CN105184394B - Optimal control method based on CPS online data mining of power distribution network - Google Patents
Optimal control method based on CPS online data mining of power distribution network Download PDFInfo
- Publication number
- CN105184394B CN105184394B CN201510530978.3A CN201510530978A CN105184394B CN 105184394 B CN105184394 B CN 105184394B CN 201510530978 A CN201510530978 A CN 201510530978A CN 105184394 B CN105184394 B CN 105184394B
- Authority
- CN
- China
- Prior art keywords
- data
- power distribution
- distribution network
- cps
- event
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000007418 data mining Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 9
- 238000005065 mining Methods 0.000 description 8
- 230000010354 integration Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The optimization control method based on the CPS online data mining of the power distribution network comprises the following steps: acquiring a data source of a CPS of the power distribution network, and cleaning the data source; establishing an incidence relation model between a data source and a control quantity, and carrying out data mining; using the actual power distribution network as an example to verify whether the association relationship is correct, if so, receiving the real-time data of the power distribution network, matching the real-time data with the association rule, and outputting a matching result; otherwise, modifying the association rule; and controlling the power distribution network according to the output result. The method reduces the cost of power enterprises and promotes the development of the power market on the premise of ensuring the safe operation of the power distribution network.
Description
Technical Field
The invention relates to an optimization control method, in particular to an optimization control method based on CPS online data mining of a power distribution network.
Background
The Cyber Physical Systems (CPS), also called Cyber Physical fusion system, is a new research field emerging in recent years with the rapid development of information and communication technologies, and was originally proposed in 2006 by the National Science Foundation (NSF). CPS is expected to become the third wave of world information technology after computers and the Internet, and the core of CPS is the fusion of calculation, communication and control, as shown in FIG. 2. The CPS is a controllable, credible and extensible networked physical equipment system with computing, communication and control capabilities deeply integrated on the basis of environment perception, achieves deep integration and real-time interaction through feedback circulation of mutual influence of a computing process and a physical process to add or extend new functions, monitors or controls a physical entity in a safe, reliable, efficient and real-time mode, and comprises ubiquitous system engineering such as environment perception, embedded computing, network communication, network control and the like, so that the physical system has the functions of computing, communication, accurate control, remote cooperation and autonomy.
With the development of smart power grids, the configuration of power distribution networks becomes increasingly complex, and smart power distribution networks include a power grid primary part (distributed power supplies, feeders, transformers, loads), a large number of data acquisition devices (sensors, FTUs, RTUs, and embedded data acquisition devices), an advanced high-speed communication network (power dedicated optical fiber networks, dispatch data communication networks, public wired Internet and wireless networks), a control center, and a large number of computational analysis resources, which are typical CPS, in an organization structure. The CPS of the power distribution network relies on rich information monitoring equipment in the real world and a perfect and reliable communication network, and integration and mutual use of operation scheduling of the power distribution network and related information quantity of internal data, external data and the like are achieved. The power distribution network is used as the CPS, so that the actual power distribution network is better described, and the operation scheduling can be more accurately and effectively controlled.
In the context of smart grids, the power distribution network CPS provides massive data, which have become the basis for decision making by power enterprises. However, the accumulation of the simple data cannot bring benefits to the power enterprises, and only by applying related technical means to deeply process the massive data, find and utilize the implicit information, and further guide the power enterprises to make correct decisions, the function of the massive data can be brought into full play.
The rapid development of computer technology and communication technology has brought human society into the information age. In order to further improve the utilization rate of Data information, Knowledge Discovery (KDD) based on a Database and a core technology thereof, Data Mining (DM), have been developed. KDD is the entire process of discovering useful knowledge from data, and data mining is a particular step in the KDD process. There are several versions of the definition of KDD, the definition now commonly adopted is as follows: KDD refers to a nontrivial process of extracting an efficient, novel, potentially useful, and ultimately understandable schema from a large amount of data. In a narrow sense, data mining is a major step in the knowledge mining process. Data mining in a power distribution network generally represents the whole knowledge mining process, and refers to a high-level process of extracting information and knowledge which are hidden in data and are unknown in advance but potentially useful by people, and finally representing the information and knowledge in an understandable mode for people.
