CN107958338A - Electricity consumption policy recommendation method and device, storage medium - Google Patents

Electricity consumption policy recommendation method and device, storage medium Download PDF

Info

Publication number
CN107958338A
CN107958338A CN201711297765.6A CN201711297765A CN107958338A CN 107958338 A CN107958338 A CN 107958338A CN 201711297765 A CN201711297765 A CN 201711297765A CN 107958338 A CN107958338 A CN 107958338A
Authority
CN
China
Prior art keywords
msub
mrow
electricity consumption
msup
prime
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
Application number
CN201711297765.6A
Other languages
Chinese (zh)
Inventor
周开乐
黄晓茜
万山越
张庆义
张萌
朱贺祥
陈文儒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei University of Technology
Original Assignee
Hefei University of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hefei University of Technology filed Critical Hefei University of Technology
Priority to CN201711297765.6A priority Critical patent/CN107958338A/en
Publication of CN107958338A publication Critical patent/CN107958338A/en
Pending legal-status Critical Current

Links

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
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The present invention provides a kind of electricity consumption policy recommendation method and device, storage medium, and this method can include：Obtain history electricity consumption data of several users in preset time period；Classify to the history electricity consumption data according to the classification of electrical equipment, obtain multiclass history electricity consumption data；Every a kind of history electricity consumption data is clustered using default clustering algorithm, obtains multiple groups；For each group in every a kind of history electricity consumption data, corresponding electricity consumption characteristics of mean is determined；Electricity consumption strategy corresponding with the electricity consumption characteristics of mean is searched in the electricity consumption policy library pre-established, and the electricity consumption strategy is sent to the user corresponding to the group.Method provided by the invention considers the type of electrical equipment, the use habit of electrical equipment, with factors such as electrical features, can provide a kind of personalized electricity consumption policy recommendation to the user, can meet the needs of different user is to electricity consumption.

Description

Electricity consumption policy recommendation method and device, storage medium
Technical field
This application involves power consumption management technical field, more particularly, to a kind of electricity consumption policy recommendation method and device, storage Medium.
Background technology
With the development of society, the electrical equipment of residential housing, commercial building etc. in quantity, capacity and species also by Year increase, meanwhile, the use habit of user can also have a huge impact power consumption.It is therefore desirable to provide a kind of personalization Service, to meet the needs of different types of user group is to electricity consumption.
The content of the invention
Present application example provides a kind of electricity consumption policy recommendation method and device, storage medium, disclosure satisfy that different user pair The demand of electricity consumption.
The electricity consumption policy recommendation method that the application provides includes：
Obtain history electricity consumption data of several users in preset time period；
Classify to the history electricity consumption data according to the classification of electrical equipment, obtain multiclass history electricity consumption data；
Every a kind of history electricity consumption data is clustered using default clustering algorithm, obtains multiple groups；
For each group in every a kind of history electricity consumption data, corresponding electricity consumption characteristics of mean is determined；
Electricity consumption strategy corresponding with the electricity consumption characteristics of mean is searched in the electricity consumption policy library pre-established, and by described in Electricity consumption strategy is sent to the user corresponding to the group.
The electricity consumption policy recommendation device that the application provides includes：
Data acquisition module, for obtaining history electricity consumption data of several users in preset time period；
Data categorization module, for classifying to the history electricity consumption data according to the classification of electrical equipment, obtains more Class history electricity consumption data；
Data clusters module, for being clustered using default clustering algorithm to every a kind of history electricity consumption data, is obtained more A group；
Characteristic determination module, for for each group in every a kind of history electricity consumption data, determining corresponding electricity consumption Characteristics of mean；
Policy recommendation module, it is corresponding with the electricity consumption characteristics of mean for being searched in the electricity consumption policy library pre-established Electricity consumption strategy, and the electricity consumption strategy is sent to the user corresponding to the group.
The storage medium that the application provides, is stored thereon with computer program, it is characterised in that the program is held by processor Realized during row such as the step of the above method.
Based on above-mentioned technical proposal, classify according to the type of electrical equipment to history electricity consumption data, and then to each Class data are clustered, can be by the similar electricity consumption data of use habit of the user to same class electrical equipment in every a kind of data A group is polymerized to, and then the electricity consumption characteristics of mean to each group is analyzed, obtain each group uses electrical feature, then Corresponding electricity consumption strategy is searched in the electricity consumption policy library pre-established according to electrical feature, and then recommends the user of the group. As it can be seen that this recommendation method, the type of electrical equipment, the use habit of electrical equipment are considered, with the factors such as electrical feature, Neng Gouwei User provides a kind of personalized electricity consumption policy recommendation, can meet the needs of different user is to electricity consumption.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also To obtain other attached drawings according to these attached drawings.
Fig. 1 is the flow diagram of electricity consumption policy recommendation method in the embodiment of the present invention；
Fig. 2 is the structure diagram of electricity consumption policy recommendation device in the embodiment of the present invention；
Fig. 3 is the structure diagram of Computer equipment of the embodiment of the present invention.
Embodiment
The embodiment of the present invention proposes a kind of electricity consumption policy recommendation method, and this method can be performed by any electronic equipment, As shown in Figure 1, this method includes：
S1, obtain history electricity consumption data of several users in preset time period；
Above-mentioned electricity consumption data can be represented in the form of time series, for example, [xt] (t=0,1 ..., n-1), in mistake The n time point gone, power consumption of several users in different electrical equipments.
Here, history electricity consumption data specifically can be obtained or gathered by intelligent electric meter.
In the specific implementation, after history electricity consumption data is got, abnormal electricity consumption data therein can be rejected, it is so-called Abnormal electricity consumption data according to circumstances depending on, for example, damaged data or too low data.
In the specific implementation, the rejecting of abnormal data is whether carried out, can be to history electricity consumption data into Row noise Filtering and data reduction, specific processing procedure can include：
S101, carry out the history electricity consumption data using the first formula discrete Fourier transformation processing, obtains plural number Sequence；Wherein, first formula includes：
Xf=Rf+iIf (1)
In formula, f=0,1 ..., n/2, XfFor f-th of plural number in the sequence of complex numbers；RfFor XfReal part；IfFor Xf's Imaginary part；xtFor the history electricity consumption data [xt] t-th of data in (t=0,1 ..., n-1)；N is number in history electricity consumption data According to number；
It will be appreciated that after being handled by above-mentioned Fourier transformation, electricity consumption data [xt] n data be transformed to include Sequence of complex numbers [the X of n/2+1 plural numberf].For sequence of complex numbers, the inverse operations using the following formula (4) can be recovered as former state：
Here, certain transformation is carried out to above-mentioned formula (4), increases a compression ratio parameter p and a noise filtering ginseng Number w, obtains the second formula i.e. formula (5).
S102, using the second formula to the sequence of complex numbers carry out inverse transformation processing；Wherein, second formula includes：
In formula, u is compression ratio parameter, and w is noise filtering parameter, xt' it is to XfCarry out the electricity consumption obtained after inverse transformation processing Data, R0And Rn/2ByObtain.
By above-mentioned second formula, the electricity consumption data [x after being handledt'] (t=0,1 ..., n-1).[xt'] relative to [xt] reduce noise, and data are because of the more yojan through overcompression.
Since the processing such as above-mentioned rejecting abnormalities data and denoising, data compression are not necessary to what is performed, The history electricity consumption data used in following steps can be [xt] or [xt'], after can also be rejecting abnormalities data Data, can also be not only carry out data reject and carry out denoising and compress after data.
S2, classify the history electricity consumption data according to the classification of electrical equipment, obtains multiclass history electricity consumption data；
Here classification, is classified according to the classification of electrical equipment, the electricity consumption data of same category of electrical equipment For one kind.For example, it is divided into M classes.
S3, using default clustering algorithm cluster every a kind of history electricity consumption data, obtains multiple groups；
Above-mentioned default clustering algorithm,, can be with after means clustering algorithm for example, means clustering algorithm (K-means) The history electricity consumption data of m classes is gathered for kmA group, m=1,2 ... M, wherein the history electricity consumption of i-th of group of m classes Data can be withRepresent, by clustering the user corresponding to the same group in certain obtained one kind to such electrical equipment Use habit is similar.
S4, for each group in every a kind of history electricity consumption data, determine corresponding electricity consumption characteristics of mean；
The electricity consumption characteristics of mean of one group, the electricity consumption data of the group for referring to be calculated by the way of average Feature.
In practice, the computational methods of electricity consumption characteristics of mean have a variety of, and a kind of optional method is described below：
S401, to each group in every a kind of history electricity consumption data, mark multiple vital points；
Multiple vital points of one group, refer to multiple history electricity consumption datas in the group.Vital point can select at random Select, certain rule selection can also be used, this embodiment of the present invention is not limited.
For example, in i-th of group of m classesH vital point of middle mark.
Electricity consumption characteristics of mean value between the adjacent vital point of S402, calculating each two, obtains multiple electricity consumption characteristics of mean Value；And the electricity consumption characteristics of mean using the multiple electricity consumption characteristics of mean value as the group.
For example, the electricity consumption characteristics of mean between q+1 vital point and q-th of vital point is calculated using the 3rd formula Value, the 3rd formula include：
In formula, aiFor the electricity consumption characteristics of mean value between q+1 vital point and q-th of vital point；For m classes The history electricity consumption data of i-th of group, t areThe location variable of middle data；pqExist for q-th of vital pointIn position Put, pq+1Exist for the q+1 vital pointIn position, wherein, q ∈ { 0,1,2 ..., h-1 }.
Multiple electricity consumption characteristics of mean value a can be obtained by above-mentioned formulai, these electricity consumption characteristics of mean values aiForm one Characteristic set
S5, search electricity consumption strategy corresponding with the electricity consumption characteristics of mean in the electricity consumption policy library pre-established, and will The electricity consumption strategy is sent to the user corresponding to the group.
It will be appreciated that electricity consumption policy library includes multiple electricity consumption strategies, different electricity consumption strategies corresponds to different electricity consumptions Characteristics of mean.For the ease of searching, two word banks can be set in electricity consumption policy library：Electricity consumption characteristics of mean word bank and strategy Storehouse, wherein, a variety of electricity consumption characteristics of mean of all kinds of electrical equipments are stored with electricity consumption characteristics of mean word bank.And in tactful word bank Be stored with the various corresponding Energy Saving Strategies of electricity consumption characteristics of mean in electricity consumption characteristics of mean word bank, what different strategies was applicable in The factor such as season and weather may be different, can be come out factors such as these seasons, weathers as the labeled marker of corresponding strategy.
When strategy is searched, first, the electricity consumption characteristics of mean calculated for each group, in electricity consumption characteristics of mean Corresponding electricity consumption characteristics of mean is searched in storehouse, is then searched according to the electricity consumption characteristics of mean found in tactful word bank corresponding Electricity consumption strategy.The counterparty of the above-mentioned electricity consumption characteristics of mean calculated and electricity consumption characteristics of mean in electricity consumption characteristics of mean word bank Formula, can be identical or similar, i.e., the gap between electricity consumption characteristics of mean is within a preset range.
Electricity consumption policy recommendation method provided in an embodiment of the present invention, according to electrical equipment type to history electricity consumption data into Row classification, and then every a kind of data are clustered, can be by use of the user to same class electrical equipment in every a kind of data It is accustomed to similar electricity consumption data and is polymerized to a group, and then the electricity consumption characteristics of mean to each group is analyzed, and is obtained each Group uses electrical feature, and corresponding electricity consumption strategy is then searched in the electricity consumption policy library pre-established according to electrical feature, into And recommend the user of the group.As it can be seen that this recommendation method, consider the type of electrical equipment, the use habit of electrical equipment, With factors such as electrical features, a kind of personalized electricity consumption policy recommendation can be provided to the user, different user can be met to electricity consumption Demand.
In the specific implementation, electricity consumption policy recommendation method provided in an embodiment of the present invention can also include：
S601, for each group in every a kind of history electricity consumption data, determine corresponding electricity consumption trend feature；
It will be appreciated that the electricity consumption trend feature of a group, refers to the variation tendency of electricity consumption data for characterizing the group Feature.
The electricity consumption trend feature of one group, can be represented in the form of data acquisition system, for example,Here Electricity consumption trend feature for the group has g electricity consumption trend feature value.
In practical application, there is the method for a variety of calculating electricity consumption trend features, a kind of optional mode is described below and calculates m The electricity consumption trend feature of i-th of group of class：
A1, mark h' mark point p' in the history electricity consumption data of i-th of group of m classesq',q'∈{0,1, 2 ..., h'-1 }, the mark point includes electricity consumption peak pick point and electricity consumption valley mark point, wherein：
Electricity consumption peak pick point is：
Electricity consumption valley marks point
A2, calculate in constraintsUnder the 4th formula, the constraints represent Regulation segmentation number g does not include the mark point of mark, obtains the i-th of m classes not less than point h' is marked in all segmentation open intervals The optimal segmentation of the history electricity consumption data of a group, the four formula, that is, formula (7) include：
A3, by five formula, that is, formula (8) calculate m classes i-th of group history electricity consumption data in tiElectricity consumption Trend value, the 5th formula include：
A4, as six formula, that is, formula (9) calculate the history electricity consumption data of i-th of group of m classes obtained by above-mentioned Electricity consumption trend feature value under optimal segmentation, g electricity consumption trend feature value of the history electricity consumption data of i-th of group of m classes The electricity consumption trend feature of composition, is6th formula includes：
In formula, p'q', q' ∈ 0,1,2 ..., and h'-1 } represent history of the q' mark o'clock in i-th of group of m classes Position in electricity consumption data, bjRepresent the electricity consumption trend feature value of j-th of segmentation, sj、fjThe starting of j-th of segmentation is represented respectively And final position, b (ti) represent m classes i-th of group history electricity consumption data each time point corresponding electricity consumption trend Value, g represent the number being segmented, and h' represents the number of mark point, and for the number of g no less than the number h' for marking point, J represents that history is used Error between the electricity consumption Trend value and corresponding segments electricity consumption Trend value of electric data.
It will be appreciated that the corresponding history electricity consumption data of i-th of group of m classes is divided into g segmentation, m classes The data of j-th of segmentation can be expressed as in i-th of group AndUnderstand the number between this g segmentation According to no intersection and broken belt, there must be history electricity consumption data in each segmentation, this g sectionally smooth join gets up just to form m classes I-th of group.
If in S602, the electricity consumption trend feature there are the data for being more than the default Trend value upper limit in electricity consumption trend feature value, Then prompt message of the electricity consumption amount of increase beyond predetermined amplitude is sent to the corresponding user of the group.
For example,There are electricity consumption trend feature value to be more than default Trend value upper limit α, then can be corresponding to group User sends the larger prompt message of the recent electricity consumption increasing degree of user.
In the specific implementation, electricity consumption policy recommendation method provided in an embodiment of the present invention can also include：
S701, receive scoring of the user to used electricity consumption strategy；
Being divided into for scoring can be arranged in the range of 1~5 point, and scoring is higher, shows satisfaction of the user to electricity consumption strategy It is higher.
The scoring of S702, the prediction user to untapped electricity consumption strategy；
Since user can not possibly use electricity consumption strategy used, for no used electricity consumption strategy, It can be determined by the way of prediction.Wherein it is possible to predict user i to untapped electricity consumption using seven formula, that is, formula (10) The scoring of tactful u, the 7th formula include：
In formula, p (i, u) is scorings of the user i to untapped electricity consumption strategy u；S (i, k) is to be higher than with user's i similarities The set of k user of default similarity；rjuFor scorings of the user j to electricity consumption strategy u in S (i, k)；Sim (i, j) is user The similarity of i and user j in electricity consumption policy scores, N (u) are the set for all users for using electricity consumption strategy u.
For example, there is the scoring of N number of electricity consumption strategy, user i and user j to this N number of electricity consumption strategy to be expressed as vectorSimilarity between user i and user j can use following formula (11) to represent：
S703, the electricity consumption strategy transmission that highest in scoring of the user to untapped electricity consumption strategy is scored corresponding To the user；As it can be seen that select by the scoring to user and the scoring of prediction user here and most possibly allow user to be satisfied with Electricity consumption strategy, be then issued to user, and then realize more good recommendation service.
In the specific implementation, weather and the season in user location can also be obtained, then according to the gas in user location Wait and season selects electricity consumption strategy that is corresponding to electricity consumption characteristics of mean and having corresponding season and weather label from policy library.
In the specific implementation, certain processing can also be carried out to the electricity consumption strategy in electricity consumption policy library, for example, according to The scoring at family, determines the minimum electricity consumption strategy of scoring, then the electricity consumption strategy is improved or rejected.It is, of course, also possible to According to the user's characteristics of mean calculated, increase corresponding electricity consumption strategy in electricity consumption policy library.
The embodiment of the present invention also provides a kind of electricity consumption policy recommendation device, which can be integrated in any equipment, such as Shown in Fig. 2, which includes：
Data acquisition module 201, for obtaining history electricity consumption data of several users in preset time period；
Data categorization module 202, for classifying to the history electricity consumption data according to the classification of electrical equipment, obtains Multiclass history electricity consumption data；
Data clusters module 203, for being clustered using default clustering algorithm to every a kind of history electricity consumption data, is obtained Multiple groups；
Characteristic determination module 204, for for each group in every a kind of history electricity consumption data, determining corresponding use Electric characteristics of mean；
Policy recommendation module 205, for being searched and the electricity consumption characteristics of mean pair in the electricity consumption policy library pre-established The electricity consumption strategy answered, and the electricity consumption strategy is sent to the user corresponding to the group.
It will be appreciated that electricity consumption policy recommendation device provided in an embodiment of the present invention and above-mentioned electricity consumption policy recommendation method phase Corresponding, the content such as its explanation in relation to content, specific implementation method, citing, beneficial effect can be with the phase in the parameter above method Part is answered, details are not described herein again.
Present application example also provides a kind of computer equipment, which can be server, as shown in figure 3, the computer Equipment includes one or more processor (CPU) 302, communication module 304, memory 306, user interface 310, and is used for The communication bus 308 of these components is interconnected, wherein：
Processor 302 can be received and be sent data by communication module 304 to realize network service and/or local communication.
User interface 310 includes one or more output equipments 312, it includes one or more speakers and/or one Or multiple visual displays.User interface 310 also includes one or more input equipments 314, it is included such as, keyboard, mouse Mark, voice command input unit or loudspeaker, touch screen displays, touch sensitive tablet, posture capture camera or other inputs are pressed Button or control etc..
Memory 306 can be high-speed random access memory, such as DRAM, SRAM, DDR RAM or other deposit at random Take solid storage device；Or nonvolatile memory, such as one or more disk storage equipments, optical disc memory apparatus, sudden strain of a muscle Deposit equipment, or other non-volatile solid-state memory devices.
Memory 306 stores the executable instruction set of processor 302, including：
Operating system 316, including for handling various basic system services and program for performing hardware dependent tasks；
Using 318, including the various application programs for electricity consumption policy recommendation, this application program can be realized above-mentioned each Process flow in example, for example some or all of instruction module or unit in electricity consumption policy recommendation device can be included. Processor 302, and then can be real by performing the machine-executable instruction in memory 306 in each unit at least one unit The function of existing above-mentioned each unit or mould at least one module in the block.
It should be noted that step and module not all in above-mentioned each flow and each structure chart is all necessary, can To ignore some steps or module according to the actual needs.The execution sequence of each step be not it is fixed, can as needed into Row adjustment.The division of each module is intended merely to facilitate the division functionally that description uses, and when actually realizing, a module can Realized with point by multiple modules, the function of multiple modules can also be realized by same module, these modules can be located at same In a equipment, it can also be located in different equipment.
Hardware module in each example can in hardware or hardware platform adds the mode of software to realize.Above-mentioned software kit Machine readable instructions are included, are stored in non-volatile memory medium.Therefore, each example can also be presented as software product.
In each example, hardware can be by special hardware or the hardware realization of execution machine readable instructions.For example, hardware can be with Permanent circuit or logical device (such as application specific processor, such as FPGA or ASIC) specially to design are used to complete specifically to grasp Make.Hardware can also include programmable logic device or circuit by software provisional configuration (as included general processor or other Programmable processor) it is used to perform specific operation.
In addition, each example of the application can pass through the data processor by data processing equipment such as computer execution To realize.Obviously, data processor constitutes the application.In addition, it is generally stored inside the data processing in a storage medium Program by program by directly reading out storage medium or by installing or copying to the storage of data processing equipment by program Performed in equipment (such as hard disk and/or memory).Therefore, such storage medium also constitutes the application, present invention also provides A kind of non-volatile memory medium, wherein being stored with data processor, this data processor can be used for performing the application Any one of above method example example.
The operating system that the corresponding machine readable instructions of Fig. 3 modules can make to operate on computer etc. is described herein to complete Some or all of operation.Non-volatile computer readable storage medium storing program for executing can be inserted into set by the expansion board in computer In the memory put or write the memory set in the expanding element being connected with computer.Installed in expansion board or expansion Opening up CPU on unit etc. can be according to instruction execution part and whole practical operations.
The embodiment of the present invention also provides a kind of storage medium, is stored thereon with computer program, which is held by processor Realized during row such as the step of the above method.
It is all in spirit herein not to limit the application the foregoing is merely the preferred embodiments of the application Within principle, any modification, equivalent substitution, improvement and etc. done, should be included within the scope of the application protection.

Claims (10)

  1. A kind of 1. electricity consumption policy recommendation method, it is characterised in that including：
    Obtain history electricity consumption data of several users in preset time period；
    Classify to the history electricity consumption data according to the classification of electrical equipment, obtain multiclass history electricity consumption data；
    Every a kind of history electricity consumption data is clustered using default clustering algorithm, obtains multiple groups；
    For each group in every a kind of history electricity consumption data, corresponding electricity consumption characteristics of mean is determined；
    Search corresponding with electricity consumption characteristics of mean electricity consumption strategy in the electricity consumption policy library pre-established, and by the electricity consumption Strategy is sent to the user corresponding to the group.
  2. 2. according to the method described in claim 1, it is characterized in that, it is described to the history electricity consumption data according to electrical equipment Before classification is classified, the method further includes：
    Reject the abnormal electricity consumption data in the history electricity consumption data.
  3. 3. according to the method described in claim 1, it is characterized in that, it is described to the history electricity consumption data according to electrical equipment Before classification is classified, the method further includes：
    S101, carry out the history electricity consumption data using the first formula discrete Fourier transformation processing, obtains sequence of complex numbers； Wherein, first formula includes：
    Xf=Rf+iIf
    <mrow> <msub> <mi>R</mi> <mi>f</mi> </msub> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>t</mi> <mo>=</mo> <mn>0</mn> </mrow> <mrow> <mi>n</mi> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <msub> <mi>x</mi> <mi>t</mi> </msub> <mi>c</mi> <mi>o</mi> <mi>s</mi> <mrow> <mo>(</mo> <mn>2</mn> <mi>&amp;pi;</mi> <mi>f</mi> <mi>t</mi> <mo>/</mo> <mi>n</mi> <mo>)</mo> </mrow> </mrow>
    <mrow> <msub> <mi>I</mi> <mi>f</mi> </msub> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>t</mi> <mo>=</mo> <mn>0</mn> </mrow> <mrow> <mi>n</mi> <mo>-</mo> <mn>1</mn> </mrow> </munderover> <msub> <mi>x</mi> <mi>t</mi> </msub> <mi>s</mi> <mi>i</mi> <mi>n</mi> <mrow> <mo>(</mo> <mn>2</mn> <mi>&amp;pi;</mi> <mi>f</mi> <mi>t</mi> <mo>/</mo> <mi>n</mi> <mo>)</mo> </mrow> </mrow>
    In formula, f=0,1 ..., n/2, XfFor f-th of plural number in the sequence of complex numbers；RfFor XfReal part；IfFor XfVoid Portion；xtFor the history electricity consumption data [xt] t-th of data in (t=0,1 ..., n-1)；N is data in history electricity consumption data Number；
    S102, using the second formula to the sequence of complex numbers carry out inverse transformation processing；
    Wherein, second formula includes：
    <mrow> <msup> <msub> <mi>x</mi> <mi>t</mi> </msub> <mo>&amp;prime;</mo> </msup> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>R</mi> <mn>0</mn> </msub> <mo>+</mo> <msub> <mi>R</mi> <mrow> <mi>n</mi> <mo>/</mo> <mn>2</mn> </mrow> </msub> <mi>c</mi> <mi>o</mi> <mi>s</mi> <mo>(</mo> <mrow> <mi>&amp;pi;</mi> <mi>u</mi> <mi>t</mi> </mrow> <mo>)</mo> <mo>)</mo> </mrow> <mo>/</mo> <mn>2</mn> <mo>+</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>f</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>w</mi> </munderover> <msub> <mi>R</mi> <mi>f</mi> </msub> <mi>c</mi> <mi>o</mi> <mi>s</mi> <mrow> <mo>(</mo> <mn>2</mn> <mi>&amp;pi;</mi> <mi>f</mi> <mi>t</mi> <mi>u</mi> <mo>/</mo> <mi>n</mi> <mo>)</mo> </mrow> <mo>+</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>f</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>w</mi> </munderover> <msub> <mi>I</mi> <mi>f</mi> </msub> <mi>s</mi> <mi>i</mi> <mi>n</mi> <mrow> <mo>(</mo> <mn>2</mn> <mi>&amp;pi;</mi> <mi>f</mi> <mi>t</mi> <mi>u</mi> <mo>/</mo> <mi>n</mi> <mo>)</mo> </mrow> <mo>,</mo> <mi>t</mi> <mo>=</mo> <mn>0</mn> <mo>,</mo> <mn>1</mn> <mo>,</mo> <mo>...</mo> <mo>,</mo> <mrow> <mo>(</mo> <mi>n</mi> <mo>/</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>-</mo> <mn>1</mn> </mrow>
    In formula, u is compression ratio parameter, and w is noise filtering parameter, xt' it is to XfCarry out the electricity consumption number obtained after inverse transformation processing According to R0And Rn/2ByObtain.
  4. 4. according to the method described in claim 1, it is characterized in that, described be directed to per each in a kind of history electricity consumption data Group, determines corresponding electricity consumption characteristics of mean, including：
    To each group in every a kind of history electricity consumption data, multiple vital points are marked；
    User's characteristics of mean value between the adjacent vital point of each two is calculated, obtains multiple user's characteristics of mean values；And by institute State electricity consumption characteristics of mean of multiple user's characteristics of mean values as the group.
  5. 5. according to the method described in claim 4, it is characterized in that, q+1 vital point and q-th are calculated using the 3rd formula Electricity consumption characteristics of mean value between vital point, the 3rd formula include：
    <mrow> <msub> <mi>a</mi> <mi>i</mi> </msub> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>p</mi> <mrow> <mi>q</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>p</mi> <mi>q</mi> </msub> <mo>+</mo> <mn>1</mn> </mrow> </mfrac> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>t</mi> <mo>=</mo> <msub> <mi>p</mi> <mi>q</mi> </msub> </mrow> <msub> <mi>p</mi> <mrow> <mi>q</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> </munderover> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow>
    In formula, aiFor the electricity consumption characteristics of mean value between q+1 vital point and q-th of vital point,For the i-th of m classes The history electricity consumption data of a group, t areThe location variable of middle data；pqExist for q-th of vital pointIn position, pq+1Exist for the q+1 vital pointIn position.
  6. 6. according to the method described in claim 1, it is characterized in that, further include：
    For each group in every a kind of history electricity consumption data, corresponding electricity consumption trend feature is determined；
    If there are the data that electricity consumption trend feature value is more than the default Trend value upper limit in the electricity consumption trend feature, to the group Corresponding user sends the prompt message that electricity consumption amount of increase exceeds predetermined amplitude.
  7. 7. the according to the method described in claim 6, it is characterized in that, calculating of the electricity consumption trend feature of i-th of group of m classes Process includes：
    A1, mark h' mark point p' in the history electricity consumption data of i-th of group of m classesq',q'∈{0,1,2,...,h'- 1 }, the mark point includes electricity consumption peak pick point and electricity consumption valley mark point, wherein：
    Electricity consumption peak pick point is：
    <mrow> <mo>{</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;le;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>&amp;cap;</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&lt;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>}</mo> <mo>&amp;cup;</mo> <mo>{</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&lt;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>&amp;cap;</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;le;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>}</mo> </mrow>
    Electricity consumption valley marks point：
    <mrow> <mo>{</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;GreaterEqual;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>&amp;cap;</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&gt;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>}</mo> <mo>&amp;cup;</mo> <mo>{</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&gt;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>&amp;cap;</mo> <mo>&amp;lsqb;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;GreaterEqual;</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <msub> <msup> <mi>p</mi> <mo>&amp;prime;</mo> </msup> <msup> <mi>q</mi> <mo>&amp;prime;</mo> </msup> </msub> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> <mo>}</mo> </mrow>
    A2, calculate in constraintsUnder the 4th formula, obtain i-th group of m classes The optimal segmentation of the history electricity consumption data of group, the constraints represent regulation segmentation number g not less than mark point h', all segmentations The mark point of mark is not included in open interval, the 4th formula includes：
    <mrow> <mi>min</mi> <mi> </mi> <mi>J</mi> <mo>=</mo> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>k</mi> </munderover> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <msub> <mi>s</mi> <mi>j</mi> </msub> </mrow> <msub> <mi>f</mi> <mi>j</mi> </msub> </munderover> <msup> <mrow> <mo>&amp;lsqb;</mo> <mi>b</mi> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>-</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>f</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>s</mi> <mi>j</mi> </msub> <mo>+</mo> <mn>1</mn> </mrow> </mfrac> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>I</mi> <mo>=</mo> <msub> <mi>s</mi> <mi>j</mi> </msub> </mrow> <msub> <mi>f</mi> <mi>j</mi> </msub> </munderover> <mi>b</mi> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> </mrow> <mn>2</mn> </msup> </mrow>
    A3, by the 5th formula calculate m classes i-th of group history electricity consumption data in tiElectricity consumption Trend value, the described 5th Formula includes：
    <mrow> <mi>b</mi> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mrow> <mo>(</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mo>(</mo> <msub> <mi>t</mi> <mrow> <mi>i</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>)</mo> <mo>-</mo> <msub> <mi>y</mi> <msub> <mi>m</mi> <mi>i</mi> </msub> </msub> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> <mo>)</mo> </mrow> <mo>/</mo> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mrow> <mi>i</mi> <mo>+</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow>
    A4, as the 6th formula calculate the history electricity consumption data of i-th of group of m classes under the optimal segmentation obtained by above-mentioned The electricity consumption trend feature value being each segmented, g electricity consumption trend feature value group of the history electricity consumption data of i-th of group of m classes Into electricity consumption trend feature be6th formula includes：
    <mrow> <msub> <mi>b</mi> <mi>j</mi> </msub> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>f</mi> <mi>j</mi> </msub> <mo>-</mo> <msub> <mi>s</mi> <mi>j</mi> </msub> <mo>+</mo> <mn>1</mn> </mrow> </mfrac> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <msub> <mi>s</mi> <mi>j</mi> </msub> </mrow> <msub> <mi>f</mi> <mi>j</mi> </msub> </munderover> <mi>b</mi> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow>
    In formula, p'q', q' ∈ 0,1,2 ..., and h'-1 } represent history electricity consumption of the q' mark o'clock in i-th of group of m classes Position in data, bjRepresent the electricity consumption trend feature value of j-th of segmentation, sj、fjStarting and the end of j-th of segmentation are represented respectively Point position, b (ti) represent m classes i-th of group history electricity consumption data each time point corresponding electricity consumption Trend value, g The number of segmentation is represented, h' represents to mark the number of point, and the number of g is no less than the number h' of mark point, J expression history electricity consumption numbers According to electricity consumption Trend value and corresponding segments electricity consumption Trend value between error.
  8. 8. according to the method described in claim 1, it is characterized in that, further include：
    Receive scoring of the user to used electricity consumption strategy；
    Predict scoring of the user to untapped electricity consumption strategy；
    The corresponding electricity consumption strategy of highest scoring in scoring of the user to untapped electricity consumption strategy is sent to the use Family；
    Wherein, included using scorings of the 7th formula predictions user i to untapped electricity consumption strategy u, the 7th formula：
    <mrow> <mi>p</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>u</mi> <mo>)</mo> </mrow> <mo>=</mo> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>j</mi> <mo>&amp;Element;</mo> <mi>S</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>k</mi> <mo>)</mo> </mrow> <mo>&amp;cap;</mo> <mi>N</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>)</mo> </mrow> </mrow> </munder> <mi>s</mi> <mi>i</mi> <mi>m</mi> <mrow> <mo>(</mo> <mi>i</mi> <mo>,</mo> <mi>j</mi> <mo>)</mo> </mrow> <mo>&amp;times;</mo> <msub> <mi>r</mi> <mrow> <mi>j</mi> <mi>u</mi> </mrow> </msub> </mrow>
    In formula, p (i, u) is scorings of the user i to untapped electricity consumption strategy u；S (i, k) is higher than default with user i similarities The set of k user of similarity；rjuFor scorings of the user j to electricity consumption strategy u in S (i, k)；Sim (i, j) for user i and Similarities of the user j in electricity consumption policy scores, N (u) are the set for all users for using electricity consumption strategy u.
  9. A kind of 9. electricity consumption policy recommendation device, it is characterised in that including：
    Data acquisition module, for obtaining history electricity consumption data of several users in preset time period；
    Data categorization module, for classifying to the history electricity consumption data according to the classification of electrical equipment, obtains multiclass and goes through History electricity consumption data；
    Data clusters module, for being clustered using default clustering algorithm to every a kind of history electricity consumption data, obtains multiple groups Group；
    Characteristic determination module, for for each group in every a kind of history electricity consumption data, determining corresponding electricity consumption average Feature；
    Policy recommendation module, for searching electricity consumption corresponding with the electricity consumption characteristics of mean in the electricity consumption policy library pre-established Strategy, and the electricity consumption strategy is sent to the user corresponding to the group.
  10. 10. a kind of storage medium, is stored thereon with computer program, it is characterised in that the program is realized when being executed by processor The step of the method as any such as claim 1~8.
CN201711297765.6A 2017-12-08 2017-12-08 Electricity consumption policy recommendation method and device, storage medium Pending CN107958338A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711297765.6A CN107958338A (en) 2017-12-08 2017-12-08 Electricity consumption policy recommendation method and device, storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711297765.6A CN107958338A (en) 2017-12-08 2017-12-08 Electricity consumption policy recommendation method and device, storage medium

Publications (1)

Publication Number Publication Date
CN107958338A true CN107958338A (en) 2018-04-24

Family

ID=61958433

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711297765.6A Pending CN107958338A (en) 2017-12-08 2017-12-08 Electricity consumption policy recommendation method and device, storage medium

Country Status (1)

Country Link
CN (1) CN107958338A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109508858A (en) * 2018-09-30 2019-03-22 国网安徽省电力有限公司经济技术研究院 Residential households electricity consumption Intervention Strategy recommended method under a kind of timesharing step price policy
CN109977177A (en) * 2019-03-27 2019-07-05 新奥数能科技有限公司 Generate the method and device of user's portrait
CN110399430A (en) * 2019-06-14 2019-11-01 平安科技（深圳）有限公司 User characteristics determine method, apparatus, equipment and computer readable storage medium
CN110867964A (en) * 2019-11-26 2020-03-06 胡维东 Intelligent electricity utilization safety monitoring method based on Internet of things and main control computer
CN111242308A (en) * 2019-12-31 2020-06-05 深圳能源售电有限公司 Energy-saving strategy recommendation method and device, computer equipment and storage medium
CN112836886A (en) * 2021-02-09 2021-05-25 国网山西省电力公司吕梁供电公司 Energy consumption service method and device, computer equipment and storage medium
CN113554268A (en) * 2021-06-10 2021-10-26 合肥工业大学 Method and system for selecting power utilization strategy for balancing peak valley and light and vigorous seasons
CN115329907A (en) * 2022-10-14 2022-11-11 杭州致成电子科技有限公司 Electric load completion method and system based on DBSCAN clustering
CN115713435A (en) * 2022-11-15 2023-02-24 广州鲁邦通物联网科技股份有限公司 Power utilization management method and system based on MEC edge intelligent gateway

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102799656A (en) * 2012-07-03 2012-11-28 复旦大学 Target-user-oriented individualized product package extracting method
US20140142905A1 (en) * 2012-11-16 2014-05-22 Johnson Controls Technology Company Systems and methods for building energy use benchmarking
CN105023092A (en) * 2015-06-24 2015-11-04 国网山东省电力公司电力科学研究院 Power load monitoring method based on electric quantity feature analysis
CN105425034A (en) * 2015-12-17 2016-03-23 国网江西省电力科学研究院 Power utilization characteristic spectrum analysis method for specific AC components
CN106022646A (en) * 2016-06-08 2016-10-12 国网上海市电力公司 Electric power user information data analysis system and analysis method
CN106204321A (en) * 2016-06-30 2016-12-07 西安美林数据技术股份有限公司 A kind of method that intelligence formulates power customer peak load shifting strategy
CN106204162A (en) * 2016-07-26 2016-12-07 郑州郑大智能科技股份有限公司 New networking power consumer electricity consumption mode prediction method under a kind of internet environment
CN106296260A (en) * 2016-07-24 2017-01-04 国家电网公司 Power consumer package recommendation method under a kind of internet environment
CN107274025A (en) * 2017-06-21 2017-10-20 国网山东省电力公司诸城市供电公司 A kind of system and method realized with power mode Intelligent Recognition and management
CN107422645A (en) * 2017-08-07 2017-12-01 国网安徽电力节能服务有限公司 A kind of smart home power saving apparatus and method based on self study

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102799656A (en) * 2012-07-03 2012-11-28 复旦大学 Target-user-oriented individualized product package extracting method
US20140142905A1 (en) * 2012-11-16 2014-05-22 Johnson Controls Technology Company Systems and methods for building energy use benchmarking
CN105023092A (en) * 2015-06-24 2015-11-04 国网山东省电力公司电力科学研究院 Power load monitoring method based on electric quantity feature analysis
CN105425034A (en) * 2015-12-17 2016-03-23 国网江西省电力科学研究院 Power utilization characteristic spectrum analysis method for specific AC components
CN106022646A (en) * 2016-06-08 2016-10-12 国网上海市电力公司 Electric power user information data analysis system and analysis method
CN106204321A (en) * 2016-06-30 2016-12-07 西安美林数据技术股份有限公司 A kind of method that intelligence formulates power customer peak load shifting strategy
CN106296260A (en) * 2016-07-24 2017-01-04 国家电网公司 Power consumer package recommendation method under a kind of internet environment
CN106204162A (en) * 2016-07-26 2016-12-07 郑州郑大智能科技股份有限公司 New networking power consumer electricity consumption mode prediction method under a kind of internet environment
CN107274025A (en) * 2017-06-21 2017-10-20 国网山东省电力公司诸城市供电公司 A kind of system and method realized with power mode Intelligent Recognition and management
CN107422645A (en) * 2017-08-07 2017-12-01 国网安徽电力节能服务有限公司 A kind of smart home power saving apparatus and method based on self study

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
周强: "时序数据挖掘在经济领域中的应用研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109508858A (en) * 2018-09-30 2019-03-22 国网安徽省电力有限公司经济技术研究院 Residential households electricity consumption Intervention Strategy recommended method under a kind of timesharing step price policy
CN109977177A (en) * 2019-03-27 2019-07-05 新奥数能科技有限公司 Generate the method and device of user's portrait
CN110399430A (en) * 2019-06-14 2019-11-01 平安科技（深圳）有限公司 User characteristics determine method, apparatus, equipment and computer readable storage medium
CN110867964A (en) * 2019-11-26 2020-03-06 胡维东 Intelligent electricity utilization safety monitoring method based on Internet of things and main control computer
CN111242308A (en) * 2019-12-31 2020-06-05 深圳能源售电有限公司 Energy-saving strategy recommendation method and device, computer equipment and storage medium
CN111242308B (en) * 2019-12-31 2023-06-23 深圳能源售电有限公司 Energy-saving strategy recommendation method, device, computer equipment and storage medium
CN112836886A (en) * 2021-02-09 2021-05-25 国网山西省电力公司吕梁供电公司 Energy consumption service method and device, computer equipment and storage medium
CN113554268A (en) * 2021-06-10 2021-10-26 合肥工业大学 Method and system for selecting power utilization strategy for balancing peak valley and light and vigorous seasons
CN113554268B (en) * 2021-06-10 2024-03-15 合肥工业大学 Method and system for selecting electricity utilization strategies in balanced peak-valley and light-heavy seasons
CN115329907A (en) * 2022-10-14 2022-11-11 杭州致成电子科技有限公司 Electric load completion method and system based on DBSCAN clustering
CN115329907B (en) * 2022-10-14 2023-01-31 杭州致成电子科技有限公司 Electric load completion method and system based on DBSCAN clustering
CN115713435A (en) * 2022-11-15 2023-02-24 广州鲁邦通物联网科技股份有限公司 Power utilization management method and system based on MEC edge intelligent gateway

Similar Documents

Publication Publication Date Title
CN107958338A (en) Electricity consumption policy recommendation method and device, storage medium
Zhang et al. Typical wind power scenario generation for multiple wind farms using conditional improved Wasserstein generative adversarial network
CN109165301A (en) Video cover selection method, device and computer readable storage medium
CN105320957B (en) Classifier training method and device
CN110674407B (en) Hybrid recommendation method based on graph convolution neural network
Naseriparsa et al. A hybrid feature selection method to improve performance of a group of classification algorithms
CN102193936B (en) Data classification method and device
CN103258000B (en) Method and device for clustering high-frequency keywords in webpages
CN103886048B (en) Cluster-based increment digital book recommendation method
CN104142999A (en) Search result display method and device
CN106021575A (en) Retrieval method and device for same commodities in video
CN109947987B (en) Cross collaborative filtering recommendation method
CN108509407A (en) Text semantic similarity calculating method, device and user terminal
CN106156092A (en) Data processing method and device
CN109508748A (en) A kind of clustering method and device
CN110390056A (en) Big data processing method, device, equipment and readable storage medium storing program for executing
CN103353881A (en) Method and device for searching application
CN106649380A (en) Hot spot recommendation method and system based on tag
CN111767675A (en) Transformer vibration fault monitoring method and device, electronic equipment and storage medium
CN107506871A (en) A kind of method and system of interval prediction
WO2020147259A1 (en) User portait method and apparatus, readable storage medium, and terminal device
CN104035978A (en) Association discovering method and system
CN104794135B (en) A kind of method and apparatus being ranked up to search result
CN113743079A (en) Text similarity calculation method and device based on co-occurrence entity interaction graph
CN105357583A (en) Method and device for discovering interest and preferences of intelligent television user

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: 20180424

RJ01 Rejection of invention patent application after publication