CN106446967A - Novel power system load curve clustering method - Google Patents
Novel power system load curve clustering method Download PDFInfo
- Publication number
- CN106446967A CN106446967A CN201610956531.7A CN201610956531A CN106446967A CN 106446967 A CN106446967 A CN 106446967A CN 201610956531 A CN201610956531 A CN 201610956531A CN 106446967 A CN106446967 A CN 106446967A
- Authority
- CN
- China
- Prior art keywords
- load
- curve
- user
- load curve
- power system
- 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical 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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a novel power system load curve clustering method. The novel power system load curve clustering method comprises the following steps: step S1, obtaining daily load curve active power data in five or more days of loads or transformers to be classified from a monitoring, controlling and data-collecting system; step S2, taking a mean value of all workdays at every moment of each load or transformer as a user typical load curve according to the daily load curve active power data obtained in the step S1; step S3, carrying out standardization treatment on the user typical load curve obtained in the step S2; step S4, culturing the user typical load curve by using an affinity propagation algorithm to obtain preliminary classification results; step S5, calculating a user load form characteristic index, and carrying out min-max standardization treatment to obtain a standardized load form characteristic index; and step S6, carrying out secondary classification on the preliminary classification results in the step S4 based on the standardized load form characteristic index obtained in the step S5.
Description
Technical field
The present invention relates to field of power, more particularly to a kind of novel electric power system loading curve clustering method.
Background technology
With the development of intelligent power grid technology, various advanced measuring equipments are widely used in power system.
The sending out of power system, defeated, join, electricity consumption links all generate the data of magnanimity.How to extract from the electric power data of magnanimity
Valuable information is current power systematic research focus.In electricity market, sale of electricity business need to be based on the power use by time shearing of user
Behavioral characteristic carries out differentiated marketing, to react the cost of electric energy difference of different periods on Time of Day yardstick.But power consumer
Huge amount, it is difficult to formulate marketing rule by user, classification process need to be carried out according to the electricity consumption behavioral characteristic of user.User's is negative
Lotus curve has reacted the electricity consumption behavioural habits of user, by clustering to load curve, it will be appreciated that the electricity consumption behavior of user
Pattern, and then help electricity provider refinement marketing strategy.
Traditional power system load sorting technique is the Euclidean distance based on load curve, equal using Kmeans, Fuzzy C
Value, hierarchical clustering method algorithm are realized.The advantage for being clustered using the Euclidean distance of the full dimension of load curve is consideration load song
The numerical value of line whole periods, with most comprehensive information.But said method there is also deficiency, it is several using the essence of Euclidean distance
The proximity of what average distance, it is impossible to fully ensure that the similarity of seasonal effect in time series form or profile.And said method easily receives pole
End value and influence of noise.Often extract some indexs in Practical Project to represent the shape information of load, such as rate of load condensate, peak-valley difference
Rate, peak phase load factor, paddy phase load factor etc..These indexs can reflect engineering power consumption information of interest in practice, such as
Electricity using at the peak time information and different periods with electrical characteristics etc..During load characteristics clustering taking into account Load characteristics index can make to bear
Lotus curve classification is more reasonable.
For the deficiencies in the prior art, the present invention will can consider the thin of load curve based on full dimension load curve cluster
The advantage of the information of section information and Load characteristics index consideration load form is combined, it is proposed that a kind of novel electric power system loading
Curve clustering method.
Content of the invention
In view of this, it is an object of the invention to provide a kind of novel electric power system loading curve clustering method, the first step is adopted
Preliminary clusters are carried out with neighbour's propagation algorithm, second step carries out secondary classification, the party based on Load characteristics index using kNN algorithm
Method algorithm is more stable, and it is more accurate to classify.
The present invention is realized using below scheme：A kind of novel electric power system loading curve clustering method, specifically includes following
Step：
Step S1：Load to be sorted or the transformator work of more than 5 days are obtained from Monitoring and Controlling data acquisition system
The daily load curve active power data of day；
Step S2：The daily load curve active power data obtained by step S1, exist for each load or transformator
Each moment takes the meansigma methodss of all working day respectively as user's typical load curve；
Step S3：User's typical load curve that step S2 is obtained is standardized processing, using maximum standardization
Method, i.e. pij=pij/pimax, formula pijIn for j-th period of user i power, pimaxFor user i maximum electric power；
Step S4：Using neighbour's propagation algorithm, user's typical load curve is clustered, obtain preliminary classification results；
Step S5：Customer charge morphological character index is calculated, min-max is adopted to each customer charge morphological character index
Standardization obtains standardized load morphological character index.
Step S6：Based on the standardized load morphological character index that step S5 is obtained, the preliminary classification to step S4
As a result secondary classification is carried out.
Further, in step S4, neighbour's propagation algorithm is concretely comprised the following steps：
Step S41：Initialization similarity matrix S, degree of membership matrix A, Attraction Degree matrix R, preference value P, greatest iteration time
Number maxits, cluster centre stable degree；
Step S42：Below step is calculated when iterationses or cluster centre stable degree are less than setting value, otherwise enter
Next step：Rold=R '；Aold=A '；Update R and A；Calculate the matrix R ' and A ' of next step calculating；
Step S43：Choose all of r (i, i)+a (i, i)>0 point is used as cluster centre；
Step S44：Remainder strong point is assigned to nearest cluster centre as class label.
Further, in step S5, the customer charge morphological character index of employing includes rate of load condensate：Day
Peak-valley ratio：Peak phase load factor：Paddy phase load factor：Flat phase load factor：Wherein PavFor load meansigma methodss, PmaxFor load maximum, PminFor load minima, Pav.peakFor the load peak phase
Meansigma methodss, Pav.flatFor the flat phase meansigma methodss of load.Pav.valleyFor load paddy phase meansigma methodss.
Further, in step S6, secondary classification method is：For i-th load, with other all loadsAs training sample, wherein xkFor the load morphological characteristic index set vector of k-th load, ykFor k-th load
The classification for once clustering, is reclassified using kNN algorithm using the load as forecast sample, until all load classification are complete
Finish.
Compared with prior art, the present invention will can consider the details letter of load curve based on full dimension load curve cluster
The advantage of the information of breath and Load characteristics index consideration load form is combined, and the method is divided into two steps, and the first step is using being based on
The load curve clustering method of Euclidean distance obtains cluster result；Second step carries out two using kNN algorithm to power system load
Subseries.The invention has the advantages that：1st, the extremum for load curve and insensitive for noise, algorithm is more steady
Fixed.2nd, load curve configuration information can be considered, it is more accurate to classify.
Description of the drawings
Fig. 1 is method of the present invention schematic flow sheet.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention will be further described.
The present embodiment provides a kind of novel electric power system loading curve clustering method, as shown in figure 1, specifically including following step
Suddenly：
Step S1：Load to be sorted or the transformator work of more than 5 days are obtained from Monitoring and Controlling data acquisition system
The daily load curve active power data of day；
Step S2：The daily load curve active power data obtained by step S1, exist for each load or transformator
Each moment takes the meansigma methodss of all working day respectively as user's typical load curve；
Step S3：User's typical load curve that step S2 is obtained is standardized processing, using maximum standardization
Method, i.e. pij=pij/pimax, formula pijIn for j-th period of user i power, pimaxFor user i maximum electric power；
Step S4：Using neighbour's propagation algorithm, user's typical load curve is clustered, obtain preliminary classification results；
Step S5：Customer charge morphological character index is calculated, min-max is adopted to each customer charge morphological character index
Standardization obtains standardized load morphological character index.
Step S6：Based on the standardized load morphological character index that step S5 is obtained, the preliminary classification to step S4
As a result secondary classification is carried out.
In the present embodiment, neighbour's propagation algorithm concrete grammar is as follows：
Algorithm is first had to obtain similarity matrix S, the S of sample and can be measured by a lot of methods, is generally selected negative
Euclidean distance.Similarity matrix can be symmetrical can also be asymmetric, i.e. s (i, j) and s (j, i) equal also can may be used
?.Wherein s (i, i) is an important value, represents sample i as the preference of cluster centre, and s (i, i) more big then sample i makees
Bigger for the probability of cluster centre, this value is typically assigned priori value P (i).
Attraction Degree matrix R：Attraction Degree r (i, k) represents that point xi is sent to the message of candidate cluster center xk, represents that point xk makees
Appropriate level for point xi cluster centre.
Degree of membership matrix A：Degree of membership matrix is the message for being sent to point xi by candidate cluster center xk, represents that point xi is selected
Point xk is used as the degree of cluster centre.
Attraction Degree matrix is updated by similarity matrix S and degree of membership matrix A：
Degree of membership matrix is updated by Attraction Degree matrix：
Algorithm calculate when be also easy to produce vibration, therefore introduce damping factor lam to calculating new matrix and original matrix carry out
Weighted sum obtains the matrix of next step calculating：
R '=(1-lam) * R+lam*Rold
A '=(1-lam) * A+lam*Aold
In the present embodiment, in step S4, neighbour's propagation algorithm is concretely comprised the following steps：
Step S41：Initialization similarity matrix S, degree of membership matrix A, Attraction Degree matrix R, preference value P, greatest iteration time
Number maxits, cluster centre stable degree；
Step S42：Below step is calculated when iterationses or cluster centre stable degree are less than setting value, otherwise enter
Next step：Rold=R '；Aold=A '；Update R and A；Calculate the matrix R ' and A ' of next step calculating；
Step S43：Choose all of r (i, i)+a (i, i)>0 point is used as cluster centre；
Step S44：Remainder strong point is assigned to nearest cluster centre as class label.
In the present embodiment, in step S5, the customer charge morphological character index of employing includes rate of load condensate：Day peak-valley ratio：Peak phase load factor：Paddy phase load factor：The flat phase is born
Load rate：Wherein PavFor load meansigma methodss, PmaxFor load maximum, PminFor load minima, Pav.peakFor load
Peak phase meansigma methodss, Pav.flatFor the flat phase meansigma methodss of load.Pav.valleyFor load paddy phase meansigma methodss.
In the present embodiment, in step S6, secondary classification method is：For i-th load, with other all loadsAs training sample, wherein xkFor the load morphological characteristic index set vector of k-th load, ykFor k-th load
The classification for once clustering, is reclassified using kNN algorithm using the load as forecast sample, until all load classification are complete
Finish.
The foregoing is only presently preferred embodiments of the present invention, all impartial changes that is done according to scope of the present invention patent with
Modification, should all belong to the covering scope of the present invention.
Claims (4)
1. a kind of novel electric power system loading curve clustering method, it is characterised in that：Specifically include following steps：
Step S1：The workaday of load to be sorted or transformator more than 5 days is obtained from Monitoring and Controlling data acquisition system
Daily load curve active power data；
Step S2：The daily load curve active power data obtained by step S1, for each load or transformator at each
Moment takes the meansigma methodss of all working day respectively as user's typical load curve；
Step S3：User's typical load curve that step S2 is obtained is standardized processing, using maximum standardized method,
That is pij=pij/pimax, formula pijIn for j-th period of user i power, pimaxFor user i maximum electric power；
Step S4：Using neighbour's propagation algorithm, user's typical load curve is clustered, obtain preliminary classification results；
Step S5：Customer charge morphological character index is calculated, min-max standard is adopted to each customer charge morphological character index
Change is processed and obtains standardized load morphological character index.
Step S6：Based on the standardized load morphological character index that step S5 is obtained, the preliminary classification results to step S4
Carry out secondary classification.
2. a kind of novel electric power system loading curve clustering method according to claim 1, it is characterised in that：The step
In S4, neighbour's propagation algorithm is concretely comprised the following steps：
Step S41：Initialization similarity matrix S, degree of membership matrix A, Attraction Degree matrix R, preference value P, maximum iteration time
Maxits, cluster centre stable degree；
Step S42：Below step is calculated when iterationses or cluster centre stable degree are less than setting value, otherwise enter next
Step：Rold=R '；Aold=A '；Update R and A；Calculate the matrix R ' and A ' of next step calculating；
Step S43：Choose all of r (i, i)+a (i, i)>0 point is used as cluster centre；
Step S44：Remainder strong point is assigned to nearest cluster centre as class label.
3. a kind of novel electric power system loading curve clustering method according to claim 1, it is characterised in that：The step
In S5, the customer charge morphological character index of employing includes rate of load condensate：Day peak-valley ratio：The peak phase
Load factor：Paddy phase load factor：Flat phase load factor：Wherein PavFor load meansigma methodss,
PmaxFor load maximum, PminFor load minima, Pav.peakFor load peak phase meansigma methodss, Pav.flatFor the flat phase meansigma methodss of load.
Pav.valleyFor load paddy phase meansigma methodss.
4. a kind of novel electric power system loading curve clustering method according to claim 1, it is characterised in that：The step
In S6, secondary classification method is：For i-th load, with other all loadsAs training sample, wherein xk
For the load morphological characteristic index set vector of k-th load, ykFor the classification that k-th load is once clustered, using the load as
Forecast sample is reclassified using kNN algorithm, until all load classification are finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610956531.7A CN106446967A (en) | 2016-10-28 | 2016-10-28 | Novel power system load curve clustering method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610956531.7A CN106446967A (en) | 2016-10-28 | 2016-10-28 | Novel power system load curve clustering method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106446967A true CN106446967A (en) | 2017-02-22 |
Family
ID=58179715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610956531.7A Pending CN106446967A (en) | 2016-10-28 | 2016-10-28 | Novel power system load curve clustering method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106446967A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423769A (en) * | 2017-08-03 | 2017-12-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
| CN107545374A (en) * | 2017-09-15 | 2018-01-05 | 中国电力科学研究院 | A kind of daily load curve choosing method and system |
| CN107611985A (en) * | 2017-09-18 | 2018-01-19 | 安徽蓝杰鑫信息科技有限公司 | The high voltage customer industry load factor analysis method of 3 σ principles elimination capacities mutation based on SPC |
| CN107657266A (en) * | 2017-08-03 | 2018-02-02 | 华北电力大学（保定） | A kind of load curve clustering method based on improvement spectrum multiple manifold cluster |
| CN107870893A (en) * | 2017-10-24 | 2018-04-03 | 顺特电气设备有限公司 | A kind of daily load similitude quantitative analysis method of intelligent transformer |
| CN108681744A (en) * | 2018-04-18 | 2018-10-19 | 西北工业大学 | A kind of electric load curve hierarchy clustering method divided based on data |
| CN108734355A (en) * | 2018-05-24 | 2018-11-02 | 国网福建省电力有限公司 | A kind of short-term electric load method of parallel prediction and system applied to power quality harnessed synthetically scene |
| CN108898273A (en) * | 2018-05-29 | 2018-11-27 | 国网能源研究院有限公司 | A kind of user side load characteristic clustering evaluation method based on morphological analysis |
| CN109685096A (en) * | 2018-10-25 | 2019-04-26 | 广东电网有限责任公司 | A kind of distribution transformer classification method based on fuzzy clustering |
| CN109784632A (en) * | 2018-12-13 | 2019-05-21 | 东南大学 | A kind of interrupt response characteristic method for digging of industry and commerce user |
| CN110705616A (en) * | 2019-09-23 | 2020-01-17 | 广东电力交易中心有限责任公司 | Method and system for clustering user load curves based on power utilization preference |
| CN110807550A (en) * | 2019-10-30 | 2020-02-18 | 国网上海市电力公司 | Distribution transformer overload identification early warning method based on neural network and terminal equipment |
| CN110851502A (en) * | 2019-11-19 | 2020-02-28 | 国网吉林省电力有限公司 | Load characteristic scene classification method based on data mining technology |
| CN111210170A (en) * | 2020-04-21 | 2020-05-29 | 国网四川省电力公司电力科学研究院 | Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index |
| CN111612319A (en) * | 2020-05-11 | 2020-09-01 | 上海电力大学 | Load curve depth embedding clustering method based on one-dimensional convolution self-encoder |
| CN113470767A (en) * | 2021-06-16 | 2021-10-01 | 特变电工衡阳变压器有限公司 | Classification method and system based on silicon steel sheet performance, computer and storage medium |
| CN113469500A (en) * | 2021-06-07 | 2021-10-01 | 深圳供电局有限公司 | Industrial power consumption big data feature analysis method and device |
| CN113570267A (en) * | 2021-08-02 | 2021-10-29 | 福州万山电力咨询有限公司 | Method and terminal for determining spontaneous self-use proportion of distributed photovoltaic power generation |
| CN114819429A (en) * | 2021-01-18 | 2022-07-29 | 天津大学 | Optimization-based typical daily design boundary extraction method for comprehensive energy system |
| CN117132312A (en) * | 2023-10-25 | 2023-11-28 | 广东电网有限责任公司佛山供电局 | User electricity consumption behavior analysis method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009213328A (en) * | 2008-03-06 | 2009-09-17 | Kansai Electric Power Co Inc:The | Method for forming load-curve model in power system simulator |
| CN103049651A (en) * | 2012-12-13 | 2013-04-17 | 航天科工深圳（集团）有限公司 | Method and device used for power load aggregation |
| CN103106344A (en) * | 2013-01-30 | 2013-05-15 | 河海大学 | Method for establishing electrical power system clustering load model |
| CN104063480A (en) * | 2014-07-02 | 2014-09-24 | 国家电网公司 | Load curve parallel clustering method based on big data of electric power |
-
2016
- 2016-10-28 CN CN201610956531.7A patent/CN106446967A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009213328A (en) * | 2008-03-06 | 2009-09-17 | Kansai Electric Power Co Inc:The | Method for forming load-curve model in power system simulator |
| CN103049651A (en) * | 2012-12-13 | 2013-04-17 | 航天科工深圳（集团）有限公司 | Method and device used for power load aggregation |
| CN103106344A (en) * | 2013-01-30 | 2013-05-15 | 河海大学 | Method for establishing electrical power system clustering load model |
| CN104063480A (en) * | 2014-07-02 | 2014-09-24 | 国家电网公司 | Load curve parallel clustering method based on big data of electric power |
Non-Patent Citations (3)
| Title |
|---|
| 彭勃等: "《结合负荷形态指标的电力负荷曲线两步聚类算法》", 《电力建设》 * |
| 杨娟等: "《面板数据聚类的复合方法与应用》", 30 August 2016 * |
| 段丽莉: "《改进的近邻传播算法及其在图像处理中的应用》", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423769A (en) * | 2017-08-03 | 2017-12-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
| CN107657266A (en) * | 2017-08-03 | 2018-02-02 | 华北电力大学（保定） | A kind of load curve clustering method based on improvement spectrum multiple manifold cluster |
| CN107657266B (en) * | 2017-08-03 | 2021-01-08 | 华北电力大学（保定） | Load curve clustering method based on improved spectrum multi-manifold clustering |
| CN107423769B (en) * | 2017-08-03 | 2019-10-01 | 四川大学 | Electric load curve adaptive clustering scheme based on morphological feature |
| CN107545374A (en) * | 2017-09-15 | 2018-01-05 | 中国电力科学研究院 | A kind of daily load curve choosing method and system |
| CN107611985A (en) * | 2017-09-18 | 2018-01-19 | 安徽蓝杰鑫信息科技有限公司 | The high voltage customer industry load factor analysis method of 3 σ principles elimination capacities mutation based on SPC |
| CN107611985B (en) * | 2017-09-18 | 2020-12-04 | 安徽蓝杰鑫信息科技有限公司 | High-voltage user industry load rate analysis method for removing load mutation based on SPC 3 sigma principle |
| CN107870893A (en) * | 2017-10-24 | 2018-04-03 | 顺特电气设备有限公司 | A kind of daily load similitude quantitative analysis method of intelligent transformer |
| CN108681744A (en) * | 2018-04-18 | 2018-10-19 | 西北工业大学 | A kind of electric load curve hierarchy clustering method divided based on data |
| CN108681744B (en) * | 2018-04-18 | 2021-09-17 | 西北工业大学 | Power load curve hierarchical clustering method based on data partitioning |
| CN108734355A (en) * | 2018-05-24 | 2018-11-02 | 国网福建省电力有限公司 | A kind of short-term electric load method of parallel prediction and system applied to power quality harnessed synthetically scene |
| CN108898273A (en) * | 2018-05-29 | 2018-11-27 | 国网能源研究院有限公司 | A kind of user side load characteristic clustering evaluation method based on morphological analysis |
| CN109685096A (en) * | 2018-10-25 | 2019-04-26 | 广东电网有限责任公司 | A kind of distribution transformer classification method based on fuzzy clustering |
| CN109784632B (en) * | 2018-12-13 | 2020-07-31 | 东南大学 | Mining method for interruption response characteristics of industrial and commercial users |
| CN109784632A (en) * | 2018-12-13 | 2019-05-21 | 东南大学 | A kind of interrupt response characteristic method for digging of industry and commerce user |
| CN110705616A (en) * | 2019-09-23 | 2020-01-17 | 广东电力交易中心有限责任公司 | Method and system for clustering user load curves based on power utilization preference |
| CN110807550A (en) * | 2019-10-30 | 2020-02-18 | 国网上海市电力公司 | Distribution transformer overload identification early warning method based on neural network and terminal equipment |
| CN110807550B (en) * | 2019-10-30 | 2023-11-24 | 国网上海市电力公司 | Distribution transformer overload recognition and early warning method based on neural network and terminal equipment |
| CN110851502A (en) * | 2019-11-19 | 2020-02-28 | 国网吉林省电力有限公司 | Load characteristic scene classification method based on data mining technology |
| CN111210170A (en) * | 2020-04-21 | 2020-05-29 | 国网四川省电力公司电力科学研究院 | Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index |
| CN111210170B (en) * | 2020-04-21 | 2020-07-31 | 国网四川省电力公司电力科学研究院 | Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index |
| CN111612319A (en) * | 2020-05-11 | 2020-09-01 | 上海电力大学 | Load curve depth embedding clustering method based on one-dimensional convolution self-encoder |
| CN114819429A (en) * | 2021-01-18 | 2022-07-29 | 天津大学 | Optimization-based typical daily design boundary extraction method for comprehensive energy system |
| CN113469500A (en) * | 2021-06-07 | 2021-10-01 | 深圳供电局有限公司 | Industrial power consumption big data feature analysis method and device |
| CN113470767A (en) * | 2021-06-16 | 2021-10-01 | 特变电工衡阳变压器有限公司 | Classification method and system based on silicon steel sheet performance, computer and storage medium |
| CN113470767B (en) * | 2021-06-16 | 2022-04-12 | 特变电工衡阳变压器有限公司 | Classification method and system based on silicon steel sheet performance, computer and storage medium |
| CN113570267A (en) * | 2021-08-02 | 2021-10-29 | 福州万山电力咨询有限公司 | Method and terminal for determining spontaneous self-use proportion of distributed photovoltaic power generation |
| CN117132312A (en) * | 2023-10-25 | 2023-11-28 | 广东电网有限责任公司佛山供电局 | User electricity consumption behavior analysis method |
| CN117132312B (en) * | 2023-10-25 | 2024-02-13 | 广东电网有限责任公司佛山供电局 | User electricity consumption behavior analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106446967A (en) | Novel power system load curve clustering method | |
| CN111199016B (en) | Daily load curve clustering method for improving K-means based on DTW | |
| CN112561156A (en) | Short-term power load prediction method based on user load mode classification | |
| CN109063911A (en) | A kind of Load aggregation body regrouping prediction method based on gating cycle unit networks | |
| CN111091143A (en) | Distribution transformer weight overload early warning method based on deep belief network and K-means clustering | |
| CN106408008A (en) | Load curve distance and shape-based load classification method | |
| CN106327357B (en) | A kind of load identification method based on improvement probabilistic neural network | |
| CN110503256A (en) | Short-term load forecasting method and system based on big data technology | |
| CN109858728A (en) | Load forecasting method based on branch trade Analysis of Electrical Characteristics | |
| CN109902953A (en) | A kind of classification of power customers method based on adaptive population cluster | |
| CN109325631A (en) | Electric car charging load forecasting method and system based on data mining | |
| CN103942606A (en) | Residential electricity consumption customer segmentation method based on fruit fly intelligent optimization algorithm | |
| CN108399553A (en) | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method | |
| CN109685567A (en) | Electricity customer portrait new method based on convolutional neural network and fuzzy clustering | |
| CN108428055A (en) | A kind of load characteristics clustering method considering load vertical characteristics | |
| CN107248031A (en) | A kind of fast power user classification method for load curve peak-valley difference | |
| Wang et al. | Big data analytics for price forecasting in smart grids | |
| CN115186803A (en) | Data center computing power load demand combination prediction method and system considering PUE | |
| Justo et al. | Behavioral similarity of residential customers using a neural network based on adaptive resonance theory | |
| CN110909786A (en) | New user load identification method based on characteristic index and decision tree model | |
| CN108122173A (en) | A kind of conglomerate load forecasting method based on depth belief network | |
| Haq et al. | Classification of electricity load profile data and the prediction of load demand variability | |
| CN109858667A (en) | It is a kind of based on thunder and lightning weather to the short term clustering method of loading effects | |
| CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
| CN109753990B (en) | User electric energy substitution potential prediction method, system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170222 |
|
| RJ01 | Rejection of invention patent application after publication |