CN109544035A - Electric energy efficiency analysis and ranking method based on random forest - Google Patents
Electric energy efficiency analysis and ranking method based on random forest Download PDFInfo
- Publication number
- CN109544035A CN109544035A CN201811516952.3A CN201811516952A CN109544035A CN 109544035 A CN109544035 A CN 109544035A CN 201811516952 A CN201811516952 A CN 201811516952A CN 109544035 A CN109544035 A CN 109544035A
- Authority
- CN
- China
- Prior art keywords
- efficiency
- random forest
- energy efficiency
- electric energy
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004458 analytical method Methods 0.000 title claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000003066 decision tree Methods 0.000 claims abstract description 11
- 238000005265 energy consumption Methods 0.000 claims abstract description 6
- 230000002123 temporal effect Effects 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims description 13
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000013138 pruning Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 2
- 230000004075 alteration Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 229930091051 Arenine Natural products 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- QHGVXILFMXYDRS-UHFFFAOYSA-N pyraclofos Chemical compound C1=C(OP(=O)(OCC)SCCC)C=NN1C1=CC=C(Cl)C=C1 QHGVXILFMXYDRS-UHFFFAOYSA-N 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of electric energy efficiency analysis and ranking method based on random forest.Random forest theory is applied to electric energy efficiency assessment field, with more data sets, each decision tree generated to it is tested, finally according to the classification of temporal voting strategy test sample.The grading of this method is divided into 4 stages, and the respectively foundation of electric energy efficiency index system, the foundation of efficiency rating scale, the creation of random forest grader, random forest grader carries out level evaluation to electric energy efficiency.The assessment result obtained with this method, the efficiency for reflecting power consumer object is horizontal, and energy saving optimizing can be carried out for the horizontal low monitoring point of efficiency, this method can control the efficiency situation of various energy consumption system electrical equipments in real time, intelligent monitoring is carried out, the engineering significance of efficiency assessment project is improved.
Description
Technical field
The present invention relates to a kind of electric energy efficiency evaluation technology, in particular to a kind of electric energy efficiency based on random forest point
Analysis and ranking method.
Background technique
Energy consumption system production capacity backwardness, superscalar data, power quality problem is increasingly apparent, Some Enterprises power equipment aging,
Fallen behind with energy subject monitoring system, electrical equipment management is lack of standardization, and energy efficiency reduces, and electric cost excesses budget, needs to provide
The energy management scheme of safety standard, carries out certain energy saving optimizing.
Efficiency is tested and assessed to digitize means, and the technologies such as advanced communication, sensing, artificial intelligence are taken, and is realized to various consumptions
The energy consumption of electricity consumption facility is controlled in the on-line monitoring of electric equipment in real time, feeds back energy efficiency indexes data exception point, this intelligence
Change way to manage and greatly improves engineering effect of the efficiency assessment project in enterprise, it is practical.Efficiency assessment simultaneously
It is the important content of energy efficiency power plant, carrying out Energy Efficiency Analysis and grading to electricity consumption object not only can allow associated user to understand in real time
Itself efficiency is horizontal, moreover it is possible to formulate corresponding energy saving optimizing scheme according to assessment result, improve enterprise's production capacity, energy charge of terminating an agreement
With gradual perfection energy saving optimizing measure, so that the energy and economic, society, harmonious development.
Summary of the invention
It tests and assesses the present invention be directed to efficiency perfect problem, proposes a kind of electric energy efficiency analysis based on random forest
It is practical so that rating result is objective, scientific with ranking method.
The technical solution of the present invention is as follows: a kind of
The beneficial effects of the present invention are: the present invention is based on the analysis of the electric energy efficiency of random forest and ranking methods, use
The assessment result that this method obtains, the efficiency for reflecting power consumer object is horizontal, and can be for the horizontal low prison of efficiency
Measuring point carries out energy saving optimizing, and this method can control the efficiency situation of various energy consumption system electrical equipments in real time, carries out intelligent prison
Control improves the engineering significance of efficiency assessment project.
Detailed description of the invention
Fig. 1 is that the present invention is based on the analyses of the electric energy efficiency of random forest and ranking method flow chart.
Specific embodiment
Electric energy efficiency analysis based on random forest and ranking method flow chart as shown in Figure 1, method specific steps are such as
Under:
1, establish energy efficiency indexes system: index system is the basis of efficiency grading, since country not yet promulgates unified energy
Index system and grade scale are imitated, the present invention chooses the electric power of suitable (user's concern) according to national power quality standard handbook
Energy efficiency indexes.Electric energy efficiency index may include non-equilibrium among three phase voltages, power factor (PF), admissible deviation of supply volt- age, power train
System frequency departure, current harmonics total harmonic distortion, voltage harmonic aberration rate, granular material discharged, ten thousand yuan of economic value addeds, ten thousand yuan of productions
It is worth power consumption.
2, efficiency classification standard is established: based on national power quality standard and environmental protection standard, it is contemplated that use this
Standard can preferably divide industry object level corresponding to its electricity consumption object.For selected electric energy efficiency index, to every
A electric energy efficiency index is divided into 10 grades by the efficiency level of power consumer, as shown in table 1.
Table 1
3, establish random forest grader: random forest is similar with Bagging algorithm idea, is mainly based upon
Bootstrap method for resampling establishes multiple training sets.If data set size is D, the attribute number of sample is M (i.e. sample
Characteristic dimension), m be Split Attribute concentrate attribute number.
Data set includes training set and test set, according to random distribution principle in each efficiency in efficiency rate range
Theoretical sample set is divided into training set and test set by setting ratio by generative theory sample set in grade, to random forest point
Class device is trained and verifies, and random forest grader exports the corresponding efficiency grade of each energy efficiency indexes.For in table 1
Data, such as voltage harmonic aberration rate one, voltage harmonic aberration rate is x, then x≤0.5 is level-one；0.5 x≤1 < is two
Grade；1 x≤1.5 < are three-level；1.5 x≤2 < are level Four；2 x≤2.5 < are Pyatyi；2.5 x≤3 < are six grades；3 x≤3.5 <
It is seven grades；3.5 x≤4 < are eight grades；4 x≤4.5 < are nine grades；X > 4.5 is ten grades；
According to random distribution principle, the section for including at one to ten grades generates any more sample data, similarly, other
Index section generates sample data as many, and every energy efficiency indexes represent 9 feature vectors in data group.Assuming that choosing
100 groups of data are taken, 50 groups of training, remaining 50 groups are test.Obtain accuracy very by the inspection of forest energy efficiency model immediately
Height brings the prediction that actual numerical value carries out efficiency level into later.
3-1, T training set is generated at random；
3-2, random forest grader principle are to generate corresponding decision tree in each internal section using each training set
Before selecting attribute on point, Split Attribute collection of the m attribute of random selection as present node from M sample attribute, also just with
The method that machine extracts Split Attribute collection, decision tree is divided each time, and most suitable divisional mode is selected from m attribute,
In this process, character subset m is indeclinable；
Every decision tree utmostly grows in 3-3, setting random forest grader, is not necessarily to beta pruning；
It in 3-4, random forest grader, for test set, is tested, and is obtained corresponding using each decision tree
Type；
In 3-5, random forest grader, is selected using temporal voting strategy and export the most class of sample number in T decision tree
Not as final classification, that is, the classification of test set X Most current, classification corresponds to efficiency grade herein；
3-6, obtained final classification is matched with the practical corresponding classification of test sample, verifies the accuracy of the model,
It can determine that random forest grader training is completed after reaching accuracy.
4, the random forest grader after needing the input training of actual test collection (garden actual numerical value) data, can be straight
Connect to obtain efficiency grade, power consumer can correspond to efficiency grade according to each energy efficiency indexes and analyze, and formulate part most
Excellent scheme carries out reducing energy consumption.
Claims (2)
1. a kind of electric energy efficiency analysis and ranking method based on random forest, which is characterized in that specifically comprise the following steps:
1) establish energy efficiency indexes system: according to national power quality standard handbook, the electric energy efficiency for choosing power consumer concern refers to
Mark；
2) efficiency classification standard is established: based on national power quality standard and environmental protection standard, for selected electric energy efficiency
Index is divided into several efficiency grades by the efficiency level of power consumer to each electric energy efficiency index；
3) random forest grader is established:
In efficiency rate range according to random distribution principle in each efficiency grade interval generative theory sample set, will be theoretical
Sample set is divided into training set and test set by setting ratio, is trained and verifies to random forest grader, random forest
Classifier exports the corresponding efficiency grade of each energy efficiency indexes；
4) by the random forest grader after the input training of actual test collection data, corresponding efficiency grade, electric power are directly obtained
User can correspond to analyzing for efficiency grade according to each energy efficiency indexes, formulate locally optimal plan and carry out reducing energy consumption.
2. electric energy efficiency analysis and ranking method based on random forest according to claim 1, which is characterized in that the step
It is rapid 3) to specifically include:
3-1), T training set is generated at random；
3-2), random forest grader principle is to generate corresponding decision tree on each internal node using each training set
Before selecting attribute, Split Attribute collection of the m attribute as present node is randomly choosed from M sample attribute, it is also just random to take out
The method for taking Split Attribute collection, decision tree is divided each time, most suitable divisional mode is selected from m attribute, at this
During a, character subset m is indeclinable；
3-3), it sets every decision tree in random forest grader utmostly to grow, is not necessarily to beta pruning；
3-4), it in random forest grader, for test set, is tested using each decision tree, and obtain corresponding type；
3-5), it in random forest grader, is selected using temporal voting strategy and exports the most classification work of sample number in T decision tree
For final classification, that is, the classification of test set Most current, classification corresponds to efficiency grade herein；
3-6), obtained final classification is matched with the practical corresponding classification of test set, verifies the accuracy of the model, reaches quasi-
It can determine that random forest grader training is completed after true property.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811516952.3A CN109544035A (en) | 2018-12-12 | 2018-12-12 | Electric energy efficiency analysis and ranking method based on random forest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811516952.3A CN109544035A (en) | 2018-12-12 | 2018-12-12 | Electric energy efficiency analysis and ranking method based on random forest |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109544035A true CN109544035A (en) | 2019-03-29 |
Family
ID=65854603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811516952.3A Pending CN109544035A (en) | 2018-12-12 | 2018-12-12 | Electric energy efficiency analysis and ranking method based on random forest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544035A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310786A (en) * | 2020-01-15 | 2020-06-19 | 青岛海信网络科技股份有限公司 | Traffic detector abnormity diagnosis method and device based on random forest classifier |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844300A (en) * | 2016-03-24 | 2016-08-10 | 河南师范大学 | Optimized classification method and optimized classification device based on random forest algorithm |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108062560A (en) * | 2017-12-04 | 2018-05-22 | 贵州电网有限责任公司电力科学研究院 | A kind of power consumer feature recognition sorting technique based on random forest |
| CN108537281A (en) * | 2018-04-13 | 2018-09-14 | 贵州电网有限责任公司 | A kind of power consumer feature recognition sorting technique based on random forest |
-
2018
- 2018-12-12 CN CN201811516952.3A patent/CN109544035A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844300A (en) * | 2016-03-24 | 2016-08-10 | 河南师范大学 | Optimized classification method and optimized classification device based on random forest algorithm |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108062560A (en) * | 2017-12-04 | 2018-05-22 | 贵州电网有限责任公司电力科学研究院 | A kind of power consumer feature recognition sorting technique based on random forest |
| CN108537281A (en) * | 2018-04-13 | 2018-09-14 | 贵州电网有限责任公司 | A kind of power consumer feature recognition sorting technique based on random forest |
Non-Patent Citations (1)
| Title |
|---|
| 马立新 等: "能耗系统的电力能效测评与分级方法研究", 《电子测量技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310786A (en) * | 2020-01-15 | 2020-06-19 | 青岛海信网络科技股份有限公司 | Traffic detector abnormity diagnosis method and device based on random forest classifier |
| CN111310786B (en) * | 2020-01-15 | 2023-07-25 | 青岛海信网络科技股份有限公司 | Traffic detector abnormality diagnosis method and device based on random forest classifier |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106777984B (en) | A method of photovoltaic array Working state analysis and fault diagnosis are realized based on density clustering algorithm | |
| CN103091603B (en) | Breakdown intelligent classification and positioning method of electric transmission line | |
| CN104331844B (en) | A kind of power network construction project investment decision method | |
| CN110070048A (en) | Device type recognition methods and system based on double secondary K-means clusters | |
| CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
| CN110070282A (en) | A kind of low-voltage platform area line loss analysis of Influential Factors method based on Synthesis Relational Grade | |
| CN106127388A (en) | The energy efficiency evaluating method of high energy-consuming enterprises | |
| CN113723844B (en) | Low-voltage station theoretical line loss calculation method based on ensemble learning | |
| CN104408562A (en) | Photovoltaic system generating efficiency comprehensive evaluation method based on BP (back propagation) neural network | |
| CN107944495A (en) | A kind of household electricity load classification recognition methods based on deep layer forest algorithm | |
| CN112508338B (en) | New energy station grid-connected performance comprehensive evaluation system and evaluation method thereof | |
| CN107145707A (en) | It is a kind of to count and photovoltaic is exerted oneself the power distribution network transformer planing method of uncertain and overall life cycle cost | |
| Shin et al. | Spatiotemporal load-analysis model for electric power distribution facilities using consumer meter-reading data | |
| CN103793585B (en) | A kind of method for improving theoretical line loss caluclation integrality and accuracy | |
| CN111582338A (en) | Method and system for evaluating running state of electric vehicle charging facility | |
| CN109742788A (en) | A kind of grid-connected Performance Evaluating Indexes modification method of new energy power station | |
| CN109165807A (en) | A kind of energy quality comprehensive assessment method based on probabilistic neural network | |
| CN107437135A (en) | A kind of novel energy-storing selection method | |
| CN110532596A (en) | A kind of method and system generating grid simulation sample based on LSTM algorithm | |
| CN103887792B (en) | A kind of low-voltage distribution network modeling method containing distributed power source | |
| CN109066819A (en) | A kind of idle work optimization method of the power distribution network based on case reasoning | |
| CN110991689B (en) | Distributed photovoltaic power generation system short-term prediction method based on LSTM-Morlet model | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN105095971A (en) | Comprehensive assessment planning method based on power distribution network subareas | |
| Damala et al. | A simple decision tree-based disturbance monitoring system for VSC-based HVDC transmission link integrating a DFIG wind farm |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190329 |