CN113036917B - Power distribution network monitoring information monitoring system and method based on machine learning - Google Patents
Power distribution network monitoring information monitoring system and method based on machine learning Download PDFInfo
- Publication number
- CN113036917B CN113036917B CN202110250427.7A CN202110250427A CN113036917B CN 113036917 B CN113036917 B CN 113036917B CN 202110250427 A CN202110250427 A CN 202110250427A CN 113036917 B CN113036917 B CN 113036917B
- Authority
- CN
- China
- Prior art keywords
- monitoring information
- power distribution
- distribution network
- data
- network monitoring
- 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
Links
Images
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
- H02J13/00002—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
-
- 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
Abstract
The invention provides a power distribution network monitoring information monitoring system and method based on machine learning, wherein the monitoring method specifically comprises the following steps: the method comprises the steps of obtaining big data of a power grid, establishing a database, determining an analysis time period, obtaining effective monitoring information data and effective event information data, constructing a power distribution network monitoring information analysis rule base, learning by a power distribution network monitoring information analysis machine according to the power distribution network monitoring information analysis rule base, and carrying out supervision work through the learned power distribution network monitoring information analysis machine. The monitoring system comprises an information acquisition module, an information processing module, a machine learning module and a power distribution network monitoring information analysis machine, wherein the information acquisition module is connected with the information processing module, and the information processing module and the power distribution network monitoring information analysis machine are both connected with the machine learning module. The invention utilizes the actual data to train and learn the power distribution network monitoring information analysis machine, thereby replacing manual monitoring, reducing the workload of monitoring personnel and simultaneously improving the monitoring efficiency and the monitoring accuracy.
Description
Technical Field
The invention relates to the technical field of power distribution network monitoring, in particular to a power distribution network monitoring information monitoring system and method based on machine learning.
Background
In the process of monitoring the power distribution network, the received monitoring information amount is very large, and the monitoring mode adopted at present still mainly adopts manual monitoring, so that the problems of slow process and low efficiency exist in the processing and analysis of the monitoring information of the power distribution network. Especially, when the power distribution network has serious multiple faults, a large amount of power distribution network monitoring information can be instantly upwelled, and the traditional manual monitoring mode is difficult to timely process the large amount of power distribution network monitoring information. Therefore, the intellectualization of power distribution network monitoring needs to be realized, but the artificial intelligence based on various learning-type heuristic algorithms used at present is only professional weak artificial intelligence for realizing specific functions in specific scenes, and cannot adapt to variable power distribution network environments. The weak artificial intelligence can not realize the intelligent monitoring and control of the power distribution network, and the workload of a monitor is still heavy in the power distribution network monitoring work.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a power distribution network monitoring information monitoring system and method based on machine learning, so as to solve the problems of weak monitoring information processing capability and low processing efficiency of the existing power distribution network monitoring technology.
The purpose of the invention is realized by the following technical scheme:
a power distribution network monitoring information monitoring method based on machine learning comprises the following steps:
acquiring power grid big data, and establishing a database based on the power grid big data, wherein the power grid big data comprises monitoring information and event information;
determining an analysis time period, reading historical monitoring information and event information in the analysis time period in a database, and performing data extraction on the historical monitoring information and the event information to obtain effective monitoring information data and effective event information data, wherein the effective monitoring information data and the effective event information data comprise data related to power distribution network monitoring information abnormity when the power distribution network monitoring information is abnormal;
analyzing the effective monitoring information data and constructing an event library, constructing a historical document according to the effective event information data, and constructing a power distribution network monitoring information analysis rule library according to the event library and the historical document;
and step four, the power distribution network monitoring information analysis machine learns according to the power distribution network monitoring information analysis rule base, all remote signaling data and remote measuring data in the power distribution network are monitored and checked through the learned power distribution network monitoring information analysis machine, and the monitoring and checking results of the power distribution network monitoring information analysis machine are displayed through the display module.
The monitoring information analysis rule base of the power distribution network is constructed through the monitoring information and the time information of the power distribution network, data extraction is carried out on the monitoring information and the time information before construction, the monitoring information and the time information are simplified, the fact that data used when a follow-up power distribution network monitoring information analysis machine conducts training and learning is guaranteed to be in line with reality, the power distribution network monitoring information analysis machine after training and learning can monitor the power distribution network, and monitoring workload of monitoring personnel is greatly reduced. And the monitoring disc results are displayed through the display module, so that monitoring personnel can visually acquire the monitoring disc results, and the event processing efficiency is improved.
Furthermore, when data extraction is performed on the historical monitoring information and the event information in the second step, the extracted historical monitoring information data and the extracted event information data are also screened, and data except valid data in the historical monitoring information data and the event information data are filtered.
The irrelevant data is filtered, the data for establishing the power distribution network monitoring information analysis rule base are all effective data, and the accuracy of a training learning result can be guaranteed when the power distribution network monitoring information analysis machine is subsequently trained and learned.
Furthermore, when the power distribution network monitoring information analysis machine learns in the fourth step, learning grade division is further carried out on effective monitoring information data and effective event information data in the analysis rule base, correlation coefficients between various types of data in the effective monitoring information data and the effective event information data and power distribution network anomalies are calculated firstly, the correlation degree between the data with larger correlation coefficient and the power distribution network anomalies is higher, the grade number of the learning grade is determined, the correlation coefficient threshold range corresponding to each learning grade is determined according to the grade number of the learning grade and the range of the correlation coefficient, the correlation coefficients of all data are screened according to the correlation coefficient threshold range of each learning grade, the learning grade corresponding to various types of data is divided, and the learning grade is higher when the correlation coefficient is larger; when the power distribution network monitoring information analysis machine is trained and learned, the power distribution network monitoring information analysis machine is trained by adopting data of the highest learning grade, and then the power distribution network monitoring information analysis machine is trained from high to low in sequence according to the high and low sequence of the learning grade until the monitoring result of the trained power distribution network monitoring information analysis machine is the same as the actual monitoring information and the event information.
The method comprises the steps of carrying out learning grade division on effective monitoring information data and effective event message data, calculating correlation coefficients between various data conducted in the effective monitoring information data and the effective event message data and power distribution network monitoring information abnormity by taking the degree of correlation with the power distribution network monitoring information abnormity as a grade division basis, firstly considering data with high learning grade during learning after the learning grade division is carried out, improving learning efficiency, not needing to train and learn all data, stopping training as long as the requirement of learning completion is met, reducing training calculated amount and improving training and learning efficiency.
Further, after filtering invalid data in the historical monitoring information data and the event information data, unifying data formats of the historical monitoring information data and the event information data, and obtaining effective monitoring information data and effective event information data after unifying the data formats.
After the data formats are unified, the calculation amount can be reduced when the power distribution network monitoring information analysis machine is used for learning, and the training and learning time of the power distribution network monitoring information analysis machine is saved.
Further, the process of learning by the power distribution network monitoring information analysis machine according to the intelligent analysis rule base specifically comprises the following steps:
1.1, formulating a learning path and a learning content range of a power distribution network monitoring information analysis machine, installing related equipment according to the formulated range and setting related authority of the equipment;
1.2, importing related data to a power distribution network monitoring information analysis machine through equipment, and associating the power distribution network monitoring information analysis machine with a power distribution network monitoring information analysis rule base;
1.3, training the power distribution network monitoring information analysis machine by importing the relevant data in the power distribution network monitoring information analysis machine and a power distribution network monitoring information analysis rule base, and until the monitoring result of the power distribution network monitoring information analysis machine on the remote signaling data and the remote measuring data is the same as the actual monitoring information and the event information.
The learning path and the learning content range of the power distribution network monitoring information analysis machine are formulated, and the training and learning efficiency can be effectively improved.
Further, the power distribution network monitoring information monitoring method based on machine learning further comprises a fifth step, specifically: and detecting and analyzing the monitoring result of the power distribution network monitoring information analysis machine, reconstructing the power distribution network monitoring information analysis rule base when the monitoring result is different from the actual monitoring information and event information, and re-learning the power distribution network monitoring information analysis machine until the monitoring result is the same as the actual monitoring information and event information.
When the monitoring result is inconsistent with the actual result, the power distribution network monitoring information analysis rule base is reconstructed, and the power distribution network monitoring information analysis machine is retrained and learned, so that the monitoring result of the power distribution network monitoring information analysis machine can always meet the actual result. And the analysis of the power distribution network monitoring information is more accurate in the continuous training and learning of the power distribution network monitoring information analysis machine.
Further, in the first step, the grid big data is obtained through a network computing technology, and the network computing technology comprises parallel computing, cloud computing and artificial intelligence.
The network computing technology is utilized to obtain the big data of the power grid, a data base is provided for analyzing the monitoring information of the power distribution network, and the analysis result is guaranteed to be in line with the reality.
And further, labeling the effective monitoring information data and the effective event information data in the second step, associating the effective monitoring information data with the effective event information data related to the effective monitoring information data, and displaying the information data corresponding to the label and the information related to the information data simultaneously when the effective monitoring information data or the effective event information data is read through the label.
The monitoring object of the power distribution network monitoring information analysis machine is the abnormal condition of the power distribution network monitoring information, when the abnormity occurs, in order to rapidly check the abnormal reason so as to determine the maintenance scheme, the monitoring information and the event information when the abnormity occurs need to be called, so that the effective monitoring information data and the effective event information data are labeled, and the related information data are correlated with each other, the related data can be rapidly looked up only by inquiring the labeled data, and the abnormal occurrence reason is timely and rapidly determined according to the related data, and the related processing scheme is formulated.
Further, the power distribution network monitoring information monitoring system based on machine learning comprises an information acquisition module, an information processing module, a machine learning module and a power distribution network monitoring information analysis machine; the information acquisition module is connected with the information processing module and is used for acquiring the big data of the power grid; the information processing module is used for processing the big data of the power grid and constructing a power distribution network monitoring information analysis rule base; the information processing module and the power distribution network monitoring information analysis machine are both connected with the machine learning module, the machine learning module learns the power distribution network monitoring information analysis machine according to a power distribution network monitoring information analysis rule base established by the information processing module, and the power distribution network monitoring information analysis machine is used for monitoring all remote signaling data and remote measuring data in the power distribution network.
Further, the power distribution network monitoring information monitoring system based on machine learning further comprises a display module, the display module is connected with the power distribution network monitoring information analysis machine, and the display module is used for displaying a monitoring result of the power distribution network monitoring information analysis machine.
The supervision result of the power distribution network monitoring information analysis machine is directly displayed in the display module, the supervision result can be visually obtained by the monitoring personnel, the workload of the monitoring personnel is saved, and the monitoring efficiency of the power distribution network is further improved.
The invention has the beneficial effects that:
the analysis of the real-time monitoring information is realized through the power distribution network monitoring information analysis rule base, and the power distribution network monitoring information analysis rule base provides data support for the learning of the power distribution network monitoring information analysis machine, so that the analysis accuracy of the power distribution network monitoring information analysis machine is ensured. If the monitoring information is abnormal, the power distribution network monitoring information analysis machine needs to be learned again, so that the power distribution network monitoring information analysis machine can be trained and learned continuously, and the accuracy of the power distribution network monitoring information analysis machine in analyzing the monitoring information is improved continuously. And the power distribution network monitoring information analysis machine monitors all remote communication data and remote measurement data in the power distribution network in real time, and displays the monitoring result in real time, so that the monitoring pressure of manual monitoring can be effectively reduced, and the analysis efficiency is further improved.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a flow chart of a training and learning process of a monitoring information analyzing machine for a power distribution network according to the present invention;
FIG. 3 is a schematic diagram of an embodiment of the present invention;
wherein: 1. the system comprises an information acquisition module 2, an information processing module 3, a machine learning module 4, a power distribution network monitoring information analysis machine 5 and a display module.
Detailed Description
The invention is further described below with reference to the figures and examples.
Example (b):
a power distribution network monitoring information monitoring method based on machine learning, as shown in fig. 1, includes the following steps:
acquiring power grid big data, and establishing a database based on the power grid big data, wherein the power grid big data comprises monitoring information and event information;
determining an analysis time period, reading historical monitoring information and event information in the analysis time period in a database, and performing data extraction on the historical monitoring information and the event information to obtain effective monitoring information data and effective event information data, wherein the effective monitoring information data and the effective event information data comprise data related to power distribution network monitoring information abnormity when the power distribution network monitoring information is abnormal;
analyzing the effective monitoring information data and constructing an event library, constructing a historical document according to the effective event information data, and constructing a power distribution network monitoring information analysis rule library according to the event library and the historical document; when the event library is constructed according to the effective monitoring information data, association rules need to be mined, and the event library is constructed after the association rules are summarized. The power distribution network monitoring information analysis rule base is formed by mutually linking a time base and a historical document.
And step four, the power distribution network monitoring information analysis machine 4 learns according to the power distribution network monitoring information analysis rule base, all telesignaling data and telemetering data in the power distribution network are monitored and checked through the learned power distribution network monitoring information analysis machine 4, and the monitoring and checking result of the power distribution network monitoring information analysis machine 4 is displayed through the display module 5. The power distribution network monitoring information analysis rule base further has an optimization function, the display module 5 can be optimized, the abnormity of the monitoring result of the power distribution network monitoring information analysis machine 4 can be found in time, and the processing efficiency of events is improved.
And step two, when data extraction is carried out on the historical monitoring information and the event information, the extracted historical monitoring information data and the event information data are also screened, and data except valid data in the historical monitoring information data and the event information data are filtered.
When the power distribution network monitoring information analysis machine 4 learns in the fourth step, learning grade division is further carried out on effective monitoring information data and effective event information data in an analysis rule base, correlation coefficients between various types of data in the effective monitoring information data and the effective event information data and power distribution network anomalies are calculated firstly, the higher the correlation degree between the data with the larger correlation coefficient and the power distribution network anomalies is, the number of the learning grade is determined to be 5 learning grades, a correlation coefficient threshold range corresponding to each learning grade is determined according to the number of the learning grade and the range of the correlation coefficient, the data with the correlation coefficient between 0.8 and 1 is the highest learning grade, and the second learning grade is data with the correlation coefficient between 0.6 and 0.8; the third learning level is data with a correlation coefficient between 0.4 and 0.6, the fourth learning level is data between 0.2 and 0.4, and the fifth learning level is data between 0-0.5.
The data with the highest learning level is preferentially adopted for training when the power distribution network monitoring information analysis machine 4 performs learning, after the data with the highest learning level is trained, whether the monitoring result of the power distribution network monitoring information analysis machine 4 is in line with the reality or not is observed, if the monitoring result is in line with the reality, the training is not performed, and if the monitoring result is not in line with the reality, the data with the second learning level is used for training the power distribution network monitoring information analysis machine 4; by analogy, only when the supervision result of the power distribution network monitoring information analysis machine 4 does not accord with the actual result after the last learning level training, the data of the lower learning level is used for training the power distribution network monitoring information analysis machine 4, and the supervision result of the power distribution network monitoring information analysis machine 4 is analyzed after the data of one learning level is trained at each time. And the correlation coefficient is in the range of 0-1, which indicates that the data is abnormally related to the power distribution network monitoring information, and the data with the correlation coefficient smaller than 0, namely invalid data, is filtered in the second step.
And after filtering invalid data in the historical monitoring information data and the event information data, unifying the data formats of the historical monitoring information data and the event information data, and obtaining effective monitoring information data and effective event information data after unifying the data formats.
As shown in fig. 2, the process of learning by the distribution network monitoring information analysis machine 4 according to the intelligent analysis rule base specifically includes the following steps:
1.1, formulating a learning path and a learning content range of a power distribution network monitoring information analysis machine 4, installing related equipment according to the formulated range and setting related authority of the equipment;
1.2, importing related data into a power distribution network monitoring information analysis machine 4 through equipment, and associating the power distribution network monitoring information analysis machine 4 with a power distribution network monitoring information analysis rule base;
1.3, training the power distribution network monitoring information analysis machine 4 by importing the related data in the power distribution network monitoring information analysis machine 4 and a power distribution network monitoring information analysis rule base until the monitoring result of the power distribution network monitoring information analysis machine 4 on the remote signaling data and the remote measuring data is the same as the actual monitoring information and the event information.
The related data and the power distribution network monitoring information analysis rule base imported into the power distribution network monitoring information analysis machine 4 are a training sample base of the power distribution network monitoring information analysis machine 4.
The method also comprises the following step five: and detecting and analyzing the monitoring result of the power distribution network monitoring information analysis machine 4, reconstructing a power distribution network monitoring information analysis rule base when the monitoring result is different from the actual monitoring information and event information, and re-learning the power distribution network monitoring information analysis machine 4 until the monitoring result is the same as the actual monitoring information and event information.
And the power distribution network monitoring information analysis rule base is not only reconstructed when the monitoring result of the power distribution network monitoring information analysis machine 4 is abnormal, but also needs to be updated regularly, the updating time is not more than one year, so that the power distribution network monitoring information analysis rule base can be synchronized with the actual power distribution network data, and the monitoring accuracy of the power distribution network monitoring information analysis machine 4 is further ensured.
The power grid big data in the first step are obtained through a network computing technology, and the network computing technology comprises parallel computing, cloud computing and artificial intelligence.
And performing label processing on the effective monitoring information data and the effective event information data in the step two, associating the effective monitoring information data with the effective event information data related to the effective monitoring information data, and displaying the information data corresponding to the label and the information related to the information data simultaneously when the effective monitoring information data or the effective event information data is read through the label.
A power distribution network monitoring information monitoring system based on machine learning is shown in figure 3 and comprises an information acquisition module 1, an information processing module 2, a machine learning module 3 and a power distribution network monitoring information analysis machine 4; the information acquisition module 1 is connected with the information processing module 2, and the information acquisition module 1 is used for acquiring big data of a power grid; the information processing module 2 is used for processing the big data of the power grid and constructing a power distribution network monitoring information analysis rule base; the information processing module 2 and the power distribution network monitoring information analysis machine 4 are both connected with the machine learning module 3, the machine learning module 3 learns the power distribution network monitoring information analysis machine 4 according to a power distribution network monitoring information analysis rule base constructed by the information processing module 2, and the power distribution network monitoring information analysis machine 4 is used for monitoring all remote signaling data and remote measuring data in the power distribution network.
The power distribution network monitoring information analysis system is characterized by further comprising a display module 5, wherein the display module 5 is connected with the power distribution network monitoring information analysis machine 4, and the display module 5 is used for displaying a monitoring result of the power distribution network monitoring information analysis machine 4.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (7)
1. A power distribution network monitoring information monitoring method based on machine learning is characterized by comprising the following steps:
acquiring power grid big data, and establishing a database based on the power grid big data, wherein the power grid big data comprises monitoring information and event information;
determining an analysis time period, reading historical monitoring information and event information in the analysis time period in a database, and performing data extraction on the historical monitoring information and the event information to obtain effective monitoring information data and effective event information data, wherein the effective monitoring information data and the effective event information data comprise data related to power distribution network monitoring information abnormity when the power distribution network monitoring information is abnormal;
analyzing the effective monitoring information data and constructing an event library, constructing a historical document according to the effective event information data, and constructing a power distribution network monitoring information analysis rule library according to the event library and the historical document;
step four, the power distribution network monitoring information analysis machine (4) learns according to the power distribution network monitoring information analysis rule base, all telesignaling data and telemetering data in the power distribution network are monitored and controlled through the learned power distribution network monitoring information analysis machine (4), and the monitoring and controlling result of the power distribution network monitoring information analysis machine (4) is displayed through the display module (5);
when the power distribution network monitoring information analysis machine (4) learns in the fourth step, learning grade division is further carried out on effective monitoring information data and effective event information data in an analysis rule base, correlation coefficients between various data in the effective monitoring information data and the effective event information data and power distribution network monitoring information anomalies are calculated firstly, the higher the correlation degree between the data with the larger correlation coefficient and the power distribution network monitoring information anomalies is, the grade number of the learning grade is determined, the correlation coefficient threshold range corresponding to each learning grade is determined according to the grade number of the learning grade and the range of the correlation coefficient, the correlation coefficients of all data are screened according to the correlation coefficient threshold range of each learning grade, the learning grade corresponding to various data is divided, and the larger the correlation coefficient is, the higher the learning grade is; when the power distribution network monitoring information analysis machine (4) is trained and learned, the power distribution network monitoring information analysis machine (4) is trained by adopting data with the highest learning grade, and then the power distribution network monitoring information analysis machine (4) is trained from high to low in sequence according to the high and low sequence of the learning grade until the monitoring result of the trained power distribution network monitoring information analysis machine (4) is the same as the actual monitoring information and the event information.
2. The machine learning-based power distribution network monitoring information monitoring method according to claim 1, wherein when data extraction is performed on the historical monitoring information and the event information in the second step, the extracted historical monitoring information data and the extracted event information data are further screened to filter out data except valid data in the historical monitoring information data and the event information data.
3. The machine learning-based power distribution network monitoring information monitoring method according to claim 2, wherein after invalid data in the historical monitoring information data and the event information data are filtered, data formats of the historical monitoring information data and the event information data are unified, and after the data formats are unified, valid monitoring information data and valid event information data are obtained.
4. The power distribution network monitoring information monitoring method based on machine learning according to claim 1, wherein the process of learning by the power distribution network monitoring information analysis machine (4) according to an intelligent analysis rule base specifically comprises the following steps:
1.1, formulating a learning path and a learning content range of a power distribution network monitoring information analysis machine (4), installing related equipment according to the formulated range and setting related authority of the equipment;
1.2, importing related data into a power distribution network monitoring information analysis machine (4) through equipment, and associating the power distribution network monitoring information analysis machine (4) with a power distribution network monitoring information analysis rule base;
1.3, training the power distribution network monitoring information analysis machine (4) by importing the related data in the power distribution network monitoring information analysis machine (4) and a power distribution network monitoring information analysis rule base until the monitoring result of the power distribution network monitoring information analysis machine (4) on the remote signaling data and the remote measuring data is the same as the actual monitoring information and the event information.
5. The machine learning-based power distribution network monitoring information monitoring method according to claim 1, further comprising a fifth step, specifically: and detecting and analyzing the monitoring result of the power distribution network monitoring information analysis machine (4), reconstructing a power distribution network monitoring information analysis rule base when the monitoring result is different from the actual monitoring information and event information, and re-learning the power distribution network monitoring information analysis machine (4) until the monitoring result is the same as the actual monitoring information and event information.
6. The machine learning-based monitoring information method for the power distribution network according to claim 1, wherein the grid big data in the first step is obtained through network computing technologies, and the network computing technologies include parallel computing, cloud computing and artificial intelligence.
7. The machine learning-based monitoring information monitoring method for power distribution networks according to claim 1, further performing label processing on the effective monitoring information data and the effective event information data in the step two, associating the effective monitoring information data with the effective event information data related to the effective monitoring information data, and displaying the information data corresponding to the label and the information related to the information data simultaneously when the effective monitoring information data or the effective event information data is read through the label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110250427.7A CN113036917B (en) | 2021-03-08 | 2021-03-08 | Power distribution network monitoring information monitoring system and method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110250427.7A CN113036917B (en) | 2021-03-08 | 2021-03-08 | Power distribution network monitoring information monitoring system and method based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113036917A CN113036917A (en) | 2021-06-25 |
| CN113036917B true CN113036917B (en) | 2023-04-07 |
Family
ID=76466854
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110250427.7A Active CN113036917B (en) | 2021-03-08 | 2021-03-08 | Power distribution network monitoring information monitoring system and method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113036917B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688004A (en) * | 2021-07-30 | 2021-11-23 | 济南浪潮数据技术有限公司 | Cloud platform time sequence monitoring data management method, device, equipment and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2882796A1 (en) * | 2007-05-16 | 2009-02-12 | Power Analytics Corporation | Real-time predictive systems for intelligent energy monitoring and management of electrical power networks |
| CN102509178B (en) * | 2011-11-25 | 2014-12-17 | 江苏省电力公司淮安供电公司 | Distribution network device status evaluating system |
| CN103455563B (en) * | 2013-08-15 | 2016-12-28 | 国家电网公司 | A kind of data digging method being applicable to intelligent substation integrated monitoring system |
| CN106204330A (en) * | 2016-07-18 | 2016-12-07 | 国网山东省电力公司济南市历城区供电公司 | A kind of power distribution network intelligent diagnosis system |
| CN106483947A (en) * | 2016-09-21 | 2017-03-08 | 国网江苏省电力公司南通供电公司 | Distribution Running State assessment based on big data and method for early warning |
| CN106504116B (en) * | 2016-10-31 | 2020-05-22 | 山东大学 | Stability evaluation method based on power grid operation and transient stability margin index correlation |
| CN107945053A (en) * | 2017-12-29 | 2018-04-20 | 广州思泰信息技术有限公司 | A kind of multiple source power distribution network data convergence analysis platform and its control method |
| US20200292608A1 (en) * | 2019-03-13 | 2020-09-17 | General Electric Company | Residual-based substation condition monitoring and fault diagnosis |
| CN112183990A (en) * | 2020-09-22 | 2021-01-05 | 国网冀北电力有限公司计量中心 | Self-adaptive inspection monitoring management platform and method based on big data machine learning |
| CN112234711A (en) * | 2020-10-09 | 2021-01-15 | 广东电网有限责任公司广州供电局 | Intelligent interconnection power distribution operation and maintenance management system |
-
2021
- 2021-03-08 CN CN202110250427.7A patent/CN113036917B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113036917A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711659B (en) | Yield improvement management system and method for industrial production | |
| CN109186813A (en) | A kind of temperature sensor self-checking unit and method | |
| CN111160791A (en) | Abnormal user identification method based on GBDT algorithm and factor fusion | |
| CN114781476B (en) | System and method for analyzing faults of measuring equipment | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN113902241A (en) | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation | |
| CN113036917B (en) | Power distribution network monitoring information monitoring system and method based on machine learning | |
| CN113780375A (en) | Virtual-real interaction wind power plant wind power monitoring system based on digital twins and application | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN116823226A (en) | Electric power district fault monitoring system based on big data | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN116345699B (en) | Internet-based power transmission circuit information acquisition system and acquisition method | |
| CN112803587A (en) | Intelligent inspection method for state of automatic equipment based on diagnosis decision library | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN106650154B (en) | Nuclear power conventional island equipment reliability monitoring method based on thermal performance index | |
| CN115392313A (en) | State detection and fault intelligent diagnosis system for shielding motor valve | |
| CN110455370B (en) | Flood-prevention drought-resisting remote measuring display system | |
| CN113807690A (en) | Online evaluation and early warning method and system for operation state of regional power grid regulation and control system | |
| CN113691390A (en) | Cloud-end-coordinated edge node alarm system and method | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN116773238B (en) | Fault monitoring method and system based on industrial data | |
| CN117353462B (en) | Power grid operation monitoring analysis method and platform based on artificial intelligence | |
| Li et al. | Health Monitoring Framework for Weather Radar Based on Long Short-Term Memory Network with a Real Case Study | |
| CN116185757B (en) | Intelligent monitoring system for energy consumption of machine room | |
| CN116011983A (en) | Power grid equipment overhaul plan making system |
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 |