CN117277316A - Power load prediction method, system, medium and equipment - Google Patents
Power load prediction method, system, medium and equipment Download PDFInfo
- Publication number
- CN117277316A CN117277316A CN202311557589.0A CN202311557589A CN117277316A CN 117277316 A CN117277316 A CN 117277316A CN 202311557589 A CN202311557589 A CN 202311557589A CN 117277316 A CN117277316 A CN 117277316A
- Authority
- CN
- China
- Prior art keywords
- data
- load
- load prediction
- historical load
- historical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000003595 spectral effect Effects 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 14
- 230000008030 elimination Effects 0.000 claims description 11
- 238000003379 elimination reaction Methods 0.000 claims description 11
- 238000006467 substitution reaction Methods 0.000 claims description 11
- 230000001360 synchronised effect Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 230000001174 ascending effect Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000005611 electricity Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005624 perturbation theories Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Power Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
Abstract
The invention belongs to the field of power load prediction, and provides a power load prediction method, a system, a medium and equipment, which aim to solve the problems that the influence of various influencing factors on a load is not considered and the problem that clustering is inaccurate in the clustering analysis of the load, and comprise the following steps: clustering the preprocessed historical load data by an improved spectral clustering algorithm based on various associated influence factors; fusing according to time sequence based on clustered historical load data; and based on the fused historical load data, carrying out load prediction by utilizing a pre-trained power load prediction model to obtain a power load prediction result. Historical load data clustering is carried out based on various associated factors influencing power load prediction, and an improved spectral clustering algorithm enables a load clustering effect to be better, so that the accuracy of power load prediction is improved while the data quantity is simplified.
Description
Technical Field
The invention belongs to the technical field of power load prediction, and particularly relates to a power load prediction method, a power load prediction system, a power load prediction medium and power load prediction equipment.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Much research is done on power load prediction. According to the predicted time range, it is largely classified into ultra-short term, medium term and long term. The ultra-short-term load prediction refers to load prediction shorter than one day, and is mainly used for real-time power dispatching and daytime dispatching; the short-term load prediction refers to load prediction from one day to one week, and is used for daytime operation of the power system, such as energy transaction and power system safety research; mid-load forecast refers to a forecast of several weeks to one year for fuel supply scheduling and infrastructure adjustment; long-term load prediction is typically a prediction over a year for long-term power system planning.
At present, the existing deep learning-based method for predicting the power load performs analysis and prediction by using a single influence factor, and does not consider various factors influencing the power load comprehensively, so that the power load prediction precision is insufficient.
Disclosure of Invention
In order to solve the problems, the invention provides a power load prediction method, a system, a medium and equipment.
According to some embodiments, a first aspect of the present invention provides a power load prediction method, which adopts the following technical scheme:
a method of power load prediction, comprising:
acquiring historical load data and various associated influence factors at corresponding moments and preprocessing;
clustering the preprocessed historical load data by an improved spectral clustering algorithm based on various associated influence factors; the improved spectral clustering algorithm is improved based on a synchronous back-substitution elimination method of the kanto ovich distance;
fusing the clustered historical load data according to a time sequence to obtain fused historical load data;
based on the fused historical load data, carrying out load prediction by utilizing a pre-trained power load prediction model to obtain a power load prediction result;
the load prediction is performed by using a pre-trained power load prediction model to obtain a power load prediction result, which specifically comprises the following steps:
extracting data key features based on clustered historical load data;
load prediction is carried out according to the key characteristics of the data;
and obtaining a power load prediction result.
Further, the step of obtaining and preprocessing the historical load data and various associated influence factors at corresponding moments specifically includes:
acquiring historical load data and various associated influence factors at corresponding moments;
performing data complement on the historical load data;
normalizing the completed historical load data;
and obtaining the preprocessed historical load data.
Further, the historical load data includes load characteristic indicators within a set acquisition period.
Further, the associated influencing factors include environmental factors, social factors, and power policies.
Further, the preprocessed historical load data is clustered through an improved spectral clustering algorithm based on various associated influence factors, and the method specifically comprises the following steps:
classifying according to the related influence factors based on the preprocessed historical load data;
selecting a set of historical load data for each associated influencing factor;
constructing a similar matrix for each set of historical load data;
constructing a similarity matrix according to the similarity matrix;
calculating the eigenvalues of the similarity matrix, and arranging the eigenvalues in descending order;
calculating an intrinsic gap sequence of a similarity matrix and automatically determining cluster data;
calculating the eigenvalue of the normalized Laplace matrix, and arranging the eigenvalue according to ascending order;
selecting a feature vector corresponding to a first k minimum feature value of the normalized Laplace matrix to construct a feature vector space, wherein k is an integer and is larger than 0;
clustering data points in the feature vector space by using a synchronous back-substitution elimination method based on kanto ovich distance;
and mapping the obtained result back to the original sample set to obtain a clustering result of each group of history load.
