CN109325537A - Power consumption management method, apparatus, computer equipment and storage medium - Google Patents
Power consumption management method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109325537A CN109325537A CN201811126557.4A CN201811126557A CN109325537A CN 109325537 A CN109325537 A CN 109325537A CN 201811126557 A CN201811126557 A CN 201811126557A CN 109325537 A CN109325537 A CN 109325537A
- Authority
- CN
- China
- Prior art keywords
- power
- feature
- power consumption
- history
- consumption management
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 198
- 238000012545 processing Methods 0.000 claims abstract description 181
- 230000005611 electricity Effects 0.000 claims abstract description 104
- 238000000034 method Methods 0.000 claims abstract description 80
- 230000008569 process Effects 0.000 claims abstract description 58
- 230000010354 integration Effects 0.000 claims description 80
- 238000004590 computer program Methods 0.000 claims description 27
- 230000006399 behavior Effects 0.000 claims description 19
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 25
- 238000010586 diagram Methods 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering 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—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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
This application involves a kind of power consumption management method, apparatus, computer equipment and storage mediums.The described method includes: obtaining the history power information and power consumption management decision information of power consumer；History power information and power consumption management decision information are normalized respectively, obtain history electrical feature and power consumption management decision feature；Clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；Processing is associated to history electrical feature and power consumption management decision feature according to clustering processing result, obtains association process result；Classification of power customers model is established according to association process result, wherein classification of power customers model is for being managed the electricity consumption behavior of power consumer.Above-mentioned power consumption management method, apparatus, electronic equipment and storage medium use electrical feature by the available power consumer of classification of power customers model, accurately reflect the power demand of power consumer, and coordinate electric power resource.
Description
Technical field
This application involves technical field of electric power, more particularly to a kind of power consumption management method, apparatus, computer equipment and deposit
Storage media.
Background technique
With the progress of computer technology and the development of society, people are higher and higher to the degree of dependence of electricity consumption, to electricity consumption
It is required that also higher and higher.Currently, the placing separation increasingly forms, and the competition of power sales swashs increasingly with the progress of electric Power Reform
It is strong.Electric power enterprise needs to meet the needs of people by management electricity consumption, keeps more power consumers here, promotes power consumer
Value and self-value, reach the mutual benefit of power consumer and electric power enterprise.
However, traditional power consumption management method, can not accurately reflect power demand, ask there are electric power resource is uncoordinated
Topic.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can accurately reflect that the electricity consumption of power consumer needs
It asks, coordinates power consumption management method, apparatus, computer equipment and the storage medium of electric power resource.
A kind of power consumption management method, method include:
Obtain the history power information and power consumption management decision information of power consumer；
History power information and power consumption management decision information are normalized respectively, obtain history electrical feature with
Power consumption management decision feature；
Clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；
Processing is associated to history electrical feature and power consumption management decision feature according to clustering processing result, is associated with
Processing result；
Classification of power customers model is established according to association process result, wherein classification of power customers model is used for electric power
The electricity consumption behavior of user is managed.
A kind of power consumption management device, which is characterized in that device includes:
Module is obtained, for obtaining the history power information and power consumption management decision information of power consumer；
Normalization module is obtained for history power information and power consumption management decision information to be normalized respectively
To history electrical feature and power consumption management decision feature；
Clustering processing module is obtained for carrying out clustering processing according to history electrical feature and power consumption management decision feature
Clustering processing result；
Association process module, for being carried out to history with electrical feature and power consumption management decision feature according to clustering processing result
Association process obtains association process result；
Classification of power customers model generation module, for establishing classification of power customers model according to association process result,
In, classification of power customers model is for being managed the electricity consumption behavior of power consumer.
A kind of computer equipment, including memory and processor, memory are stored with computer program, and processor executes meter
The step of realizing above-mentioned report on the evaluation of tenders generation method when calculation machine program.
A kind of computer readable storage medium is stored thereon with computer program, when computer program is executed by processor
The step of realizing above-mentioned report on the evaluation of tenders generation method.
Above-mentioned power consumption management method, apparatus, computer equipment and storage medium, by the history electricity consumption for obtaining power consumer
Information and power consumption management decision information；Then place is normalized respectively to history power information and power consumption management decision information
Reason, obtains history electrical feature and power consumption management decision feature；Then according to history electrical feature and power consumption management decision feature
Clustering processing is carried out, clustering processing result is obtained；Further according to clustering processing result to history electrical feature and power consumption management decision
Feature is associated processing, obtains association process result；Classification of power customers model is finally established according to association process result,
In, classification of power customers model is for being managed the electricity consumption behavior of power consumer.It can be with by classification of power customers model
Obtain power consumer uses electrical feature, accurately reflects the power demand of power consumer, and coordinates electric power resource.
Detailed description of the invention
Fig. 1 is the applied environment figure of power consumption management method in one embodiment；
Fig. 2 is the flow diagram of power consumption management method in one embodiment；
Fig. 3 is the flow diagram of normalized step in one embodiment；
Fig. 4 is the structural block diagram of power consumption management device in one embodiment；
Fig. 5 is the structural block diagram of power consumption management device in another embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Power consumption management method provided by the embodiments of the present application, can be applied in application environment as shown in Figure 1.Wherein,
The terminal 104 that power consumer uses is communicated with server 102 by network, and terminal 104 can be by the history of power consumer
Power information and power consumption management decision information can upload onto the server and be stored on 102.Then server 102 is available
The history power information and power consumption management decision information of power consumer；Then to history power information and power consumption management decision information
It is normalized respectively, obtains history electrical feature and power consumption management decision feature；Then according to history electrical feature with
Power consumption management decision feature carries out clustering processing, obtains clustering processing result；It is special to history electricity consumption further according to clustering processing result
Sign is associated processing with power consumption management decision feature, obtains association process result；Electricity is finally established according to association process result
Power user's disaggregated model, classification of power customers model is for being managed the electricity consumption behavior of power consumer.Wherein, terminal 104
It can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and portable wearable device,
Server 102 can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, as shown in Fig. 2, providing a kind of power consumption management method, it is applied in Fig. 1 in this way
It is illustrated for terminal, comprising the following steps:
Step 202, the history power information and power consumption management decision information of power consumer are obtained.
Wherein, power consumer refers to the user of access electric power resource, may include but does not limit domestic consumer, enterprise uses
Family, government customer etc..History power information can be the different dimensions such as daily power consumption, moon electricity consumption, peak load, electricity consumption period
Information.Power consumption management decision information can be customer consumption ability information, payment information, customer service information etc..Wherein, customer consumption
Ability information may include the different dimensions information such as income level, level of consumption；Payment information may include bill date of issue, pay
Take the different dimensions information such as expiration date, electricity cost grade, payment channel preference, payment timeliness；Customer service information may include
Payment feedback, have a power failure the different dimensions information such as complaint.
Specifically, the history power information and power consumption management decision information that can obtain power consumer in real time, can also determine
Phase obtains the history power information and power consumption management decision information of power consumer, as obtained the same day power consumer when daily 24
History power information and power consumption management decision information.
It, can be according to history power information after the history power information and power consumption management decision information that obtain power consumer
Excel table or Word document etc. are generated with power consumption management decision information, and is stored in the storage equipment of terminal, convenient for electricity
Power enterprise is checked.
It in one embodiment, can be with after the history power information and power consumption management decision information that obtain power consumer
By the history power information of power consumer and power consumption management decision information according to the time be sequentially generated power consumer use fulgurite
Timing diagram is managed, and the timing node changed in history power information generates remark information, if power consumer was 12 days 16: 38 May
Point electricity consumption in 50 seconds increases 5kWh, pays the fees within 50 seconds 56 minutes successfully, etc. 16 points of May 18.
It in one embodiment, can also after the history power information and power consumption management decision information that obtain power consumer
The history power information of power consumer and power consumption management decision information to be generated to the electricity consumption of power consumer according to the relationship of position
Map is managed, the specific location and power consumer mark of each power consumer are shown on power consumption management map, by clicking electricity
Power user identifier can enter the interaction interface of power consumer, can show power consumer by handover information interactive interface
Power consumption management timing diagram or power consumer history power information and power consumption management decision information generate Excel table
Or Word document etc..
Step 204, history power information and power consumption management decision information are normalized respectively, obtain history use
Electrical feature and power consumption management decision feature.
Wherein, normalized refers in the identical dimensional of power consumer, by each history power information and electricity consumption
The numerical value of administrative decision information is respectively mapped between 0-1, it is therefore an objective to make different information using unified standard, convenient for subsequent
It calculates.History with electrical feature refer to that history power information obtains after normalized for indicating that power consumer electricity consumption is special
The information of sign；Power consumption management decision feature refer to that power consumption management decision information obtains after normalized for indicating electricity
The information of power user power utilization feature.
Specifically, normalized can refer to following formula and obtain:
Wherein, lijRefer to power consumer i in history power information or one of dimension of power consumption management decision information
The numerical value of degree j, min (j) refer to all power consumers wherein the one of history power information or power consumption management decision information
The minimum value of a dimension j, max (j) refer to one of dimension j of history power information or power consumption management decision information
Greatest measure, kijRefer to that the power consumer i after normalized is special in history electrical feature or power consumption management decision
The numerical value of one of dimension j of sign.
For example, there are five power consumers, and in this dimension of daily power consumption j=1, the daily power consumption point of history power information
It Wei not l11=5kWh, l21=10kWh, l31=11kWh, l41=15kWh, l51=20kWh, then min (j)=
5kWh, max (j)=20kWh, then after normalized
The history of the daily power consumption of five power consumers i.e. after normalized is respectively k with electrical feature11=0, k21=
0.33, k31=0.4, k41=0.67, k51=1.
Further, it is possible to the corresponding power information term of reference of the history power information for obtaining power consumer and electricity consumption
The corresponding decision information term of reference of administrative decision information；History power information in power information term of reference is returned
One change processing, obtains history electrical feature；Power consumption management decision information in decision information term of reference is normalized
Processing, obtains power consumption management decision feature.
Step 206, clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing knot
Fruit.
Wherein, clustering processing refers to carrying out history electrical feature or power consumption management decision feature in same dimension
The processing method of classification.
Specifically, in same dimension, by the history electrical feature obtained after normalized or power consumption management decision
Feature is classified, and the clustering processing result of history electrical feature or power consumption management decision feature in same dimension is obtained.It will
The each dimension for including in the history each dimension for including in electrical feature and power consumption management decision feature is in turn classified,
Obtain the clustering processing of each dimension for including in history electrical feature and each dimension for including in power consumption management decision feature
As a result.
For example, in this dimension of the income level of customer consumption ability information, the income water for the power consumer that will acquire
After equalling the power consumption management decision information normalized of this dimension, the income level of power consumer this dimension has been obtained
Power consumption management decision feature, then by the power consumption management decision feature progress of this dimension of the income level of obtained power consumer
Clustering processing, obtain clustering processing as a result, if clustering processing result is three classes: income level is rich, and income level is moderately well-off, income
It is horizontal poor.
Further, clustering processing is carried out with electrical feature according to history and obtains the first clustering processing as a result, and according to fulgurite
Reason decision feature carries out clustering processing and obtains the second clustering processing result.
Further, clustering processing is carried out with the fisrt feature for each dimension for including in electrical feature according to history respectively, is obtained
To corresponding first cluster labels of power consumer；According to the second feature for each dimension for including in power consumption management decision feature point
Not carry out clustering processing, obtain corresponding second cluster labels of power consumer.
Step 208, processing is associated to history electrical feature and power consumption management decision feature according to clustering processing result,
Obtain association process result.
Wherein, association process refers to for history being associated with electrical feature and power consumption management decision feature, obtains history
With the incidence relation between electrical feature and power consumption management decision feature.
Specifically, each according to include in each dimension for including in history electrical feature and power consumption management decision feature
The clustering processing of dimension is as a result, each by include in each dimension for including in history electrical feature and power consumption management decision feature
A dimension is associated processing, obtains association process result.
For example, this dimension of moon electricity consumption for including in history electrical feature and the receipts for including in power consumption management decision feature
Enter the clustering processing of this horizontal dimension as a result, moon electricity consumption clustering processing result is three classes: the moon the less, moon electricity consumption of electricity consumption
The medium, moon, electricity consumption was more；Income level clustering processing result is three classes: income level is rich, income level is moderately well-off, income water
Flat poverty.
By the income level in this dimension of moon electricity consumption for including in history electrical feature and power consumption management decision feature
This dimension is associated processing, obtain moon electricity consumption and income level association process result (moon electricity consumption it is less；Take in water
Flat affluence), (moon electricity consumption it is medium；Income level is rich), (moon electricity consumption it is more；Income level is rich), (in moon electricity consumption
Deng；Income level is rich), (moon electricity consumption it is medium；Income level is moderately well-off), (moon electricity consumption it is medium；Income level is poor), (moon
Electricity consumption is more；Income level is rich), (moon electricity consumption it is more；Income level is moderately well-off), (moon electricity consumption it is more；Income level is poor
It is tired).
Further, correlation rule is generated by association process result.Wherein, in the present embodiment, correlation rule refers to
The rule that the relevance of history electrical feature and power consumption management decision feature is strong and weak and generates.Wherein, relevance power can
To be embodied by the result of association process.
For example, according to association process as a result, when (moon electricity consumption it is medium；Income level is moderately well-off) number that occurs is more
When, then generate a correlation rule: (moon electricity consumption medium) → (income level is moderately well-off), i.e., power consumer " income level is small
Health " and the incidence relation of " moon electricity consumption medium " are stronger.
Further, the relation integration that the first clustering processing result and the second clustering processing result generate is obtained；Count each
The corresponding support of a relation integration；The association process of history electrical feature Yu power consumption management decision feature is obtained according to support
As a result.
Further, the relation integration that the first clustering processing result and the second clustering processing result generate is obtained, including following
Step: obtaining first object cluster labels from the first cluster labels, and the second target cluster is obtained from the second cluster labels
Label；Relation integration is generated according to first object cluster labels and the second target cluster labels.
Further, the corresponding support of each relation integration is counted the following steps are included: according to each power consumer
The first cluster labels and the second cluster labels, generate corresponding cluster labels set；Each relation integration is counted to cluster
The number occurred in tag set；The corresponding support of each relation integration is calculated according to number.
Step 210, classification of power customers model is established according to association process result, wherein classification of power customers model is used
It is managed in the electricity consumption behavior to power consumer.
Wherein, classification of power customers model may include but be not limited to old man family, office worker, vacant room, business residence
The people, enterprise etc..
Specifically, correlation rule can be generated according to association process result, corresponding electric power is established according to correlation rule and is used
Family disaggregated model.The classification of power customers model according to belonging to power consumer, can the electricity consumption behavior to power consumer carry out pipe
Reason.
For example, including a correlation rule in obtained association process result: (evening electricity consumption period and vacation, moon electricity consumption
Measure medium) → (income level is medium, and the level of consumption is medium, pays the fees on channel preference line), then the correlation rule indicates " income water
Put down medium, the level of consumption is medium, payment channel preference line on " power consumer " the electricity consumption period at night and vacation, and the moon use
Electricity is medium ".Corresponding user can be so obtained according to this correlation rule is classified as " office worker ".It is associated with according to another
The correlation rule for including in processing result: (moon, electricity consumption was less, and peak load is smaller) → (electricity cost grade level-one, payment
Not in time), this correlation rule indicates that " electricity cost lower grade, indicates that electricity cost is lower, indicates that electricity cost is low and pays
Take not in time " power consumer moon electricity consumption it is less and peak load is smaller.It can so be obtained according to this correlation rule pair
The user answered is classified as " vacant room ".And so on, according to the above method, available all users classify, thus according to institute
Classification of power customers model is established in some user's classification.
It is understood that the electricity consumption behavior of power consumer can meet a correlation rule, a plurality of pass can also be met
Connection rule, accordingly, power consumer may belong to a classification of power customers model, also may belong to multiple classification of power customers
Model.
Further, the classification of power customers model according to belonging to power consumer, can electricity consumption behavior to power consumer into
Row management.Specifically, electric power resource can be carried out coordinated allocation by the classification of power customers model according to belonging to power consumer.
For example, daytime period on weekdays, can be the electricity of " office worker " and " vacant room " by classification of power customers model
The electric power resource of power user distributes to the power consumer that classification of power customers model is " business resident " and " enterprise "；At night and
The electric power resource for the power consumer that power consumer model is " business resident " and " enterprise " can be distributed to electric power by holiday periods
User's disaggregated model is the power consumer of " office worker " and " old man family ".
Further, service strategy is generated according to classification of power customers model；According to service strategy to power consumer in electricity consumption
The power information generated in the process is handled.
In above-mentioned power consumption management method, the history power information and power consumption management decision information of power consumer are obtained first；
History power information and power consumption management decision information are normalized respectively, obtain history electrical feature and power consumption management
Decision feature；Then clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；
Processing is associated to history electrical feature and power consumption management decision feature then according to clustering processing result, obtains association process
As a result；Classification of power customers model is finally established according to association process result, wherein classification of power customers model is used for electric power
The electricity consumption behavior of user is managed.Electrical feature is used by the available power consumer of classification of power customers model, accurately
Reflect the power demand of power consumer, and coordinates electric power resource.
In one embodiment, as shown in figure 3, carrying out normalizing respectively to history power information and power consumption management decision information
Change processing, obtains history electrical feature and power consumption management decision feature, comprising:
Step 302, the corresponding power information term of reference of history power information and the power consumption management of power consumer are obtained
The corresponding decision information term of reference of decision information.
Wherein, the history power information of power consumer needed for power information term of reference refers to electric power enterprise is corresponding
Range；The corresponding model of power consumption management decision information of power consumer needed for decision information term of reference refers to electric power enterprise
It encloses.Power information term of reference can be inputted to obtain with decision information term of reference by electric power enterprise.
Step 304, the history power information in power information term of reference is normalized, obtains history use
Electrical feature.
Specifically, the corresponding power information term of reference of history power information for obtaining power consumer, when power consumer
History power information then obtains the history power information of the power consumer in power information term of reference.When power consumer
For history power information not in power information term of reference, which is bad information, gives up the history power information.
Step 306, the power consumption management decision information in decision information term of reference is normalized, is used
Electric administrative decision feature.
Specifically, the corresponding decision information term of reference of power consumption management decision information is obtained, uses fulgurite when power consumer
Decision information is managed in decision information term of reference, then obtains the power consumption management decision information of the power consumer.Work as power consumer
Power consumption management decision information not in decision information term of reference, the power consumption management decision information be abnormal information, house
Abandon the power consumption management decision information.
For example, the dimension daily power consumption that the history power information for obtaining five power consumers includes is respectively 10kW
H, 16 points of -5kWh, 20kWh, June 2 38 minutes 50 seconds, 150kWh, power information term of reference are 0-100kWh,
Then -5kWh, 38 minutes and 50 seconds 16 points of June 2 not in power information term of reference, for bad information, are given up with 150kWh；Then
It obtains in the 10kWh and 20kWh that power information term of reference is 0-100kWh.
Further, it obtains in the history power information in power information term of reference and in decision information term of reference
Power consumption management decision information constructs power consumer database.
In above-mentioned power consumption management method, the corresponding power information of history power information of power consumer is obtained with reference to model
It encloses and the corresponding decision information term of reference of power consumption management decision information；History in power information term of reference is used
Power information is normalized, and obtains history electrical feature；To the power consumption management decision letter in decision information term of reference
Breath is normalized, and obtains power consumption management decision feature；Then according to history electrical feature and power consumption management decision feature
Clustering processing is carried out, clustering processing result is obtained；Further according to clustering processing result to history electrical feature and power consumption management decision
Feature is associated processing, obtains association process result；Classification of power customers model is established according to association process result, electric power is used
Family disaggregated model is for being managed the electricity consumption behavior of power consumer.This power consumption management method, gives up not in power information
The bad information of term of reference and decision information term of reference can more accurately reflect power demand.
In one embodiment, history electrical feature and power consumption management decision feature carry out clustering processing, obtain at cluster
Manage result, comprising: clustering processing is carried out with electrical feature according to history and obtains the first clustering processing as a result, and determining according to power consumption management
Plan feature carries out clustering processing and obtains the second clustering processing result.
Wherein, the first clustering processing result refers to each dimension for being included after history carries out clustering processing with electrical feature
Result.Second clustering processing result refers to that power consumption management decision feature carries out each dimension for being included after clustering processing
As a result.
For example, including multiple dimensions, such as daily power consumption, electricity consumption period in history electrical feature, according to each dimension
Available corresponding first clustering processing result after clustering processing.First clustering processing result can be daily power consumption it is more,
Daily power consumption is medium, daily power consumption is less and the electricity consumption period is evening and vacation, daytime on working day electricity consumption period, electricity consumption period
Whole day etc..
For example, also including multiple dimensions in power consumption management decision feature, as income level, electricity consumption grade, payment channel are inclined
Good, power failure complaint etc., according to corresponding second clustering processing result available after each dimension clustering processing.Second cluster
Processing result can be rich income level, income level well-to-do level, income level poverty, electricity cost grade level-one, energy charge
With grade second level, electricity cost grade three-level, pays the fees on channel line, under payment channel line, on payment channel line and under line, have a power failure
Complain fierce, the complaint that has a power failure is mild etc..
In one embodiment, according to clustering processing as a result, being carried out to history with electrical feature and power consumption management decision feature
Association process obtains association process result, comprising: obtains the pass that the first clustering processing result and the second clustering processing result generate
Connection set；Count the corresponding support of each relation integration；History is obtained according to support to be determined with electrical feature and power consumption management
The association process result of plan feature.
Wherein, relation integration refers to that the first clustering processing result is associated with the collection generated later with the second clustering processing result
It closes.Support refers to that relation integration goes out in the first clustering processing result and the second clustering processing result of all power consumers
Existing frequency.
Specifically, include multiple dimensions in history electrical feature, clustering processing is carried out according to each dimension, it is poly- to obtain first
Class processing result；Similarly, include multiple dimensions in power consumption management decision feature, clustering processing is carried out according to each dimension, is obtained
To the second clustering processing result.By comprising each dimension the first clustering processing result with comprising each dimension second gather
It is associated in class processing result, generates relation integration.The corresponding support of each relation integration is counted, when relation integration is corresponding
When support is greater than support threshold, then correlation rule corresponding in relation integration is generated, wherein correlation rule is by incidence set
Corresponding history electrical feature and power consumption management decision feature form in conjunction, and then, correlation rule is by history power information and uses
Fulgurite manages decision information composition, such as correlation rule: (moon, electricity consumption was less, and peak load is smaller) → (electricity cost grade second level,
Payment is not in time).
In one embodiment, clustering processing is carried out with electrical feature according to history and obtains the first clustering processing as a result, simultaneously root
Clustering processing is carried out according to power consumption management decision feature and obtains the second clustering processing result, comprising: is wrapped according to history in electrical feature
The fisrt feature of each dimension contained carries out clustering processing respectively, obtains corresponding first cluster labels of power consumer；According to
The second feature for each dimension for including in electric administrative decision feature carries out clustering processing respectively, obtains power consumer corresponding
Two cluster labels；Obtain the relation integration that the first clustering processing result and the second clustering processing result generate, comprising: poly- from first
First object cluster labels are obtained in class label, and the second target cluster labels are obtained from the second cluster labels；According to first
Target cluster labels and the second target cluster labels generate relation integration.
Wherein, fisrt feature refers to the information of a dimension in the history electrical feature after normalized, such as daily
The fisrt feature of this dimension of electricity is 0.2,0.3,0.4,0.6,0.8,0.9.First cluster labels refer to that fisrt feature is logical
The classification formed after clustering processing is crossed, in this dimension of daily power consumption, the first cluster labels can be for daily power consumption is less, day
Electricity consumption is medium, daily power consumption is more.Second feature refers to a dimension in the power consumption management decision feature after normalized
The information of degree, if the second feature of income level this dimension is 0.2,0.3,0.4,0.5,0.8,0.9.Second cluster labels refer to
Be second feature by the classification that is formed after clustering processing, in this dimension of income level, the second cluster labels can be
Income level is poor, income level is moderately well-off, income level is rich.
First object cluster labels refer to the first cluster labels for generating relation integration, the second target cluster labels
The second cluster labels for generating relation integration are referred to, as (daily power consumption is less, and peak load is smaller for relation integration；With
Electric expense level second level, payment is not in time), then first object cluster labels be a month electricity consumption be it is less, peak load is smaller, the
Two target cluster labels are that electricity cost is grade second level, and payment is not in time.
Specifically, include the fisrt feature of each dimension in history electrical feature, the fisrt feature of each dimension is distinguished
Clustering processing is carried out, the classification of the fisrt feature of each dimension is formd, power consumer corresponding the is obtained by each classification
One cluster labels；Include the second feature of each dimension in power consumption management decision feature, the second feature of each dimension is distinguished
Clustering processing is carried out, the classification of the second feature of each dimension is formd, power consumer corresponding the is obtained by each classification
Two cluster labels.
For example, the fisrt feature of " daily power consumption " dimension for including in history electrical feature is 0.2,0.3,0.4,0.6,
0.8,0.9.By clustering processing, such as daily power consumption is divided into three classes, three fisrt feature in selection daily power consumption: 0.2,
0.8,0.9 central value as three classes then calculates separately the distinctiveness ratio of the fisrt feature and these three central values in daily power consumption,
The calculating of distinctiveness ratio can refer to following formula: distinctiveness ratio=remaining fisrt feature-central value.Wherein, distinctiveness ratio is positive number.Then
The distinctiveness ratio of fisrt feature and central value 0.2 in daily power consumption is respectively as follows: 0,0.1,0.2,0.4,0.6,0.7；Daily power consumption
In fisrt feature and the distinctiveness ratio of central value 0.8 be respectively as follows: 0.6,0.5,0.4,0.2,0,0.1；First in daily power consumption
The distinctiveness ratio of feature and central value 0.9 is respectively as follows: 0.7,0.6,0.5,0.3,0.1,0.
Using in fisrt feature with the smallest fisrt feature of central value distinctiveness ratio as one kind, recalculate the center of every one kind
Value.Then three classes are respectively (0.2,0.3,0.4), and (0.6,0.8), (0.9) recalculates the respective central value of three classes.Central value
The arithmetic average for being calculated as fisrt feature in every one kind, the central value of three classes is respectively as follows: (0.2+0.3+0.4)/3=0.3,
(0.6+0.8)/2=0.7,0.9, i.e. the central value of three classes is respectively 0.3,0.7,0.9.
Recalculate the distinctiveness ratio of the fisrt feature and these three central values 0.3,0.7,0.9 in daily power consumption, then by
The central value of every one kind is recalculated as one kind with the smallest fisrt feature of central value distinctiveness ratio in one feature.Work as central value
When constant, then clustering processing is completed.
Specifically, the distinctiveness ratio of the fisrt feature in daily power consumption and central value 0.3 is respectively as follows: 0.1,0,01,0.3,
0.5,0.6；The distinctiveness ratio of fisrt feature and central value 0.7 in daily power consumption is respectively as follows: 0.5,0.4,0.3,0.1,0.1,
0.2；The distinctiveness ratio of fisrt feature and central value 0.9 in daily power consumption is respectively as follows: 0.7,0.6,0.5,0.3,0.1,0.By day
The distinctiveness ratio of fisrt feature and three central values 0.3,0.7,0.9 in electricity consumption is the smallest as one kind, then three classes are respectively
(0.2,0.3,0.4), (0.6,0.8), (0.9), the central value for calculating three classes is respectively 0.3,0.7,0.9, and central value is constant,
Then clustering processing is completed.
Further, one kind (0.2,0.3,0.4) in the fisrt feature in daily power consumption is generated into the first cluster labels: day
Electricity consumption is less；One kind (0.6,0.8) in fisrt feature in daily power consumption is generated into the first cluster labels: in daily power consumption
Deng；One kind (0.9) in fisrt feature in daily power consumption is generated the first cluster labels: daily power consumption is more.
Similarly, the fisrt feature for another the dimension peak load for including in history electrical feature passes through cluster
It handles, the first cluster labels generated in the fisrt feature of available this dimension of peak load lower, peak for peak load
Duty value is medium, peak load is higher.
Similarly, the second feature for a dimension income level for including in power consumption management decision feature, passes through cluster
It handles, the second cluster labels generated in the second feature of available this dimension of income level are that income level is poor, receive
Enter horizontal moderately well-off, income level affluence.
Similarly, the second feature for a dimension level of consumption for including in power consumption management decision feature, passes through cluster
It handles, the second cluster labels generated in the second feature of available this dimension of the level of consumption are the lower consumption level, disappear
Water wasting puts down that medium, the level of consumption is higher.
Each dimension that above embodiments include using history electrical feature of the K-means clustering algorithm to power consumer
The fisrt feature of degree, the second feature for each dimension for including with power consumption management decision feature carry out clustering processing, can also adopt
With the of each dimension that the history electrical feature to power consumer such as mean shift clustering algorithm, C means clustering algorithm includes
One feature, the second feature for each dimension for including with power consumption management decision feature carry out clustering processing, it is not limited here.
Further, one or more first cluster labels is obtained as first object cluster labels；Similarly, one is obtained
A or multiple second cluster labels mark first object cluster labels and the second target cluster as the second target cluster labels
Label generate relation integration.
Less in the first cluster labels daily power consumption of daily power consumption this dimension, daily power consumption is medium, daily power consumption compared with
The less first object cluster labels as this dimension of daily power consumption of daily power consumption are obtained in more；In this dimension of peak load
The first cluster labels peak load it is lower, peak load is medium, and peak load obtains that peak load is medium to be used as the compared with senior middle school
One target cluster labels；In the second cluster labels income level poverty of this dimension of income level, income level is moderately well-off, income
Second target cluster labels of the income level well-to-do level as this dimension of income level are obtained in horizontal affluence；The level of consumption this
The second cluster labels lower consumption level of dimension, the level of consumption is medium, and the level of consumption is medium compared with senior middle school's acquisition level of consumption
As the second target cluster labels of this dimension of the level of consumption, then generating relation integration is that (daily power consumption is less, peak load
It is medium；Income level is moderately well-off, and the level of consumption is medium).
In one embodiment, the corresponding support of each relation integration is counted, comprising: according to each power consumer
The first cluster labels and the second cluster labels, generate corresponding cluster labels set；Each relation integration is counted to cluster
The number occurred in tag set；The corresponding support of each relation integration is calculated according to number.
Wherein, cluster labels set refers to all the first cluster labels of power consumer and all the second cluster labels can
Can composition set, use electrical feature for indicate power consumer.Support refers to relation integration in all power consumers
The frequency occurred in first clustering processing result and the second clustering processing result, that is, relation integration is in all cluster labels collection
The frequency occurred in conjunction.
Specifically, according to the first cluster labels of each power consumer and the second cluster labels, corresponding cluster is generated
Tag set.Wherein, cluster labels set includes that all of power consumer use electrical feature.According to first object cluster labels and
After two target cluster labels generate relation integration, the number that each relation integration occurs in cluster labels set is counted.Root
The corresponding support of each relation integration is calculated according to number.When the number that relation integration occurs in cluster labels set is more
When, then it represents that the support of corresponding relation integration is higher, that is, the first object cluster labels and second in relation integration
Target cluster labels relevance is stronger.
For example, the first cluster labels of this dimension of daily power consumption are respectively in daily power consumption in 5 power consumers
Deng, daily power consumption is lower, daily power consumption is medium, daily power consumption is higher, daily power consumption is medium；The first of this dimension of peak load
Cluster labels are respectively that peak load is medium, peak load is lower, peak load is medium, peak load is higher, in peak load
Deng；Second cluster labels of this dimension of income level are respectively that income level is moderately well-off, income level is poor, income level is rich
It is abundant, income level is rich, income level is moderately well-off；Second cluster labels of payment this dimension of channel preference are respectively channel of paying the fees
On preference line, under payment channel preference line, on payment channel preference line, on payment channel preference line, on payment channel preference line；
Then the cluster labels set of 5 power consumers is respectively that (daily power consumption is medium, and peak load is medium, and income level is moderately well-off, payment
On channel preference line), (daily power consumption is lower, and peak load is lower, and income level is poor, pays the fees under channel preference line), (daily
Electricity is medium, and peak load is medium, and income level is rich, pays the fees on channel preference line), (daily power consumption is higher, peak load compared with
Height, income level are rich, pay the fees on channel preference line), (daily power consumption is medium, and peak load is medium, and income level is moderately well-off, pays
Take on channel preference line).
It is obtained in the first cluster labels of this dimension of the first cluster labels with peak load of daily power consumption this dimension
Take first object cluster labels；Income level this dimension the second cluster labels and payment this dimension of channel preference the
The second target cluster labels are obtained in two cluster labels, the relation integration of generation can be for (daily power consumption is medium；Channel of paying the fees is inclined
On good line), or (daily power consumption is medium；Income level is moderately well-off, pays the fees on channel preference line), it can also be (day electricity consumption
Measure medium, peak load is medium；Income level is moderately well-off, pays the fees on channel preference line), it is not limited here.
The number that each relation integration occurs in the cluster labels set of all power consumers is counted, then relation integration
(daily power consumption is medium；On payment channel preference line) occur in the cluster labels of 5 power consumers number 3 times；Incidence set
(daily power consumption is medium for conjunction；Income level is moderately well-off, pays the fees on channel preference line) occur in the cluster labels of 5 power consumers
Number 2 times；(daily power consumption is medium, and peak load is medium for relation integration；Income level is moderately well-off, pays the fees on channel preference line) 5
The number occurred in the cluster labels of a power consumer 2 times.
According to the number that each relation integration occurs in the cluster labels set of all power consumers, each is calculated
The corresponding support of relation integration.Wherein, support can refer to following formula calculating: support=relation integration is in cluster labels
The number occurred in set/cluster labels set number.Then (daily power consumption is medium for relation integration；Pay the fees on channel preference line)
Support=3/5；(daily power consumption is medium for relation integration；Income level is moderately well-off, pays the fees on channel preference line) support=2/
5；(daily power consumption is medium, and peak load is medium for relation integration；Income level is moderately well-off, pays the fees on channel preference line) support=
2/5。
Further, the support threshold of relation integration is obtained；When the support of relation integration is more than or equal to corresponding support
When spending threshold value, the corresponding correlation rule of relation integration is generated.
Specifically, the support threshold of all relation integrations may be the same or different, it is not limited here.Work as pass
When the support of connection set is more than or equal to corresponding support threshold, the first object cluster labels in relation integration and the are indicated
Two target cluster labels relevances are strong, generate the corresponding correlation rule of relation integration；It is corresponded to when the support of relation integration is less than
Support threshold when, then it represents that the first object cluster labels and the second target cluster labels relevance in relation integration are weak,
Give up the relation integration.
For example, the support threshold for obtaining all relation integrations is 3/5, then (daily power consumption is medium for relation integration；Payment canal
On road preference line) support be more than or equal to support threshold 3/5, generate the corresponding correlation rule of relation integration, i.e. (day electricity consumption
Measure medium) → (payment channel preference line on), which indicates that the daily power consumption of power consumer is medium inclined with channel of paying the fees
Relevance is strong on good line；Then (daily power consumption is medium for relation integration；Income level is moderately well-off, pays the fees on channel preference line) support
Less than support threshold 3/5, give up the relation integration；Then (daily power consumption is medium, and peak load is medium for relation integration；Take in water
Flat well-to-do level, pays the fees on channel preference line) support be less than support threshold 3/5, give up the relation integration.
In one embodiment, the above method further include: service strategy is generated according to classification of power customers model；According to clothes
The power information that business strategy generates power consumer during electricity consumption is handled.
Wherein, what service strategy referred to obtaining by classification of power customers model analysis can preferably service electric power use
The strategy at family.It may include the potential value, credit risk and method of servicing etc. of power consumer in service strategy.
Wherein, the potential value of power consumer can pass through the income level and the level of consumption in classification of power customers model
Etc. obtaining.For example, classification of power customers model be " office worker " or " business resident " power consumer high income and
The level of consumption is higher, it can be deduced that the potential value of power consumer is higher.
The credit risk of power consumer can by the payment expiration date of the payment information in classification of power customers model and
Payment timeliness etc. obtains.For example, not in time by payment expiration date in classification of power customers model and payment etc., it can obtain
The credit risk of power consumer is higher out.
The method of servicing of power consumer can pass through the payment of electricity consumption period, customer service information in classification of power customers model
Feedback and the complaint etc. that has a power failure obtain.For example, the electricity consumption period that classification of power customers model is " office worker " is evening and weekend, pays
Take feedback is good, have a power failure complain the information such as mild it can be concluded that power consumer method of servicing: at night with weekend and electric power use
Family linked up, is complained to the higher authorities about an injustice and request fair settlement and is perhaps repaired etc. or sent in terminal device of the instant messages to power consumer on daytime.For another example,
Classification of power customers model be " old man family " the electricity consumption period be whole day, payment channel preference line under, peak load it is lower, take in
Horizontal more low information it can be concluded that power consumer method of servicing: linked up, complained to the higher authorities about an injustice and request fair settlement or tieed up with power consumer on daytime
It repairs, notices old man in power consumer man and live.
Specifically, service strategy is generated according to classification of power customers model.Classification of power customers mould belonging to power consumer
Type can be one, or multiple；Correspondingly, the service strategy of power consumer can be one kind, or a variety of
It is comprehensive.Then it is handled according to the power information that service strategy generates power consumer during electricity consumption, that is, will be electric
The power informations such as peak load, electricity consumption period that power user generates during electricity consumption are handled.
It can be " office worker " or for " old man family " etc. by classification of power customers model for example, daytime on weekdays
A part of electricity resource of power consumer distribute to the electricity that classification of power customers model is " business resident " or " enterprise " etc.
Power user；Correspondingly, perhaps classification of power customers model can be " business resident " or " enterprise " etc. by vacation at night
A part of electricity resource of power consumer distributes to the electric power that classification of power customers model is " office worker " or " old man family "
User.
Further, it is possible to according to belonging to the potential value of power consumer, credit risk, service strategy etc. and power consumer
Classification of power customers model, the features such as the social class for obtaining power consumer, Behavior preference.
Wherein, social class can be elite, worker, unemployment or unemployed etc..Behavior preference can be power consumer
Payment channel preference be, evening time for falling asleep and get up time etc. in morning.By the social class, the row that obtain power consumer
For features such as preferences, service strategy can be more accurately provided, is preferably power consumer service.
It should be understood that although each step in the flow chart of Fig. 2-3 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-3
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 4, providing a kind of power consumption management device, comprising: obtain module 402, normalizing
Change module 404, clustering processing module 406, association process module 408 and classification of power customers model generation module 410, in which:
Module 402 is obtained, for obtaining the history power information and power consumption management decision information of power consumer.
Module 404 is normalized, for history power information and power consumption management decision information to be normalized respectively,
Obtain history electrical feature and power consumption management decision feature.
Clustering processing module 406 is obtained for carrying out clustering processing according to history electrical feature and power consumption management decision feature
To clustering processing result.
Association process module 408 is used for according to clustering processing result to history electrical feature and power consumption management decision feature
It is associated processing, obtains association process result.
Classification of power customers model generation module 410, for establishing classification of power customers model according to association process result,
Wherein, classification of power customers model is for being managed the electricity consumption behavior of power consumer.
In above-mentioned power consumption management device, the history power information and power consumption management decision information of power consumer are obtained first；
History power information and power consumption management decision information are normalized respectively, obtain history electrical feature and power consumption management
Decision feature；Then clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；
Processing is associated to history electrical feature and power consumption management decision feature then according to clustering processing result, obtains association process
As a result；Classification of power customers model is finally established according to association process result, wherein classification of power customers model is used for electric power
The electricity consumption behavior of user is managed.Electrical feature is used by the available power consumer of classification of power customers model, accurately
Reflect the power demand of power consumer, and coordinates electric power resource.
In one embodiment, the history power information that above-mentioned normalization module 404 is also used to obtain power consumer corresponds to
Power information term of reference and the corresponding decision information term of reference of power consumption management decision information；Join in power information
The history power information examined in range is normalized, and obtains history electrical feature；To in decision information term of reference
Power consumption management decision information be normalized, obtain power consumption management decision feature.
In one embodiment, above-mentioned clustering processing module 406 is also used to carry out clustering processing with electrical feature according to history
The first clustering processing is obtained as a result, and obtaining the second clustering processing result according to power consumption management decision feature progress clustering processing.
In one embodiment, above-mentioned association process module 408 is also used to obtain the first clustering processing result and gathers with second
The relation integration that class processing result generates；Count the corresponding support of each relation integration；History is obtained according to support to use
The association process result of electrical feature and power consumption management decision feature.
In one embodiment, above-mentioned clustering processing module 406 is also used to each according to include in history electrical feature
The fisrt feature of dimension carries out clustering processing respectively, obtains corresponding first cluster labels of power consumer；It is determined according to power consumption management
The second feature for each dimension for including in plan feature carries out clustering processing respectively, obtains the corresponding second cluster mark of power consumer
Label.
In one embodiment, above-mentioned association process module 408 is also used to obtain first object from the first cluster labels
Cluster labels, and the second target cluster labels are obtained from the second cluster labels；According to first object cluster labels and the second mesh
It marks cluster labels and generates relation integration.
In one embodiment, association process module 408 is also used to the first cluster labels according to each power consumer
With the second cluster labels, corresponding cluster labels set is generated；Each relation integration is counted to occur in cluster labels set
Number；The corresponding support of each relation integration is calculated according to number.
In one embodiment, as shown in figure 5, providing a kind of power consumption management device, comprising: obtain module 402, normalizing
Change module 404, clustering processing module 406, association process module 408, classification of power customers model generation module 410 and service plan
Slightly generation module 412.Wherein:
Service strategy generation module 412, for generating service strategy according to classification of power customers model；According to service strategy
The power information generated during electricity consumption to power consumer is handled.
In above-mentioned power consumption management device, the history power information and power consumption management decision information of power consumer are obtained first；
History power information and power consumption management decision information are normalized respectively, obtain history electrical feature and power consumption management
Decision feature；Then clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；
Processing is associated to history electrical feature and power consumption management decision feature then according to clustering processing result, obtains association process
As a result；Classification of power customers model is finally established according to association process result, wherein classification of power customers model is used for electric power
The electricity consumption behavior of user is managed, and generates service strategy by classification of power customers model, according to service strategy to electric power
The power information that user generates during electricity consumption is handled.Pass through the available power consumer of classification of power customers model
With electrical feature, accurately reflect the power demand of power consumer, and coordinates electric power resource.
Specific about power consumption management device limits the restriction that may refer to above for power consumption management method, herein not
It repeats again.Modules in above-mentioned power consumption management device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of power consumption management method.The display screen of the computer equipment can be liquid crystal display or electric ink display screen,
The input unit of the computer equipment can be the touch layer covered on display screen, be also possible to be arranged on computer equipment shell
Key, trace ball or Trackpad, can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor execute computer program when perform the steps of obtain power consumer history power information with
Power consumption management decision information；History power information and power consumption management decision information are normalized respectively, obtain history
With electrical feature and power consumption management decision feature；Clustering processing is carried out according to history electrical feature and power consumption management decision feature, is obtained
To clustering processing result；Processing is associated to history electrical feature and power consumption management decision feature according to clustering processing result,
Obtain association process result；Classification of power customers model is established according to association process result, wherein classification of power customers model is used
It is managed in the electricity consumption behavior to power consumer.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains going through for power consumer
The corresponding power information term of reference of history power information and the corresponding decision information term of reference of power consumption management decision information；
History power information in power information term of reference is normalized, history electrical feature is obtained；To in decision
Power consumption management decision information within the scope of information reference is normalized, and obtains power consumption management decision feature.
In one embodiment, it also performs the steps of when processor executes computer program according to history electrical feature
It carries out clustering processing and obtains the first clustering processing as a result, and carrying out clustering processing according to power consumption management decision feature to obtain second poly-
Class processing result.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains the first clustering processing
As a result the relation integration generated with the second clustering processing result；Count the corresponding support of each relation integration；According to support
Degree obtains the association process result of history electrical feature Yu power consumption management decision feature.
In one embodiment, it also performs the steps of when processor executes computer program according to history electrical feature
In include the fisrt feature of each dimension carry out clustering processing respectively, obtain corresponding first cluster labels of power consumer；Root
Clustering processing is carried out respectively according to the second feature for each dimension for including in power consumption management decision feature, and it is corresponding to obtain power consumer
The second cluster labels；First object cluster labels are obtained from the first cluster labels, and obtain from the second cluster labels the
Two target cluster labels；Relation integration is generated according to first object cluster labels and the second target cluster labels.
In one embodiment, it also performs the steps of when processor executes computer program and is used according to each electric power
First cluster labels and the second cluster labels at family, generate corresponding cluster labels set；Each relation integration is counted poly-
The number occurred in class tag set；The corresponding support of each relation integration is calculated according to number.
In one embodiment, it also performs the steps of when processor executes computer program according to classification of power customers
Model generates service strategy；It is handled according to the power information that service strategy generates power consumer during electricity consumption.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of the history power information for obtaining power consumer when being executed by processor and power consumption management decision is believed
Breath；History power information and power consumption management decision information are normalized respectively, obtain history electrical feature and electricity consumption
Administrative decision feature；Clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；
Processing is associated to history electrical feature and power consumption management decision feature according to clustering processing result, obtains association process knot
Fruit；Classification of power customers model is established according to association process result, wherein classification of power customers model is used for power consumer
Electricity consumption behavior is managed.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains power consumer
The corresponding power information term of reference of history power information and the corresponding decision information of power consumption management decision information refer to model
It encloses；History power information in power information term of reference is normalized, history electrical feature is obtained；To certainly
Power consumption management decision information within the scope of plan information reference is normalized, and obtains power consumption management decision feature.
In one embodiment, it is also performed the steps of when computer program is executed by processor special according to history electricity consumption
Sign carries out clustering processing and obtains the first clustering processing as a result, and obtaining second according to power consumption management decision feature progress clustering processing
Clustering processing result.
In one embodiment, it also performs the steps of and is obtained at the first cluster when computer program is executed by processor
Manage the relation integration that result and the second clustering processing result generate；Count the corresponding support of each relation integration；According to branch
Degree of holding obtains the association process result of history electrical feature Yu power consumption management decision feature.
In one embodiment, it is also performed the steps of when computer program is executed by processor special according to history electricity consumption
The fisrt feature for each dimension for including in sign carries out clustering processing respectively, obtains corresponding first cluster labels of power consumer；
Clustering processing is carried out respectively according to the second feature for each dimension for including in power consumption management decision feature, obtains power consumer pair
The second cluster labels answered；First object cluster labels are obtained from the first cluster labels, and are obtained from the second cluster labels
Second target cluster labels；Relation integration is generated according to first object cluster labels and the second target cluster labels.
In one embodiment, it also performs the steps of when computer program is executed by processor according to each electric power
The first cluster labels and the second cluster labels of user, generate corresponding cluster labels set；Each relation integration is counted to exist
The number occurred in cluster labels set；The corresponding support of each relation integration is calculated according to number.
In one embodiment, it is also performed the steps of when computer program is executed by processor according to power consumer point
Class model generates service strategy；It is handled according to the power information that service strategy generates power consumer during electricity consumption.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of power consumption management method, which comprises
Obtain the history power information and power consumption management decision information of power consumer；
The history power information is normalized respectively with power consumption management decision information, obtain history electrical feature with
Power consumption management decision feature；
Clustering processing is carried out according to history electrical feature and power consumption management decision feature, obtains clustering processing result；
Processing is associated to history electrical feature and power consumption management decision feature according to the clustering processing result, is obtained
Association process result；
Establish classification of power customers model according to the association process result, wherein the classification of power customers model for pair
The electricity consumption behavior of the power consumer is managed.
2. the method according to claim 1, wherein described to the history power information and power consumption management decision
Information is normalized respectively, obtains history electrical feature and power consumption management decision feature, comprising:
Obtain the power consumer the corresponding power information term of reference of history power information and the power consumption management decision
The corresponding decision information term of reference of information；
The history power information in the power information term of reference is normalized, it is special to obtain history electricity consumption
Sign；
The power consumption management decision information in the decision information term of reference is normalized, obtains using fulgurite
Manage decision feature.
3. the method according to claim 1, wherein the history electrical feature and power consumption management decision feature into
Row clustering processing obtains clustering processing result, comprising:
Clustering processing, which is carried out, with electrical feature according to the history obtains the first clustering processing as a result, and determining according to the power consumption management
Plan feature carries out clustering processing and obtains the second clustering processing result.
4. according to the method described in claim 3, it is characterized in that, it is described according to the clustering processing as a result, to the history
It is associated processing with electrical feature and power consumption management decision feature, obtains association process result, comprising:
Obtain the relation integration that the first clustering processing result and the second clustering processing result generate；
Count the corresponding support of each relation integration；
The association process result of the history electrical feature Yu power consumption management decision feature is obtained according to the support.
5. according to the method described in claim 4, it is characterized in that, described carry out clustering processing with electrical feature according to the history
The first clustering processing is obtained as a result, and obtaining the second clustering processing knot according to power consumption management decision feature progress clustering processing
Fruit, comprising:
Clustering processing is carried out respectively with the fisrt feature for each dimension for including in electrical feature according to history, is obtained the electric power and is used
Corresponding first cluster labels in family；
Clustering processing is carried out respectively according to the second feature for each dimension for including in the power consumption management decision feature, obtains institute
State corresponding second cluster labels of power consumer；
The relation integration for obtaining the first clustering processing result and the second clustering processing result and generating, comprising:
First object cluster labels are obtained from first cluster labels, and obtain the second mesh from second cluster labels
Mark cluster labels；
Relation integration is generated according to the first object cluster labels and the second target cluster labels.
6. according to the method described in claim 5, it is characterized in that, the corresponding support of described each relation integration of statistics,
Include:
According to the first cluster labels and the second cluster labels of each power consumer, corresponding cluster labels set is generated；
Count the number that each described relation integration occurs in the cluster labels set；
The corresponding support of each relation integration is calculated according to the number.
7. method according to any one of claim 1 to 6, which is characterized in that the method also includes:
Service strategy is generated according to the classification of power customers model；
It is handled according to the power information that the service strategy generates the power consumer during electricity consumption.
8. a kind of power consumption management device, which is characterized in that described device includes:
Module is obtained, for obtaining the history power information and power consumption management decision information of power consumer；
Normalization module is obtained for the history power information to be normalized respectively with power consumption management decision information
To history electrical feature and power consumption management decision feature；
Clustering processing module is obtained for carrying out clustering processing according to history electrical feature and power consumption management decision feature
Clustering processing result；
Association process module is used for according to the clustering processing result to the history electrical feature and power consumption management decision feature
It is associated processing, obtains association process result；
Classification of power customers model generation module, for establishing classification of power customers model according to the association process result,
In, the classification of power customers model is for being managed the electricity consumption behavior of the power consumer.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811126557.4A CN109325537A (en) | 2018-09-26 | 2018-09-26 | Power consumption management method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811126557.4A CN109325537A (en) | 2018-09-26 | 2018-09-26 | Power consumption management method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109325537A true CN109325537A (en) | 2019-02-12 |
Family
ID=65265003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811126557.4A Pending CN109325537A (en) | 2018-09-26 | 2018-09-26 | Power consumption management method, apparatus, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325537A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109856984A (en) * | 2019-03-04 | 2019-06-07 | 深圳供电局有限公司 | Power consumption management method, apparatus, computer equipment and storage medium |
| CN110119881A (en) * | 2019-04-12 | 2019-08-13 | 国网河北省电力有限公司邢台供电分公司 | Power decision method, apparatus and terminal based on electricity consumption perception |
| CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
| CN111626543A (en) * | 2020-04-03 | 2020-09-04 | 国网浙江杭州市富阳区供电有限公司 | Method and device for processing power related data |
| CN111932069A (en) * | 2020-07-08 | 2020-11-13 | 深圳市深鹏达电网科技有限公司 | Household power consumer electricity utilization efficiency analysis method, computer equipment and storage medium |
| CN113514717A (en) * | 2021-04-22 | 2021-10-19 | 微企（天津）信息技术有限公司 | Non-invasive power load monitoring system |
| EP3961548A4 (en) * | 2019-05-29 | 2022-11-30 | Siemens Aktiengesellschaft | Power grid user classification method and device, and computer-readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020022989A (en) * | 2000-09-21 | 2002-03-28 | 박영진 | Electrical Load Forecasting using Neuro-Fuzzy Models |
| US7289518B2 (en) * | 2002-12-18 | 2007-10-30 | Intel Corporation | Method and apparatus for reducing power consumption in a wireless network station |
| CN103577883A (en) * | 2013-11-18 | 2014-02-12 | 国家电网公司 | Grid-load intelligent interaction method and device |
| CN104181898A (en) * | 2014-09-01 | 2014-12-03 | 东北电力大学 | Intelligent control method and system for interactive home appliances on basis of time-of-use electricity price response |
| CN105184402A (en) * | 2015-08-31 | 2015-12-23 | 国家电网公司 | Personalized user short-term load forecasting algorithm based on decision-making tree |
| CN105184455A (en) * | 2015-08-20 | 2015-12-23 | 国家电网公司 | High dimension visualized analysis method facing urban electric power data analysis |
| CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
| US20160247043A1 (en) * | 2015-02-19 | 2016-08-25 | Warren Rieutort-Louis | Thin-film Sensing and Classification System |
| CN106372969A (en) * | 2016-09-06 | 2017-02-01 | 国家电网公司 | Power user feature identification method and system |
| CN107730117A (en) * | 2017-10-17 | 2018-02-23 | 中国电力科学研究院 | A kind of cable maintenance method for early warning and system based on heterogeneous data comprehensive analysis |
| CN108399553A (en) * | 2018-03-02 | 2018-08-14 | 江苏电力信息技术有限公司 | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method |
-
2018
- 2018-09-26 CN CN201811126557.4A patent/CN109325537A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20020022989A (en) * | 2000-09-21 | 2002-03-28 | 박영진 | Electrical Load Forecasting using Neuro-Fuzzy Models |
| US7289518B2 (en) * | 2002-12-18 | 2007-10-30 | Intel Corporation | Method and apparatus for reducing power consumption in a wireless network station |
| CN103577883A (en) * | 2013-11-18 | 2014-02-12 | 国家电网公司 | Grid-load intelligent interaction method and device |
| CN104181898A (en) * | 2014-09-01 | 2014-12-03 | 东北电力大学 | Intelligent control method and system for interactive home appliances on basis of time-of-use electricity price response |
| US20160247043A1 (en) * | 2015-02-19 | 2016-08-25 | Warren Rieutort-Louis | Thin-film Sensing and Classification System |
| CN105184455A (en) * | 2015-08-20 | 2015-12-23 | 国家电网公司 | High dimension visualized analysis method facing urban electric power data analysis |
| CN105184402A (en) * | 2015-08-31 | 2015-12-23 | 国家电网公司 | Personalized user short-term load forecasting algorithm based on decision-making tree |
| CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
| CN106372969A (en) * | 2016-09-06 | 2017-02-01 | 国家电网公司 | Power user feature identification method and system |
| CN107730117A (en) * | 2017-10-17 | 2018-02-23 | 中国电力科学研究院 | A kind of cable maintenance method for early warning and system based on heterogeneous data comprehensive analysis |
| CN108399553A (en) * | 2018-03-02 | 2018-08-14 | 江苏电力信息技术有限公司 | It is a kind of to consider geographical and circuit subordinate relation user characteristics label setting method |
Non-Patent Citations (2)
| Title |
|---|
| 叶明全，伍长荣主编: "《数据库技术与应用》", 31 July 2015 * |
| 李琳，袁景凌，熊盛武主编: "《云计算与大数据实验教材系列 MAHOUT实验指南》", 30 April 2017 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109856984A (en) * | 2019-03-04 | 2019-06-07 | 深圳供电局有限公司 | Power consumption management method, apparatus, computer equipment and storage medium |
| CN110119881A (en) * | 2019-04-12 | 2019-08-13 | 国网河北省电力有限公司邢台供电分公司 | Power decision method, apparatus and terminal based on electricity consumption perception |
| EP3961548A4 (en) * | 2019-05-29 | 2022-11-30 | Siemens Aktiengesellschaft | Power grid user classification method and device, and computer-readable storage medium |
| CN110363382A (en) * | 2019-06-03 | 2019-10-22 | 华东电力试验研究院有限公司 | Almightiness type Township Merging integrated business integration technology |
| CN111626543A (en) * | 2020-04-03 | 2020-09-04 | 国网浙江杭州市富阳区供电有限公司 | Method and device for processing power related data |
| CN111932069A (en) * | 2020-07-08 | 2020-11-13 | 深圳市深鹏达电网科技有限公司 | Household power consumer electricity utilization efficiency analysis method, computer equipment and storage medium |
| CN113514717A (en) * | 2021-04-22 | 2021-10-19 | 微企（天津）信息技术有限公司 | Non-invasive power load monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325537A (en) | Power consumption management method, apparatus, computer equipment and storage medium | |
| CN109066670B (en) | Distributed power supply management method based on Internet of things block chain | |
| Casalicchio et al. | From investment optimization to fair benefit distribution in renewable energy community modelling | |
| Scheller et al. | Energy system optimization at the municipal level: An analysis of modeling approaches and challenges | |
| Foley et al. | A strategic review of electricity systems models | |
| Kristiansen | The flow based market coupling arrangement in Europe: Implications for traders | |
| Ilić et al. | A decision-making framework and simulator for sustainable electric energy systems | |
| Jia et al. | Analysis on demand-side interactive response capability for power system dispatch in a smart grid framework | |
| CN112001576A (en) | Accounting method for electric power consumption of renewable energy source | |
| Junlakarn et al. | A cross-country comparison of compensation mechanisms for distributed photovoltaics in the Philippines, Thailand, and Vietnam | |
| Mohapatra et al. | Improving operational efficiency in utility sector through technology intervention | |
| Henni et al. | Industrial peak shaving with battery storage using a probabilistic forecasting approach: Economic evaluation of risk attitude | |
| Ramoliya et al. | ML-Based Energy Consumption and Distribution Framework Analysis for EVs and Charging Stations in Smart Grid Environment | |
| CN112463760B (en) | Information processing method, apparatus, computer device, and storage medium | |
| CN109472511A (en) | A kind of resource allocation method, device, computer equipment and storage medium | |
| Moazzen et al. | Optimal DRPs selection using a non‐linear model based on load profile clustering | |
| JP2021135833A (en) | Power transaction system | |
| JP2024059039A (en) | Environmental value assessment system, environmental value assessment method, and program | |
| CN103620420B (en) | System and method for determining communal facility cost savings | |
| CN115130885A (en) | Power demand side management alternate optimization method, device, equipment and medium | |
| CN114240049A (en) | Flexible calculation method for electric power spot market indexes | |
| CN114240416A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113344612B (en) | Electric power transaction matching method and system, intelligent ammeter, server and storage medium | |
| CN116416027B (en) | Micro-grid energy trading method and system | |
| dos Santos et al. | Assessment of the impacts of distributed generation and electric vehicles as mobile sources through a nodal and zonal pricing methodology |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190212 |
|
| RJ01 | Rejection of invention patent application after publication |