similarity value, and the step of inputting the sample equipment information and the sample operation information into the state evaluation model to be trained is returned;
if yes, ending the circulation, and taking the current state evaluation model to be trained as a target state evaluation model.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the method of any one of claims 1 to 6 when executing the computer program.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any one of claims 1 to 6.
CN202110987962.0A 2021-08-26 2021-08-26 Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment Active CN113708493B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110987962.0A CN113708493B (en) 2021-08-26 2021-08-26 Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110987962.0A CN113708493B (en) 2021-08-26 2021-08-26 Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment

Publications (2)

Publication Number Publication Date
CN113708493A CN113708493A (en) 2021-11-26
CN113708493B true CN113708493B (en) 2023-07-28

Family

ID=78655125

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110987962.0A Active CN113708493B (en) 2021-08-26 2021-08-26 Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment

Country Status (1)

Country Link
CN (1) CN113708493B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114399112A (en) * 2022-01-14 2022-04-26 成都秦川物联网科技股份有限公司 User evaluation obtaining method and system for natural gas energy metering
CN114937043B (en) * 2022-07-26 2022-10-25 中国工业互联网研究院 Equipment defect detection method, device, equipment and medium based on artificial intelligence
CN115378841B (en) * 2022-08-03 2024-01-26 深圳前海环融联易信息科技服务有限公司 Method and device for detecting state of equipment accessing cloud platform, storage medium and terminal
CN116016120A (en) * 2023-01-05 2023-04-25 中国联合网络通信集团有限公司 Fault processing method, terminal device and readable storage medium
CN116109295B (en) * 2023-04-07 2023-07-25 华能济南黄台发电有限公司 Maintenance decision method based on power distribution terminal
CN117057786B (en) * 2023-10-11 2024-01-02 中电科大数据研究院有限公司 Intelligent operation and maintenance management method, system and storage medium for data center

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012249340A (en) * 2011-05-25 2012-12-13 Meidensha Corp Remote maintenance device for digital protection relay system
CN112367046A (en) * 2020-11-11 2021-02-12 兰州理工大学 Cloud edge cooperative remote operation and maintenance system suitable for distributed photovoltaic of remote areas
CN112381306A (en) * 2020-11-20 2021-02-19 广西电网有限责任公司防城港供电局 Intelligent operation and maintenance management and control platform for power distribution network
CN112527613A (en) * 2020-11-30 2021-03-19 北京航天智造科技发展有限公司 Equipment fault maintenance method and device based on cloud edge cooperation
CN112669172A (en) * 2020-12-31 2021-04-16 国电南瑞南京控制系统有限公司 Power distribution network regional autonomous rapid response method and system based on dynamic fusion of edge data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012249340A (en) * 2011-05-25 2012-12-13 Meidensha Corp Remote maintenance device for digital protection relay system
CN112367046A (en) * 2020-11-11 2021-02-12 兰州理工大学 Cloud edge cooperative remote operation and maintenance system suitable for distributed photovoltaic of remote areas
CN112381306A (en) * 2020-11-20 2021-02-19 广西电网有限责任公司防城港供电局 Intelligent operation and maintenance management and control platform for power distribution network
CN112527613A (en) * 2020-11-30 2021-03-19 北京航天智造科技发展有限公司 Equipment fault maintenance method and device based on cloud edge cooperation
CN112669172A (en) * 2020-12-31 2021-04-16 国电南瑞南京控制系统有限公司 Power distribution network regional autonomous rapid response method and system based on dynamic fusion of edge data

Also Published As

Publication number Publication date
CN113708493A (en) 2021-11-26

Similar Documents

Publication Publication Date Title
CN113708493B (en) Cloud edge cooperation-based power distribution terminal operation and maintenance method and device and computer equipment
CN111047082B (en) Early warning method and device of equipment, storage medium and electronic device
AU2019413432B2 (en) Scalable system and engine for forecasting wind turbine failure
CN113112086B (en) Intelligent production system based on edge calculation and identification analysis
CN114282434A (en) Industrial equipment health management system and method
CN114267178B (en) Intelligent operation maintenance method and device for station
CN108445410A (en) A kind of method and device of monitoring accumulator group operating status
CN116360377B (en) Data processing method for battery cell formation component capacity and distributed control system
CN116755964A (en) Fault prediction and health management system for reinforcement server
CN113992602B (en) Cable monitoring data uploading method, device, equipment and storage medium
CN117714260A (en) Remote centralized operation and maintenance method for distributed resource edge gateway under cloud edge fusion architecture
CN110427689B (en) Method for monitoring and diagnosing gas turbine unit group based on new information technology
CN111614504A (en) Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis
CN115277473A (en) Remote operation and maintenance method and device for edge gateway, computer equipment and storage medium
CN116843314A (en) Monitoring terminal operation and maintenance management method, system, equipment and storage medium
CN113570473B (en) Equipment fault monitoring method, device, computer equipment and storage medium
CN114422332B (en) Network slice control method, device, processing equipment and storage medium
CN110890988B (en) Server cluster operation monitoring system
CN117875946B (en) Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment
WO2022202324A1 (en) Abnormality detection device, abnormality detection method, and computer program
CN117972493A (en) Method and device for diagnosing faults of power exchange station equipment, electronic equipment and storage medium
CN116934302A (en) Management method and system for shared operation and maintenance of distributed photovoltaic power station
CN117853087A (en) Data analysis system of power equipment
Ke et al. Research on fault early warning technology for power middleware system
CN117831238A (en) Energy storage battery multistage safety early warning method and system based on cloud edge end cooperation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant