CN104966244A - Spearman rank correlation self-adaption classification method for electric power system cross-specialty monitoring indexes - Google Patents
Spearman rank correlation self-adaption classification method for electric power system cross-specialty monitoring indexes Download PDFInfo
- Publication number
- CN104966244A CN104966244A CN201510318900.5A CN201510318900A CN104966244A CN 104966244 A CN104966244 A CN 104966244A CN 201510318900 A CN201510318900 A CN 201510318900A CN 104966244 A CN104966244 A CN 104966244A
- Authority
- CN
- China
- Prior art keywords
- index
- rank correlation
- correlation coefficient
- disciplinary
- spearman rank
- 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
Abstract
A spearman rank correlation self-adaption classification method for electric power system cross-specialty monitoring indexes adopts a Spearman rank correlation coefficient to calculate, calculates and analyzes trans-department data, performs classification according to grading ranking, calculates threshold values of correlation coefficients of all index pairs, screens out all index pairs that are larger than the threshold values, and thus can automatically obtain representative cross-specialty index pairs. The Spearman rank correlation self-adaption classification method for the electric power system cross-specialty monitoring indexes provided by the invention effectively analyzes trans-department data and maximizes benefits.
Description
Technical field
The present invention relates to electric power supervisory control field, the Spearman rank correlation adaptive classification method of the multi-disciplinary monitor control index of especially a kind of electric system.
Background technology
Along with the Rapid Variable Design of the outside business environment of grid company, power grid enterprises are faced with social power consumption speedup and decline, the unfavorable situation that income increase is slowed down.Therefore power grid enterprises need the visual angle from company's sustainable development, carry out of overall importance, comprehensive analysis to the operation situation of company, find the ability short slab existed in company operation, enable decision maker formulate corresponding strategy and are eliminated ability short slab.Meanwhile, also need in daily dynamic operation process, can continuous print, the unusual fluctuation that exists in quick discovery company operation, review reason, enable company adjust own operations ability dynamically, tackle fast-changing inside and outside portion environment.
Provincial Utilities Electric Co. needs the analytical work such as monitoring daily paper, company's monthly operation performance analysis report company operation dynamically having been carried out to normalization, defines preliminary support to the assurance of company leader to company operation situation.Can support decision-making except finding out, judging the important indicator of operation state, we also wish the coupling index that can find multi-disciplinary, this often easily ignore by people, but really need to be taken seriously.These associations often can assist us more clearly to get a grip on, and are therefore analyzed the interdepartmental index of difference, and the relevance between finding out just seems abnormal urgent.
Summary of the invention
In order to overcome existing power system monitoring mode cannot effectively analyze trans-departmental between the deficiency of data, the invention provides a kind of effective analysis trans-departmental between data, maximizing the benefits the Spearman rank correlation adaptive classification method of the multi-disciplinary monitor control index of electric system.
The technical solution adopted for the present invention to solve the technical problems is:
A Spearman rank correlation adaptive classification method for the multi-disciplinary monitor control index of electric system, described method comprises the following steps:
(1) from the database of m different majors, extract n the achievement data of the same quarter respectively, n represents the index total amount of the specialized database that index quantity is maximum;
(2) classifying and numbering is carried out to the index from different majors, and data are added set XS={x
ij| i=1,2 ... mj=1,2 ... n}, x
ijnamely in i-th specialty jth season achievement data;
(3) rank correlation coefficient that multi-disciplinary index is right calculates
(3.1) first in m specialty, two professional e, f are chosen arbitrarily;
(3.2) in professional e, then choose arbitrarily an index and be denoted as a, and in professional f, choose arbitrarily an index be denoted as b;
(3.3) to both two the multi-disciplinary index a choosing out and b calculating Spearman rank correlation coefficient, if C (u, v) is Copula rank value computing function, wherein parameter u and parameter v is achievement data, then rank correlation coefficient computing formula
and calculating income value is added set TS={t
eafb| e ≠ f=1,2 ... m a ≠ b=1,2 ... n}, t
eafbi.e. achievement data x
eawith achievement data x
fbspearman rank correlation coefficient value;
(3.4) from step (3.2) cycling until in professional e in arbitrary index and professional f all indexs all carried out Spearman rank correlation coefficient and calculated;
(3.5) from step (3.1) cycling until all m specialty is all selected between two;
(3.6) the set TS recording the right rank correlation coefficient of all indexs is obtained;
(4) index pair of screening association
(4.1) descending operation is carried out to set TS, arrange from big to small by the value of t;
(4.2) then the quadratic sum of getting all t in set opens radical sign, the result obtained we be denoted as Δ t, i.e. threshold values;
(4.3) all t being greater than threshold values in set TS are taken out
eafb, the index that these rank correlation coefficient subscripts mark is to being the multi-disciplinary coupling index pair that we find;
(5) submit to coupling index to data
(5.1) in set XS, the right all achievement data x of obtain multi-disciplinary coupling index are found out;
(5.2) by these achievement datas by index to for dividing into groups, and to be stored in database.
Technical conceive of the present invention is: the present invention devises the Sperman rank correlation adaptive classification of the multi-disciplinary monitor control index of a kind of electric system.In actual analysis process, we extract the indicator-specific statistics data of the same quarter respectively from the different majors database of different department, certainly these multi-disciplinary data analyses are no longer simple Linear correlative analysis, we adopt Spearman rank correlation, rank correlation reflection be dull dependence between variable, therefore remain unchanged under Nonlinear Monotone change, statistical property is due to linear correlation.Then we obtain the right rank correlation coefficient of all multi-disciplinary indexs, threshold values is found out according to our scheme, get all indexs pair being greater than threshold values, these indexs to being exactly that we think the index pair of multi-disciplinary association, and submit the statistics of these indexs to database.This invention uses rank correlation coefficient to calculate, and calculates the relevance of the index between different majors, and by our screening scheme, finds out us and thinks the multi-disciplinary index pair that association is strong.These indexs to disclose between different department contact and interact, supplement and to a certain extent company for the assurance of operation, for leadership's decision-making provides thinking and direction, contribute to imitating tighten management, timely adjustment operation, concussion of avoiding risk, realizes maximizing the benefits.
Beneficial effect of the present invention is mainly manifested in: adopt Spearman rank correlation coefficient to calculate, data between trans-departmental are calculated and analyzed, and classify according to classification rank, calculate the threshold values of the right related coefficient of all indexs, screening is greater than all indexs pair of threshold values, the multi-disciplinary index pair that automatable acquisition is representative; Maximizing the benefits, aid decision making, multianalysis.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the Spearman rank correlation adaptive classification method of the multi-disciplinary monitor control index of electric system.
Fig. 2 is the structural drawing of the Spearman rank correlation adaptive classification optimization system of the multi-disciplinary monitor control index of electric system.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.
See figures.1.and.2, the Spearman rank correlation adaptive classification method of the multi-disciplinary monitor control index of a kind of electric system, comprises the following steps:
The first step: n the achievement data extracting the same quarter from the database of m different majors respectively.
Second step: classifying and numbering is carried out to the index from different majors, and data are added set XS={x
ij| i=1,2 ... mj=1,2 ... n}, x
ijnamely in i-th specialty jth season achievement data.
3rd step: choose arbitrarily two professional e, f in m specialty.
4th step: an optional index a in professional e, an optional index b in professional f.
5th step: calculate its Spearman rank correlation coefficient to multi-disciplinary two indices and calculate, if C (u, v) is Copula rank value computing function, wherein parameter u and parameter v is achievement data, then rank correlation coefficient computing formula
and add set TS={t
eafb| e ≠ f=1,2 ... m a ≠ b=1,2 ... n}, t
eafbthe i.e. Spearman rank correlation coefficient value of index b in index a and professional f in professional e.
6th step: judge in professional e, whether arbitrary index all carries out the calculating of Spearman rank correlation coefficient with all indexs in professional f.If so, then next step is carried out.If not, the 4th step is got back to.
7th step: judge whether m specialty is all selected between two.If so, then next step is carried out.If not, then the 3rd step is got back to.
8th step: descending operation is carried out to set TS, arranges from big to small by t value.
9th step: then the quadratic sum of getting all t in set opens radical sign, the result obtained is denoted as Δ t, i.e. threshold values.
Tenth step: take out all t being greater than threshold values in set TS
eafb, the index that these rank correlation coefficient subscripts mark is to being the multi-disciplinary coupling index pair that we find.
11 step: find out the multi-disciplinary coupling index that obtains to must all achievement datas in set XS.
12 step: these achievement datas are stored in database after grouping by index.
With reference to Fig. 2, the Spearman rank correlation adaptive classification optimization system of the multi-disciplinary monitor control index of electric system that application this method realizes, mainly comprises: the index of the rank correlation coefficient computing module that multi-disciplinary index is right, screening association to module, submit to coupling index to data module, user interactive module.
(1) the rank correlation coefficient computing module that multi-disciplinary index is right: the calculating of Spearman rank correlation coefficient is carried out to multi-disciplinary achievement data.
(2) index of screening association is to module: carry out squared to all rank correlation coefficients and open radical sign operation, obtaining threshold values.Get all indexs pair being greater than threshold values, these indexs and multi-disciplinary coupling index pair.
(3) submit to coupling index to data module: to find out the data that these indexs are right, data are submitted to database according to index to form.
(4) user interactive module: client configures, index analysis result, data visualization is shown, index analysis algorithmic tool.
Claims (1)
1. a Spearman rank correlation adaptive classification method for the multi-disciplinary monitor control index of electric system, is characterized in that: described method comprises the following steps:
(1) from the database of m different majors, extract n the achievement data of the same quarter respectively, n represents the index total amount of the specialized database that index quantity is maximum;
(2) classifying and numbering is carried out to the index from different majors, and data are added set XS={x
ij| i=1,2 ... mj=1,2 ... n}, x
ijnamely in i-th specialty jth season achievement data;
(3) rank correlation coefficient that multi-disciplinary index is right calculates
(3.1) first in m specialty, two professional e, f are chosen arbitrarily;
(3.2) in professional e, then choose arbitrarily an index and be denoted as a, and in professional f, choose arbitrarily an index be denoted as b;
(3.3) to both two the multi-disciplinary index a choosing out and b calculating Spearman rank correlation coefficient, if C (u, v) is Copula rank value computing function, wherein parameter u and parameter v is achievement data, then rank correlation coefficient computing formula
and calculating income value is added set TS={t
eafb| e ≠ f=1,2 ... m a ≠ b=1,2 ... n}, t
eafbi.e. achievement data x
eawith achievement data x
fbspearman rank correlation coefficient value;
(3.4) from step (3.2) cycling until in professional e in arbitrary index and professional f all indexs all carried out Spearman rank correlation coefficient and calculated;
(3.5) from step (3.1) cycling until all m specialty is all selected between two;
(3.6) the set TS recording the right rank correlation coefficient of all indexs is obtained;
(4) index pair of screening association
(4.1) descending operation is carried out to set TS, arrange from big to small by the value of t;
(4.2) then the quadratic sum of getting all t in set opens radical sign, the result obtained we be denoted as Δ t, i.e. threshold values;
(4.3) all t being greater than threshold values in set TS are taken out
eafb, the index that these rank correlation coefficient subscripts mark is to being the multi-disciplinary coupling index pair that we find;
(5) submit to coupling index to data
(5.1) in set XS, the right all achievement data x of obtain multi-disciplinary coupling index are found out;
(5.2) by these achievement datas by index to for dividing into groups, and to be stored in database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510318900.5A CN104966244B (en) | 2015-06-11 | The Spearman rank correlation adaptive classification methods of the multi-disciplinary monitor control index of electric system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510318900.5A CN104966244B (en) | 2015-06-11 | The Spearman rank correlation adaptive classification methods of the multi-disciplinary monitor control index of electric system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104966244A true CN104966244A (en) | 2015-10-07 |
| CN104966244B CN104966244B (en) | 2018-06-01 |
Family
ID=
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991819A (en) * | 2019-11-15 | 2020-04-10 | 国网浙江省电力有限公司经济技术研究院 | Method and system for checking causal relationship among multiple department operation indexes of power system |
| CN112711601A (en) * | 2021-03-29 | 2021-04-27 | 广州欧赛斯信息科技有限公司 | Information processing method and system for higher education professional data indexes |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020423A (en) * | 2012-11-21 | 2013-04-03 | 华中科技大学 | Copula-function-based method for acquiring relevant characteristic of wind power plant capacity |
| CN103207944A (en) * | 2013-02-04 | 2013-07-17 | 国家电网公司 | Electric power statistical index relevance analysis method |
| CN104182583A (en) * | 2014-08-22 | 2014-12-03 | 国家电网公司 | Distribution network device status indicator weight analysis method based on conjoint analysis |
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020423A (en) * | 2012-11-21 | 2013-04-03 | 华中科技大学 | Copula-function-based method for acquiring relevant characteristic of wind power plant capacity |
| CN103207944A (en) * | 2013-02-04 | 2013-07-17 | 国家电网公司 | Electric power statistical index relevance analysis method |
| CN104182583A (en) * | 2014-08-22 | 2014-12-03 | 国家电网公司 | Distribution network device status indicator weight analysis method based on conjoint analysis |
Non-Patent Citations (2)
| Title |
|---|
| 何艳频等: "Spearman等级相关系数计算公式及其相互关系的探讨", 《中国现代药物应用》 * |
| 高金凤等: "电力建设项目经济评价指标分类比较", 《能源技术经济》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991819A (en) * | 2019-11-15 | 2020-04-10 | 国网浙江省电力有限公司经济技术研究院 | Method and system for checking causal relationship among multiple department operation indexes of power system |
| CN112711601A (en) * | 2021-03-29 | 2021-04-27 | 广州欧赛斯信息科技有限公司 | Information processing method and system for higher education professional data indexes |
| CN112711601B (en) * | 2021-03-29 | 2021-07-13 | 广州欧赛斯信息科技有限公司 | Information processing method and system for higher education professional data indexes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Metzler et al. | Machine learned sentence selection strategies for query-biased summarization | |
| CN102567807B (en) | Method for predicating gas card customer churn | |
| CN111539845B (en) | Enterprise environment-friendly management and control response studying and judging method based on power consumption mode membership grade | |
| CN104408667A (en) | Comprehensive assessment method and system of power quality | |
| CN104809660A (en) | Dynamic screening and comprehensive weight setting method for low-voltage transformer area line loss rate analysis indexes | |
| CN102034214A (en) | Health evaluation method for eutrophic lakes | |
| Cui et al. | Risk spillovers and time-varying links between international oil and China’s commodity futures markets: Fresh evidence from the higher-order moments | |
| WO2021007871A1 (en) | Alumina production operation optimization system and method employing cloud-side collaboration | |
| CN103632306A (en) | Distribution network power supply area division method based on clustering analysis | |
| CN103106535A (en) | Method for solving collaborative filtering recommendation data sparsity based on neural network | |
| CN111210170A (en) | Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index | |
| CN103226736A (en) | Method for predicting medium and long term power load based on cluster analysis and target theory | |
| CN104966244A (en) | Spearman rank correlation self-adaption classification method for electric power system cross-specialty monitoring indexes | |
| CN104966244B (en) | The Spearman rank correlation adaptive classification methods of the multi-disciplinary monitor control index of electric system | |
| CN103985061A (en) | Comprehensive evaluation method for power enterprise asset efficiency based on entropy evaluation method | |
| CN115511365A (en) | Comprehensive benefit evaluation method for distributed photovoltaic project | |
| CN104268804A (en) | High-quality electric power customer data mining method based on hierarchical data envelopment analysis | |
| Jiang et al. | Research on the impact of ownership structure to operation performance of the Chinese listed port companies | |
| CN112001551B (en) | Ground and commercial power grid sales electricity quantity prediction method based on large-user electricity quantity information | |
| CN103928923B (en) | A kind of network stationary power quality method for early warning based on sensitivity analysis | |
| Qin et al. | Multi-objective comprehensive evaluation approach to a river health system based on fuzzy entropy | |
| Dhamo et al. | Using the R-package to forecast time series: ARIMA models and Application | |
| Li et al. | Incorporation of Social Media Data into Macroeconomic Forecast Systems: A Mixed Frequency Modelling Approach. | |
| Geng et al. | Study on index model of tropical cyclone intensity change based on projection pursuit and evolution strategy | |
| AU2021101776A4 (en) | Ecosystem Service Supply-demand Index Change Detection Method Oriented to The Natural Resource Management Field |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201112 Address after: 11th floor, donglecheng international, Shuguang Road, Chengguan Street, Dongming County, Heze City, Shandong Province Patentee after: Heze Jianshu Intelligent Technology Co., Ltd Address before: The city Zhaohui six districts Chao Wang Road Hangzhou city Zhejiang province Zhejiang University of Technology No. 18 310014 Patentee before: ZHEJIANG University OF TECHNOLOGY |
|
| TR01 | Transfer of patent right |