CN106096805A - A kind of residential electricity consumption load classification method based on entropy assessment feature selection - Google Patents
A kind of residential electricity consumption load classification method based on entropy assessment feature selection Download PDFInfo
- Publication number
- CN106096805A CN106096805A CN201610303136.9A CN201610303136A CN106096805A CN 106096805 A CN106096805 A CN 106096805A CN 201610303136 A CN201610303136 A CN 201610303136A CN 106096805 A CN106096805 A CN 106096805A
- Authority
- CN
- China
- Prior art keywords
- feature
- electricity consumption
- user
- entropy
- weight
- 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.)
- Withdrawn
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000000605 extraction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 claims 1
- 238000004422 calculation algorithm Methods 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 4
- 239000004575 stone Substances 0.000 abstract description 2
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 238000012216 screening Methods 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of residential electricity consumption load classification method based on entropy assessment feature selection, comprise the following steps: obtain user power utilization data;Selection sort influence factor, i.e. for the feature of classification;Feature is carried out preferably by the comentropy and the respective weights that calculate each feature;User data is trained by the feature after using preferably, is clustered user by clustering algorithm;Sample after training is identified.The present invention preferably further dimensionality reduction by user data feature, effectively reduce the amount of calculation of cluster process, consider each feature clustering effect when computed range, each feature to be weighted simultaneously, improve the accuracy of cluster, thus be load prediction, flood peak staggered regulation, the intelligent power consumption strategy such as demand response lays the first stone.
Description
Technical field
The invention belongs to intelligent power technical field, particularly relate to a kind of residential electricity consumption based on entropy assessment feature selection and bear
Lotus sorting technique.
Background technology
Along with the in-depth of power system reform, enterprise implement dsm alleviates the nervous situation of operation of power networks and excellent
Change and utilize resource, therefore analyze customer charge characteristic and improve Power System Reliability important in inhibiting for more preferable, based on negative
The cluster analysis research of lotus characteristic is also more widely used.
In the face of colony is more and more huger, electricity consumption user power utilization behavior the most flexibly, implementing Demand Side Response measure
Before, it is not necessary that it is also impossible to each user is gone one by one Modeling Research, but by the method for cluster, by them with
The typical user's classification confirmed compares, and goes out their use electrical characteristics by that analogy, thus back-up needs responds project implementation,
It is greatly improved work efficiency.
In cluster process, when user data is extracted feature, choosing of feature is all artificial subjective selection, wherein selected
The feature taken the most effectively does not has an objective appraisal, therefore existing characteristics too much causes calculating the problem increased, therefore have must
The feature of subjective selection is carried out preferably.
Summary of the invention
Based on this, the invention provides a kind of residential electricity consumption load classification method based on entropy assessment feature selection.
This based on entropy assessment feature selection the residential electricity consumption load classification method that the present invention provides specifically includes following
Step:
Step 1: obtain the user power utilization data of required classification;
Step 2: select the feature of user power utilization load classification, user data is carried out feature extraction;
Step 3: use entropy assessment to calculate comentropy and the entropy weight of user power utilization load characteristic;
Step 4: user power utilization load characteristic is carried out preferably according to entropy weight;
Step 5: the user power utilization load characteristic after using preferably carries out cluster training to user data;
Step 6: the electricity consumption behavior to the typical user after training is identified.
Compared with general technology, present invention residential electricity consumption based on entropy assessment feature selection load classification method, except master
See the feature selected for classification, also feature has been carried out objective screening, further user data has been carried out dimensionality reduction, effectively
The amount of calculation reducing cluster process, simultaneously because get rid of during preferably is the poor feature of effect, so row
Except rear less on Clustering Effect impact, substantially can guarantee that the accuracy of cluster, and it is special to have considered each in cluster process
Levy Clustering Effect, thus each feature can be weighted when computed range, thus improve Clustering Effect.
Advantageously reduce the amount of calculation of user power utilization load classification, and make the precision of analysis of user power utilization behavior higher,
Thus for load prediction, flood peak staggered regulation, the intelligent power consumption strategy such as demand response lays the first stone.
Accompanying drawing explanation
Fig. 1 is the inventive method overall flow figure.
Fig. 2 is the inventive method comentropy and weight calculation flow chart.
Fig. 3 is the inventive method feature preferred flow charts.
Fig. 4 is the typical user's curve synoptic diagram after the inventive method.
Detailed description of the invention
By further illustrating the technological means and the effect of acquirement that the present invention taked, below in conjunction with the accompanying drawings and the most real
Execute example, to technical scheme, carry out clear and complete description.
As it is shown in figure 1, a kind of residential electricity consumption load classification method based on entropy assessment feature selection comprises the following steps:
Step 1: obtain user power utilization data;
Extracted the load curve of electricity consumption user by power information acquisition system, this load curve is generally intelligent electric meter every 15
Minute gather 1 point, one day 96 point, power information acquisition system is by being calculated the power information of ammeter collection
24 hours load curves of user.
Step 2: select the feature of residential electricity consumption load classification, user data is carried out feature extraction;
Selecting key feature pointedly according to classification purpose, it includes but not limited to electricity consumption total amount, and during peak, consumption rate (is defined as
Peak period power consumption with the ratio of total electricity consumption), paddy electrostrictive coefficient (is defined as the ratio of low-valley interval power consumption and total electricity consumption), flat
Section electricity consumption percentage ratio (being defined as the ratio of flat section power consumption and total electricity consumption), peak-valley difference, rate of load condensate (is defined as user's average load
Ratio with peak load) etc. load characteristic.
Step 3: use entropy assessment to calculate comentropy and the entropy weight thereof of residential electricity consumption load characteristic;
As in figure 2 it is shown, calculate comentropy and the entropy weight thereof of residential electricity consumption load characteristic according to following steps:
To be treated that preferred feature forms following state matrix R', wherein r' by the n of m userjiRepresent that i-th user is in jth
Eigenvalue in individual feature,
According to below equation, R' is standardized process and obtains standardized state matrix R, wherein r'jiRepresent through standard
The i-th user that change processes eigenvalue in jth feature, its value is all between 0 ~ 1,
The proportion P of the user power utilization behavior characteristics of each object is calculated according to below equationji,
According to proportion PjiEntropy corresponding as follows,
Wherein as p=0, PjilnPji=0, then counted entropy all meets 0≤eijThe constraints of≤1;
The feature weight w for judging is calculated according to below equation according to comentropyj,
。
Step 4: residential electricity consumption load characteristic is carried out preferably according to entropy weight;
As it is shown on figure 3, feature is carried out preferably according to calculating gained entropy weight according to following steps:
First according to formulaCalculate preferred threshold value, wherein NFNumber for feature selected in step 2;Then select
Select maximum feature corresponding to weights in feature weight set and, from selecting proposition characteristic set, put into preferred feature set;?
Calculate the weight sum that the feature in preferred feature set is corresponding, it is judged that whether it is more than threshold value, if more than threshold value, preferably tying
Bundle, exports preferred feature set, if less than threshold value, repeats selection course, until weight and more than threshold value, exports preferred feature
Set.
Step 5: user data is trained by the feature after using preferably, is clustered user by clustering algorithm;
With set of preferred features cooperation for input data, given FUZZY WEIGHTED index, cluster classification number, iteration stopping threshold value is set,
Initialize cluster centre, iteration count is set, use fuzzy C-mean algorithm (FCM) algorithm that it is clustered.Cluster process is fallen into a trap
Below equation is used to be weighted when calculating distance,
Wherein d (Xm,Xn) represent the distance between sample and sample, wjRepresent the comentropy weight that user power utilization behavior characteristics is corresponding,
xmjAnd xnjRepresent the feature of sample.
Step 6: the electricity consumption behavior to the typical resident after training is identified.
According to sorted class of subscriber, the electricity consumption behavior to all types of user is analyzed, identify its use power mode.
The present invention is described in detail below by a specific embodiment.
The day power load curve of 800 residents in certain city is extracted, as example, according to this by information acquisition system
Invent described method to classify.
First it is to obtain user power utilization data, as a example by 24 hours power loads of a user, its load such as table 1 below institute
Show,
24 hours power load statistics of table 1 user
Time | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 |
Power consumption | 0.958 | 0.2396 | 0.2673 | 0.4506 | 0.478 | 0.4629 | 0.7966 | 0.8744 |
Time | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 |
Power consumption | 0.5548 | 0.9877 | 1.6138 | 0.8411 | 1.143 | 0.3751 | 1.0529 | 0.5595 |
Time | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 |
Power consumption | 0.9121 | 0.2622 | 0.4524 | 0.201 | 0.1533 | 0.1685 | 0.1714 | 0.1963 |
Then according to user power utilization curve, extract power load feature according to, by with power consumption when selecting peak as a example by 1 user
Rate, paddy electrostrictive coefficient, flat section electricity consumption percentage ratio, rate of load condensate four kinds represents the key feature of user power utilization load fluctuation situation, accordingly
Can be calculated this user power utilization load characteristic as shown in table 2 below,
Table 2 power load eigenvalue
Consumption rate during peak | Paddy electrostrictive coefficient | Flat section electricity consumption percentage ratio | Rate of load condensate |
0.3838 | 0.2716 | 0.3446 | 0.3659 |
Again user characteristics set is normalized, the user power utilization load characteristic as a example by 10 users, after normalization
It is as shown in the table,
Table 3 certain customers normalization load characteristic
User's sequence number | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
Consumption rate during peak | 0.32 | 0.70 | 0.21 | 0.35 | 0.00 | 0.22 | 0.51 | 1.00 | 0.08 | 0.45 |
Paddy electrostrictive coefficient | 0.67 | 0.34 | 0.52 | 0.48 | 0.96 | 0.54 | 0.41 | 0.27 | 0.83 | 0.38 |
Flat section electricity consumption percentage ratio | 0.47 | 0.37 | 0.74 | 0.62 | 0.52 | 0.71 | 0.52 | 0.12 | 0.56 | 0.62 |
Rate of load condensate | 0.98 | 0.28 | 0.30 | 0.59 | 0.57 | 0.47 | 0.48 | 0.04 | 0.52 | 0.57 |
And calculate the entropy of each feature, result is as shown in the table,
Table 4 user power utilization load characteristic entropy
Consumption rate during peak | Paddy electrostrictive coefficient | Flat section electricity consumption percentage ratio | Rate of load condensate |
0.9360 | 0.9477 | 0.9751 | 0.9714 |
Gained weight is calculated as shown in the table according to entropy
Table 5 user power utilization load characteristic comentropy weight
Consumption rate during peak | Paddy electrostrictive coefficient | Flat section electricity consumption percentage ratio | Rate of load condensate |
0.3768 | 0.3079 | 0.1467 | 0.1686 |
Carrying out preferably according to the method for the invention, original feature has carried out dimensionality reduction, last gained preferred feature is peak
Time consumption rate, paddy electrostrictive coefficient, rate of load condensate.
Then with these three user power utilization load characteristic carry out cluster training, clusters number is set to 5, initial cluster center with
Machine is chosen, and FUZZY WEIGHTED index is set to, and iteration stopping threshold value is set to 10-6, use FCM algorithm that user is clustered, cluster knot
All kinds of typical curves in Guo are as shown in Figure 4.It is as shown in the table with traditional algorithm comparing result, and the present invention can be to user
The further dimensionality reduction of power load feature, and the accuracy having lifted clustering algorithm can be improved simultaneously.
Table 6 algorithm performance contrasts
Algorithm | Characteristic Number | Accuracy |
Traditional F CM algorithm | 4 | 83.25% |
The present invention provides algorithm | 3 | 95.75% |
Result shown in 4 with reference to the accompanying drawings, being identified with power mode user, it is seen that first kind user's whole day power consumption one
Directly it is in high levels;And the 2nd class user can in the afternoon 3 to electricity consumptions a large amount of between morning;3rd class user power utilization is less, but still
Exist rise and fall, its by day electricity consumption apparently higher than evening;4th class user's electricity consumption in the morning is more, and morning, electricity consumption was less, remaining period
Electricity consumption is mild;There is obvious peak of power consumption in the 5th class user, its electricity consumption is concentrated mainly on morning 7 and mid-afternoon.
The above, the only present invention preferably detailed description of the invention, but protection scope of the present invention is not limited thereto,
Any those familiar with the art in the technical scope that the invention discloses, the change that can readily occur in or replacement,
All should contain within protection scope of the present invention;Therefore, protection scope of the present invention should be with scope of the claims
It is as the criterion.
Claims (5)
1. a distribution line information monitoring service communication method for predicting, it is characterised in that comprise the following steps:
A kind of residential electricity consumption load classification method based on entropy assessment feature selection, it is characterised in that comprise the following steps:
Step 1: obtain the user power utilization data of required classification;
Step 2: select the feature of user power utilization load classification, user data is carried out feature extraction;
Step 3: use entropy assessment to calculate comentropy and the entropy weight of user power utilization load characteristic;
Step 4: user power utilization load characteristic is carried out preferably according to entropy weight;
Step 5: the user power utilization load characteristic after using preferably carries out cluster training to user data;
Step 6: the electricity consumption behavior to the typical user after training is identified.
2., according to the residential electricity consumption load classification method based on entropy assessment feature selection described in claim 1, its feature exists
In, use entropy assessment to calculate comentropy and the entropy weight thereof of resident's power load feature, it is as follows that it calculates process:
First the proportion of the residential electricity consumption load characteristic of each object is calculated,
According to proportion PjiEntropy corresponding as follows,
The feature weight w for judging is calculated according to below equation according to comentropyj,
。
3., according to the residential electricity consumption load classification method based on entropy assessment feature selection described in claim 1, its feature exists
In, its described preferred process is as follows, first calculates comentropy and the respective weights of feature, resets for preferred threshold value p,
Then select in feature weight set the feature corresponding to maximum weight to put into preferred feature set, calculate preferred feature set
The weight sum that middle feature is corresponding, it is judged that whether it is more than threshold value, if more than threshold value, exporting preferred feature set, if less than threshold
Value then repeats selection course, until weight and more than threshold value, exports preferred feature set.
Residential electricity consumption load classification method based on entropy assessment feature selection the most according to claim 3, it is characterised in that root
Preferred threshold value is calculated according to below equationp,, wherein NFNumber for selected feature.
5., according to the residential electricity consumption load classification method based on entropy assessment feature selection described in claim 1, its feature exists
In, cluster process is calculated in available preferred process sample distance calculating is weighted by weight.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610303136.9A CN106096805A (en) | 2016-05-10 | 2016-05-10 | A kind of residential electricity consumption load classification method based on entropy assessment feature selection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610303136.9A CN106096805A (en) | 2016-05-10 | 2016-05-10 | A kind of residential electricity consumption load classification method based on entropy assessment feature selection |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106096805A true CN106096805A (en) | 2016-11-09 |
Family
ID=57229855
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610303136.9A Withdrawn CN106096805A (en) | 2016-05-10 | 2016-05-10 | A kind of residential electricity consumption load classification method based on entropy assessment feature selection |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106096805A (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229602A (en) * | 2017-05-22 | 2017-10-03 | 湘潭大学 | A kind of recognition methods of intelligent building microgrid electricity consumption behavior |
CN107703854A (en) * | 2017-10-26 | 2018-02-16 | 国网黑龙江省电力有限公司信息通信公司 | power load monitoring system and method |
CN107729455A (en) * | 2017-09-25 | 2018-02-23 | 山东科技大学 | A kind of social network opinion leader sort algorithm based on multidimensional characteristic analysis |
CN108960657A (en) * | 2018-07-13 | 2018-12-07 | 国网上海市电力公司 | One kind being based on the preferred building Load Characteristic Analysis method of feature |
CN109193674A (en) * | 2018-08-30 | 2019-01-11 | 中国南方电网有限责任公司 | Substation's load different degree online evaluation method based on entropy weight |
CN109241991A (en) * | 2018-07-23 | 2019-01-18 | 南昌大学 | A kind of data clusters integrated approach based on comentropy weight incremental learning strategy |
CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
CN109685552A (en) * | 2018-12-06 | 2019-04-26 | 国网山东省电力公司青岛供电公司 | The analysis of non-intrusion type residential electricity consumption efficiency and method of servicing |
CN109816034A (en) * | 2019-01-31 | 2019-05-28 | 清华大学 | Signal characteristic combines choosing method, device, computer equipment and storage medium |
CN110009231A (en) * | 2019-04-04 | 2019-07-12 | 上海电力学院 | A kind of power load recognition methods and device based on repeatability and entropy weight distinction |
WO2019184131A1 (en) * | 2018-03-29 | 2019-10-03 | 清华大学 | Entropy method and density clustering method integrated power stealing detection method and apparatus |
CN110659699A (en) * | 2019-09-30 | 2020-01-07 | 重庆大学 | Distributed double-layer clustering analysis method based on feature index dimension reduction |
CN110766032A (en) * | 2018-07-27 | 2020-02-07 | 国网江西省电力有限公司九江供电分公司 | Power distribution network data clustering integration method based on hierarchical progressive strategy |
CN110826641A (en) * | 2019-11-13 | 2020-02-21 | 上海积成能源科技有限公司 | System and method for classifying electricity consumption condition of residents based on cluster analysis |
CN110825723A (en) * | 2019-10-09 | 2020-02-21 | 上海电力大学 | Residential user classification method based on power load analysis |
CN111144447A (en) * | 2019-12-09 | 2020-05-12 | 国网新疆电力有限公司电力科学研究院 | Power grid peak-valley time interval division method for preventing peak regulation risk caused by new energy output |
CN111612275A (en) * | 2020-05-29 | 2020-09-01 | 云南电网有限责任公司 | Method and device for predicting load of regional user |
CN111915116A (en) * | 2019-05-10 | 2020-11-10 | 国网能源研究院有限公司 | Electric power resident user classification method based on K-means clustering |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779510A (en) * | 2012-07-19 | 2012-11-14 | 东南大学 | Speech emotion recognition method based on feature space self-adaptive projection |
-
2016
- 2016-05-10 CN CN201610303136.9A patent/CN106096805A/en not_active Withdrawn
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102779510A (en) * | 2012-07-19 | 2012-11-14 | 东南大学 | Speech emotion recognition method based on feature space self-adaptive projection |
Non-Patent Citations (3)
Title |
---|
张素香等: ""基于云计算的居民用电行为分析模型研究"", 《电网技术》 * |
王国伟等: ""基于熵权法加权的模糊C均值聚类算法研究"", 《农业网络信息》 * |
高翠芳等: ""基于信息熵加权的协同聚类改进算法"", 《计算机应用研究》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229602A (en) * | 2017-05-22 | 2017-10-03 | 湘潭大学 | A kind of recognition methods of intelligent building microgrid electricity consumption behavior |
CN107729455A (en) * | 2017-09-25 | 2018-02-23 | 山东科技大学 | A kind of social network opinion leader sort algorithm based on multidimensional characteristic analysis |
CN107703854A (en) * | 2017-10-26 | 2018-02-16 | 国网黑龙江省电力有限公司信息通信公司 | power load monitoring system and method |
WO2019184131A1 (en) * | 2018-03-29 | 2019-10-03 | 清华大学 | Entropy method and density clustering method integrated power stealing detection method and apparatus |
CN108960657A (en) * | 2018-07-13 | 2018-12-07 | 国网上海市电力公司 | One kind being based on the preferred building Load Characteristic Analysis method of feature |
CN108960657B (en) * | 2018-07-13 | 2021-11-12 | 国网上海市电力公司 | Building load characteristic analysis method based on feature optimization |
CN109241991A (en) * | 2018-07-23 | 2019-01-18 | 南昌大学 | A kind of data clusters integrated approach based on comentropy weight incremental learning strategy |
CN110766032A (en) * | 2018-07-27 | 2020-02-07 | 国网江西省电力有限公司九江供电分公司 | Power distribution network data clustering integration method based on hierarchical progressive strategy |
CN109193674A (en) * | 2018-08-30 | 2019-01-11 | 中国南方电网有限责任公司 | Substation's load different degree online evaluation method based on entropy weight |
CN109492667A (en) * | 2018-10-08 | 2019-03-19 | 国网天津市电力公司电力科学研究院 | A kind of feature selecting discrimination method for non-intrusive electrical load monitoring |
CN109685552A (en) * | 2018-12-06 | 2019-04-26 | 国网山东省电力公司青岛供电公司 | The analysis of non-intrusion type residential electricity consumption efficiency and method of servicing |
CN109816034A (en) * | 2019-01-31 | 2019-05-28 | 清华大学 | Signal characteristic combines choosing method, device, computer equipment and storage medium |
CN109816034B (en) * | 2019-01-31 | 2021-08-27 | 清华大学 | Signal characteristic combination selection method and device, computer equipment and storage medium |
CN110009231A (en) * | 2019-04-04 | 2019-07-12 | 上海电力学院 | A kind of power load recognition methods and device based on repeatability and entropy weight distinction |
CN111915116A (en) * | 2019-05-10 | 2020-11-10 | 国网能源研究院有限公司 | Electric power resident user classification method based on K-means clustering |
CN110659699A (en) * | 2019-09-30 | 2020-01-07 | 重庆大学 | Distributed double-layer clustering analysis method based on feature index dimension reduction |
CN110825723A (en) * | 2019-10-09 | 2020-02-21 | 上海电力大学 | Residential user classification method based on power load analysis |
CN110825723B (en) * | 2019-10-09 | 2023-04-25 | 上海电力大学 | Resident user classification method based on electricity load analysis |
CN110826641A (en) * | 2019-11-13 | 2020-02-21 | 上海积成能源科技有限公司 | System and method for classifying electricity consumption condition of residents based on cluster analysis |
CN111144447A (en) * | 2019-12-09 | 2020-05-12 | 国网新疆电力有限公司电力科学研究院 | Power grid peak-valley time interval division method for preventing peak regulation risk caused by new energy output |
CN111144447B (en) * | 2019-12-09 | 2022-05-31 | 国网新疆电力有限公司电力科学研究院 | Power grid peak-valley time interval division method for preventing peak regulation risk caused by new energy output |
CN111612275A (en) * | 2020-05-29 | 2020-09-01 | 云南电网有限责任公司 | Method and device for predicting load of regional user |
CN111612275B (en) * | 2020-05-29 | 2022-04-01 | 云南电网有限责任公司 | Method and device for predicting load of regional user |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106096805A (en) | A kind of residential electricity consumption load classification method based on entropy assessment feature selection | |
CN108280479B (en) | Power grid user classification method based on load characteristic index weighted clustering algorithm | |
CN104809658B (en) | A kind of rapid analysis method of low-voltage distribution network taiwan area line loss | |
CN106529707A (en) | Load power consumption mode identification method | |
CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
CN105389636A (en) | Low-voltage area KFCM-SVR reasonable line loss prediction method | |
CN111242161B (en) | Non-invasive non-resident user load identification method based on intelligent learning | |
CN108805213B (en) | Power load curve double-layer spectral clustering method considering wavelet entropy dimensionality reduction | |
CN108428055B (en) | Load clustering method considering load longitudinal characteristics | |
CN110610121B (en) | Small-scale source load power abnormal data identification and restoration method based on curve clustering | |
CN110109971A (en) | A kind of low-voltage platform area user power utilization Load Characteristic Analysis method | |
CN108376262A (en) | A kind of analysis model construction method of wind power output typical characteristics | |
CN108122057B (en) | Comprehensive evaluation method and device for intelligent park energy utilization scheme | |
CN107784518A (en) | A kind of power customer divided method based on multidimensional index | |
CN111461921B (en) | Load modeling typical user database updating method based on machine learning | |
CN106777005A (en) | User power utilization behavior analysis method based on big data technological improvement clustering algorithm | |
CN112132488A (en) | Reservoir ecological scheduling method based on coupling modeling, optimization and optimization | |
CN107169655A (en) | A kind of method and device of preferred power distribution network project compatibility | |
CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
CN111798333A (en) | Energy utilization evaluation and electricity utilization safety analysis method and system | |
CN110244099A (en) | Stealing detection method based on user's voltage | |
CN107248031A (en) | A kind of fast power user classification method for load curve peak-valley difference | |
Lu et al. | Adaptive weighted fuzzy clustering algorithm for load profiling of smart grid customers | |
CN110363384A (en) | Exception electric detection method based on depth weighted neural network | |
CN111339167A (en) | Method for analyzing influence factors of transformer area line loss rate based on K-means and principal component linear regression |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20161109 |