Based on the massive operation data generated by the power distribution network CPS every day. How to utilize the existing technology and means to discover potential value from such numerous data, and then better control distribution network improves distribution network operation's security, reliability, is the problem that needs to solve at present.
The ultimate goal of implementing the CPS in the power distribution network is to enhance the control capability of the physical system. The current distribution network adopts a relatively simple and fixed control mode, has poor control flexibility, and has to sacrifice the overall operation efficiency of the system due to the difficulty in realizing the optimal control in the system range.
Aiming at the problem that a large amount of operation data are continuously generated and accumulated in the operation process of the power distribution network, a plurality of scholars research and apply a data mining technology to reveal the operation characteristics or rules of equipment hidden behind the power distribution network, find out a method for ensuring the power distribution network to operate more safely and reliably, and improve the decision level of operators. The data mining technology has five tasks: prediction (Prediction), Classification (Classification), Association Rules Analysis (Association Rules Analysis), Cluster Analysis (Cluster), and Outlier Analysis (Outlier Analysis). At present, various tasks are applied to a power system. However, various applications based on data mining do not consider the power distribution network as a CPS, nor do the applications consider the real-time performance of data, and the data mining result cannot further act on various physical entities in the power distribution network, so that the optimal control of the overall integration of the power distribution network cannot be realized.
Disclosure of Invention
In order to solve the problems, the invention provides an optimization control method based on CPS online data mining of a power distribution network, which comprises the following steps: the method comprises the steps of cleaning massive historical data and real-time data provided by the CPS of the power distribution network, mining potential values of the data, finding out association relations among the data, analyzing and verifying validity of association rules through examples, continuously correcting the association rules, matching the real-time data provided by the CPS of the power distribution network with mining results, outputting the results and feeding the results back to a CPS control center of the power distribution network, and achieving optimal control of the power distribution network.
The purpose of the invention is realized by adopting the following technical scheme:
the optimization control method based on the CPS online data mining of the power distribution network comprises the following steps:
(1) acquiring a data source of a CPS of the power distribution network, and cleaning the data source;
(2) establishing an association rule model between a data source and a control quantity, and performing data mining;
(3) taking the actual power distribution network as an example, verifying whether the association rule is correct, if so, turning to the step (4), otherwise, correcting the association rule;
(4) and receiving the real-time data of the power distribution network, matching the real-time data with the association rule, and outputting a matching result.
Preferably, the method for acquiring the data source of the power distribution network CPS in the step (1) includes embedding a sensor in the power distribution network CPS for acquiring real-time data and historical data in the power distribution network CPS.
Preferably, the cleansing of the data source includes,
step (1-1) filling up missing data of a data source by adopting a Lagrange interpolation method; y isn+1For missing data, then:
wherein x isiIs the ith data in the array, and n is the data quantity contained in the array; let x0,x1,…,xn+1And y0,y1,…,ynIn known amounts.
Step (1-2) adopts a statistical detection method to respectively calculate the number series x0,x1,…,xnAverage value of (2)And obtaining suspected abnormal data in the data source according to the standard deviation, wherein the expression is as follows:
judging the current data x based on Chebyshev's theoremiWhether the data is suspected abnormal data; if it isOrX is theniThe data is suspected to be abnormal; wherein epsilon is a self-defined factor.
Step (1-3) for the suspected abnormal data xiPerforming an analysis if said xiFailure of the acquisition device and/or acquisition channel, xiIs error data; if it is generated by a line fault, xiIs the correct data.
Further, whether the analysis result is correctly included is verified, and the data x is usediWith the data x acquired in the next data acquisition cyclei' by comparison, if xi'·(1-λ)≤xi≤xi' (1+ lambda), then xiIs correct data, otherwise xiIs error data; wherein, λ is a user-defined constant, and the value is 5%.
Further, after the verification is completed, correcting error data; the data correction method is the same as the missing data completion method.
Preferably, the step (2) of establishing the association rule model between the data source and the control quantity includes defining the data mining object as a data item set I ═ I1,i2,…,im-comprising m different data items; i.e. ikIs the kth data item k ═ 1,2, …, m; the number of elements in the I, namely the length and the length of the data item setThe data item set with the degree k is a k-dimensional data item set;
the event T is a subset of the data item set I, each event carries a unique identifier tid which is connected with the event T and is marked as T1; 1 is the tid value; a plurality of different events constitute an event database D;
let X be the collection of items in the set of data items I, ifIt means that event T contains X.
Further, the association rule is a modelIs of the formulaAnd isIncluding support, confidence and relevance.
Preferably, the data mining in the step (2) is performed to obtain the support degree, the confidence degree and the correlation degree, and specifically includes:
is provided withFor a data item set, B is the number of events in the event set D containing X, a is the total number of all events in the event set D, and the support degree of the data item set X is sup (X), then:
defining a confidence Conf (R) of the association rule R, describing the reliability of the rule,wherein the content of the first and second substances,and isThen:
the correlation degree is used for representing the correlation degree between X and Y, and the expression is as follows:
wherein Sup (Y) is the ratio of the number of events including Y in event D to the total number of all events in event D.
Preferably, the verification method in step (3) specifically includes, if Sup (X ═ Y) ═ Sup (X) Sup (Y), meaning X is independent of Y; if the correlation degree is greater than 1, X and Y are positive correlation, otherwise, if the correlation degree is less than 1, the mode X and Y are negative correlation, and the rule is deleted.
Preferably, the step (4) of outputting the matching result includes:
in the formula, SuminFor minimum support, SupminIs greater than 0; if the data item set meets the minimum support degree, the data item set is a frequent item set; confminFor minimum confidence, Confmin＞0；RelminFor minimum correlation, Relmin＞1。
Compared with the prior art, the invention has the following beneficial effects:
the power distribution network CPS organically combines global control and local distributed control, so that a data mining result is transmitted to a control center of the power distribution network CPS, the power distribution network CPS can locally control physical equipment through various embedded control systems, and the control center coordinates and optimizes the whole system by adjusting parameters of the control system on line and directly controlling the physical equipment if necessary, thereby realizing closed-loop control of the power distribution network.
The method comprises the steps of cleaning massive historical data and real-time data provided by the CPS of the power distribution network, mining potential values of the data, finding out association relations among the data, analyzing and verifying validity of association rules through examples, continuously correcting the association rules, matching the real-time data provided by the CPS of the power distribution network with mining results, outputting the results and feeding the results back to the CPS of the power distribution network, and achieving optimal control of the CPS of the power distribution network.
The method has the advantages that historical data and real-time data output by the CPS of the power distribution network are fully utilized, potential and useful information of the power distribution network is deeply mined, the mining results with high accuracy, good timeliness and good data effectiveness are fed back to the CPS control center of the power distribution network, the optimal control of the overall integration of the power distribution network is achieved, and the method plays an important role in the aspects of cost reduction of power enterprises, safe operation of the power distribution network and the like.
Drawings
FIG. 1 is a flow chart of an optimization control method based on CPS online data mining of a power distribution network;
FIG. 2 is a core diagram of a CPS provided in the background art;
fig. 3 is a schematic diagram of a closed-loop control process based on the power distribution network CPS.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
As shown in fig. 1, an optimization control method based on CPS online data mining of a power distribution network is proposed for the characteristics of complexity, contradiction, redundancy and the like of health information of the power distribution network under the condition of health information of the power distribution network, wherein the power distribution network is a typical CPS;
the method comprises the following specific steps:
(1) acquiring a data source of a CPS of the power distribution network, and cleaning the data source; the premise and the basis of the invention are to clean the data source, the information condition and the data format of the power distribution network.
The acquisition method in the step (1) comprises the step of embedding a sensor in the CPS of the power distribution network, and the sensor is used for acquiring real-time data and historical data in the CPS of the power distribution network. Sensing equipment is embedded in physical entities in the CPS of the power distribution network so as to realize information acquisition and behavior perception of the power distribution system and provide sufficient data resources for the method and the system.
The data provided by the power distribution network CPS is automatically generated by taking time as a main line, but data loss and data abnormity can be generated due to the problems of acquisition equipment and acquisition channels. Therefore, in the step (1-1), the Lagrange interpolation method is adopted to complete the missing data of the data source; let x be as shown in the following table0,x1,…,xn+1And y0,y1,…,ynIs a known amount of yn+1Is missing data;
| x | x0 | x1 | x2 | …… | xn | xn+1 |
| y | y0 | y1 | y2 | …… | yn | yn+1(unknown) |
TABLE 1A set of automatically recorded data at a time
According to lagrange polynomials:
and lagrangian coefficient calculation formula:
thereby obtaining:
wherein x isiIs the ith data in the array, and n is the data quantity contained in the array;
step (1-2) adopts a statistical detection method to respectively calculate the number series x0,x1,…,xnThe average value and the standard deviation of the data are obtained, and suspected abnormal data in the data source are obtained, wherein the expression of the data is as follows:
based on the Chebyshev theorem: in any one data set, the proportion or portion which lies within the range of its mean number m standard deviations is at least 1 to 1 per square meter, where m is any positive number greater than 1. The following results are given for m-2 and m-3: of all data, at least 3/4 (or 75%) of the data were within 2 standard deviations of the mean; of all the data, at least 8/9 (or 88.9%) were within 3 standard deviations of the mean; of all the data, at least 24/25 (or 96%) were within 5 standard deviations of the mean. Judging the current data xiWhether the data is suspected abnormal data;for abnormal data, a statistical detection method is adopted for primary identification, and then the abnormal data is compared with data acquired in the next data acquisition period for secondary identification;
if it isOrX is theniThe data is suspected to be abnormal; wherein epsilon is a self-defined factor and can be determined according to actual conditions, and the value range is more than 0 and less than or equal to epsilon and less than or equal to 5.
Step (1-3) for the suspected abnormal data xiPerforming an analysis if said xiFailure of the acquisition device and/or acquisition channel, xiIs error data; if it is generated by a line fault, xiIs the correct data.
To avoid causing xiMisjudging the data into abnormal data for correct data, verifying whether the analysis result is included correctly, and adding the data xiWith the data x acquired in the next data acquisition cyclei' by comparison, if xi'·(1-λ)≤xi≤xi' (1+ lambda), then xiIs correct data, otherwise xiIs error data; wherein, λ is a user-defined constant, and the value is 5%.
After the verification is finished, correcting error data; the data correction method is the same as the missing data completion method.
(2) Establishing an association rule model between a data source and a control quantity, and performing data mining; the association rule mining is an important method in the data mining technology, and the association valuable data patterns hidden in mass data can be found, so that the method has important practical value for decision generation.
The step (2) of establishing the association rule model between the data source and the control quantity comprises defining the data mining object as a data item set I ═ I1,i2,…,im-comprising m different data items; i.e. ikThe number of data items k is 1,2,…, m; the number of elements in the I is the length of a data item set, and the data item set with the length of k is a k-dimensional data item set (k-Itemset);
events (transactions) T are a subset of the data item set I, each event carries a unique identifier tid and is connected with the event, and the event is marked as T1; 1 is the tid value; a plurality of different events constitute an event database D (i.e., a transaction database);
let X be the collection of items in the set of data items I, ifIt means that event T contains X.
The association rule is a modelIs of the formulaAnd isIncluding support, confidence and relevance.
By performing the data mining of the step (2), obtaining a Support degree (Support), a Confidence degree (Confidence) and a correlation degree (Relevance), specifically including:
is provided withFor a data item set, B is the number of events in the event set D containing X, a is the total number of all events in the event set D, and the support degree of the data item set X is sup (X), then:
defining a confidence Conf (R) of the association rule R, describing the reliability of the rule,wherein the content of the first and second substances,and isThen:
the correlation degree is used for representing the correlation degree between X and Y, and the expression is as follows:
wherein Sup (Y) is the ratio of the number of events including Y in event D to the total number of all events in event D.
(3) Taking the actual power distribution network as an example, verifying whether the association rule is correct, if so, turning to the step (4), otherwise, correcting the association rule;
the verification method in step (3) includes, if Sup (X ═ Y) ═ Sup (X) Sup (Y), indicating that X is independent of Y; if the correlation degree is more than 1, X and Y are positive correlation, otherwise, if the correlation degree is less than 1, the pattern X and Y are negative correlation, namely the appearance probability of the front piece (condition) and the back piece (result) of the rule is reciprocal, and the rule is deleted if the rule does not accord with objective logic.
(4) And receiving the real-time data of the power distribution network, matching the real-time data with the association rule, and outputting a matching result.
The step (4) of outputting the matching result comprises the following steps:
in the formula, SuminFor minimum support, SupminIs greater than 0; if the data item set meets the minimum support degree, the data item set is a frequent item set;
Confminfor minimum confidence, Confmin＞0；RelminFor minimum correlation, Relmin＞1。
And controlling the power distribution network according to the output result, wherein the control method comprises a data mining algorithm, such as but not limited to a statistical analysis method, a decision tree method, a neural network method, a rough set method and the like. As shown in fig. 3, the power distribution network control transmits the data mining result to a control center of the power distribution network CPS, the power distribution network CPS can locally control physical devices through various embedded control systems, and the control center can coordinate and optimize the whole system by adjusting parameters of the control system on line and directly controlling the physical devices as necessary, so that closed-loop control of the power distribution network is realized.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting the protection scope thereof, and although the present application is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: numerous variations, modifications, and equivalents will occur to those skilled in the art upon reading the present application and are within the scope of the claims appended hereto.
Claims (7)
1. The optimization control method based on the CPS online data mining of the power distribution network is characterized by comprising the following steps of:
(1) acquiring a data source of a CPS of the power distribution network, and cleaning the data source;
(2) establishing an association rule model between a data source and a control quantity, and performing data mining;
(3) taking the actual power distribution network as an example, verifying whether the association rule is correct, if so, turning to the step (4),
otherwise, modifying the association rule;
(4) receiving real-time data of the power distribution network, matching the real-time data with the association rule, and outputting a matching result; feeding the matching result back to a CPS control center of the power distribution network to realize the optimal control of the power distribution network;
the step (1) of cleaning the data source comprises,
step (1-1) filling up missing data of a data source by adopting a Lagrange interpolation method; y isn+1In order to have the data missing,then:
wherein x isiIs the ith data in the array, and n is the data quantity contained in the array; let x0,x1,…,xn+1And y0,y1,…,ynIs a known amount;
step (1-2) adopts a statistical detection method to respectively calculate the number series x0,x1,…,xnThe average value and the standard deviation of the data are obtained, and suspected abnormal data in the data source are obtained, wherein the expression of the data is as follows:
judging the current data x based on Chebyshev's theoremiWhether the data is suspected abnormal data; if it isOrX is theniThe data is suspected to be abnormal; wherein epsilon is a self-defined factor;
step (1-3) for the suspected abnormal data xiPerforming an analysis if said xiFailure of the acquisition device and/or acquisition channel, xiIs error data; if it is generated by a line fault, xiIs correct data;
verifying whether the analysis result is correctly included, and adding the data xiAnd data x 'acquired in the next data acquisition period'iComparison is made if x'i·(1-λ)≤xi≤x'i1+ λ), then xiIs correct data, otherwise xiIs error data; wherein, the lambda is a user-defined constant and takes a value of 5%; after the verification is finished, correcting error data; the data correction method is the same as the missing data completion method.
2. The method as claimed in claim 1, wherein the step (1) of obtaining the data source of the power distribution network CPS comprises embedding a sensor in the power distribution network CPS for obtaining real-time data and historical data in the power distribution network CPS.
3. The method of claim 1, wherein the step (2) of establishing a rule model of association between data sources and control quantities includes defining data mining objects as a set of data items I ═ I1,i2,…,im-comprising m different data items; i.e. ikIs the kth data item k ═ 1,2, …, m; the number of elements in the I is the length of a data item set, and the data item set with the length of k is a k-dimensional data item set;
the event T is a subset of the data item set I, and each event carries a unique identifier tid which is connected with the event T and is marked as Tl; l is the tid value; a plurality of different events constitute an event database D;
let X be the collection of items in the set of data items I, ifIt means that event T contains X.
4. The method of claim 3, wherein the association rule model is as followsIs of the formulaAnd isIncluding support, confidence and relevance.
5. The method according to claim 1 or 4, wherein the obtaining of the support, confidence and relevance by performing the data mining of step (2) specifically comprises:
is provided withFor a data item set, B is the number of events in the event set D containing X, a is the total number of all events in the event set D, and the support degree of the data item set X is sup (X), then:
defining a confidence Conf (R) of the association rule R, describing the reliability of the rule,wherein the content of the first and second substances,and isThen:
the correlation degree is used for representing the correlation degree between X and Y, and the expression is as follows:
wherein Sup (Y) is the ratio of the number of events including Y in event D to the total number of all events in event D.
6. The method according to claim 1, wherein the verification method of step (3) comprises, in particular, if Sup (X ═ Y) ═ Sup (X) Sup (Y), meaning X is independent of Y; if the correlation degree is greater than 1, X and Y are positive correlation, otherwise, if the correlation degree is less than 1, the mode X and Y are negative correlation, and the rule is deleted.
7. The method of claim 1, wherein the step (4) of outputting the matching result comprises:
in the formula, SuminFor minimum support, SupminIs greater than 0; if the data item set meets the minimum support degree, the data item set is a frequent item set;
Confminfor minimum confidence, Confmin＞0；RelminFor minimum correlation, Relmin＞1。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510530978.3A CN105184394B (en) | 2015-08-26 | 2015-08-26 | Optimal control method based on CPS online data mining of power distribution network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510530978.3A CN105184394B (en) | 2015-08-26 | 2015-08-26 | Optimal control method based on CPS online data mining of power distribution network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105184394A CN105184394A (en) | 2015-12-23 |
| CN105184394B true CN105184394B (en) | 2019-12-24 |
Family
ID=54906457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510530978.3A Active CN105184394B (en) | 2015-08-26 | 2015-08-26 | Optimal control method based on CPS online data mining of power distribution network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105184394B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107291716B (en) * | 2016-03-30 | 2020-07-21 | 阿里巴巴集团控股有限公司 | Link data checking method and device |
| CN105930424A (en) * | 2016-04-19 | 2016-09-07 | 国网重庆市电力公司电力科学研究院 | Method for realizing online asynchronous acquisition and intelligent mining of power distribution network data |
| CN107484196B (en) * | 2017-08-14 | 2020-10-09 | 博锐尚格科技股份有限公司 | Data quality assurance method for sensor network and computer readable medium |
| CN109067837A (en) * | 2018-07-03 | 2018-12-21 | 沈阳电电科技有限公司 | Controller switching equipment Internet of Things and information collecting platform |
| CN110687346A (en) * | 2018-07-04 | 2020-01-14 | 国网上海市电力公司 | Method for checking and optimizing power grid voltage abnormity reason data |
| CN109492048A (en) * | 2019-01-21 | 2019-03-19 | 国网河北省电力有限公司经济技术研究院 | A kind of extracting method, system and the terminal device of power consumer electrical characteristics |
| CN110034532A (en) * | 2019-02-26 | 2019-07-19 | 国家电网公司华东分部 | The discrimination method and device of the actual measurement parameter of line impedance |
| CN110224427B (en) * | 2019-03-14 | 2020-08-18 | 浙江工业大学 | Information physical system modeling method based on micro-grid energy control strategy |
| CN112785108A (en) * | 2019-11-11 | 2021-05-11 | 国网天津市电力公司 | Power grid operation data correlation analysis method and system based on regulation cloud |
| CN111679634A (en) * | 2020-01-20 | 2020-09-18 | 武汉裕大华纺织有限公司 | Intelligent roving management system |
| CN113641726B (en) * | 2021-08-06 | 2024-01-30 | 国网北京市电力公司 | Unsupervised sheath current data mining system based on generation of countermeasure network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455563A (en) * | 2013-08-15 | 2013-12-18 | 国家电网公司 | Data mining method applicable to integrated monitoring system of intelligent substation |
| CN103728507A (en) * | 2013-11-18 | 2014-04-16 | 芜湖大学科技园发展有限公司 | Grid fault diagnosis method based on data mining |
| CN103985023A (en) * | 2014-06-11 | 2014-08-13 | 国家电网公司 | Operation and maintenance decision support system for secondary equipment of intelligent substation and data mining method |
| CN103996077A (en) * | 2014-05-22 | 2014-08-20 | 中国南方电网有限责任公司电网技术研究中心 | Electric equipment fault forecasting method based on multi-dimension time sequence |
-
2015
- 2015-08-26 CN CN201510530978.3A patent/CN105184394B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455563A (en) * | 2013-08-15 | 2013-12-18 | 国家电网公司 | Data mining method applicable to integrated monitoring system of intelligent substation |
| CN103728507A (en) * | 2013-11-18 | 2014-04-16 | 芜湖大学科技园发展有限公司 | Grid fault diagnosis method based on data mining |
| CN103996077A (en) * | 2014-05-22 | 2014-08-20 | 中国南方电网有限责任公司电网技术研究中心 | Electric equipment fault forecasting method based on multi-dimension time sequence |
| CN103985023A (en) * | 2014-06-11 | 2014-08-13 | 国家电网公司 | Operation and maintenance decision support system for secondary equipment of intelligent substation and data mining method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105184394A (en) | 2015-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105184394B (en) | Optimal control method based on CPS online data mining of power distribution network | |
| Chen et al. | Data quality of electricity consumption data in a smart grid environment | |
| CN108593990B (en) | Electricity stealing detection method based on electricity consumption behavior mode of electric energy user and application | |
| CN106796577A (en) | Use the energy foundation facility sensor data correction of regression model | |
| Li et al. | Multi-agent system based distributed pattern search algorithm for non-convex economic load dispatch in smart grid | |
| CN103869192B (en) | Intelligent grid line loss detection method and system | |
| CN103439114B (en) | A kind of Steam Turbine thermal performance test system and device | |
| US11544632B2 (en) | Non-intrusive load monitoring using ensemble machine learning techniques | |
| CN104331846A (en) | Multi-source modeling and collaborative analysis method for electricity stealing behavior | |
| US20210158150A1 (en) | Non-Intrusive Load Monitoring Using Machine Learning | |
| US20210158186A1 (en) | Non-Intrusive Load Monitoring Using Machine Learning and Processed Training Data | |
| CN106296315A (en) | Context aware systems based on user power utilization data | |
| Dong et al. | Forecasting smart meter energy usage using distributed systems and machine learning | |
| CN110222098A (en) | Electric power high amount of traffic abnormality detection based on flow data clustering algorithm | |
| CN105447767A (en) | Power consumer subdivision method based on combined matrix decomposition model | |
| CN117559443A (en) | Ordered power utilization control method for large industrial user cluster under peak load | |
| CN103268329B (en) | Plasma panel manufacturing process data digging system | |
| CN114676931B (en) | Electric quantity prediction system based on data center technology | |
| Liu et al. | An Efficient Supervised Energy Disaggregation Scheme for Power Service in Smart Grid. | |
| Peng et al. | Uck-means: A customized k-means for clustering uncertain measurement data | |
| CN105608638B (en) | A kind of method and its system of the table code data synchronous regime determining intelligent terminal and electric energy meter | |
| Jiang | Design and implementation of smart community big data dynamic analysis model based on logistic regression model | |
| CN108717444A (en) | A kind of big data clustering method and device based on distributed frame | |
| CN106708838A (en) | Flow data query method and apparatus | |
| CN109001985B (en) | Photovoltaic power station modeling method and device based on codes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |