CN107944495A - A kind of household electricity load classification recognition methods based on deep layer forest algorithm - Google Patents
A kind of household electricity load classification recognition methods based on deep layer forest algorithm Download PDFInfo
- Publication number
- CN107944495A CN107944495A CN201711260609.2A CN201711260609A CN107944495A CN 107944495 A CN107944495 A CN 107944495A CN 201711260609 A CN201711260609 A CN 201711260609A CN 107944495 A CN107944495 A CN 107944495A
- Authority
- CN
- China
- Prior art keywords
- deep layer
- forest
- household electricity
- electricity load
- data
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention and to a kind of household electricity load classification recognition methods based on deep layer forest algorithm, intelligent collection is carried out to the performance data of different home power load by home intelligent acquisition terminal first, secondly by mass data storage in server end, it is carried out at the same time data prediction, reuse wide area information server and establish training dataset, and deep layer forest algorithm model is trained, intelligent classification identification finally is carried out to household electricity load using the deep layer forest algorithm that training is completed.The present invention has the advantages that deep layer characteristic features are excavated, can voluntarily determine the screening number of plies to reduce calculation amount, can be to effectively carrying out intelligent recognition to family's Overload Class, acquired results can serve the various aspects such as grid DSM, electricity market, so as to be conducive to improve the economic benefit of electric power enterprise.
Description
Technical field
The present invention relates to household electricity load classification to identify field, more particularly to a kind of family based on deep layer forest algorithm
Front yard power load classifying identification method.
Background technology
Peak load is presently, there are in face of power grid and constantly refreshes historical high, and the present situation that peak-valley difference further widens, is carried out
Demand-side electric energy management is the effective way solved the problems, such as.But residential households electricity consumption at present participate in the ratio of Load Regulation also compared with
It is small.One reason for this is that accurately the power load of domestic consumer accurately can not be identified at present, and for excavating not
The adjustable potentiality of same family.In order to tackle such a situation, intelligent classification identification is carried out to household electricity load, is new shape
An effective measure of demand Side Management is promoted under state.
Novel intelligent home progressively starts to come into huge numbers of families, and the household electricity information for obtaining magnanimity has no longer been a difficulty
Topic.But it is continuously increased with the classification of domestic electric appliances, it is unpractiaca artificially to carry out Classification and Identification to household electricity information.Cause
This, in face of the processing and classification of domestic consumer's electricity consumption data of magnanimity, electric power enterprise is badly in need of finding a method rapidly and efficiently
To classify to power consumer electricity consumption classification.
The content of the invention
It is right it is an object of the invention to provide a kind of household electricity load classification recognition methods based on deep layer forest algorithm
Household electricity load is extracted and remembered with electrical feature, the electricity consumption characteristic index with considerable influence degree is carried out successively strong
Chemistry is practised, so as to reach the target that deep layer intelligent recognition is carried out to domestic consumer's Overload Class.
To achieve the above object, the present invention provides following technical solution：
A kind of household electricity load classification recognition methods based on deep layer forest algorithm, comprises the following steps：
S110：Intelligent collection is carried out to the performance data of different home power load by home intelligent acquisition terminal；
S120：The household electricity load data collected is uploaded onto the server and end and is stored to household electricity load data
Storehouse, while the data of household electricity load are pre-processed and the calculating of the important key parameters of household electricity load；
S130：The training of deep layer forest algorithm is established using data in household electricity load database and important key parameters
Data set, the training dataset include set of data samples and test set；
S140：Needed to set the parameter of deep layer forest algorithm according to user, determine the generation algorithm of forest, decision tree
Number；
S150：It is trained, is formed with the deep layer for successively strengthening screening using training sample set pair deep layer forest algorithm
Forest model；
S160：Tested using the accuracy of classification of the test set to deep layer forest model, determine deep layer forest model
The number of plies；
S170：Certain time interval is set, using the household electricity load data being continuously generated, to deep layer forest model
It is updated；
S180：After obtaining the deep layer forest model of training completion, the family for needing newly to access is inputted into deep layer forest model
The observation Value Data of front yard load, the classification results of final output load type.
Preferably, domestic consumer's power load performance data includes：The voltage of electrical appliance, electric current, active power,
Reactive capability curve, the home intelligent acquisition terminal carry out high frequency to the voltage, electric current, harmonic data of all kinds of domestic electric appliances
Collection, and the data upload server of domestic electric appliances is stored.
Preferably, the important key parameters of household electricity load include：Active power scope, Overload Class, day He Feng
Number, inrush current multiple, the duration of operation, the cycle of operation etc..
Preferably, the parameter of the step S140 mid-deep strata forest algorithms includes：Forest production method, the complete journey of forest
Decision tree number in degree, each forest.
Preferably, the step S150 mid-deep stratas forest model has the forest screening combined process of certain level：Will be every
One layer of output result strengthens screening dynamics into next layer of forest, successively strengthens, carry as enhancing vector, further processing
The precision of high-class；The important key parameters of household electricity load calculated are carried out with family's load classification identification of deep layer.
Preferably, the number of plies of the step S160 mid-deep strata forests can be obtained according to the size of classification task, training set
Scale voluntarily determines that when training every layer of forest, algorithm will be tested the ability of existing model using test set, deep layer forest
Training process will continue to increase depth, improve recognition capability, until the accuracy of classification reaches certain numerical value, or the increase number of plies pair
The accuracy lifting of category of model is little, then stops the number of plies of increase deep layer forest.
Preferably, the deep layer forest model can voluntarily update, and improve the accuracy of Classification and Identification.With new family
The continuous upload server of front yard electrical appliance data, new data and past historical data are combined, establish new training sample set
Deep layer forest model is trained, further improves the accuracy of Classification and Identification.
Intelligent collection is carried out to the performance data of different home power load by home intelligent acquisition terminal first, its
It is secondary by mass data storage in server end, be carried out at the same time data prediction, reuse wide area information server and establish training
Data set, and deep layer forest algorithm model is trained, the deep layer forest algorithm finally completed using training is to household electricity
Load carries out intelligent classification identification.
Compared with prior art, usefulness of the present invention is：
The present invention considers mass data collection and processing method, is held each using machine learning and deep learning are theoretical
Relation between the different attribute of electrical appliance；Using deep layer forest algorithm, this is that a kind of newer machine learning data mining is calculated
Method, have training speed it is fast, can with parallel training and excavation, accuracy of identification is high the advantages that；Can be at regular intervals to classification
Model is updated, can be all to household electricity load into Mobile state online recognition；Can be to effectively carrying out intelligence to family's Overload Class
It can identify, acquired results can serve the various aspects such as grid DSM, electricity market, so as to be conducive to improve electric power enterprise
Economic benefit.
Brief description of the drawings
The present invention is further described below in conjunction with the accompanying drawings.
Fig. 1 is the household electricity load classification recognition methods flow chart based on deep layer forest algorithm of the present invention；
Fig. 2 is forest algorithm schematic diagram；
Fig. 3 is with the deep layer forest model for successively strengthening screening capacity.
Embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention will be described in detail：
Please refer to Fig.1, Fig. 2 and Fig. 3, the present invention provide a kind of household electricity load classification based on deep layer forest algorithm and know
Other method, based on magnanimity domestic electric appliances load data, intelligence is carried out using deep layer forest algorithm to family's part throttle characteristics
Excavate, the power consumer electricity consumption classifying identification method based on deep layer forest algorithm comprises the following steps：
S110：Intelligent collection is carried out to the performance data of different home power load by home intelligent acquisition terminal；
The concrete function of above-mentioned home intelligent acquisition terminal predominantly records real-time voltage, the electricity for the domestic electric appliances being currently accessed
Stream, active power output and the data such as voltage, current harmonic content, the terminal have the function module that information uploads, in real time
Data are uploaded onto the server and end and are stored to household electricity load database.
S120：The household electricity load data collected is uploaded onto the server and end and is stored to household electricity load data
Storehouse, while the data of household electricity load are pre-processed and the calculating of the important key parameters of household electricity load；Data
The normalized of numeric data is predominantly rejected in pretreatment, is eliminated the dimension impact between index, is described in detail below：
Wherein xminFor the maximum of sample data, xmaxFor the minimum value of sample data, x*To return to sample data
One result changed.
Important key parameters mainly include power factor (PF), power bound, loadtype, electrical appliance the cycle of operation,
The multiple of inrush current and normal operating current, indivedual Parameters Calculation methods are as follows：
Wherein P is active power, and Q is reactive power,For power factor (PF).
The loadtype of the load can be determined by the state of cos φ.
Wherein I ' is inrush current value when electrical appliance accesses, that is, starts the current maxima of moment.I0For electricity consumption
Electric current when device works normally, γ impact multiple for starting current.
Categorical data for electrical appliance corresponds therewith, it is necessary to which numeric data is manually set so that computer can
It is identified.
S130：The training of deep layer forest algorithm is established using data in household electricity load database and important key parameters
Data set, the output using the corresponding attribute data of each power load as deep layer forest model, establishes trained data sample
Collection and test set, training data sample set and test set respectively account for the 80% and 20% of sample total.
S140：Needed to set the parameter of deep layer forest algorithm according to user, determine the generation algorithm of forest, decision tree
Number；The parameter of deep layer forest algorithm includes：Determining in the generating mode of forest, the type of forest, the number of forest, each forest
Plan tree number, design parameter are as follows：
Algorithm types：CART algorithms, C4.5 algorithms a variety of are used in mixed way；
The type of forest：Completely random tree forest, random forest；
The number of forest：Even number generally is taken, it is preferable using 2/4/8 classifying quality.
Decision tree number in each forest：Acquiescence 500, scope for (0,1000].
S150：It is trained, is formed with the deep layer for successively strengthening screening using training sample set pair deep layer forest algorithm
Forest model；
As shown in Fig. 2, with the deep layer forest model such as Fig. 3 for successively strengthening screening capacity, it is specifically described forest algorithm
It is as follows：
To training complete deep layer forest model train input vector, each layer of forest set will produce enhancing vector as
Next layer of input, is successively screened, and effective information is successively transmitted and constantly accumulated, until obtaining final classification recognition result.
S160：Tested using the accuracy of classification of the test set to deep layer forest model, determine deep layer forest model
The number of plies；The number of plies of deep layer forest can be according to the size of classification task, and training set obtains scale and voluntarily determines, every layer of training is gloomy
Lin Shi, algorithm will be tested the ability of existing model using test set, and deep layer forest training process will continue to increase depth,
If the accuracy of classification reaches certain numerical value, or the increase number of plies lifts less the accuracy of category of model, then it is deep to stop increase
The number of plies of layer forest.
S170：Certain time interval is set, using the household electricity load data being continuously generated, to deep layer forest model
It is updated, is described in detail below：
It is combined using new magnanimity household electricity data and historical data base, builds new training sample set, returns to step
Rapid S140, renewal can be used for the deep layer forest model of household electricity load classification identification, improve nicety of grading.
S180：After obtaining the deep layer forest model of training completion, the family for needing newly to access is inputted into deep layer forest model
The observation Value Data of front yard load, the classification results of final output load type.
The above step of electrical appliance classification corresponding to can be obtained by by to(for) new household electricity load observation, leads to
The Classification and Identification to the load is crossed, power grid enterprises can be served and carry out become more meticulous demand side management, balanced load total amount, so that
Be conducive to improve the economic benefit of electric power enterprise.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of changes, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of household electricity load classification recognition methods based on deep layer forest algorithm, it is characterised in that comprise the following steps：
S110：Intelligent collection is carried out to the performance data of different home power load by home intelligent acquisition terminal；
S120：The household electricity load data collected is uploaded onto the server and end and is stored to household electricity load database,
The data of household electricity load are pre-processed at the same time and the calculating of the important key parameters of household electricity load；
S130：The training data of deep layer forest algorithm is established using data in household electricity load database and important key parameters
Collection, the training dataset include set of data samples and test set；
S140：Needed to set the parameter of deep layer forest algorithm according to user, determine the generation algorithm of forest, decision tree number；
S150：It is trained, is formed with the deep layer forest for successively strengthening screening using training sample set pair deep layer forest algorithm
Model；
S160：Tested using the accuracy of classification of the test set to deep layer forest model, determine the layer of deep layer forest model
Number；
S170：Certain time interval is set, using the household electricity load data being continuously generated, deep layer forest model is carried out
Renewal；
S180：After obtaining the deep layer forest model of training completion, the family that being inputted into deep layer forest model needs newly to access bears
The observation Value Data of lotus, the classification results of final output load type.
2. the household electricity load classification recognition methods according to claim 1 based on deep layer forest algorithm, its feature exist
In：The home intelligent acquisition terminal carries out the voltage, electric current, harmonic data of all kinds of domestic electric appliances high frequency collection, and will
The data upload server of domestic electric appliances is stored.
3. the household electricity load classification recognition methods according to claim 1 based on deep layer forest algorithm, its feature exist
In：The important key parameters of household electricity load include：The power factor of electrical appliance, the power bound of electrical appliance, electricity consumption
The multiple of the operating mode of device, electrical appliance starting current and rated current.
4. the household electricity load classification recognition methods according to claim 1 based on deep layer forest algorithm, its feature exist
In：The parameter of the step S140 mid-deep strata forest algorithms includes：Forest production method, the integrated degree of forest, each forest
In decision tree number.
5. the household electricity load classification recognition methods according to claim 1 based on deep layer forest algorithm, its feature exist
In：The step S150 mid-deep stratas forest model has the forest screening combined process of certain level：By each layer of output knot
Fruit strengthens screening dynamics into next layer of forest, successively strengthens, improve the accurate of classification as enhancing vector, further processing
Degree.
6. the household electricity load classification recognition methods according to claim 1 based on deep layer forest algorithm, its feature exist
In：The number of plies of the step S160 mid-deep strata forests can be according to the size of classification task, and training set obtains scale and voluntarily determines,
During every layer of forest of training, algorithm will be tested the ability of existing model using test set, and deep layer forest training process will not
Disconnected increasing depths, when the accuracy of classification reaches certain numerical value, or the accuracy that the increase number of plies classifies deep layer forest model carries
When rising little, then stop the number of plies of increase deep layer forest.
7. the household electricity load classification recognition methods according to claim 1 based on deep layer forest algorithm, its feature exist
In：The deep layer forest model can voluntarily update, and improve the accuracy of Classification and Identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711260609.2A CN107944495A (en) | 2017-12-04 | 2017-12-04 | A kind of household electricity load classification recognition methods based on deep layer forest algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711260609.2A CN107944495A (en) | 2017-12-04 | 2017-12-04 | A kind of household electricity load classification recognition methods based on deep layer forest algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107944495A true CN107944495A (en) | 2018-04-20 |
Family
ID=61947444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711260609.2A Pending CN107944495A (en) | 2017-12-04 | 2017-12-04 | A kind of household electricity load classification recognition methods based on deep layer forest algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944495A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491893A (en) * | 2018-04-13 | 2018-09-04 | 贵州电网有限责任公司 | A kind of household electricity load classification recognition methods based on deep layer forest algorithm |
| CN108776968A (en) * | 2018-06-22 | 2018-11-09 | 西安电子科技大学 | SAR image change detection based on depth forest |
| CN110443479A (en) * | 2019-07-25 | 2019-11-12 | 东南大学 | A kind of intrusive electric energy management system in intelligence community half and method |
| CN110533089A (en) * | 2019-08-19 | 2019-12-03 | 三峡大学 | Adaptive non-intrusion type load recognition methods based on random forest |
| CN110728391A (en) * | 2018-07-17 | 2020-01-24 | 广西大学 | Depth regression forest short-term load prediction method based on expandable information |
| CN111242391A (en) * | 2020-03-06 | 2020-06-05 | 云南电网有限责任公司电力科学研究院 | Machine learning model training method and system for power load identification |
| CN111404150A (en) * | 2020-03-30 | 2020-07-10 | 广西电网有限责任公司电力科学研究院 | Transient stability assessment method and system suitable for large power grid operation |
| CN111412948A (en) * | 2020-03-31 | 2020-07-14 | 南京云思顿环保科技有限公司 | Kitchen waste equipment fault diagnosis method based on deep forest |
| CN115545119A (en) * | 2022-11-24 | 2022-12-30 | 国网天津市电力公司城南供电分公司 | Method, system and application for identifying electricity consumption data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN106503728A (en) * | 2016-09-30 | 2017-03-15 | 深圳云天励飞技术有限公司 | A kind of image-recognizing method and device |
| CN106874959A (en) * | 2017-03-01 | 2017-06-20 | 南京大学 | A kind of multiple dimensioned scanning cascade forestry practises the training method of machine |
| CN107145976A (en) * | 2017-04-28 | 2017-09-08 | 北京科技大学 | A kind of method for predicting user power utilization load |
| 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 |
-
2017
- 2017-12-04 CN CN201711260609.2A patent/CN107944495A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN106503728A (en) * | 2016-09-30 | 2017-03-15 | 深圳云天励飞技术有限公司 | A kind of image-recognizing method and device |
| CN106874959A (en) * | 2017-03-01 | 2017-06-20 | 南京大学 | A kind of multiple dimensioned scanning cascade forestry practises the training method of machine |
| CN107145976A (en) * | 2017-04-28 | 2017-09-08 | 北京科技大学 | A kind of method for predicting user power utilization load |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| ZHI-HUA ZHOU ET AL: "Deep Forest: Towards An Alternative to Deep Neural Networks", 《ARXIV:1702.08835V2 [CS.LG]》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491893A (en) * | 2018-04-13 | 2018-09-04 | 贵州电网有限责任公司 | A kind of household electricity load classification recognition methods based on deep layer forest algorithm |
| CN108776968A (en) * | 2018-06-22 | 2018-11-09 | 西安电子科技大学 | SAR image change detection based on depth forest |
| CN110728391A (en) * | 2018-07-17 | 2020-01-24 | 广西大学 | Depth regression forest short-term load prediction method based on expandable information |
| CN110728391B (en) * | 2018-07-17 | 2022-07-05 | 广西大学 | Depth regression forest short-term load prediction method based on expandable information |
| CN110443479A (en) * | 2019-07-25 | 2019-11-12 | 东南大学 | A kind of intrusive electric energy management system in intelligence community half and method |
| CN110533089A (en) * | 2019-08-19 | 2019-12-03 | 三峡大学 | Adaptive non-intrusion type load recognition methods based on random forest |
| CN110533089B (en) * | 2019-08-19 | 2023-07-11 | 三峡大学 | Self-adaptive non-invasive load identification method based on random forest |
| CN111242391A (en) * | 2020-03-06 | 2020-06-05 | 云南电网有限责任公司电力科学研究院 | Machine learning model training method and system for power load identification |
| CN111404150A (en) * | 2020-03-30 | 2020-07-10 | 广西电网有限责任公司电力科学研究院 | Transient stability assessment method and system suitable for large power grid operation |
| CN111412948A (en) * | 2020-03-31 | 2020-07-14 | 南京云思顿环保科技有限公司 | Kitchen waste equipment fault diagnosis method based on deep forest |
| CN115545119A (en) * | 2022-11-24 | 2022-12-30 | 国网天津市电力公司城南供电分公司 | Method, system and application for identifying electricity consumption data |
| CN115545119B (en) * | 2022-11-24 | 2023-05-02 | 国网天津市电力公司城南供电分公司 | Power consumption data identification method, system and application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944495A (en) | A kind of household electricity load classification recognition methods based on deep layer forest algorithm | |
| CN107273920A (en) | A kind of non-intrusion type household electrical appliance recognition methods based on random forest | |
| CN109829604A (en) | A kind of grid side energy-accumulating power station operational effect comprehensive estimation method | |
| CN108154430A (en) | A kind of credit scoring construction method based on machine learning and big data technology | |
| CN111368904B (en) | Electrical equipment identification method based on electric power fingerprint | |
| CN106485089B (en) | The interval parameter acquisition methods of harmonic wave user's typical condition | |
| CN108011367B (en) | Power load characteristic mining method based on depth decision tree algorithm | |
| CN107038167A (en) | Big data excavating analysis system and its analysis method based on model evaluation | |
| CN108051660A (en) | A kind of transformer fault combined diagnosis method for establishing model and diagnostic method | |
| CN103869192B (en) | Intelligent grid line loss detection method and system | |
| CN107909208A (en) | Damage method drops in a kind of taiwan area distribution | |
| CN111242161B (en) | Non-invasive non-resident user load identification method based on intelligent learning | |
| CN108491893A (en) | A kind of household electricity load classification recognition methods based on deep layer forest algorithm | |
| CN105654196A (en) | Adaptive load prediction selection method based on electric power big data | |
| CN106777005A (en) | User power utilization behavior analysis method based on big data technological improvement clustering algorithm | |
| CN111628494A (en) | Low-voltage distribution network topology identification method and system based on logistic regression method | |
| CN110297469A (en) | The production line fault judgment method of Ensemble feature selection algorithm based on resampling | |
| CN105809573A (en) | Big data analysis based load nature authentication method | |
| CN112200209A (en) | Poor user identification method based on day-to-day power consumption | |
| CN113962477A (en) | Industrial electric quantity association aggregation prediction method, device, equipment and storage medium | |
| CN112508254B (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN107808245A (en) | Based on the network scheduler system for improving traditional decision-tree | |
| CN117034149A (en) | Fault processing strategy determining method and device, electronic equipment and storage medium | |
| CN110349050A (en) | A kind of intelligent stealing criterion method and device extracted based on electrical network parameter key feature | |
| CN108493933A (en) | A kind of Characteristics of Electric Load method for digging based on depth decision Tree algorithms |
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: 20180420 |
|
| WD01 | Invention patent application deemed withdrawn after publication |