CN110490220A - A kind of bus load discrimination method and system - Google Patents
A kind of bus load discrimination method and system Download PDFInfo
- Publication number
- CN110490220A CN110490220A CN201910591109.XA CN201910591109A CN110490220A CN 110490220 A CN110490220 A CN 110490220A CN 201910591109 A CN201910591109 A CN 201910591109A CN 110490220 A CN110490220 A CN 110490220A
- Authority
- CN
- China
- Prior art keywords
- bus
- load
- data
- neural network
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012850 discrimination method Methods 0.000 title claims abstract description 9
- 238000013528 artificial neural network Methods 0.000 claims abstract description 74
- 238000000034 method Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 14
- 230000005611 electricity Effects 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 7
- 239000002245 particle Substances 0.000 claims description 7
- 240000002853 Nelumbo nucifera Species 0.000 claims description 4
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims description 4
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 210000004218 nerve net Anatomy 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of bus load discrimination method and systems, comprising: acquires the load Identification Data of bus to be identified；The corresponding load power time series data of all kinds of power loads on the bus to be identified is determined according to the load Identification Data of the bus to be identified；Technical solution provided by the invention is realized the identification of the load type to load extensive, diversified on bus by the learning ability of LSTM neural network, improves the precision of identification.
Description
Technical field
The present invention relates to Automation of Electric Systems analysis technical fields, and in particular to a kind of bus load discrimination method and is
System.
Background technique
Some large size supply nodes (Bulk Supply Points, BSPs) in power grid, such as provincial power network 220kV substation
Transformer duty value node, area power grid 10kV feed connection node etc., usually couple the totally different load of a large amount of variety classes, characteristic
Resource, how to be effectively predicted these bus nodes load powers variation and how to efficiently use join on these nodes flexibility bear
The polymerization property of lotus response is the emphasis that dispatching of power netwoks personnel is concerned about.Determine the classification sum number of the coupled load of large size supply node
Amount is to carry out basis and the key of the studies above.However, being limited to measurement cost, inaccurate network mould in actual electric network
The problems such as type and the system right of attribution, the composition of BSP load is often difficult to directly acquire by measurement equipment.Existing load identification
It is had the following problems with extracting method: first is that existing burdened resource identification technique spininess is to small-scale domestic consumer, research side
Method is difficult to use in the identification problem of extensive, diversified load side resource；Second is that existing load identification algorithm is to load classification, list
The factors such as body scale, load model, external environment are all more sensitive, and identification precision is limited.
Therefore, it is necessary to a kind of methods that can be accurately recognized to load extensive, diversified on bus.
Summary of the invention
In view of the deficiencies of the prior art, the object of the present invention is to provide a kind of bus load discrimination method and systems, utilize
The ability that LSTM neural network is good at handling non-linear, reciprocal effect complex data accurately recognizes extensive, multiplicity on bus
Change the load type of load.
The purpose of the present invention is adopt the following technical solutions realization:
A kind of bus load discrimination method, it is improved in that the described method includes:
Acquire the load Identification Data of bus to be identified；
Determine that all kinds of power loads are corresponding on the bus to be identified according to the load Identification Data of the bus to be identified
Load power time series data；
Wherein, the load Identification Data includes: power time series data, time data and meteorological data.
Preferably, the type of the power load includes: industrial load, agriculture load, municipal household electricity load and friendship
Logical transport power load.
Preferably, the load Identification Data according to the bus to be identified determines all kinds of use on the bus to be identified
The corresponding load power time series data of electric load, comprising:
The load Identification Data of the bus to be identified is substituted into the LSTM neural network pre-established, is obtained described wait distinguish
Know the corresponding load power time series data of all kinds of power loads on bus.
Further, the training process of the LSTM neural network pre-established includes:
Acquire the corresponding load power time series data of all kinds of power loads on bus historical juncture corresponding bus and its right
The time data and meteorological data answered；
Successively by the corresponding load power time series data of power loads all kinds of on the bus historical juncture corresponding bus
And its corresponding time data and meteorological data are pre-processed using maximum value method for normalizing, using based on particle group optimizing
Fuzzy clustering algorithm, it is quasi- to carry out clustering and data using Dai Weisenbaoding index index as the evaluation index of Cluster Validity
It closes, obtains the load Identification Data of virtual bus；
Using a part of load Identification Data in the load Identification Data of virtual bus as initial LSTM neural network
Input layer training sample makees the corresponding load power time series data of power loads all kinds of on bus historical juncture corresponding bus
For the output layer training sample of initial LSTM neural network, the initial LSTM neural network is trained, is pre-established described in acquisition
LSTM neural network.
Further, the verification process of the LSTM neural network pre-established includes:
Another part load Identification Data in the load Identification Data of virtual bus is substituted into the LSTM mind pre-established
Through network, the output data of the LSTM neural network pre-established described in acquisition；
Compare the corresponding load power of all kinds of power loads on output data bus corresponding with the bus historical juncture
Time series data, if on output data bus corresponding with the bus historical juncture when the corresponding load power of all kinds of power loads
The relative error of ordinal number evidence is less than preset threshold, then the LSTM neural network pre-established is qualified, otherwise, described to build in advance
Vertical LSTM neural network is unqualified.
A kind of bus load identification system, it is improved in that the system comprises:
Acquisition module, for acquiring the load Identification Data of bus to be identified；
Determining module, it is all kinds of on the bus to be identified for being determined according to the load Identification Data of the bus to be identified
The corresponding load power time series data of power load；
Wherein, the load Identification Data includes: power time series data, time data and meteorological data.
Preferably, the type of the power load includes: industrial load, agriculture load, municipal household electricity load and friendship
Logical transport power load.
Preferably, the determining module is used for:
The load Identification Data of the bus to be identified is substituted into the LSTM neural network pre-established, is obtained described wait distinguish
Know the corresponding load power time series data of all kinds of power loads on bus.
Further, the training process of the LSTM neural network pre-established includes:
Acquire the corresponding load power time series data of all kinds of power loads on bus historical juncture corresponding bus and its right
The time data and meteorological data answered；
Successively by the corresponding load power time series data of power loads all kinds of on the bus historical juncture corresponding bus
And its corresponding time data and meteorological data are pre-processed using maximum value method for normalizing, using based on particle group optimizing
Fuzzy clustering algorithm, it is quasi- to carry out clustering and data using Dai Weisenbaoding index index as the evaluation index of Cluster Validity
It closes, obtains the load Identification Data of virtual bus；
Using a part of load Identification Data in the load Identification Data of virtual bus as initial LSTM neural network
Input layer training sample makees the corresponding load power time series data of power loads all kinds of on bus historical juncture corresponding bus
For the output layer training sample of initial LSTM neural network, the initial LSTM neural network is trained, is pre-established described in acquisition
LSTM neural network.
Further, the verification process of the LSTM neural network pre-established includes:
Another part load Identification Data in the load Identification Data of virtual bus is substituted into the LSTM mind pre-established
Through network, the output data of the LSTM neural network pre-established described in acquisition；
Compare the corresponding load power of all kinds of power loads on output data bus corresponding with the bus historical juncture
Time series data, if on output data bus corresponding with the bus historical juncture when the corresponding load power of all kinds of power loads
The relative error of ordinal number evidence is less than preset threshold, then the LSTM neural network pre-established is qualified, otherwise, described to build in advance
Vertical LSTM neural network is unqualified.
Compared with the immediate prior art, the invention has the benefit that
The load Identification Data that technical solution provided by the invention passes through acquisition bus to be identified；According to the mother to be identified
The load Identification Data of line determines the corresponding load sequence of all kinds of power loads on the bus to be identified, passes through LSTM nerve net
The learning ability of network realizes the accurate identification of the load type of extensive, diversified load.
Detailed description of the invention
Fig. 1 is a kind of flow chart of bus load discrimination method provided by the invention；
Fig. 2 is the multilayer LSTM neural network structure figure for bus load identification that example in real time of the invention provides；
Fig. 3 is a kind of structure chart of bus load identification system provided by the invention.
Specific embodiment
Specific embodiments of the present invention will be described in further detail with reference to the accompanying drawing.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The present invention provides a kind of bus load discrimination methods, are good at handling using big data analysis and artificial intelligence non-thread
Property, reciprocal effect complex data advantage, carry out clusterings first against all kinds of load datas of power grid to be analyzed, thus
To the electrical feature of using of the main typical load in the region, building classification typical load electricity consumption feature database；On this basis, analysis is external
The multi-source informations such as meteorology, season, date, time form the multiple information sources that effectively identification bus load is constituted；Finally, being based on
The load type that LSTM neural network is included to specific large-scale supply node recognizes, as shown in Figure 1, the method packet
It includes:
Step 101, the load Identification Data of bus to be identified is acquired；
Step 102, all kinds of electricity consumptions on the bus to be identified are determined according to the load Identification Data of the bus to be identified
The corresponding load power time series data of load；
Wherein, the load Identification Data includes: power time series data, time data and meteorological data.
The type of the power load includes: that industrial load, agriculture load, municipal household electricity load and communications and transportation are used
Electric load.
The step 102, as shown in Figure 2, comprising:
The load Identification Data of the bus to be identified is substituted into the LSTM neural network pre-established, is obtained described wait distinguish
Know the corresponding load power time series data of all kinds of power loads on bus.
The training process of the LSTM neural network pre-established includes:
Acquire the corresponding load power time series data of all kinds of power loads on bus historical juncture corresponding bus and its right
The time data and meteorological data answered；
Successively by the corresponding load power time series data of power loads all kinds of on the bus historical juncture corresponding bus
And its corresponding time data and meteorological data are pre-processed using maximum value method for normalizing, using based on particle group optimizing
Fuzzy clustering algorithm, it is quasi- to carry out clustering and data using Dai Weisenbaoding index index as the evaluation index of Cluster Validity
It closes, obtains the load Identification Data of virtual bus；
Using a part of load Identification Data in the load Identification Data of virtual bus as initial LSTM neural network
Input layer training sample makees the corresponding load power time series data of power loads all kinds of on bus historical juncture corresponding bus
For the output layer training sample of initial LSTM neural network, the initial LSTM neural network is trained, is pre-established described in acquisition
LSTM neural network.
The verification process of the LSTM neural network pre-established includes:
Another part load Identification Data in the load Identification Data of virtual bus is substituted into the LSTM mind pre-established
Through network, the output data of the LSTM neural network pre-established described in acquisition；
Compare the corresponding load power of all kinds of power loads on output data bus corresponding with the bus historical juncture
Time series data, if on output data bus corresponding with the bus historical juncture when the corresponding load power of all kinds of power loads
The relative error of ordinal number evidence is less than preset threshold, then the LSTM neural network pre-established is qualified, otherwise, described to build in advance
Vertical LSTM neural network is unqualified.
Based on above scheme, optimum embodiment provided by the invention be may include steps of:
Step 1, the function that all kinds of power loads on standard year bus are collected from extraction system or user's Energy Management System
Rate time series data；According to the power time series data of all kinds of power loads carry out clustering, using all kinds of load characteristics clustering centers as
All kinds of typical load indicatrixes.
Step 2, from meteorological data net (or each power grid meteorogical phenomena database) collection step 1 load Characteristic Curve data pair
The standard year outside weather information answered, and binding time and each type load electricity consumption indicatrix with association in time are formed and are used
In the multiple information sources data of region bus load identification；
Step 3, based on multiple information sources data, formed bus load constitute analysis training sample set and verifying sample
This collection is respectively trained and verifies the network parameter of LSTM neural network, specifically include data preparation link, data processing link,
Network training link and network verification link.
Step 4, using the load power time series data of bus to be identified and associated time, outside weather information as defeated
Enter data, the load type for being included to it based on LSTM neural network recognizes；The output of LSTM neural network is should
The corresponding load variations sequence of all kinds of power loads of bus.
Wherein, specific step is as follows for step 1:
Step S1-1: the standard year of corresponding climatic province bus load is collected from extraction system or user's Energy Management System
Electric power time series data, using bus load standard year electric power time series data as the input quantity of clustering.
Step S1-2: data are pre-processed using maximum value method for normalizing.
Step S1-3: the fuzzy clustering algorithm based on particle group optimizing is used, with Dai Weisenbaoding index (Davies-
Bouldin, DBI) evaluation index of the index as Cluster Validity, clustering is carried out to each type load, obtains having obvious
The load characteristics clustering center of difference.
Step S1-4: all kinds of typical load indicatrixes are formed using load characteristics clustering center as typical load.
Wherein, specific step is as follows for step 3:
Step S3-1: data preparation link: based on the multiple information sources data of standard year bus load identification, will have
There are all kinds of typical load Characteristic Curve datas of same time respectively multiplied by different coefficients, (is not less than 1 so that analog synthesis is a large amount of
Ten thousand) different load constitute virtual bus load Identification Data.It will be any 80% in the load Identification Data of virtual bus
Training sample data of the data as initial LSTM neural network, remaining 20% data is as the LSTM nerve pre-established
The verifying sample data of network.
Step S3-2: data processing link: sample data is filtered, difference processing and normalized, is instructed
Practice sample set (Xk,Yk) and verifying sample set (Xj,Yj)。
Wherein, XkFor the training sample input data of initial LSTM neural network, the load function at kth moment on bus is indicated
Rate time series data and its corresponding outside weather data, k=1,2 ..., n；For initial LSTM nerve net
The training sample output data of network indicates the load power time series data of each type load on k moment bus；XjIt pre-establishes
The test sample input data of LSTM neural network, the load power time series data of expression j moment bus and its corresponding outside
Meteorological data, j=1,2 ..., n；Test sample data for the LSTM neural network pre-established, table
Show the load power time series data of each type load on j moment bus.
Step S3-3: network training link: training sample set (X is utilizedk,Yk) initial LSTM neural network is trained,
The LSTM neural network pre-established.
Step S3-4: network verification link: by XjThe LSTM neural network pre-established is inputted, output data is obtained, and
Utilize output data and verifying sample set (Xj,Yj) in YjCompare with analytical error.
The present invention also provides a kind of bus load identification systems, as shown in figure 3, the system comprises:
Acquisition module, for acquiring the load Identification Data of bus to be identified；
Determining module, it is all kinds of on the bus to be identified for being determined according to the load Identification Data of the bus to be identified
The corresponding load power time series data of power load；
Wherein, the load Identification Data includes: power time series data, time data and meteorological data.
The type of the power load includes: that industrial load, agriculture load, municipal household electricity load and communications and transportation are used
Electric load.
The determining module is used for:
The load Identification Data of the bus to be identified is substituted into the LSTM neural network pre-established, is obtained described wait distinguish
Know the corresponding load power time series data of all kinds of power loads on bus.
The training process of the LSTM neural network pre-established includes:
Acquire the corresponding load power time series data of all kinds of power loads on bus historical juncture corresponding bus and its right
The time data and meteorological data answered；
Successively by the corresponding load power time series data of power loads all kinds of on the bus historical juncture corresponding bus
And its corresponding time data and meteorological data are pre-processed using maximum value method for normalizing, using based on particle group optimizing
Fuzzy clustering algorithm, it is quasi- to carry out clustering and data using Dai Weisenbaoding index index as the evaluation index of Cluster Validity
It closes, obtains the load Identification Data of virtual bus；
Using a part of load Identification Data in the load Identification Data of virtual bus as initial LSTM neural network
Input layer training sample makees the corresponding load power time series data of power loads all kinds of on bus historical juncture corresponding bus
For the output layer training sample of initial LSTM neural network, the initial LSTM neural network is trained, is pre-established described in acquisition
LSTM neural network.
The verification process of the LSTM neural network pre-established includes:
Another part load Identification Data in the load Identification Data of virtual bus is substituted into the LSTM mind pre-established
Through network, the output data of the LSTM neural network pre-established described in acquisition；
Compare the corresponding load power of all kinds of power loads on output data bus corresponding with the bus historical juncture
Time series data, if on output data bus corresponding with the bus historical juncture when the corresponding load power of all kinds of power loads
The relative error of ordinal number evidence is less than preset threshold, then the LSTM neural network pre-established is qualified, otherwise, described to build in advance
Vertical LSTM neural network is unqualified.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, to the greatest extent
Invention is explained in detail referring to above-described embodiment for pipe, it should be understood by those ordinary skilled in the art that: still
It can be with modifications or equivalent substitutions are made to specific embodiments of the invention, and without departing from any of spirit and scope of the invention
Modification or equivalent replacement, should all cover within the scope of the claims of the present invention.
Claims (10)
1. a kind of bus load discrimination method, which is characterized in that the described method includes:
Acquire the load Identification Data of bus to be identified；
Determine that all kinds of power loads are corresponding negative on the bus to be identified according to the load Identification Data of the bus to be identified
Lotus power time series data；
Wherein, the load Identification Data includes: power time series data, time data and meteorological data.
2. the method as described in claim 1, which is characterized in that the type of the power load includes: that industrial load, agricultural are negative
Lotus, municipal household electricity load and communications and transportation power load.
3. the method as described in claim 1, which is characterized in that the load Identification Data according to the bus to be identified is true
The corresponding load power time series data of all kinds of power loads on the fixed bus to be identified, comprising:
The load Identification Data of the bus to be identified is substituted into the LSTM neural network pre-established, obtains the mother to be identified
The corresponding load power time series data of all kinds of power loads on line.
4. method as claimed in claim 3, which is characterized in that the training process packet of the LSTM neural network pre-established
It includes:
Acquire the corresponding load power time series data of all kinds of power loads on bus historical juncture corresponding bus and its corresponding
Time data and meteorological data；
Successively by the corresponding load power time series data of power loads all kinds of on the bus historical juncture corresponding bus and its
Corresponding time data and meteorological data are pre-processed, using maximum value method for normalizing using the mould based on particle group optimizing
Clustering algorithm is pasted, clustering is carried out as the evaluation index of Cluster Validity using Dai Weisenbaoding index index and data are fitted,
Obtain the load Identification Data of virtual bus；
Using a part of load Identification Data in the load Identification Data of virtual bus as the input of initial LSTM neural network
Layer training sample, using the corresponding load power time series data of power loads all kinds of on bus historical juncture corresponding bus as just
The output layer training sample of beginning LSTM neural network is trained the initial LSTM neural network, is pre-established described in acquisition
LSTM neural network.
5. method as claimed in claim 4, which is characterized in that the verification process packet of the LSTM neural network pre-established
It includes:
Another part load Identification Data in the load Identification Data of virtual bus is substituted into the LSTM nerve net pre-established
Network, the output data of the LSTM neural network pre-established described in acquisition；
Compare the corresponding load power timing of all kinds of power loads on output data bus corresponding with the bus historical juncture
Data, if ordinal number when all kinds of power loads corresponding load power on output data bus corresponding with the bus historical juncture
According to relative error be less than preset threshold, then the LSTM neural network pre-established is qualified, otherwise, described to pre-establish
LSTM neural network is unqualified.
6. a kind of bus load identification system, which is characterized in that the system comprises:
Acquisition module, for acquiring the load Identification Data of bus to be identified；
Determining module, for determining all kinds of electricity consumptions on the bus to be identified according to the load Identification Data of the bus to be identified
The corresponding load power time series data of load；
Wherein, the load Identification Data includes: power time series data, time data and meteorological data.
7. system as claimed in claim 6, which is characterized in that the type of the power load includes: that industrial load, agricultural are negative
Lotus, municipal household electricity load and communications and transportation power load.
8. system as claimed in claim 6, which is characterized in that the determining module is used for:
The load Identification Data of the bus to be identified is substituted into the LSTM neural network pre-established, obtains the mother to be identified
The corresponding load power time series data of all kinds of power loads on line.
9. system as claimed in claim 8, which is characterized in that the training process packet of the LSTM neural network pre-established
It includes:
Acquire the corresponding load power time series data of all kinds of power loads on bus historical juncture corresponding bus and its corresponding
Time data and meteorological data；
Successively by the corresponding load power time series data of power loads all kinds of on the bus historical juncture corresponding bus and its
Corresponding time data and meteorological data are pre-processed, using maximum value method for normalizing using the mould based on particle group optimizing
Clustering algorithm is pasted, clustering is carried out as the evaluation index of Cluster Validity using Dai Weisenbaoding index index and data are fitted,
Obtain the load Identification Data of virtual bus；
Using a part of load Identification Data in the load Identification Data of virtual bus as the input of initial LSTM neural network
Layer training sample, using the corresponding load power time series data of power loads all kinds of on bus historical juncture corresponding bus as just
The output layer training sample of beginning LSTM neural network is trained the initial LSTM neural network, is pre-established described in acquisition
LSTM neural network.
10. system as claimed in claim 9, which is characterized in that the verification process of the LSTM neural network pre-established
Include:
Another part load Identification Data in the load Identification Data of virtual bus is substituted into the LSTM nerve net pre-established
Network, the output data of the LSTM neural network pre-established described in acquisition；
Compare the corresponding load power timing of all kinds of power loads on output data bus corresponding with the bus historical juncture
Data, if ordinal number when all kinds of power loads corresponding load power on output data bus corresponding with the bus historical juncture
According to relative error be less than preset threshold, then the LSTM neural network pre-established is qualified, otherwise, described to pre-establish
LSTM neural network is unqualified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910591109.XA CN110490220A (en) | 2019-07-02 | 2019-07-02 | A kind of bus load discrimination method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910591109.XA CN110490220A (en) | 2019-07-02 | 2019-07-02 | A kind of bus load discrimination method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110490220A true CN110490220A (en) | 2019-11-22 |
Family
ID=68546605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910591109.XA Pending CN110490220A (en) | 2019-07-02 | 2019-07-02 | A kind of bus load discrimination method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110490220A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680744A (en) * | 2020-06-05 | 2020-09-18 | 中国电力科学研究院有限公司 | Bus load composition identification method and machine readable storage medium |
| CN112085111A (en) * | 2020-09-14 | 2020-12-15 | 南方电网科学研究院有限责任公司 | Load identification method and device |
| CN114115150A (en) * | 2021-11-24 | 2022-03-01 | 山东建筑大学 | Data-based heat pump system online modeling method and device |
-
2019
- 2019-07-02 CN CN201910591109.XA patent/CN110490220A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680744A (en) * | 2020-06-05 | 2020-09-18 | 中国电力科学研究院有限公司 | Bus load composition identification method and machine readable storage medium |
| WO2021243930A1 (en) * | 2020-06-05 | 2021-12-09 | 中国电力科学研究院有限公司 | Method for identifying composition of bus load, and machine-readable storage medium |
| CN112085111A (en) * | 2020-09-14 | 2020-12-15 | 南方电网科学研究院有限责任公司 | Load identification method and device |
| CN114115150A (en) * | 2021-11-24 | 2022-03-01 | 山东建筑大学 | Data-based heat pump system online modeling method and device |
| CN114115150B (en) * | 2021-11-24 | 2023-06-06 | 山东建筑大学 | Online modeling method and device for heat pump system based on data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110231528B (en) | Transformer household variation common knowledge identification method and device based on load characteristic model library | |
| US10223167B2 (en) | Discrete resource management | |
| CN104794206B (en) | A kind of substation data QA system and method | |
| CN111639815A (en) | Method and system for predicting power grid defect materials through multi-model fusion | |
| CN104008432A (en) | Micro-grid short-term load forecasting method based on EMD-KELM-EKF | |
| CN110490220A (en) | A kind of bus load discrimination method and system | |
| CN113177366B (en) | Comprehensive energy system planning method and device and terminal equipment | |
| CN110782153A (en) | Modeling method and system for comprehensive energy efficiency assessment system of enterprise park | |
| CN104376371B (en) | A kind of distribution based on topology is layered load forecasting method | |
| CN105469219A (en) | Method for processing power load data based on decision tree | |
| CN112307003A (en) | Power grid data multidimensional auxiliary analysis method, system, terminal and readable storage medium | |
| Dong et al. | Forecasting smart meter energy usage using distributed systems and machine learning | |
| CN109860736A (en) | The big data system and method utilized for battery echelon | |
| CN116148753A (en) | Intelligent electric energy meter operation error monitoring system | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN104915727B (en) | Various dimensions allomer BP neural network optical power ultra-short term prediction method | |
| CN110298567A (en) | The method for determining typical day load curve using integrated energy system energy consumption big data | |
| CN109066819A (en) | A kind of idle work optimization method of the power distribution network based on case reasoning | |
| CN108122173A (en) | A kind of conglomerate load forecasting method based on depth belief network | |
| CN106849064A (en) | A kind of regional power grid load prediction management system based on meteorological data | |
| Zhang et al. | The power big data-based energy analysis for intelligent community in smart grid | |
| CN110165657A (en) | Consider substation's load characteristics clustering analysis method of user's industry attribute | |
| CN108053074A (en) | A kind of computational methods and system of power consumption contributive rate | |
| Zhang et al. | Analysis of influencing factors of transmission line loss based on GBDT algorithm | |
| CN104240144B (en) | A kind of power load aggregation method based on demand response |
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 |