CN103177404A - Energy-using data analysis system based on data mining - Google Patents
Energy-using data analysis system based on data mining Download PDFInfo
- Publication number
- CN103177404A CN103177404A CN2013101323250A CN201310132325A CN103177404A CN 103177404 A CN103177404 A CN 103177404A CN 2013101323250 A CN2013101323250 A CN 2013101323250A CN 201310132325 A CN201310132325 A CN 201310132325A CN 103177404 A CN103177404 A CN 103177404A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- analysis
- mining
- data analysis
- 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.)
- Granted
Links
Images
Abstract
The invention discloses an energy-using data analysis system based on data mining. The system comprises a (1) a data integration module, (2) a data-mining-based data analysis module and (3) an intelligent data processing module, wherein the the data-mining-based data analysis module is used for analyzing the data in a classifying and itemizing way; the intelligent data processing module comprises a missing value processing module and a data analysis and predication module; the missing value processing module is used for selecting a missing value to compute the acquisition loss of model compensating electric quantity data; and the data analysis and predication module is used for carrying out the data mining by artificially triggering an explore mode, selecting a data algorithm module to process the selected data, and carrying out the normal data mining under a normal mode. After the data analysis system disclosed by the invention is used, the comprehensive analysis and process of a data system can be effectively guaranteed, so that the analysis and process work of the energy-using data can be completed. Furthermore, the data can be effectively preprocessed by certain algorithms in the aspects of data mining in the prior art, so that the electric energy data quality evaluation and the electric energy data analysis and predication can be carried out through the advanced and effective algorithm after the processing.
Description
Technical field
Patent of the present invention relates to using of a kind of based on data excavation can data analysis system.The invention belongs to the electric power system data analysis field.
Background technology
Electric system is in the past said from function with the energy data analysis and is disperseed, incomplete, fail to form the system architecture of an integral body, and the data of using are also the partial datas that disperses, can not carry out comprehensive with can data analysis and many scenes with can data display.In addition, data analysis and process in the past fails to consider all sidedly mass data analysis and processing problem, therefore carry out energy analysis correlative study more deeply, simultaneously according to existing information disclosure demand status urgently propose a holonomic system with can data analysis system, very necessary.
Intelligence be the strong intelligent grid second batch pilot project that national grid is assigned with the energy management system, is one of great sub-project in intelligent grid Integrated Demonstration district, middle nascent state city of assigning of Tianjin Utilities Electric Co..By current intelligent power system state of development and user's demand is carried out deep investigation, studied intelligent with the energy functional specification, and gordian technique has been carried out detailed deep research, a thorough energy analysis method can be proposed, can bring into play the intelligence important exemplary role of energy management system, this system puts forward under this background.
Summary of the invention
The purpose of this invention is to provide that a kind of based on data excavates with can data analysis system, a comprehensive energy analysis is proposed, give full play to intelligence with the effect of energy management system.
The use energy data analysis system that a kind of based on data excavates is characterized in that, comprises:
(1) Data Integration module: the electric power data unification is placed on the server of information Intranet, when fetching data, adopt intermediate database as interface database, realize tentatively collecting of data, and timer, timing extraction and deal with data be set in intermediate database; Link by database communication at last different electric power datas sources is merged, realize the integration of data;
(2) data analysis module of based on data excavation: on the basis of Data Integration, the classification subitem carries out power consumption analysis, KPI analysis, anomaly analysis and client's efficiency status analysis to data;
(3) intelligent data processing module:
1) missing values processing module:
Choose the disappearance that the missing values computation model that is fit to the current time section makes up electric quantity data acquisition;
2) data analysis and prediction module:
Comprise and multiple back-up algorithm storehouse carry out data mining by artificial triggering exploration pattern, choose the data algorithm module in the exploration pattern selected data is processed, produce data results; The data algoritic module is estimated, the algoritic module of evaluation result optimum is moved on in the conventional algorithm storehouse, carry out routine data at normal mode and excavate.
Also comprise quality of power supply evaluation module, the integrated evaluating method that has adopted entropy power and fuzzy evaluation to combine carries out comprehensive evaluation to the quality of power supply; The evaluation of the quality of power supply is carried out comprehensive evaluation from voltage deviation, voltage fluctuation, voltage flicker, frequency departure, three-phase degree of asymmetry, harmonic wave, power factor, transient overvoltage aspect; After preliminary each factor weight of acquisition, adopt entropy to weigh to carry out the correction of each factor weight.
Described missing values computation model is: mean value interpolation, similar mean value interpolation, maximum likelihood are estimated or multiple interpolation.
Described data algorithm module has: the correlation rule of the intelligent diagnostics of electric weight abnormal data, time-of-use tariffs and electric quantity consumption extracts, the load of electric power.
The beneficial effect that the present invention reaches:
Data analysis system of the present invention can guarantee efficiently that not only data system analyzes all sidedly and process, thereby complete with data analysis dealing with the work, and utilize some algorithms of current data excavation aspect to carry out effective pre-service to data, can carry out energy data quality assessment, energy data analysis and prediction by advanced Effective arithmetic after processing.
Description of drawings
Fig. 1 is of the present invention with energy data analysis system schematic diagram.
Embodiment
According to shown in Figure 1, all data are all in the information Intranet, data except the intelligent building data all are stored in data center's database (data center's external libraries), for the processing that guarantees that data timing is real-time, in the interlude section, power information data to needs are carried out timing extraction and conversion, with result store in power information acquisition system middle database.
The overall electricity charge structure analysis of the electricity charge of further investigation maximum demand, the power factor (PF) electricity charge is carried out each level to data and is divided, and carries out statistical study and is showed according to different scenes.Realize the comprehensive analysis of data by measure performance analysis and data exception analysis, utilize data-base cluster and data mining technology means to guarantee the high efficiency that this systematization is analyzed.
Analysis and processing with the energy data are to carry out on the basis that each data source is integrated, and the inner intelligent building data that gather directly are written to intelligence with in the energy database by interface routine, and other data are unified to process.Level chromatographic analysis processing service time in processing, namely according to quarter, the time, sky, the moon, year the different time granularity process, the former result is the input that the latter processes, and has greatly improved the data utilization ratio, has reduced widely the calculated amount that data analysis is processed.
The function of native system:
1. efficient Data Integration: consider the characteristics that electric power data security and data volume are huge, the data unification is placed on the server of information Intranet, when fetching data, system adopts intermediate database to be used as interface database tentatively collecting as data, and timer, timing extraction and deal with data be set in intermediate database.Fetch by the database communication chain at last different data sources is merged, unifiedly carry out analysis and the processing of data.
2. the data analysis function that excavates of based on data: on the basis of Data Integration, omnibearing data analysis scene has been proposed, the classification subitem carries out power consumption analysis, KPI analysis, anomaly analysis and client's efficiency status analysis etc. to data, analyze all sidedly and diagnose user's efficiency level, improve the user and use the energy service efficiency.In the quality of power supply was estimated, the integrated evaluating method that has adopted entropy power and fuzzy evaluation to combine carried out comprehensive effectively evaluating to the quality of power supply.The evaluation of the quality of power supply is carried out comprehensive evaluation from voltage deviation, voltage fluctuation, voltage flicker, frequency departure, three-phase degree of asymmetry, harmonic wave, power factor, transient overvoltage aspect.After preliminary each factor weight of acquisition, in order to overcome subjectivity, adopt entropy to weigh to carry out the correction of each factor weight.
3. realize the mass data analytical approach: realized that thorough data are efficiently processed, analytical approach, that is: storing process is arranged on the data server cluster, to data on time intermediate node carry out the layering Timing Processing, intermediate data set with analyzing and processing in processing procedure stores in middle table, improve sharing of data intermediate data set, greatly reduce the workload of mass data analyzing and processing, improved the speed that data are processed.Moreover also show aspect following two at data analysis and process:
1) missing values processing aspect
In order to make up the disappearance of electric quantity data acquisition, can adopt the many algorithms model to process, calculate according to J curve effectJ and the eigenwert selecting to produce, choose the specific missing values computation model that is fit to the current time section thereby can be assessed the effect of algorithm by the professional.The missing values computation model that is mainly concerned with comprises: mean value interpolation, similar mean value interpolation, maximum likelihood are estimated, multiple interpolation.
2) data analysis and prediction aspect
Under the condition that guarantees the electric power data completeness, the data analysis algorithm uses in a kind of occasion, may be in the situation that the replacing time data, and significant data analysis algorithm changes to some extent.In order greatly to utilize current data to carry out the trial that several data is analyzed, with the dirigibility of performance data mining.Exploratory data mining can be carried out by artificial triggering in the data analysis module multiple back-up algorithm of design storehouse.Choose the data analysis algorithm in the exploration pattern selected data is processed, produce data results.According to artificial experience, mining model is selected, through a plurality of professionals and the selection of a period of time marking, can be to the data analysis algorithm statistics of giving a mark, the generation form, for your guidance.Can choose the high algorithm of giving a mark and move on in the conventional algorithm storehouse, can be used for carrying out routine data at normal mode and excavate.The algoritic module that is designed into has: the correlation rule of the intelligent diagnostics of electric weight abnormal data, time-of-use tariffs and electric quantity consumption extracts, the load of electric power.
Claims (4)
1. the use energy data analysis system that based on data excavates, is characterized in that, comprises:
(1) Data Integration module: the electric power data unification is placed on the server of information Intranet, when fetching data, adopt intermediate database as interface database, realize tentatively collecting of data, and timer, timing extraction and deal with data be set in intermediate database; Link by database communication at last different electric power datas sources is merged, realize the integration of data;
(2) data analysis module of based on data excavation: on the basis of Data Integration, the classification subitem carries out power consumption analysis, KPI analysis, anomaly analysis and client's efficiency status analysis to data;
(3) intelligent data processing module:
1) missing values processing module:
Choose the disappearance that the missing values computation model that is fit to the current time section makes up electric quantity data acquisition;
2) data analysis and prediction module:
Comprise and multiple back-up algorithm storehouse carry out data mining by artificial triggering exploration pattern, choose the data algorithm module in the exploration pattern selected data is processed, produce data results; The data algoritic module is estimated, the algoritic module of evaluation result optimum is moved on in the conventional algorithm storehouse, carry out routine data at normal mode and excavate.
2. the use energy data analysis system of based on data excavation according to claim 1, is characterized in that, also comprises quality of power supply evaluation module, and the integrated evaluating method that has adopted entropy power and fuzzy evaluation to combine carries out comprehensive evaluation to the quality of power supply; The evaluation of the quality of power supply is carried out comprehensive evaluation from voltage deviation, voltage fluctuation, voltage flicker, frequency departure, three-phase degree of asymmetry, harmonic wave, power factor, transient overvoltage aspect; After preliminary each factor weight of acquisition, adopt entropy to weigh to carry out the correction of each factor weight.
3. the use energy data analysis system of based on data excavation according to claim 1, is characterized in that, described missing values computation model is: mean value interpolation, similar mean value interpolation, maximum likelihood are estimated or multiple interpolation.
4. the use energy data analysis system of based on data excavation according to claim 1, is characterized in that, described data algorithm module has: the correlation rule of the intelligent diagnostics of electric weight abnormal data, time-of-use tariffs and electric quantity consumption extracts, the load of electric power.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310132325.0A CN103177404B (en) | 2013-04-17 | 2013-04-17 | Can data analysis system based on using of data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310132325.0A CN103177404B (en) | 2013-04-17 | 2013-04-17 | Can data analysis system based on using of data mining |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103177404A true CN103177404A (en) | 2013-06-26 |
CN103177404B CN103177404B (en) | 2015-11-18 |
Family
ID=48637237
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310132325.0A Active CN103177404B (en) | 2013-04-17 | 2013-04-17 | Can data analysis system based on using of data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103177404B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217108A (en) * | 2014-08-29 | 2014-12-17 | 中国科学院电工研究所 | Comprehensive evaluation method for transformation efficiency of grid-connected photovoltaic inverter |
CN104299167A (en) * | 2014-09-11 | 2015-01-21 | 国家电网公司 | Energy consumption analysis method for user power data of intelligent energy consumption system |
CN104992262A (en) * | 2015-05-27 | 2015-10-21 | 南京国云电力有限公司 | Power utilization big-data analysis and miningprocessing method |
CN105139295A (en) * | 2015-09-29 | 2015-12-09 | 广东电网有限责任公司电力科学研究院 | Data mining method of mass information of on-line monitoring on power equipment |
CN105786956A (en) * | 2016-01-08 | 2016-07-20 | 国家电网公司 | Power business data mining method based on business application system |
CN106291253A (en) * | 2016-09-23 | 2017-01-04 | 国网天津市电力公司 | A kind of anti-electricity-theft early warning analysis method |
CN106610616A (en) * | 2016-11-30 | 2017-05-03 | 交控科技股份有限公司 | Automatic performance tuning method and automatic performance tuning device based on big data analysis |
CN107357818A (en) * | 2017-06-12 | 2017-11-17 | 安徽中控仪表有限公司 | The big data of energy monitor Optimal Management System excavates framework |
CN107391515A (en) * | 2016-05-17 | 2017-11-24 | 李明轩 | Power system index analysis method based on Association Rule Analysis |
CN108537682A (en) * | 2018-03-26 | 2018-09-14 | 国家电网公司客户服务中心 | Scheduled outage sensitive client recognition methods based on improved entropy method |
CN108921229A (en) * | 2018-07-17 | 2018-11-30 | 成都西加云杉科技有限公司 | Data reconstruction method and device |
CN109307811A (en) * | 2018-08-06 | 2019-02-05 | 国网浙江省电力有限公司宁波供电公司 | A kind of user's dedicated transformer electricity consumption monitoring method excavated based on big data |
WO2020010569A1 (en) * | 2018-07-12 | 2020-01-16 | 深圳齐心集团股份有限公司 | Big data comprehensive analysis processing service system |
CN114089690A (en) * | 2021-10-25 | 2022-02-25 | 西北工业大学 | Edge computing device and method for workshop monitoring |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6631309B2 (en) * | 2001-02-20 | 2003-10-07 | International Business Machines Corporation | System and method to monitor datamining power usage |
CN102542347A (en) * | 2011-12-28 | 2012-07-04 | 东南大学 | Method for comprehensively evaluating electric energy quality |
CN102651116A (en) * | 2012-03-31 | 2012-08-29 | 上海市电力公司 | Power load data refining method |
-
2013
- 2013-04-17 CN CN201310132325.0A patent/CN103177404B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6631309B2 (en) * | 2001-02-20 | 2003-10-07 | International Business Machines Corporation | System and method to monitor datamining power usage |
CN102542347A (en) * | 2011-12-28 | 2012-07-04 | 东南大学 | Method for comprehensively evaluating electric energy quality |
CN102651116A (en) * | 2012-03-31 | 2012-08-29 | 上海市电力公司 | Power load data refining method |
Non-Patent Citations (2)
Title |
---|
刘芳: "《基于数据挖掘的电网数据智能分析的研究与实现》", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》, no. 10, 15 October 2008 (2008-10-15) * |
王睿等: "《基于熵权和AHP的电能质量模糊综合评估》", 《电测与仪表》, vol. 44, no. 503, 30 November 2007 (2007-11-30) * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217108B (en) * | 2014-08-29 | 2017-07-11 | 中国科学院电工研究所 | A kind of grid-connected photovoltaic inverter conversion efficiency integrated evaluating method |
CN104217108A (en) * | 2014-08-29 | 2014-12-17 | 中国科学院电工研究所 | Comprehensive evaluation method for transformation efficiency of grid-connected photovoltaic inverter |
CN104299167A (en) * | 2014-09-11 | 2015-01-21 | 国家电网公司 | Energy consumption analysis method for user power data of intelligent energy consumption system |
CN104992262A (en) * | 2015-05-27 | 2015-10-21 | 南京国云电力有限公司 | Power utilization big-data analysis and miningprocessing method |
CN105139295A (en) * | 2015-09-29 | 2015-12-09 | 广东电网有限责任公司电力科学研究院 | Data mining method of mass information of on-line monitoring on power equipment |
CN105786956A (en) * | 2016-01-08 | 2016-07-20 | 国家电网公司 | Power business data mining method based on business application system |
CN107391515A (en) * | 2016-05-17 | 2017-11-24 | 李明轩 | Power system index analysis method based on Association Rule Analysis |
CN106291253A (en) * | 2016-09-23 | 2017-01-04 | 国网天津市电力公司 | A kind of anti-electricity-theft early warning analysis method |
CN106610616B (en) * | 2016-11-30 | 2019-12-03 | 交控科技股份有限公司 | A kind of performance automated tuning method and device based on big data analysis |
CN106610616A (en) * | 2016-11-30 | 2017-05-03 | 交控科技股份有限公司 | Automatic performance tuning method and automatic performance tuning device based on big data analysis |
CN107357818A (en) * | 2017-06-12 | 2017-11-17 | 安徽中控仪表有限公司 | The big data of energy monitor Optimal Management System excavates framework |
CN108537682A (en) * | 2018-03-26 | 2018-09-14 | 国家电网公司客户服务中心 | Scheduled outage sensitive client recognition methods based on improved entropy method |
WO2020010569A1 (en) * | 2018-07-12 | 2020-01-16 | 深圳齐心集团股份有限公司 | Big data comprehensive analysis processing service system |
CN108921229A (en) * | 2018-07-17 | 2018-11-30 | 成都西加云杉科技有限公司 | Data reconstruction method and device |
CN109307811A (en) * | 2018-08-06 | 2019-02-05 | 国网浙江省电力有限公司宁波供电公司 | A kind of user's dedicated transformer electricity consumption monitoring method excavated based on big data |
CN114089690A (en) * | 2021-10-25 | 2022-02-25 | 西北工业大学 | Edge computing device and method for workshop monitoring |
CN114089690B (en) * | 2021-10-25 | 2022-05-31 | 西北工业大学 | Edge computing device and method for workshop monitoring |
Also Published As
Publication number | Publication date |
---|---|
CN103177404B (en) | 2015-11-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103177404B (en) | Can data analysis system based on using of data mining | |
CN102955977A (en) | Energy efficiency service method and energy efficiency service platform adopting same on basis of cloud technology | |
Nguyen et al. | Optimal capacity design of battery and hydrogen system for the DC grid with photovoltaic power generation based on the rapid estimation of grid dependency | |
CN111598330A (en) | Residential electricity load prediction method based on load identification technology | |
CN103198139B (en) | The energy analysis method of custom power data | |
CN102832617B (en) | Large power grid transient state stabilization analyzing method based on precision pattern discrimination | |
CN113435923B (en) | Power consumption prediction method and device and electronic equipment | |
CN103742901A (en) | Method for determining consumption difference analysis optimized target value system of circulating fluidized bed unit | |
CN107480825B (en) | Photovoltaic power station optimization planning method considering capacity credibility | |
CN101764406A (en) | Maintenance scheduling safety evaluation method based on power generation loss and load supply adequacy | |
CN104699890A (en) | Modeling method of short-term forewarning model for heavy overload of distribution transformer of urban power network | |
CN112612819A (en) | Big data analysis and mining method and system for pumped storage power station | |
CN111091240A (en) | Public institution electric power energy efficiency monitoring system and service method | |
CN104978605A (en) | Large-scale wind power prediction system and method based on deep learning network | |
Ma et al. | Economic operation evaluation of active distribution network based on fuzzy Borda method | |
CN103018611B (en) | Non-invasive load monitoring method and system based on current decomposition | |
CN104299167A (en) | Energy consumption analysis method for user power data of intelligent energy consumption system | |
YV | Simple and effective descriptive analysis of missing data anomalies in smart home energy consumption readings | |
Suciu et al. | Iot and cloud-based energy monitoring and simulation platform | |
CN107276093A (en) | The Probabilistic Load computational methods cut down based on scene | |
CN104636848A (en) | Project energy management contract system based on energy node control technology | |
Zhang et al. | Energy economy and energy structure optimization countermeasures based on big data mining | |
CN113222339A (en) | Energy consumption difference analysis method and system for enterprises of the same type based on measured panoramic data | |
CN105576825A (en) | An energy management system and method for a smart micro-grid comprising a plurality of renewable energy sources | |
CN211405605U (en) | Hierarchical step-by-step energy management system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |