CN108537281A - A kind of power consumer feature recognition sorting technique based on random forest - Google Patents
A kind of power consumer feature recognition sorting technique based on random forest Download PDFInfo
- Publication number
- CN108537281A CN108537281A CN201810331211.1A CN201810331211A CN108537281A CN 108537281 A CN108537281 A CN 108537281A CN 201810331211 A CN201810331211 A CN 201810331211A CN 108537281 A CN108537281 A CN 108537281A
- Authority
- CN
- China
- Prior art keywords
- power consumer
- power
- random forest
- data
- model
- 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
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The power consumer feature recognition sorting technique based on random forest that the invention discloses a kind of, it includes:Acquisition power consumer data obtain power consumer power load data according to the load curve of power consumer and power consumer data;Pretreatment is normalized to power consumer load data, extracts the impact factor of power consumer load data, establishes the training set and test set of random forest;The randomly drawing sample from training set is extracted k sample, is trained to k sample using decision Tree algorithms, and k Decision-Tree Classifier Model is obtained;K Decision-Tree Classifier Model is combined, assembled classification model, i.e. random forest disaggregated model are formed;Power consumer part throttle characteristics data are acquired, are classified to these data using random forest disaggregated model, the classification results of output power user;Solve the problems, such as that the prior art cannot carry out feature recognition classification to the power grid user in power grid.
Description
Technical field
The invention belongs to power consumer feature identification techniques, special more particularly to a kind of power consumer based on random forest
Levy method for identifying and classifying.
Background technology
World today's development is getting faster, and urban construction is maked rapid progress, and the wear rate of the energy is also growing day by day, due to hair
Excessive velocities are opened up, the whole world has been absorbed in deep energy crisis, and the various fossil energies such as coal, oil are constantly consumed,
Increasingly exhausted, moreover, exploitation fossil resource causes to seriously endanger to environment, consumption fossil resource also will produce largely harmful gas
Body.Requirement with world development to the energy is higher and higher and the reinforcement of people's environmental consciousness, electric vehicle, photovoltaic and storage
It equal can increasingly popularize, distributed apparatus obtains unprecedented attention and development, this is but also different user has been provided with difference
Regulation and control potentiality.Simultaneously because economically high speed development, the peak load sustainable growth of regional electric power, peak-valley difference increase gradually,
This causes grave danger to the safe operation of power grid, studies part throttle characteristics, targetedly carries out demand side pipe on this basis
Reason has a very important significance.
But by which constitute numerous distributed energies, prodigious impact is brought to the structure of traditional power grid, in order to answer
To such a situation, it is a measure for effectively solving the problems, such as this to carry out demand side management, while latent using the regulation and control of user
Power adjusts power grid, will largely improve the operation conditions of power grid.
And in numerous type of user of Demand-side, different type user has different regulation and control potentiality.If can lead to
The feature recognition for crossing power consumer, classifies to user, this will play prodigious impetus to demand side management.By right
Different users takes different regulation measures, plays the regulation and control potentiality of different power consumers as far as possible, improves the fortune of power grid
Row state, it is meaningful.Therefore, find an effective method --- the feature of user is identified, is classified, be one urgently
Problem to be solved.
Invention content
The technical problem to be solved by the present invention is to:A kind of power consumer feature recognition classification side based on random forest is provided
Method is trained Random Forest model using available data, will the obtained model of training come to the power grid user in power grid into
Row feature recognition is classified.
The technical scheme is that:
A kind of power consumer feature recognition sorting technique based on random forest, it includes:
Step S110, acquisition power consumer data obtain electricity according to the load curve of power consumer and power consumer data
Power user power utilization load data;
Step S120, pretreatment is normalized to power consumer load data, extracts power consumer load data
Impact factor establishes the training set and test set of random forest;
Step S130, the randomly drawing sample from training set, extract k sample, using decision Tree algorithms to k sample into
Row training, obtains k Decision-Tree Classifier Model;
Step S140, k Decision-Tree Classifier Model is combined, forms assembled classification model, is i.e. random forest is classified
Model;
Step S150, power consumer part throttle characteristics data are acquired, these data are carried out using random forest disaggregated model
Classification, the classification results of output power user.
The random forest disaggregated model that step S140 is established, classification knot is carried out by using test set to Random Forest model
Fruit is tested, and test result and test set result are compared, and random forest disaggregated model is verified with this.
Power consumer power load data include:
1., peak value Pmax, the maximum value in power consumer day electricity consumption curve is taken to be used as the power consumer power load curve
Peak value;
2., peak-valley difference Δ Pm, take the maximum value P in power consumer electricity consumption curvemaxWith minimum value Pmin, the difference work of the two
For the peak-to-valley value of the power consumer electricity consumption curve;
ΔPm=Pmax-Pmin
3., rate of load condensate km,
4., minimum load factor alpha,
5., power consumption Wd,
Advantageous effect of the present invention:
The present invention is based on the power consumer feature recognition sorting techniques of random forest to power consumer feature recognition and to carry out
Classification.First by collecting a large amount of original truthful data, data are divided into training set and test set with certain proportion, are utilized
Training set trains more decision trees, then all decision trees are combined into random forest, by choosing final classification knot in a vote
Then fruit is verified random forest using test set, classification finally is identified to power consumer using random forest, defeated
Go out classification results;Solve the problems, such as that the prior art cannot carry out feature recognition classification to the power grid user in power grid.
Description of the drawings
Fig. 1 is the flow diagram of the present invention.
Specific implementation mode
The present invention is based on the power consumer feature recognition sorting techniques of random forest to include the following steps:
Step S110 is acquired power consumer data by existing Power System Intelligent harvester.Above-mentioned
Electric system acquisition system is uniformly coordinated Optimal Control System for intelligent power, passes through the Intelligent electric socket pair under the system
User data is acquired, and according to the load curve of power consumer and specific data, it is special to analyze different power consumer electricity consumption datas
Sign, extracts power consumer power load main feature;
1., peak value Pmax.The maximum value in power consumer day electricity consumption curve is taken to be used as the power consumer power load curve
Peak value --- Daily treatment cost Pmax, general industry user power utilization peak value for domestic consumer or commercial user partially
Greatly;
2., peak-valley difference Δ Pm.Take the maximum value P in power consumer electricity consumption curvemaxWith minimum value Pmin, the difference work of the two
For the peak-to-valley value of the power consumer electricity consumption curve
ΔPm=Pmax-Pmin
3., rate of load condensate km。Wherein PavUser power utilization average value in indicating one day.
4., minimum load factor alpha.
5., power consumption Wd。Wherein P indicates power consumer day electric power, the power consumption of general industry load
Amount is more much bigger than general family.
Step S120 is normalized pretreatment to power consumer load data, eliminates dimension impact, extracts electric power use
The main affecting factors of family load data establish the training set and test set of random forest, specific as follows:
Normalized:Wherein, a*Indicate normalization after as a result, a indicates this feature data, amax
Indicate the maximum value of such characteristic, aminIndicate the minimum value of such characteristic;
The ratio between training set and test set capacity of random forest are 80% and 20%.
Step S130, put back to from training set randomly drawing sample, extract k sample, each sample sample appearance
Amount is as original training set;
Step S130 is trained k sample using decision Tree algorithms, obtains k Decision-Tree Classifier Model.Specific step
It is rapid as follows:
The quantity of tree is set as 300;
1, kth decision tree is built:
Build root decision point:
I, the entropy of linear model is calculated.
Ii, binary model conditional entropy is calculated.The joint probability that user type and characteristic occur together is calculated, is counted respectively
Conditional probability of the user type under different characteristic data is calculated, different characteristic data value is found out by joint probability and conditional probability
Under user type conditional entropy;
Iii, mutual information is calculated.Again after the binary model entropy under known linear model entropy and different characteristic data, calculate mutual
The value of information measures correlation highest of which kind of characteristic with user type, and carrys out structure in this, as the root node of decision tree
Build Decision-Tree Classifier Model;
K Decision-Tree Classifier Model composition is got up, forms assembled classification model by step S140, i.e. random forest is classified
Model, each decision tree by voting final classification,
Classification results test is carried out to Random Forest model using test set, test result and test set result are compared
Compared with verifying random forest disaggregated model with this;
Power consumer part throttle characteristics data are collected, are classified to these data using the model;
The classification results of output power user.
Claims (3)
1. a kind of power consumer feature recognition sorting technique based on random forest, it includes:
Step S110, power consumer data are acquired, according to the load curve of power consumer and power consumer data, obtain electric power use
Family power load data;
Step S120, pretreatment is normalized to power consumer load data, extracts the influence of power consumer load data
The factor establishes the training set and test set of random forest;
Step S130, the randomly drawing sample from training set is extracted k sample, is instructed to k sample using decision Tree algorithms
Practice, obtains k Decision-Tree Classifier Model;
Step S140, k Decision-Tree Classifier Model is combined, forms assembled classification model, i.e. random forest disaggregated model;
Step S150, power consumer part throttle characteristics data are acquired, are classified to these data using random forest disaggregated model,
The classification results of output power user.
2. a kind of power consumer feature recognition sorting technique based on random forest according to claim 1, feature exist
In:The random forest disaggregated model that step S140 is established carries out classification results survey by using test set to Random Forest model
Examination, test result and test set result are compared, and random forest disaggregated model is verified with this.
3. a kind of power consumer feature recognition sorting technique based on random forest according to claim 1, feature exist
In:Power consumer power load data include:
1., peak value Pmax, the maximum value in power consumer day electricity consumption curve is taken to be used as the peak of the power consumer power load curve
Value;
2., peak-valley difference Δ Pm, take the maximum value P in power consumer electricity consumption curvemaxWith minimum value Pmin, the difference of the two is used as should
The peak-to-valley value of power consumer electricity consumption curve;
ΔPm=Pmax-Pmin
3., rate of load condensate km,
4., minimum load factor alpha,
5., power consumption Wd,
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810331211.1A CN108537281A (en) | 2018-04-13 | 2018-04-13 | A kind of power consumer feature recognition sorting technique based on random forest |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810331211.1A CN108537281A (en) | 2018-04-13 | 2018-04-13 | A kind of power consumer feature recognition sorting technique based on random forest |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108537281A true CN108537281A (en) | 2018-09-14 |
Family
ID=63480341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810331211.1A Pending CN108537281A (en) | 2018-04-13 | 2018-04-13 | A kind of power consumer feature recognition sorting technique based on random forest |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108537281A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410074A (en) * | 2018-10-18 | 2019-03-01 | 广州市勤思网络科技有限公司 | Intelligent core protects method and system |
CN109544035A (en) * | 2018-12-12 | 2019-03-29 | 上海理工大学 | Electric energy efficiency analysis and ranking method based on random forest |
CN110795560A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Method and system for subdividing power grid electricity customers |
CN111753907A (en) * | 2020-06-24 | 2020-10-09 | 国家电网有限公司大数据中心 | Method, device, equipment and storage medium for processing electric quantity data |
CN113673579A (en) * | 2021-07-27 | 2021-11-19 | 国网湖北省电力有限公司营销服务中心(计量中心) | Power load classification algorithm based on small samples |
CN113988161A (en) * | 2021-10-15 | 2022-01-28 | 贵州大学 | User electricity consumption behavior pattern recognition method |
CN114154561A (en) * | 2021-11-15 | 2022-03-08 | 国家电网有限公司 | Electric power data management method based on natural language processing and random forest |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
CN107194600A (en) * | 2017-06-01 | 2017-09-22 | 国网山东省电力公司济南市历城区供电公司 | A kind of electric load Seasonal Characteristics sorting technique |
CN107273920A (en) * | 2017-05-27 | 2017-10-20 | 西安交通大学 | A kind of non-intrusion type household electrical appliance recognition methods 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 |
-
2018
- 2018-04-13 CN CN201810331211.1A patent/CN108537281A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
CN107273920A (en) * | 2017-05-27 | 2017-10-20 | 西安交通大学 | A kind of non-intrusion type household electrical appliance recognition methods based on random forest |
CN107194600A (en) * | 2017-06-01 | 2017-09-22 | 国网山东省电力公司济南市历城区供电公司 | A kind of electric load Seasonal Characteristics sorting technique |
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 |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109410074A (en) * | 2018-10-18 | 2019-03-01 | 广州市勤思网络科技有限公司 | Intelligent core protects method and system |
CN109544035A (en) * | 2018-12-12 | 2019-03-29 | 上海理工大学 | Electric energy efficiency analysis and ranking method based on random forest |
CN110795560A (en) * | 2019-10-21 | 2020-02-14 | 国网湖南省电力有限公司 | Method and system for subdividing power grid electricity customers |
CN111753907A (en) * | 2020-06-24 | 2020-10-09 | 国家电网有限公司大数据中心 | Method, device, equipment and storage medium for processing electric quantity data |
CN113673579A (en) * | 2021-07-27 | 2021-11-19 | 国网湖北省电力有限公司营销服务中心(计量中心) | Power load classification algorithm based on small samples |
CN113673579B (en) * | 2021-07-27 | 2024-05-28 | 国网湖北省电力有限公司营销服务中心(计量中心) | Small sample-based electricity load classification algorithm |
CN113988161A (en) * | 2021-10-15 | 2022-01-28 | 贵州大学 | User electricity consumption behavior pattern recognition method |
CN113988161B (en) * | 2021-10-15 | 2022-08-19 | 贵州大学 | User electricity consumption behavior pattern recognition method |
CN114154561A (en) * | 2021-11-15 | 2022-03-08 | 国家电网有限公司 | Electric power data management method based on natural language processing and random forest |
CN114154561B (en) * | 2021-11-15 | 2024-02-27 | 国家电网有限公司 | Electric power data management method based on natural language processing and random forest |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108537281A (en) | A kind of power consumer feature recognition sorting technique based on random forest | |
CN108062560A (en) | A kind of power consumer feature recognition sorting technique based on random forest | |
CN107273920A (en) | A kind of non-intrusion type household electrical appliance recognition methods based on random forest | |
CN103034691B (en) | A kind of expert system knowledge acquisition methods based on support vector machine | |
CN104573879B (en) | Photovoltaic plant based on optimal similar day collection goes out force prediction method | |
CN105303468A (en) | Comprehensive evaluation method of smart power grid construction based on principal component cluster analysis | |
CN102929942A (en) | Social network overlapping community finding method based on ensemble learning | |
CN104462762A (en) | Fuzzy fault classification method of electric transmission line | |
CN107194600A (en) | A kind of electric load Seasonal Characteristics sorting technique | |
CN104036073B (en) | Double-fed wind power plant dynamic equivalence modeling method suitable for active power characteristic analysis | |
CN104182803B (en) | Wind-powered electricity generation data preprocessing method and wind power forecasting method and system | |
CN102200981B (en) | Feature selection method and feature selection device for hierarchical text classification | |
CN106597154B (en) | Transformer fault diagnosis method for improving based on DAG-SVM | |
CN109919921A (en) | Based on the influence degree modeling method for generating confrontation network | |
CN111275204B (en) | Transformer state identification method based on hybrid sampling and ensemble learning | |
CN102930299A (en) | Fault diagnosis method for multi-feature selection multilevel transformer based on optimization method | |
CN102163286A (en) | Pornographic image evaluating method | |
CN106777005A (en) | User power utilization behavior analysis method based on big data technological improvement clustering algorithm | |
CN112994115A (en) | New energy capacity configuration method based on WGAN scene simulation and time sequence production simulation | |
CN105023192A (en) | Power system source-grid-load interaction control strategy evaluation method | |
CN105718941B (en) | Stellar spectrum outlier data digging method based on the classification of fuzzy large-spacing minimum ball | |
Chen et al. | Electricity theft detection model for smart meter based on residual neural network | |
CN110648066B (en) | Method for preferential generation quota of reservoir power station | |
Trappey et al. | Evaluating renewable energy policies using hybrid clustering and analytic hierarchy process modeling | |
CN114461662A (en) | Method and system for screening high-potential users in response to demands of residents |
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 |
Application publication date: 20180914 |
|
WD01 | Invention patent application deemed withdrawn after publication |