CN112649696A - Power grid abnormal state identification method - Google Patents
Power grid abnormal state identification method Download PDFInfo
- Publication number
- CN112649696A CN112649696A CN202011155812.5A CN202011155812A CN112649696A CN 112649696 A CN112649696 A CN 112649696A CN 202011155812 A CN202011155812 A CN 202011155812A CN 112649696 A CN112649696 A CN 112649696A
- Authority
- CN
- China
- Prior art keywords
- early warning
- detection unit
- power grid
- deviation
- determining
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000003672 processing method Methods 0.000 claims abstract description 24
- 238000012423 maintenance Methods 0.000 claims abstract description 17
- 239000003086 colorant Substances 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 11
- 238000004458 analytical method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 208000011380 COVID-19–associated multisystem inflammatory syndrome in children Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002319 photoionisation mass spectrometry Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- 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
- H02J13/00001—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 the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- 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
- H02J13/00002—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 monitoring
-
- 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
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
本发明提供了电网异常状态识别方法，属于电网运维技术领域，包括获取检测单元的运行数据，当运行数据超过预警标准时，确定运行数据相对预警标准的偏差度。根据偏差度以及检测单元所对应的权重值确定出加权偏差；根据预设标准，确定加权偏差所对应的预警等级。创建检测单元的神经网络识别模型，选取神经网络识别模型中与偏差度相关的处理方法；将处理方法结合预警等级上传至电网系统。本发明提供的电网异常状态识别方法中得到的加权偏差不仅能够反应出检测单元偏离正常状态的程度，同时能够反应出检测单元的权重程度，从而有针对性的处理，提高了处理的效率，保证了有效的运维。
The invention provides a method for identifying abnormal state of a power grid, belonging to the technical field of power grid operation and maintenance. The weighted deviation is determined according to the deviation degree and the weight value corresponding to the detection unit; the early warning level corresponding to the weighted deviation is determined according to the preset standard. Create a neural network recognition model of the detection unit, select the processing method related to the deviation in the neural network recognition model; upload the processing method combined with the warning level to the power grid system. The weighted deviation obtained in the method for identifying the abnormal state of the power grid provided by the present invention can not only reflect the degree that the detection unit deviates from the normal state, but also reflect the weight degree of the detection unit, so as to carry out targeted processing, improve the processing efficiency, and ensure effective operation and maintenance.
Description
Technical Field
The invention belongs to the technical field of power grid operation and maintenance, and particularly relates to a power grid abnormal state identification method.
Background
At present, when the abnormal state of a power grid is analyzed, the operation data of a detection unit is downloaded in a national grid system, and then the operation data is processed, so that the abnormal and fault information is analyzed from the operation data. However, due to the influence of the collecting device, the substation, the channel and other links, the deviation and the error exist between the collected measurement and the actual measurement. More importantly, because the detection units with the same rule have different importance degrees and different influence ranges in a certain area, if the downloaded operation data are processed together, the operation and maintenance capacity cannot be effectively distributed, the fault rate of the power grid is high, and the working efficiency is low.
Disclosure of Invention
The invention aims to provide a method for identifying an abnormal state of a power grid, and aims to solve the problems that operation and maintenance capabilities cannot be effectively distributed, the fault rate of the power grid is high and the working efficiency is low if downloaded operation data are processed together.
In order to achieve the purpose, the invention adopts the technical scheme that: the method for identifying the abnormal state of the power grid comprises the following steps:
acquiring operation data of a detection unit, and determining the deviation degree of the operation data relative to an early warning standard when the operation data exceeds the early warning standard;
determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit; determining an early warning grade corresponding to the weighted deviation according to a preset standard;
creating a neural network recognition model of the detection unit, and selecting a processing method related to the deviation degree in the neural network recognition model; and uploading the processing method and the early warning grade to an electric network system.
As another embodiment of the present application, the operation data is one or more of transformer active imbalance, bus active imbalance, line active-dead data, line active-jump data, and transformer active-dead data.
As another embodiment of the application, the detection unit comprises an electric meter, an electric meter box, a branch box and a transformer.
As another embodiment of the present application, the creating a neural network recognition model of the detection unit includes:
determining the neural network recognition model of the detection unit by taking abnormal operation data of the detection unit as a training sample;
and picking up the relevant processing method from the neural network identification model according to the operation data.
As another embodiment of the present application, when the operation data exceeds an early warning standard, the method further includes:
and when the operation data exceeds a normal standard and is lower than the early warning standard, uploading the detection unit to an operation and maintenance system.
As another embodiment of the present application, the determining the degree of deviation of the operation data from the warning criterion includes:
determining a loop ratio of the operational data relative to the pre-warning criteria.
As another embodiment of the present application, the determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit includes:
and multiplying the weight value by the deviation degree, and taking the multiplied result as the weighted deviation.
As another embodiment of the present application, the determining, according to a preset standard, an early warning level corresponding to the weighted deviation includes:
setting a plurality of early warning intervals, and carrying out one-to-one correspondence between the early warning intervals and the early warning grades;
and judging the early warning interval to which the weighted deviation belongs, and determining the early warning grade corresponding to the weighted deviation.
As another embodiment of the present application, after the determining the early warning level corresponding to the weighted deviation, the method further includes:
and carrying out one-to-one correspondence on the early warning intervals and different early warning colors, and calibrating the early warning colors on an Otto map.
As another embodiment of the present application, after the uploading the processing method in combination with the early warning level to the power grid system, the method further includes:
and recording the times of exceeding the early warning standard by the detection unit in a certain time period, and making a key supervision table.
The method for identifying the abnormal state of the power grid has the advantages that: compared with the prior art, the method for identifying the abnormal state of the power grid firstly acquires the operation data of the detection unit, and determines the deviation degree of the operation data relative to the early warning standard when the operation data exceeds the early warning standard. Determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit; and determining the early warning grade corresponding to the weighted deviation according to a preset standard. Creating a neural network recognition model of the detection unit, and selecting a processing method related to the deviation degree in the neural network recognition model; and uploading the processing method and the early warning grade to an electric network system.
When the device is used, firstly, the operating data and the early warning standard of the detection unit are analyzed to determine the degree of deviation of the operating data and the early warning standard, and after the degree of deviation is determined, the weighted deviation is obtained according to the weight value and the obtained degree of deviation. And determining the early warning interval where the weighted deviation is located, thereby determining the early warning grade. And uploading the early warning grade and the relevant processing method in the determined neural network identification model to the power grid system.
In the application, the operation data of the detection unit is weighted, the obtained weighted deviation can reflect the degree of the detection unit deviating from the normal state, and the weight degree of the detection unit can be reflected, so that the targeted processing is realized, the processing efficiency is improved, and the effective operation and maintenance are ensured.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart of a method for identifying an abnormal state of a power grid according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, a method for identifying an abnormal state of a power grid according to the present invention will now be described. The power grid abnormal state identification method comprises the steps of obtaining operation data of a detection unit, and determining the degree of deviation of the operation data relative to an early warning standard when the operation data exceeds the early warning standard.
Determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit; and determining the early warning grade corresponding to the weighted deviation according to a preset standard.
Establishing a neural network identification model of the detection unit, and selecting a processing method related to the deviation degree in the neural network identification model; and uploading the processing method and the early warning grade to the power grid system.
The method for identifying the abnormal state of the power grid has the advantages that: compared with the prior art, the method for identifying the abnormal state of the power grid firstly acquires the operation data of the detection unit, and determines the deviation degree of the operation data relative to the early warning standard when the operation data exceeds the early warning standard. Determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit; and determining the early warning grade corresponding to the weighted deviation according to a preset standard. Establishing a neural network identification model of the detection unit, and selecting a processing method related to the deviation degree in the neural network identification model; and uploading the processing method and the early warning grade to the power grid system.
When the device is used, firstly, the operating data and the early warning standard of the detection unit are analyzed to determine the degree of deviation of the operating data and the early warning standard, and after the degree of deviation is determined, the weighted deviation is obtained according to the weight value and the obtained degree of deviation. And determining the early warning interval where the weighted deviation is located, thereby determining the early warning grade. And uploading the early warning grade and the relevant processing method in the determined neural network identification model to the power grid system.
In the application, the operation data of the detection unit is weighted, the obtained weighted deviation can reflect the degree of the detection unit deviating from the normal state, and the weight degree of the detection unit can be reflected, so that the targeted processing is realized, the processing efficiency is improved, and the effective operation and maintenance are ensured.
As a specific implementation manner of the method for identifying the abnormal state of the power grid, the operation data is one or more of transformer active imbalance, bus active imbalance, line active and dead data, and transformer active and dead data.
Before determining the weighted deviation, the weights of different detection units need to be determined, and the weights are set to avoid the detection units from being treated equally, so that the final grid operation effect is not ideal. And determining a key detection unit for priority processing by setting different weight values. An example is that the weighting value is higher for the detection unit that is more critical and lower for the non-critical device.
As a specific implementation manner of the method for identifying the abnormal state of the power grid, the detection unit includes an electric meter, an electric meter box, a branch box and a transformer.
In the present application, the range of the detecting unit includes single family, cell, street and city, etc., and the detecting unit can be all transformers in a specific area.
The transformer is connected with a plurality of branch boxes, and the branch boxes are in parallel relation; the third level is an electric meter box unit, each branch box can generate ABC three phases, and each phase can be connected with a plurality of electric meter box units; the fourth level is the ammeter, can connect a plurality of ammeters under each ammeter case unit.
As a specific implementation manner of the method for identifying an abnormal state of a power grid provided by the present invention, when the operation data exceeds the early warning standard, the method includes:
and when the operation data exceeds the normal standard and is lower than the early warning standard, uploading the detection unit to the operation and maintenance system.
In the application, the detection unit can generate operation data in the daily operation process, and the specific state of the detection unit is determined by analyzing the operation data in the abnormal recognition process. In order to improve the operation and maintenance efficiency, the division of labor is clear, and the working flow is shortened.
The method comprises the steps of firstly setting a normal standard and an early warning standard, and when a detection unit is higher than the normal standard but lower than the early warning standard, because the detection unit does not reach the early warning standard, the degree of failure is low, at the moment, a related processing method does not need to be determined in a neural network identification model, the related processing method does not need to be uploaded to an electric network system, the operation and maintenance system only needs to be uploaded, and related personnel can check and patrol the operation and maintenance system.
As a specific implementation manner of the method for identifying an abnormal state of a power grid provided by the present invention, determining a degree of deviation of the operation data with respect to the early warning standard includes:
a loop ratio of the operational data to the pre-warning criteria is determined.
In the present application, the types of the parameters in the detection unit need to be determined in advance. In order to visually calibrate the fault occurrence degree and facilitate accurate and visual analysis, the operation data is compared with the early warning standard, and the loop ratio of the operation data to the early warning standard is calculated. The degree of deviation of the operation data of the detection unit from the early warning standard can be accurately reflected by setting the ring ratio, so that different deviation degrees can be analyzed from separate numbers. By setting the deviation degree, the degree of the parameter faults of various types of the detection unit can be reflected, so that different types of parameters are changed into the same reference standard, and the analysis is facilitated.
The embodiment is that when the temperature and the power of the detection unit exceed the early warning standard, the loop ratio of the temperature and the loop ratio of the power of the detection unit are respectively determined, and because the loop ratio is a specific numerical value, the degree of temperature and power failure occurrence can be accurately reflected through the numerical value, and the change conditions of the temperature and the power are represented by using the numerical value, so that the analysis and the processing are convenient.
As a specific implementation manner of the method for identifying an abnormal state of a power grid, determining a weighted deviation according to the deviation degree and a weight value corresponding to the detection unit includes:
and multiplying the weight value by the deviation degree, and taking the multiplication result as the weighted deviation.
In the application, a plurality of identical devices are inevitably installed in a certain area range, but the importance degrees of the devices are different, particularly the devices which are positioned at key positions and have influences on other devices, the quality of the devices directly influences the normal operation of the whole system, and the weight value of the devices is emphasized to be improved.
For the equipment which is in a remote area or does not have influence on other equipment, the weighted value of the equipment is properly reduced, on one hand, the maintenance capability can be reasonably distributed, and on the other hand, the normal operation of the whole system framework can be ensured.
The weighted value is multiplied by the deviation degree to obtain the weighted deviation, and the numerical value which reflects the fault condition of the detection unit can be obtained according to the final numerical value of the weighted deviation, so that the larger the weighted deviation is, the larger the weighted value of the detection unit is proved to be in a certain aspect, and the higher the deviation degree from the early warning standard is. Therefore, the detection unit of the fault needing to be solved immediately can be determined according to the weighted deviation.
As a specific implementation manner of the method for identifying an abnormal state of a power grid, according to a preset standard, determining an early warning level corresponding to a weighted deviation includes:
and setting a plurality of early warning intervals, and carrying out one-to-one correspondence on the early warning intervals and the early warning grades.
And judging the early warning interval to which the weighted deviation belongs, and determining the early warning grade corresponding to the weighted deviation.
In the application, a plurality of early warning intervals are set and are respectively used for corresponding to a plurality of early warning levels, after the weighted deviation is calculated, the early warning interval to which the weighted deviation belongs is judged according to the weighted deviation, so that the early warning level corresponding to the detection unit is determined, and the early warning condition of the detection unit is judged according to the early warning level.
In the present application, the detection unit is a unit of reference analysis, and the minimum is an ammeter. Namely, the operation data of the electric meter at a certain moment is determined by acquiring the power grid basic data, the load curve, the overload information and the like of the electric meter.
Some of the data mentioned above needs to be uploaded into the system by each department through the system. The data related to the detection unit can also be retrieved through the network by taking the detection unit as a reference standard. Such as a power consumption information acquisition system of a marketing specialty, a PIMS system of a transport inspection specialty, a D5000 system of a regulation and control system and the like. At present, the systems mainly rely on power grid basic data provided by operation and inspection professions, load curves provided by regulation and control professions, heavy overload information monitored by provincial and municipal companies and other data, all of which are in a table form, and then professional personnel analyze and summarize the data.
To further increase the speed of integration of information, application to database analysis techniques is therefore required. When each sub-business system is developed, the problem of data combination is not considered, so that the adopted database type, the data table structure and the data type are not uniformly planned. Therefore, in the process of processing and integrating, the data types of the grid service data in each sub-service system need to be converted into a uniform data type.
The power grid operation data records power utilization data of each area, so that the data volume is huge. The traditional relational database can not meet the application requirement when processing the operation efficiency of huge data volume, so that the operation data of the power grid is stored in the distributed file system, the calling speed is increased, and the processing efficiency is improved. The power grid data are mostly stored in respective relational databases in the form of relational data tables, and are extracted from each sub-service system through a data warehouse technology (ETL), preprocessed and pre-stored in the relational databases. And then, extracting data from the relational database by taking a reference as a unit through a data phase transfer tool Sqoop, and storing the data into the distributed file system HDFS.
By extracting and preprocessing data, storing and calculating data, analyzing and mining data and visually displaying data, the huge data volume is quickly and effectively processed, and data support is provided for subsequent changes of load conditions.
Traditionally, effective data cannot be mastered by a power grid planning professional, all basic data are transmitted through a table and are easily influenced by human factors, data factors and the like, the data obtained by the planning professional are inaccurate, analysis is not in place, problems are not accurate, and planning direction deviation is caused finally.
The development direction of the power grid load in the region and the power consumption requirement of users are required to be totally dependent on manpower to find out professional inquiry, basic data fusion and analysis are lacked, problems exist in the aspect of big data application, and power grid planning and power grid construction are always in a passive state.
And by extracting and analyzing the data, an analysis model taking the reference as a standard can be formed, so that analysis files of a plurality of independent reference in different time periods are formed, the pertinence is high, and the result referential performance is guaranteed.
As a specific implementation manner of the method for identifying an abnormal state of a power grid, after determining an early warning level corresponding to a weighted deviation, the method further includes:
and carrying out one-to-one correspondence on the plurality of early warning intervals and different early warning colors, and calibrating the early warning colors on the Olympic map.
In this application, at first need determine different early warning intervals, after determining the weighted deviation, need at first determine that this weighted deviation falls into which early warning interval according to the early warning interval of difference to different early warning intervals correspond different early warning grades. The higher the early warning level is, the larger the corresponding weighted deviation is. Different early warning levels are determined, so that subsequent pertinence analysis is facilitated.
The method and the system reduce the tedious work of collecting a large amount of data, searching data, analyzing data and the like for planning professionals. By utilizing multi-professional data, the weak points of the power grid are analyzed, a problem pre-judging mechanism is established, load correction is carried out on the equipment to be heavily overloaded in advance, and overload operation of the equipment is avoided. The method comprises the steps of determining the planning direction of a regional power grid, establishing a power grid planning technical support, improving the intelligent planning foundation of the power grid, improving the power supply capacity of the power grid, predicting a load increase point, conspiring to plan the power grid layout in advance, and achieving intelligent planning and accurate investment.
In this application, a bus bar is explained first, and the bus bar needs to be constructed on the periphery of a load center. Generally, the load center refers to a city, especially a large city, which has large power demand and heavy load. By adopting the partition network construction, the average electrical distance between the transformer stations can be increased, and the aims of controlling short-circuit current, weakening the influence between direct currents and the like are fulfilled. Meanwhile, by utilizing a bus network, each subarea is connected to the bus through a plurality of power supply channels, and each subarea has no direct alternating current contact in the load center, so that the wiring mode among the subareas is changed, and the purposes of subarea power supply, scattered direct current distribution and short-circuit current and accident range reduction are achieved. The mutual supporting and electric mutual agent capacity between the subareas is maintained through bus connection.
When the buses are constructed in different areas, all load centers of the local area are fully considered to be partitioned around the load centers, and the buses are constructed. Due to different partitions, the bus structures constructed in the same region may be different. The periphery of the load center generally refers to a predetermined distance from the load center point, and the specific distance meeting the peripheral standard also considers meeting the electrical requirements of the center, and the like.
As a specific implementation manner of the method for identifying the abnormal state of the power grid, after the processing method is uploaded to the power grid system in combination with the early warning level, the method further comprises the following steps:
and recording the times of exceeding the early warning standard by the detection unit in a certain time period, and making a key supervision table.
In this application, in order to maintain the detecting element that easily breaks down in a targeted manner, therefore in the actual operation and maintenance process, a detection time period needs to be set, and after the operating data of a certain detecting element exceeds the early warning standard, the recording is once, so that the star becomes a fault times table, the detecting element that breaks down more is maintained in a targeted manner, the normal operation of the system can be ensured, and the length of the time period is determined according to the number of the detecting elements.
As a specific implementation manner of the method for identifying an abnormal state of a power grid provided by the present invention, creating a neural network identification model of a detection unit includes:
taking abnormal operation data of the detection unit as a training sample, and determining a neural network identification model of the detection unit;
and picking up relevant processing methods from the neural network recognition model according to the operation data.
According to the method and the device, a neural network identification model needs to be created, when similar faults occur again in the operation data of the detection unit, relevant processing methods can be extracted as soon as possible through the model, after the operation data and the early warning grades are uploaded to a power grid system, operation and maintenance personnel can determine the fault degree of the detection unit according to the early warning grades, and timely and pertinently maintenance is carried out through the processing methods provided by the neural network identification model, so that the working efficiency is improved.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The method for identifying the abnormal state of the power grid is characterized by comprising the following steps:
acquiring operation data of a detection unit, and determining the deviation degree of the operation data relative to an early warning standard when the operation data exceeds the early warning standard;
determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit; determining an early warning grade corresponding to the weighted deviation according to a preset standard;
creating a neural network recognition model of the detection unit, and selecting a processing method related to the deviation degree in the neural network recognition model; and uploading the processing method and the early warning grade to an electric network system.
2. The method according to claim 1, wherein the operation data is one or more of transformer active imbalance, bus active imbalance, line dead data, line active jump data, and transformer dead data.
3. The grid abnormal state identification method according to claim 1, wherein the detection unit includes an electricity meter, an electricity meter box, a branch box, and a transformer.
4. The grid abnormal state recognition method according to claim 1, wherein the creating of the neural network recognition model of the detection unit comprises:
determining the neural network recognition model of the detection unit by taking abnormal operation data of the detection unit as a training sample;
and picking up the relevant processing method from the neural network identification model according to the operation data.
5. The method for identifying an abnormal state of a power grid according to claim 1, wherein when the operation data exceeds an early warning standard, the method comprises:
and when the operation data exceeds a normal standard and is lower than the early warning standard, uploading the detection unit to an operation and maintenance system.
6. The method for identifying abnormal states of a power grid according to claim 1, wherein the determining the degree of deviation of the operation data from the early warning standard comprises:
determining a loop ratio of the operational data relative to the pre-warning criteria.
7. The method for identifying an abnormal state of a power grid according to claim 1, wherein the determining a weighted deviation according to the deviation degree and the weight value corresponding to the detection unit comprises:
and multiplying the weight value by the deviation degree, and taking the multiplied result as the weighted deviation.
8. The method for identifying abnormal states of a power grid according to claim 1, wherein the step of determining the early warning level corresponding to the weighted deviation according to a preset standard comprises the steps of:
setting a plurality of early warning intervals, and carrying out one-to-one correspondence between the early warning intervals and the early warning grades;
and judging the early warning interval to which the weighted deviation belongs, and determining the early warning grade corresponding to the weighted deviation.
9. The method for identifying abnormal states of a power grid according to claim 8, wherein after determining the early warning level corresponding to the weighted deviation, the method further comprises:
and carrying out one-to-one correspondence on the early warning intervals and different early warning colors, and calibrating the early warning colors on an Otto map.
10. The method for identifying abnormal states of a power grid according to claim 1, wherein after the processing method is uploaded to a power grid system in combination with the early warning level, the method further comprises the following steps:
and recording the times of exceeding the early warning standard by the detection unit in a certain time period, and making a key supervision table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011155812.5A CN112649696A (en) | 2020-10-26 | 2020-10-26 | Power grid abnormal state identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011155812.5A CN112649696A (en) | 2020-10-26 | 2020-10-26 | Power grid abnormal state identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112649696A true CN112649696A (en) | 2021-04-13 |
Family
ID=75347008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011155812.5A Pending CN112649696A (en) | 2020-10-26 | 2020-10-26 | Power grid abnormal state identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112649696A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114865794A (en) * | 2022-06-01 | 2022-08-05 | 南京瑞普思科技有限公司 | Visual analysis system for configuration files of intelligent substation |
| CN115833400A (en) * | 2023-02-07 | 2023-03-21 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104103019A (en) * | 2014-06-20 | 2014-10-15 | 清华大学 | Operation risk assessment method and assessment system of power distribution network containing distributed power supply |
| CN104269844A (en) * | 2014-09-10 | 2015-01-07 | 国家电网公司 | Power distribution network state estimation abnormality recognition method and device |
| CN104795894A (en) * | 2015-03-28 | 2015-07-22 | 合肥天海电气技术有限公司 | Fault information intelligent processing system of large power grid |
| CN105160604A (en) * | 2015-09-29 | 2015-12-16 | 广东电网有限责任公司电力科学研究院 | Power grid equipment state pre-warning platform based on abnormal operation condition identification |
| CN106529696A (en) * | 2016-09-22 | 2017-03-22 | 国网山西省电力公司晋城供电公司 | Early warning method and early warning apparatus for equipment in power grid |
| CN206312210U (en) * | 2016-08-11 | 2017-07-07 | 中国南方电网有限责任公司电网技术研究中心 | State evaluation system of power distribution network equipment |
| CN107202952A (en) * | 2017-07-06 | 2017-09-26 | 北京信息科技大学 | Rotary kiln method for diagnosing faults, fault diagnosis GUI and system based on wavelet neural network |
| CN108108839A (en) * | 2017-12-18 | 2018-06-01 | 华北电力大学 | Grid information system equipment state method for early warning based on reverse Fuzzy Level Analytic Approach |
| US20180180657A1 (en) * | 2016-12-23 | 2018-06-28 | Sanil Electric Co., Ltd. | Transformer condition-based risk management system and method |
| CN108471111A (en) * | 2018-03-19 | 2018-08-31 | 深圳供电局有限公司 | Power grid operation risk assessment method for bus fault |
| CN109471205A (en) * | 2018-10-18 | 2019-03-15 | 国网山东省电力公司应急管理中心 | A monitoring and early warning method based on gridded meteorological data in power grid operation |
| CN109474067A (en) * | 2018-08-14 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | An auxiliary decision-making method for power grid dispatching fault handling |
| CN109740884A (en) * | 2018-12-19 | 2019-05-10 | 国家电网公司西北分部 | Grid risk early warning method, system and electronic device |
| CN110929915A (en) * | 2019-10-14 | 2020-03-27 | 武汉烽火众智数字技术有限责任公司 | Intelligent early warning model establishing method and device for alarm situation occurrence area and storage medium |
-
2020
- 2020-10-26 CN CN202011155812.5A patent/CN112649696A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104103019A (en) * | 2014-06-20 | 2014-10-15 | 清华大学 | Operation risk assessment method and assessment system of power distribution network containing distributed power supply |
| CN104269844A (en) * | 2014-09-10 | 2015-01-07 | 国家电网公司 | Power distribution network state estimation abnormality recognition method and device |
| CN104795894A (en) * | 2015-03-28 | 2015-07-22 | 合肥天海电气技术有限公司 | Fault information intelligent processing system of large power grid |
| CN105160604A (en) * | 2015-09-29 | 2015-12-16 | 广东电网有限责任公司电力科学研究院 | Power grid equipment state pre-warning platform based on abnormal operation condition identification |
| CN206312210U (en) * | 2016-08-11 | 2017-07-07 | 中国南方电网有限责任公司电网技术研究中心 | State evaluation system of power distribution network equipment |
| CN106529696A (en) * | 2016-09-22 | 2017-03-22 | 国网山西省电力公司晋城供电公司 | Early warning method and early warning apparatus for equipment in power grid |
| US20180180657A1 (en) * | 2016-12-23 | 2018-06-28 | Sanil Electric Co., Ltd. | Transformer condition-based risk management system and method |
| CN107202952A (en) * | 2017-07-06 | 2017-09-26 | 北京信息科技大学 | Rotary kiln method for diagnosing faults, fault diagnosis GUI and system based on wavelet neural network |
| CN108108839A (en) * | 2017-12-18 | 2018-06-01 | 华北电力大学 | Grid information system equipment state method for early warning based on reverse Fuzzy Level Analytic Approach |
| CN108471111A (en) * | 2018-03-19 | 2018-08-31 | 深圳供电局有限公司 | Power grid operation risk assessment method for bus fault |
| CN109474067A (en) * | 2018-08-14 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | An auxiliary decision-making method for power grid dispatching fault handling |
| CN109471205A (en) * | 2018-10-18 | 2019-03-15 | 国网山东省电力公司应急管理中心 | A monitoring and early warning method based on gridded meteorological data in power grid operation |
| CN109740884A (en) * | 2018-12-19 | 2019-05-10 | 国家电网公司西北分部 | Grid risk early warning method, system and electronic device |
| CN110929915A (en) * | 2019-10-14 | 2020-03-27 | 武汉烽火众智数字技术有限责任公司 | Intelligent early warning model establishing method and device for alarm situation occurrence area and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陈碧云: "云模型在变电站作业风险感知中的应用", 《电力系统及其自动化学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114865794A (en) * | 2022-06-01 | 2022-08-05 | 南京瑞普思科技有限公司 | Visual analysis system for configuration files of intelligent substation |
| CN115833400A (en) * | 2023-02-07 | 2023-03-21 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
| CN115833400B (en) * | 2023-02-07 | 2023-04-18 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111177101B (en) | Multi-dimensional visualization platform for power distribution network based on big data architecture | |
| CN109816161B (en) | A distribution network operation auxiliary decision analysis system and its application method | |
| CN105245185B (en) | A kind of area distribution formula photovoltaic fault diagnosis system and method for accessing power distribution network | |
| CN112131441B (en) | A method and system for quickly identifying abnormal behavior of electricity consumption | |
| CN109460833B (en) | Method and system for processing equipment data and repair work order data of distribution network fault | |
| CN110071579A (en) | Power grid power supply based on ubiquitous electric power Internet of Things ensures and intelligent managing and control system | |
| CN106872856B (en) | Active repair system and method for distribution network faults based on multiple fault acquisition | |
| CN110928866A (en) | Method and system for line topology verification based on big data analysis of power outage information | |
| JP2009089594A (en) | Spatio-temporal load analysis system for power equipment using meter reading data and load calculation method | |
| CN107147215A (en) | Distribution network fault location system and method combined with line overload data analysis | |
| CN106529708A (en) | Distribution network planning system based on cloud platform | |
| CN110148938A (en) | A kind of method of holographic perception and layering line loss calculation | |
| CN110675018B (en) | Line loss anomaly analysis and closed-loop management method based on expert rules | |
| CN118884117A (en) | A method and system for identifying power grid line faults | |
| CN116596512B (en) | A method and system for enhancing power operation and maintenance safety based on information system | |
| CN104851054A (en) | Equipment maintenance method in 10kV voltage substation operation | |
| CN116522746A (en) | Power distribution hosting method for high-energy-consumption enterprises | |
| CN112649696A (en) | Power grid abnormal state identification method | |
| CN119209910A (en) | Low voltage distribution substation area topology identification method and system based on cluster analysis and graph theory | |
| CN104834305A (en) | Distribution network automated terminal telemetering abnormity analyzing system and method based on DMS system | |
| CN119402363A (en) | An Internet of Things gateway and an operation method thereof | |
| CN115833387A (en) | Automatic state inspection method for energy storage power station | |
| CN118446528B (en) | A system and device for power safety evaluation | |
| CN114168662A (en) | A method and system for sorting out and analyzing distribution network problems based on multiple data sources | |
| CN112053086A (en) | Working method of operation diagnosis system based on big data power grid |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210413 |
|
| RJ01 | Rejection of invention patent application after publication |