CN110210677A - A kind of bus Short-term Load Forecast method and apparatus of combination cluster and deep learning algorithm - Google Patents
A kind of bus Short-term Load Forecast method and apparatus of combination cluster and deep learning algorithm Download PDFInfo
- Publication number
- CN110210677A CN110210677A CN201910492521.6A CN201910492521A CN110210677A CN 110210677 A CN110210677 A CN 110210677A CN 201910492521 A CN201910492521 A CN 201910492521A CN 110210677 A CN110210677 A CN 110210677A
- Authority
- CN
- China
- Prior art keywords
- bus
- load
- deep learning
- short
- term
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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 disclosure discloses the bus Short-term Load Forecast method and apparatus of a kind of combination cluster and deep learning algorithm, this method comprises: receiving power grid bus data, analyze power grid bus load characteristic, determine the short-term bus load predicted impact factor；The feature of impact factor is extracted, data normalization processing is carried out, establishes load database；The bus with similar features is polymerize using clustering algorithm, true defining K value；The corresponding prediction model of K kind mode is established by deep learning shot and long term memory network；Using Momentum algorithm optimization prediction model, bus load prediction is completed.
Description
Technical field
The disclosure belongs to the technical field of dispatching of power netwoks department load prediction, is related to a kind of combination cluster and deep learning is calculated
The bus Short-term Load Forecast method and apparatus of method.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
The precision of bus load prediction result, can significantly affect Security Checking and plan a few days ago, in order to guarantee electric system
Safety and stability is economically run, and avoids unnecessary energy waste, must just grasp the changing rule and hair of various loads
Exhibition trend.Bus load prediction result can provide imaginary flow data for power grid, be security and stability analysis, idle work optimization, dynamic
The base of state estimation, plant stand Partial controll etc. is tucked inside the sleeve, and the lean and intelligent level of dispatching of power netwoks are improved.
However, inventor has found in the course of the research, the difficult point of bus load prediction is compared with system loading, bus
The base lotus of load is small, fluctuation is big, burr is more, and linear regression method common at present has been unable to reach ideal precision.
Summary of the invention
For the deficiencies in the prior art, solve the problem of that bus Numerous has a large capacity and a wide range, one of the disclosure
Or multiple embodiments provide the bus Short-term Load Forecast method and apparatus of a kind of combination cluster and deep learning algorithm, have
Effect improves bus Short-term Load Forecast precision.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of combination cluster and deep learning algorithm are provided
Bus Short-term Load Forecast method.
A kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm, this method comprises:
Power grid bus data are received, power grid bus load characteristic is analyzed, determines the short-term bus load predicted impact factor；
The feature of impact factor is extracted, data normalization processing is carried out, establishes load database；
The bus with similar features is polymerize using clustering algorithm, true defining K value；
The corresponding prediction model of K kind mode is established by deep learning shot and long term memory network；
Using Momentum algorithm optimization prediction model, bus load prediction is completed.
Further, in the method, the power grid bus data include bussed supply type, date type, temperature, light
According to situation, electricity price and daily load.
Further, in the method, the specific steps of the short-term bus load predicted impact factor of the determination include:
The related coefficient between the power grid bus data is determined using correlation analysis method；.
The power grid bus data that related coefficient is greater than relevance threshold are determined as the short-term bus load predicted impact factor.
Further, in the method, normalizing is carried out to the feature for extracting impact factor using Z-score standardized method
Standardization.
Further, in the method, using k-means clustering algorithm by the bus with similar features into
Row polymerization, specific steps include:
Euclidean distance as unit of bus, in calculated load database between all data；
The density between each data object is calculated, the point that density is greater than density threshold is formed into density set；
Density is selected from density set at maximum o'clock as first initial point, find out first initial point distance of distance most
Remote point；
Selection and first initial point of first initial point and distance are maximum most apart from farthest point in density set
The point of small distance；
Selection and the point for having selected the maximum minimum range of cluster centre, as second initial point；
Iterative calculation calculates K obtained initial point as the starting point of mean algorithm.
Further, in the method, the density threshold is obtained according to object data set number progress extracting operation.
It is further, in the method, described that by deep learning shot and long term memory network to establish K kind mode corresponding pre-
Survey model specific steps include:
Build the deep learning shot and long term memory models of load prediction；
For divided K kind bus mode, respectively to the bus training of each pattern, corresponding K kind model is established.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device loads and executes the bus Short-term Load Forecast method of a kind of the combination cluster and deep learning algorithm.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of terminal device is provided.
A kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction；Meter
Calculation machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed a kind of combination for storing a plurality of instruction, described instruction
The bus Short-term Load Forecast method of cluster and deep learning algorithm.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of combination cluster and deep learning algorithm are provided
Bus Short-term Load Forecast device.
A kind of bus Short-term Load Forecast device of combination cluster and deep learning algorithm, based on a kind of combination
The bus Short-term Load Forecast method of cluster and deep learning algorithm, comprising:
Impact factor determining module is configured as receiving power grid bus data, analyzes power grid bus load characteristic, determine short
The phase bus load predicted impact factor；
Load database establishes module, is configured as extracting the feature of impact factor, carries out data normalization processing, establish
Load database；
Mode classification module is configured as being polymerize the bus with similar features using clustering algorithm, determines K
Value；
Prediction model constructs module, is configured as establishing K kind mode by deep learning shot and long term memory network corresponding
Prediction model；
Bus load prediction module is configured as that it is pre- to complete bus load using Momentum algorithm optimization prediction model
It surveys.
The disclosure the utility model has the advantages that
(1) the bus Short-term Load Forecast method and dress for a kind of the combination cluster and deep learning algorithm that the disclosure provides
It sets, radix low problem more for bus model quantity, together by the similar model aggregation of feature is built using clustering algorithm
Corresponding model is found, to improve accuracy.
(2) the bus Short-term Load Forecast method and dress for a kind of the combination cluster and deep learning algorithm that the disclosure provides
It sets, using advanced algorithm, prediction accuracy is high.Daily load uses shot and long term memory models algorithm in advance, fully considers time series,
Effectively solve the insoluble timing knotty problem under traditional algorithm.
(3) the bus Short-term Load Forecast method and dress for a kind of the combination cluster and deep learning algorithm that the disclosure provides
It sets, using Momentum algorithm optimization, bus Short-term Load Forecast result is more accurate.
Detailed description of the invention
The accompanying drawings constituting a part of this application is used to provide further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation are not constituted an undue limitation on the present application for explaining the application.
Fig. 1 is the short-term daily load of bus according to a kind of the combination cluster and deep learning algorithm of one or more embodiments
Prediction technique flow chart；
Fig. 2 is the shot and long term memory network LSTM network structure according to one or more embodiments；
Fig. 3 is certain bus Short-term Load Forecast result figure according to one or more embodiments.
Specific embodiment:
Below in conjunction with the attached drawing in one or more other embodiments of the present disclosure, to one or more other embodiments of the present disclosure
In technical solution be clearly and completely described, it is clear that described embodiment is only disclosure a part of the embodiment,
Instead of all the embodiments.Based on one or more other embodiments of the present disclosure, those of ordinary skill in the art are not being made
Every other embodiment obtained under the premise of creative work belongs to the range of disclosure protection.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the application.Unless another
It indicates, all technical and scientific terms used have to be generally understood with the application person of an ordinary skill in the technical field
Identical meanings.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
It should be noted that flowcharts and block diagrams in the drawings show according to various embodiments of the present disclosure method and
The architecture, function and operation in the cards of system.It should be noted that each box in flowchart or block diagram can represent
A part of one module, program segment or code, a part of the module, program segment or code may include one or more
A executable instruction for realizing the logic function of defined in each embodiment.It should also be noted that some alternately
Realization in, function marked in the box can also occur according to the sequence that is marked in attached drawing is different from.For example, two connect
The box even indicated can actually be basically executed in parallel or they can also be executed in a reverse order sometimes,
This depends on related function.It should also be noted that each box and flow chart in flowchart and or block diagram
And/or the combination of the box in block diagram, the dedicated hardware based system that functions or operations as defined in executing can be used are come
It realizes, or the combination of specialized hardware and computer instruction can be used to realize.
In the absence of conflict, the feature in the embodiment and embodiment in the disclosure can be combined with each other, and tie below
It closes attached drawing and embodiment is described further the disclosure.
Embodiment one
According to the one aspect of one or more other embodiments of the present disclosure, a kind of combination cluster and deep learning algorithm are provided
Bus Short-term Load Forecast method.
As shown in Figure 1, a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm, this method packet
It includes:
Step S1: the part throttle characteristics of analysis power grid bus determines the short-term bus load predicted impact factor；
Step S2: extracting the feature of impact factor, carries out data normalization processing, establishes load database；
Step S3: using big data clustering algorithm, the bus with similar features condensed together, and completes mode point
Class, true defining K value；
Step S4: according to the K kind mode in step S3, corresponding prediction is established by deep learning shot and long term memory network
Model；
Step S5: optimizing model using Momentum algorithm, completes bus load prediction.
In the embodiment of the present invention step S1, the part throttle characteristics of power grid bus is analyzed, determines short-term bus load prediction
Impact factor, determining bussed supply type, date type using correlation analysis method, (Monday to Sunday, section are false
Day), temperature, light conditions, the related coefficient between electricity price and daily load, determine short-term load forecasting data dependence size.
Related coefficient calculation formula is as follows:
Wherein, X is respectively bussed supply type, date type (Monday to Sunday, festivals or holidays), temperature, illumination feelings
The set of condition, Y represent load value set.Cov (X, Y) is X, and the covariance of Y, D (X), D (Y) are respectively X, the auto-variance of Y, and-
1≤ρXY≤1；ρXYWhen > 0, X, Y are positively correlated；ρXYWhen < 0, X, Y are negatively correlated.If relevance threshold absolute value is recognized 0.5 or more
To have correlation, it is determined as input quantity.
In the embodiment of the present invention step S2, to the feature for extracting impact factor in step S1, data normalization is carried out
Processing, establishes load database D；
Bussed supply type includes (commercial power, residential electricity consumption, farming power, municipal electricity consumption, iron and steel enterprise's electricity consumption), day
Phase type (Monday to Sunday, festivals or holidays), temperature, electricity price, light conditions, as shown in table 1.
Table 1
Using Z-score standardized method, transformation to initial data makes result fall on [0,1] section.Normalize formula
It is as follows:
Wherein, x*Indicate data after converting, x indicates data before converting, and u indicates swap data set average value, σ expression standard
Deviation, N indicate data set number, and i is represented i-th, xiRepresent i-th of data.
In the embodiment of the present invention step S3, using big data clustering algorithm, the bus with similar features is polymerize
Together, pattern classification, true defining K value are completed.
As unit of bus, cluster data collection F is formed with load database, the load data established in step S2.Using
K-means clustering algorithm algorithm is clustered, and determines bus mode K.A kind of base is used in the present embodiment
Pattern classification is carried out in the means clustering algorithm of packing density, the specific steps are as follows:
(1) Euclidean distance in the database D in step S2 between all data is calculated, calculates average departure according to the following formula
From.
In formula, D is data set, and n is object data set number.
(2) density between each computing object is calculated, density is greater thanPoint form density set.
(3) density is selected from density set at maximum o'clock as first initial point k1, then find out distance k1Distance is farthest
Point k2。
(4) selection and k in density set1And k2The point k of maximum minimum range3。
(5) continue selection and select the point of the maximum minimum range of cluster centre.
(6) the K initial point that will be obtained, the starting point as mean algorithm are calculated.
Under normal conditions, no matter object n scale to be clustered has much in data set, and the K value of cluster is not more than
Therefore averagely each cluster number isSelectionPartitioning standards as density points.
In the embodiment of the present invention step S4, according to the K kind mode in step S3, remembered by deep learning shot and long term
Network establishes corresponding prediction model；Build deep learning shot and long term memory (the Long Short Term of load prediction
Memory, LSTM) model, as shown in Fig. 2, divided K kind bus mode is directed to, respectively to the bus training of each pattern, foundation
Corresponding K kind model.Each pattern corresponds to different input quantities according to actual conditions influence factor.
In the embodiment of the present invention step S5, model is optimized using Momentum algorithm.
For data (YLSTM-1,YPractical -1), (YLSTM-2,YPractical -2) ..., (YLSTM-n,YPractical-n), construct multinomial F (Y)=λ1
+λ2YLSTM+λ3YLSTM 2+…+λmYLSTM m-1(m < n), makes it
Wherein YLSTM-iFor the output in step S3, YPractical-iFor actual value,
λ1, λ2..., λmFor parameter to be asked.
IfIt asks
It leads:
J=1,2 ..., m, solution obtain λ1, λ2..., λm, and then obtain F (Y)=λ1+λ2YLSTM+λ3YLSTM 2+…+λmYLSTM m-1(m < n) is final load prediction results.Certain bus Short-term Load Forecast result figure as shown in Figure 3.
Embodiment two
According to the one aspect of one or more other embodiments of the present disclosure, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device loads and executes the bus Short-term Load Forecast method of a kind of the combination cluster and deep learning algorithm.
Embodiment three
According to the one aspect of one or more other embodiments of the present disclosure, a kind of terminal device is provided.
A kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction；Meter
Calculation machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed a kind of combination for storing a plurality of instruction, described instruction
The bus Short-term Load Forecast method of cluster and deep learning algorithm.
These computer executable instructions execute the equipment according to each reality in the disclosure
Apply method or process described in example.
In, computer program product may include computer readable storage medium, containing for executing the disclosure
Various aspects computer-readable program instructions.Computer readable storage medium, which can be, can keep and store to be held by instruction
The tangible device for the instruction that row equipment uses.Computer readable storage medium for example can be-- but it is not limited to-- electricity storage
Equipment, magnetic storage apparatus, light storage device, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate group
It closes.The more specific example (non exhaustive list) of computer readable storage medium include: portable computer diskette, hard disk, with
Machine access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or flash memory), it is static with
Machine accesses memory (SRAM), Portable compressed disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, soft
Disk, mechanical coding equipment, the punch card for being for example stored thereon with instruction or groove internal projection structure and above-mentioned any appropriate
Combination.Computer readable storage medium used herein above is not interpreted instantaneous signal itself, such as radio wave or
The electromagnetic wave of other Free propagations, the electromagnetic wave propagated by waveguide or other transmission mediums are (for example, the light for passing through fiber optic cables
Pulse) or pass through electric wire transmit electric signal.
Computer-readable program instructions described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing present disclosure operation can be assembly instruction, instruction set architecture (ISA)
Instruction, machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programmings
The source code or object code that any combination of language is write, the programming language include the programming language-of object-oriented such as
C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer-readable program refers to
Order can be executed fully on the user computer, partly be executed on the user computer, as an independent software package
Execute, part on the user computer part on the remote computer execute or completely on a remote computer or server
It executes.In situations involving remote computers, remote computer can include local area network by the network-of any kind
(LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize internet
Service provider is connected by internet).In some embodiments, by being believed using the state of computer-readable program instructions
Breath comes personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or programmable logic
Array (PLA), the electronic circuit can execute computer-readable program instructions, to realize the various aspects of present disclosure.
Example IV
According to the one aspect of one or more other embodiments of the present disclosure, a kind of combination cluster and deep learning algorithm are provided
Bus Short-term Load Forecast device.
A kind of bus Short-term Load Forecast device of combination cluster and deep learning algorithm, based on a kind of combination
The bus Short-term Load Forecast method of cluster and deep learning algorithm, comprising:
Impact factor determining module is configured as receiving power grid bus data, analyzes power grid bus load characteristic, determine short
The phase bus load predicted impact factor；
Load database establishes module, is configured as extracting the feature of impact factor, carries out data normalization processing, establish
Load database；
Mode classification module is configured as being polymerize the bus with similar features using clustering algorithm, determines K
Value；
Prediction model constructs module, is configured as establishing K kind mode by deep learning shot and long term memory network corresponding
Prediction model；
Bus load prediction module is configured as that it is pre- to complete bus load using Momentum algorithm optimization prediction model
It surveys.
It should be noted that although being referred to several modules or submodule of equipment in the detailed description above, it is this
Division is only exemplary rather than enforceable.In fact, in accordance with an embodiment of the present disclosure, two or more above-described moulds
The feature and function of block can embody in a module.Conversely, the feature and function of an above-described module can be with
Further division is to be embodied by multiple modules.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.Therefore, the disclosure is not intended to be limited to this
These embodiments shown in text, and it is to fit to the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm, which is characterized in that this method packet
It includes:
Power grid bus data are received, power grid bus load characteristic is analyzed, determines the short-term bus load predicted impact factor；
The feature of impact factor is extracted, data normalization processing is carried out, establishes load database；
The bus with similar features is polymerize using clustering algorithm, true defining K value；
The corresponding prediction model of K kind mode is established by deep learning shot and long term memory network；
Using Momentum algorithm optimization prediction model, bus load prediction is completed.
2. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm as described in claim 1,
Be characterized in that, in the method, the power grid bus data include bussed supply type, date type, temperature, light conditions,
Electricity price and daily load.
3. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm as described in claim 1,
It is characterized in that, in the method, the specific steps of the short-term bus load predicted impact factor of determination include:
The related coefficient between the power grid bus data is determined using correlation analysis method；.
The power grid bus data that related coefficient is greater than relevance threshold are determined as the short-term bus load predicted impact factor.
4. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm as described in claim 1,
It is characterized in that, in the method, the feature for extracting impact factor is carried out at normalizing standardization using Z-score standardized method
Reason.
5. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm as described in claim 1,
It is characterized in that, in the method, polymerize the bus with similar features using k-means clustering algorithm have
Body step includes:
Euclidean distance as unit of bus, in calculated load database between all data；
The density between each data object is calculated, the point that density is greater than density threshold is formed into density set；
Density is selected from density set at maximum o'clock as first initial point, it is farthest to find out distance first initial point distance
Point；
Selection is with first initial point of first initial point and distance apart from the farthest maximum most narrow spacing of point in density set
From point；
Selection and the point for having selected the maximum minimum range of cluster centre, as second initial point；
Iterative calculation calculates K obtained initial point as the starting point of mean algorithm.
6. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm as claimed in claim 5,
It is characterized in that, in the method, the density threshold carries out extracting operation according to object data set number and obtains.
7. a kind of bus Short-term Load Forecast method of combination cluster and deep learning algorithm as described in claim 1,
It is characterized in that, it is in the method, described that the corresponding prediction model of K kind mode is established by deep learning shot and long term memory network
Specific steps include:
Build the deep learning shot and long term memory models of load prediction；
For divided K kind bus mode, respectively to the bus training of each pattern, corresponding K kind model is established.
8. a kind of computer readable storage medium, wherein being stored with a plurality of instruction, which is characterized in that described instruction is suitable for by terminal
The processor of equipment is loaded and is executed such as a kind of described in any item mothers of combination cluster and deep learning algorithm of claim 1-7
Line Short-term Load Forecast method.
9. a kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction；It calculates
Machine readable storage medium storing program for executing is for storing a plurality of instruction, which is characterized in that described instruction is suitable for being loaded by processor and being executed such as power
Benefit requires a kind of described in any item bus Short-term Load Forecast methods of combination cluster and deep learning algorithm of 1-7.
10. the bus Short-term Load Forecast device of a kind of combination cluster and deep learning algorithm, which is characterized in that based on as weighed
Benefit requires a kind of described in any item bus Short-term Load Forecast methods of combination cluster and deep learning algorithm of 1-7, comprising:
Impact factor determining module is configured as receiving power grid bus data, analyzes power grid bus load characteristic, determines short-term female
The specific electric load predicted impact factor；
Load database establishes module, is configured as extracting the feature of impact factor, carries out data normalization processing, establish load
Database；
Mode classification module is configured as polymerizeing the bus with similar features using clustering algorithm, true defining K value；
Prediction model constructs module, is configured as establishing the corresponding prediction of K kind mode by deep learning shot and long term memory network
Model；
Bus load prediction module is configured as completing bus load prediction using Momentum algorithm optimization prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910492521.6A CN110210677B (en) | 2019-06-06 | 2019-06-06 | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910492521.6A CN110210677B (en) | 2019-06-06 | 2019-06-06 | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110210677A true CN110210677A (en) | 2019-09-06 |
| CN110210677B CN110210677B (en) | 2022-03-04 |
Family
ID=67791300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910492521.6A Active CN110210677B (en) | 2019-06-06 | 2019-06-06 | Bus short-term daily load prediction method and device combining clustering and deep learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210677B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111505406A (en) * | 2020-03-16 | 2020-08-07 | 剑科云智(深圳)科技有限公司 | Power distribution cabinet and wire monitoring method |
| CN110826795B (en) * | 2019-10-31 | 2023-06-09 | 国网辽宁省电力有限公司经济技术研究院 | Day-ahead load prediction method for extreme temperature weather day bus |
| CN116826745A (en) * | 2023-08-30 | 2023-09-29 | 山东海兴电力科技有限公司 | Layered and partitioned short-term load prediction method and system in power system background |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090179626A1 (en) * | 2008-01-10 | 2009-07-16 | Smith David E | Characterization Of AC Mains Circuit Parameters |
| CN107590567A (en) * | 2017-09-13 | 2018-01-16 | 南京航空航天大学 | A kind of Recognition with Recurrent Neural Network short-term load forecasting method based on comentropy cluster and notice mechanism |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
-
2019
- 2019-06-06 CN CN201910492521.6A patent/CN110210677B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090179626A1 (en) * | 2008-01-10 | 2009-07-16 | Smith David E | Characterization Of AC Mains Circuit Parameters |
| CN107590567A (en) * | 2017-09-13 | 2018-01-16 | 南京航空航天大学 | A kind of Recognition with Recurrent Neural Network short-term load forecasting method based on comentropy cluster and notice mechanism |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826795B (en) * | 2019-10-31 | 2023-06-09 | 国网辽宁省电力有限公司经济技术研究院 | Day-ahead load prediction method for extreme temperature weather day bus |
| CN111505406A (en) * | 2020-03-16 | 2020-08-07 | 剑科云智(深圳)科技有限公司 | Power distribution cabinet and wire monitoring method |
| CN116826745A (en) * | 2023-08-30 | 2023-09-29 | 山东海兴电力科技有限公司 | Layered and partitioned short-term load prediction method and system in power system background |
| CN116826745B (en) * | 2023-08-30 | 2024-02-09 | 山东海兴电力科技有限公司 | Layered and partitioned short-term load prediction method and system in power system background |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110210677B (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108022001A (en) | Short term probability density Forecasting Methodology based on PCA and quantile estimate forest | |
| CN112488395A (en) | Power distribution network line loss prediction method and system | |
| CN105678398A (en) | Power load forecasting method based on big data technology, and research and application system based on method | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| CN108959187A (en) | A kind of variable branch mailbox method, apparatus, terminal device and storage medium | |
| CN108388974A (en) | Top-tier customer Optimum Identification Method and device based on random forest and decision tree | |
| CN110232483A (en) | Deep learning load forecasting method, device and terminal device | |
| CN110689162B (en) | Bus load prediction method, device and system based on user side classification | |
| Li et al. | A two-tier wind power time series model considering day-to-day weather transition and intraday wind power fluctuations | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| Zhao et al. | Short-term microgrid load probability density forecasting method based on k-means-deep learning quantile regression | |
| CN110210677A (en) | A kind of bus Short-term Load Forecast method and apparatus of combination cluster and deep learning algorithm | |
| Lee et al. | Probabilistic wind power forecasting based on the laplace distribution and golden search | |
| CN112308335A (en) | Short-term electricity price prediction method and device based on xgboost algorithm | |
| CN110210661A (en) | A kind of Mid-long term load forecasting method and device for using energy characteristic based on user | |
| CN104820942A (en) | Electricity market trade evaluation criterion measuring and calculating method based on hierarchical clustering | |
| CN113902181A (en) | Short-term prediction method and equipment for common variable heavy overload | |
| CN110490220A (en) | A kind of bus load discrimination method and system | |
| CN114140009A (en) | Power grid distribution network engineering technology evaluation method and device, terminal and storage medium | |
| CN115829418B (en) | Method and system for constructing load characteristic portraits of power consumers suitable for load management | |
| Chen et al. | A power line loss analysis method based on boost clustering | |
| CN112365164A (en) | Medium-large energy user energy characteristic portrait method based on improved density peak value fast search clustering algorithm | |
| CN110458479A (en) | A kind of new energy field technological achievement is converted into the potential evaluation method of technical standard | |
| CN114970357A (en) | Energy-saving effect evaluation method, system, device and storage medium | |
| CN115081515A (en) | Energy efficiency evaluation model construction method and device, terminal and storage medium |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Jiao Min Inventor after: Wang Wenjun Inventor after: Chen Lin Inventor after: Chen Zewei Inventor after: Chen Aiyou Inventor after: Liang Longfei Inventor after: Qin Zijian Inventor after: Ding Jifeng Inventor after: Zhang Fangfen Inventor after: Li Xinlei Inventor after: Li Kang Inventor after: Liu Hengjie Inventor after: Mi Xiaoyan Inventor after: Hu Changlun Inventor after: Meng Fanmin Inventor after: Liu Xiaoyu Inventor after: Wang Tao Inventor after: Xu Xiaomin Inventor before: Li Kang Inventor before: Chen Lin Inventor before: Chen Zewei Inventor before: Chen Aiyou Inventor before: Liang Longfei Inventor before: Qin Zijian Inventor before: Ding Jifeng Inventor before: Zhang Fangfen Inventor before: Li Xinlei Inventor before: Liu Hengjie Inventor before: Mi Xiaoyan Inventor before: Hu Changlun Inventor before: Meng Fanmin Inventor before: Liu Xiaoyu Inventor before: Wang Tao Inventor before: Xu Xiaomin Inventor before: Wang Wenjun |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |