CN106204162A - New networking power consumer electricity consumption mode prediction method under a kind of internet environment - Google Patents
New networking power consumer electricity consumption mode prediction method under a kind of internet environment Download PDFInfo
- Publication number
- CN106204162A CN106204162A CN201610593647.9A CN201610593647A CN106204162A CN 106204162 A CN106204162 A CN 106204162A CN 201610593647 A CN201610593647 A CN 201610593647A CN 106204162 A CN106204162 A CN 106204162A
- Authority
- CN
- China
- Prior art keywords
- user
- electricity consumption
- existing subscriber
- networking
- customer group
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 46
- 230000006855 networking Effects 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 16
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 238000000205 computational method Methods 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 abstract description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
-
- 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)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides new networking power consumer electricity consumption mode prediction method under a kind of internet environment, including the relational network building Internet user existing subscriber and its label；Calculate same label number W between each existing subscriber and Xin networking user respectively, then the existing subscriber corresponding with the element descending order in W is ranked up, take front M existing subscriber and form customer group A, number N of same label between any two users in calculating customer group AijElectricity consumption behavior similarity S with the user representated by this two nodeij, then calculate the mutual relation weight between this two node；In calculating customer group B, the meansigma methods of user's daily load curve is as the electricity consumption model prediction value of new networking user.The present invention is not in the case of having user's historical load, by the attribute tags of user, in conjunction with similar users cluster analysis, it was predicted that new networking user uses power mode, and then helps sale of electricity body to provide personalized power supply service to recommend for new user.
Description
Technical field
The invention belongs to intelligent power technical field, be specifically related to new networking power consumer electricity consumption under a kind of internet environment
Mode prediction method.
Background technology
Along with national energy Internet Strategy and the continuous propelling of power system reform policy, electricity market reform direction
The distinctest.Power consumer is power purchase and electricity consumption value-added service on the Internet sale of electricity platform, has the user data of abundant species,
Including using the UADs such as population, living space, house market average price, heating type, the Internet sale of electricity body can be to respectively
Kind of user data type carries out classifying, quantitative demarcation interval, forms the label list of definition user, accordingly by user's classification and to
Electricity consumption Behavior preference and the Internet Behavior preference of family colony are analyzed and predict.
Under internet environment, many sales of electricity body forms competitive relation, needs fully to identify the attribute tags of user, and to
Family be predicted assessment with power mode and Behavior preference, in order to provide the user personalized power supply service, promote service quality,
Strengthen user's viscosity.At present, it is mainly based upon user's substantial amounts of historical load data to the analysis of power mode, utilizes cluster etc.
Data analysing method, identifies that user's uses power mode, but for there is no the user of history power load data, it is difficult to carry out electricity consumption
The assessment of pattern, is unfavorable for that sale of electricity body is that new user provides personalized service.
Therefore, sale of electricity body how under internet environment by analyzing power consumer groupment behavior, it was predicted that newly network use
Family power mode, and recommend electricity consumption set meal or electricity consumption value-added service for new networking user, it is that a technology being badly in need of solving is asked
Topic.
Summary of the invention
It is an object of the invention to provide new networking power consumer electricity consumption mode prediction method under a kind of internet environment, can root
According to user property label, form similar users colony, and by analyzing similar users colony electricity consumption pattern feature, estimate new networking
User power utilization pattern.Thus helping the sale of electricity body very first time is that user recommends efficient electricity consumption set meal or electricity consumption value-added service.
It is an object of the invention to realize in the following manner:
New networking power consumer electricity consumption mode prediction method under a kind of internet environment, comprises the following steps:
(1) building the relational network of Internet user existing subscriber and its label, in described relational network, user represents with node；
(2) calculate same label number W between each existing subscriber and Xin networking user respectively, the element in W is pressed numerical value
Size carries out descending sort, then the existing subscriber corresponding with the element descending order in W is ranked up, and takes front M and has
User forms customer group A,
W represents the same label number object vector of existing subscriber and new networking user；
(3) number N of same label between any two users is calculated in customer group AijUse with the user representated by this two node
Electricity behavior similarity Sij, then calculate the mutual relation weight between this two node:
QUOTE Wherein, i, j represent two different nodes respectively,
By the numerical values recited of α, take front K party A-subscriber group and form customer group B；
(4) meansigma methods of user's daily load curve is calculated in customer group B as the electricity consumption model prediction value of new networking user.
Electricity consumption behavior similarity S in described step (3)ijComputational methods be:
Calculate the average load of each hour in the daily load curve of user i, form user average daily load vector Li；
Calculate the average load of each hour in the daily load curve of user j, form user average daily load vector Lj；
Described electricity consumption behavior similarity SijFor:
QUOTE 。
The label of described user includes UAD, internet behavior data, electricity consumption behavioral data.
Compared with prior art, the beneficial outcomes of the present invention is: in the case of not having user's historical load, pass through user
Attribute tags, in conjunction with similar users cluster analysis, it was predicted that new networking user with power mode, and then to help sale of electricity body be new user
Personalized power supply service is provided to recommend.
Accompanying drawing explanation
Fig. 1 is new networking user's electricity consumption mode prediction method flow chart of the present invention.
Detailed description of the invention
Below in conjunction with Fig. 1 and detailed description of the invention, the present invention is described in further details.
Before being predicted, firstly, it is necessary to extract characteristic quantity according to electric power, the electric quantity data of networking user and then obtain
All daily load curves to networking user；Secondly, label is distributed to each user.Label refers to UAD (people
Mouth, living space, house market average price, heating type etc.), electricity consumption behavioral data (historical load data), internet behavior data
(buying type of service, electricity consumption report read state, demand response situation, user credit etc.), can be to various user data classes
Type carries out classifying, quantitative demarcation interval, forms the label list of each networking user.
Then, being predicted with power mode new networking user.Specifically include following steps:
STP1: building the relational network of Internet user existing subscriber and its label, a node in relational network represents one
Individual user, distributes suitable label for new networking user simultaneously.
STP2: calculate the vectorial W of same label number between each existing subscriber and Xin networking user respectively, by W
Element carry out descending sort by the size of numerical value, then the existing subscriber corresponding with the element descending order in W is arranged
Sequence, obtains the existing subscriber's sequence with new networking user's same label number descending, and before extracting in front W, M element is corresponding
M existing subscriber form customer group A, this customer group A is the similar users group most like with new networking user.
STP3: number N of same label between any two users in calculating customer group AijWith the use representated by this two node
Electricity consumption behavior similarity S at familyij, then calculate the mutual relation weight between this two node:
QUOTE Wherein, i, j represent two different nodes respectively,
By the numerical values recited of α, take front K party A-subscriber group and form customer group B.Wherein K is the setting value of the Internet sale of electricity body.
STP4: in calculating customer group B, the meansigma methods of user's daily load curve is as the electricity consumption model prediction of new networking user
Value.
In above-mentioned STP3, electricity consumption behavior similarity SijComputational methods be:
First the average load of each hour in all daily load curves of user i, composition user's average daily load vector are calculated
Li；Calculate the average load of each hour in all daily load curves of user j, form user average daily load vector Lj；In A dual-purpose
The daily load curve at family is the meansigma methods of two average daily load curves of user.
Now electricity consumption behavior similarity SijFor:
QUOTE 。
Assume certain embodiment calculates
Li=[2,3,4,5,4,6,4,7,5,6,4,3,5,9,5,6,4,3,7,2,1,3,2,1],
Lj=[1,2,4,5,4,6,4,7,8,2,4,3,5,6,5,7,4,3,6,2,1,2,2,1],
Then their electricity consumption behavior similarity is
Two node mutual relation weight table are shown as
QUOTE 。
Above-described is only the preferred embodiment of the present invention, it is noted that for a person skilled in the art,
Without departing under general idea premise of the present invention, it is also possible to making some changes and improvements, these also should be considered as the present invention's
Protection domain.
Claims (3)
1. new networking power consumer electricity consumption mode prediction method under an internet environment, it is characterised in that comprise the following steps:
(1) building the relational network of Internet user existing subscriber and its label, in described relational network, user represents with node；
(2) calculate same label number W between each existing subscriber and Xin networking user respectively, the element in W is pressed numerical value
Size carries out descending sort, then the existing subscriber corresponding with the element descending order in W is ranked up, and takes front M and has
User forms customer group A,
W represents the same label number object vector of existing subscriber and new networking user；
(3) number N of same label between any two users is calculated in customer group AijUse with the user representated by this two node
Electricity behavior similarity Sij, then calculate the mutual relation weight between this two node:
Wherein, i, j represent two different nodes respectively,
By the numerical values recited of α, take front K party A-subscriber group and form customer group B；
(4) meansigma methods of user's daily load curve is calculated in customer group B as the electricity consumption model prediction value of new networking user.
2., according to networking power consumer electricity consumption mode prediction method new under a kind of internet environment shown in claim 1, it is special
Levy and be: electricity consumption behavior similarity S in described step (3)ijComputational methods be:
Calculate the average load of each hour in the daily load curve of user i, form user average daily load vector Li；
Calculate the average load of each hour in the daily load curve of user j, form user average daily load vector Lj；
Described electricity consumption behavior similarity SijFor:
。
3., according to networking power consumer electricity consumption mode prediction method new under a kind of internet environment shown in claim 1, it is special
Levy and be: the label of described user includes UAD, internet behavior data, electricity consumption behavioral data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610593647.9A CN106204162A (en) | 2016-07-26 | 2016-07-26 | New networking power consumer electricity consumption mode prediction method under a kind of internet environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610593647.9A CN106204162A (en) | 2016-07-26 | 2016-07-26 | New networking power consumer electricity consumption mode prediction method under a kind of internet environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106204162A true CN106204162A (en) | 2016-12-07 |
Family
ID=57495252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610593647.9A Pending CN106204162A (en) | 2016-07-26 | 2016-07-26 | New networking power consumer electricity consumption mode prediction method under a kind of internet environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106204162A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679105A (en) * | 2017-09-13 | 2018-02-09 | 国网信通亿力科技有限责任公司 | A kind of user information retrieval method based on vector similarity |
| CN107958338A (en) * | 2017-12-08 | 2018-04-24 | 合肥工业大学 | Electricity consumption policy recommendation method and device, storage medium |
| CN108363721A (en) * | 2018-01-03 | 2018-08-03 | 国网信通亿力科技有限责任公司 | A kind of user information retrieval system |
| CN109934675A (en) * | 2019-02-27 | 2019-06-25 | 中国联合网络通信集团有限公司 | Package recommendation method, apparatus and system for new networking user |
| CN109993392A (en) * | 2017-12-31 | 2019-07-09 | 中国移动通信集团安徽有限公司 | Business complaint risk predictor method, calculates equipment and storage medium at device |
| CN110278250A (en) * | 2019-06-10 | 2019-09-24 | 腾讯科技（深圳）有限公司 | Terminal selection method, device and storage medium |
| CN110503256A (en) * | 2019-08-14 | 2019-11-26 | 北京国网信通埃森哲信息技术有限公司 | Short-term load forecasting method and system based on big data technology |
| CN111882398A (en) * | 2020-07-31 | 2020-11-03 | 深圳市华云中盛科技股份有限公司 | Smart city service recommendation method and device, computer equipment and storage medium |
-
2016
- 2016-07-26 CN CN201610593647.9A patent/CN106204162A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679105A (en) * | 2017-09-13 | 2018-02-09 | 国网信通亿力科技有限责任公司 | A kind of user information retrieval method based on vector similarity |
| CN107958338A (en) * | 2017-12-08 | 2018-04-24 | 合肥工业大学 | Electricity consumption policy recommendation method and device, storage medium |
| CN109993392A (en) * | 2017-12-31 | 2019-07-09 | 中国移动通信集团安徽有限公司 | Business complaint risk predictor method, calculates equipment and storage medium at device |
| CN108363721A (en) * | 2018-01-03 | 2018-08-03 | 国网信通亿力科技有限责任公司 | A kind of user information retrieval system |
| CN108363721B (en) * | 2018-01-03 | 2020-08-25 | 国网信通亿力科技有限责任公司 | Power consumer information retrieval system based on data mining |
| CN109934675A (en) * | 2019-02-27 | 2019-06-25 | 中国联合网络通信集团有限公司 | Package recommendation method, apparatus and system for new networking user |
| CN110278250A (en) * | 2019-06-10 | 2019-09-24 | 腾讯科技（深圳）有限公司 | Terminal selection method, device and storage medium |
| CN110278250B (en) * | 2019-06-10 | 2021-11-30 | 腾讯科技（深圳）有限公司 | Terminal selection method, device and storage medium |
| CN110503256A (en) * | 2019-08-14 | 2019-11-26 | 北京国网信通埃森哲信息技术有限公司 | Short-term load forecasting method and system based on big data technology |
| CN110503256B (en) * | 2019-08-14 | 2022-08-05 | 北京国网信通埃森哲信息技术有限公司 | Short-term load prediction method and system based on big data technology |
| CN111882398A (en) * | 2020-07-31 | 2020-11-03 | 深圳市华云中盛科技股份有限公司 | Smart city service recommendation method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106204162A (en) | New networking power consumer electricity consumption mode prediction method under a kind of internet environment | |
| Llanos et al. | Load estimation for microgrid planning based on a self-organizing map methodology | |
| CN109063945A (en) | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system | |
| CN104331840B (en) | The optimal power purchase method of load retailer under Power Market | |
| CN110246037B (en) | Transaction characteristic prediction method, device, server and readable storage medium | |
| CN106446967A (en) | Novel power system load curve clustering method | |
| CN106874355A (en) | The collaborative filtering method of social networks and user's similarity is incorporated simultaneously | |
| CN107391582B (en) | The information recommendation method of user preference similarity is calculated based on context ontology tree | |
| CN111724039B (en) | Recommendation method for recommending customer service personnel to power users | |
| Ferraro et al. | Comparison and clustering analysis of the daily electrical load in eight European countries | |
| CN107506845A (en) | A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion | |
| CN106022646A (en) | Electric power user information data analysis system and analysis method | |
| Albert et al. | Predictive segmentation of energy consumers | |
| CN106202480A (en) | A kind of network behavior based on K means and LDA bi-directional verification custom clustering method | |
| CN103942606A (en) | Residential electricity consumption customer segmentation method based on fruit fly intelligent optimization algorithm | |
| CN106257503A (en) | A kind of the Internet power-using body similar users recognition methods | |
| CN108596467B (en) | Market operation simulation transaction simulation system suitable for electricity selling company | |
| Akpinar et al. | Forecasting natural gas consumption with hybrid neural networks—Artificial bee colony | |
| CN106886559A (en) | The collaborative filtering method of good friend's feature and similar users feature is incorporated simultaneously | |
| CN111581516A (en) | Investment product recommendation method and related device | |
| CN109034853A (en) | Similar users method, apparatus, medium and electronic equipment are found based on seed user | |
| CN106846082A (en) | Tourism cold start-up consumer products commending system and method based on hardware information | |
| CN107248031A (en) | A kind of fast power user classification method for load curve peak-valley difference | |
| Miraftabzadeh et al. | K-means and alternative clustering methods in modern power systems | |
| Behera et al. | XGBoost regression model-based electricity tariff plan recommendation in smart grid environment |
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: 20161207 |
|
| RJ01 | Rejection of invention patent application after publication |