Further, the training process of the power load prediction model specifically comprises the following steps:
acquiring historical load sample data and associated influence factors of corresponding moments;
calculating the correlation degree of the historical load sample data and the correlation influence factors of the corresponding moments;
influence factor data with the correlation degree larger than a threshold value is reserved and used as training factor data;
training a convolutional neural network model based on the correlation between the historical load sample data and the training factor data;
taking the classification loss of the historical load sample data and the classification loss of the training factor data as total loss, and repeating the training process until convergence conditions are reached;
and saving the network model with the minimum loss value as a final training result.
Further, the clustered historical load data is fused according to time sequence, so as to obtain fused historical load data, which is specifically as follows:
acquiring a time sequence mark in clustered historical load data;
the historical load data which are clustered and returned are ordered one by one based on the sequence of the time sequence marks;
and obtaining the fused historical load data.
According to some embodiments, a second aspect of the present invention provides an electrical load prediction system, which adopts the following technical scheme:
a power load prediction system, comprising:
the data acquisition module is configured to acquire historical load data and various associated influence factors at corresponding moments and perform preprocessing;
the data clustering module is configured to cluster the preprocessed historical load data through an improved spectral clustering algorithm based on various associated influence factors; the improved spectral clustering algorithm is improved based on a synchronous back-substitution elimination method of the kanto ovich distance;
the data fusion module is configured to fuse the clustered historical load data according to time sequence to obtain fused historical load data;
the power load prediction module is configured to perform load prediction by utilizing a pre-trained power load prediction model based on the fused historical load data to obtain a power load prediction result;
the load prediction is performed by using a pre-trained power load prediction model to obtain a power load prediction result, which specifically comprises the following steps:
extracting data key features based on clustered historical load data;
load prediction is carried out according to the key characteristics of the data;
and obtaining a power load prediction result.
According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a method of power load prediction as described in the first aspect above.
According to some embodiments, a fourth aspect of the invention provides a computer device.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in a power load prediction method as described in the first aspect above when the program is executed.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, historical load data clustering is carried out based on various associated factors influencing power load prediction, then fusion is carried out according to clustered data time sequence, and then power load prediction is carried out based on a deep learning model, so that the accuracy of power load prediction is improved while the data quantity is simplified, the problem that the accuracy of power load prediction is insufficient due to the fact that various factors influencing the power load are not considered comprehensively in the prior art is solved, and a synchronous back-substitution elimination method based on kantorovich distance is adopted to improve a spectral clustering algorithm, so that the load clustering effect is better, and the accuracy of subsequent load prediction is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a method of power load prediction in an embodiment of the invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
As shown in fig. 1, the present embodiment provides a power load prediction method, and the present embodiment is applied to a server for illustration by using the method, and it can be understood that the method may also be applied to a terminal, and may also be applied to a system and a terminal, and implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, security services CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, which is not limited herein. In this embodiment, the method includes the steps of:
acquiring historical load data and various associated influence factors at corresponding moments and preprocessing;
clustering the preprocessed historical load data by an improved spectral clustering algorithm based on various associated influence factors; the improved spectral clustering algorithm is improved based on a synchronous back-substitution elimination method of the kanto ovich distance;
fusing the clustered historical load data according to a time sequence to obtain fused historical load data;
based on the fused historical load data, carrying out load prediction by utilizing a pre-trained power load prediction model to obtain a power load prediction result;
the load prediction is performed by using a pre-trained power load prediction model to obtain a power load prediction result, which specifically comprises the following steps:
extracting data key features based on clustered historical load data;
load prediction is carried out according to the key characteristics of the data;
and obtaining a power load prediction result.
The method comprises the steps of obtaining historical load data and various associated influence factors at corresponding moments, and preprocessing, wherein the steps are as follows:
acquiring historical load data and various associated influence factors at corresponding moments;
performing data complement on the historical load data;
normalizing the completed historical load data;
and obtaining the preprocessed historical load data.
The historical load data includes load characteristic indicators within a set acquisition period. The load characteristic index is a characteristic index of the electric load. Including maximum load, minimum load, average load, load factor, peak-to-valley difference, and/or peak-to-valley difference rate. Taking a setting period of 1 day as an example, the load characteristic index includes a daily maximum load, a daily minimum load, a daily average load, a daily load rate, a daily peak-valley difference, and/or a daily peak-valley difference rate.
The maximum load is the maximum load value of the load data recorded in the set period, the minimum load is the minimum load value of the load data recorded in the set period, the average load is the average value of the electricity consumption in the set period, the load rate is the ratio of the average load to the maximum load (representing the balance of load distribution), the peak-valley difference is the difference between the maximum load and the minimum load, and the peak Gu Chalv is the ratio of the peak-valley difference to the maximum load.
It will be appreciated that the load characteristic indicators described above are examples only, and that different data may be selected depending on the particular predicted requirements.
The associated influencing factors include environmental factors, social factors, and power policies.
Specifically, the environmental factors obtain temperature data, humidity, precipitation, previous temperature data and the like at the moment corresponding to the load data; and social factors, describing electricity consumption behaviors by analyzing the characteristics of the electricity consumption shapes of users, and describing the shapes of electricity consumption curves from three dimensions of fluctuation points, mean values and variances.
Clustering the preprocessed historical load data based on various associated influence factors, wherein the clustering specifically comprises the following steps:
classifying according to the related influence factors based on the preprocessed historical load data;
selecting a set of historical load data for each associated influencing factor;
constructing a similar matrix for each set of historical load data;
constructing a similarity matrix according to the similarity matrix;
calculating the eigenvalues of the similarity matrix, and arranging the eigenvalues in descending order;
calculating an intrinsic gap sequence of a similarity matrix and automatically determining cluster data;
calculating the eigenvalue of the normalized Laplace matrix, and arranging the eigenvalue according to ascending order;
selecting a feature vector corresponding to the first k minimum feature value of the normalized Laplace matrix to construct a feature vector space;
clustering data points in the feature vector space by using a synchronous back-substitution elimination method based on kanto ovich distance;
and mapping the obtained result back to the original sample set to obtain a clustering result of each group of history load.
Specifically, the construction of the similarity matrix of the historical load data is specifically as follows:
wherein,representing historical load data->And->Similarity between->For historical load data->And (3) withEuropean distance between->To control parameters of the neighborhood size of the data points exp represents an exponential function based on e.
Constructing a similarity matrix from the similarity matrixThe method specifically comprises the following steps:
building a normalized Laplace matrix from a similarity matrixThe method specifically comprises the following steps:
wherein E is an identity matrix, and D is a group of similar matrices of historical loads.
According to the matrix perturbation theory, after matrix eigenvalues are arranged in descending order, the difference value between two adjacent eigenvalues is called an eigenvalue gap.
And calculating eigenvalues of the normalized Laplace matrix, arranging according to ascending order, and selecting eigenvectors corresponding to the first k minimum eigenvalues to construct an eigenvector space.
The synchronous back-substitution elimination method belongs to a heuristic scene reduction method, and through iterative calculation, the probability that one scene changes other scenes with the scene is reduced in each step, so that the probability of the residual scenes is always 1, and the number of the residual scenes reaches a set value.
Step (1): the scene reduction steps are:
step (2): traversing the distance between any two scenes in the feature vector space U, and setting the initial probability of all the scenes as；
Comprehensively considering the probability of each scene and the distance between any two scenes, and eliminating the scene with the shortest probability distance and worst representativeness from other scenes：
Wherein,for scene->Is->Distance between->For scene->Is->The probability weight of the probability is calculated,for scene->Is->Probability distance;
step (3): updating the total number of the remaining scenes, and screening out the scenes closest to the removed scene in step (2)，
Wherein,for scene->Is->Distance between->For scene->Is->A distance therebetween;
step (4): updating scene probability to be original probability and rejected sceneTo ensure that the sum of probabilities after scene subtraction is 1:
wherein,for scene->Is->Probability distance->Updated scene probability +_>Scene probability before update.
And (3) repeating the steps (2), (3) and (4) until the number of the residual scenes reaches the value of the clustering number k, wherein k is an integer and is larger than 0.
The training process of the power load prediction model specifically comprises the following steps:
acquiring historical load sample data and associated influence factors of corresponding moments;
calculating the correlation degree of the historical load sample data and the correlation influence factors of the corresponding moments;
influence factor data with the correlation degree larger than a threshold value is reserved and used as training factor data;
training a convolutional neural network model based on the correlation between the historical load sample data and the training factor data;
taking the classification loss of the historical load sample data and the classification loss of the training factor data as total loss, and repeating the training process until convergence conditions are reached;
and saving the network model with the minimum loss value as a final training result.
The clustered historical load data is fused according to time sequence to obtain fused historical load data, and the method specifically comprises the following steps:
acquiring a time sequence mark in clustered historical load data;
the historical load data which are clustered and returned are ordered one by one based on the sequence of the time sequence marks;
and obtaining the fused historical load data.
Example two
The present embodiment provides a power load prediction system including:
the data acquisition module is configured to acquire historical load data and various associated influence factors at corresponding moments and perform preprocessing;
the data clustering module is configured to cluster the preprocessed historical load data through an improved spectral clustering algorithm based on various associated influence factors; the improved spectral clustering algorithm is improved based on a synchronous back-substitution elimination method of the kanto ovich distance;
the data fusion module is configured to fuse the clustered historical load data according to time sequence to obtain fused historical load data;
the power load prediction module is configured to perform load prediction by utilizing a pre-trained power load prediction model based on the fused historical load data to obtain a power load prediction result;
the load prediction is performed by using a pre-trained power load prediction model to obtain a power load prediction result, which specifically comprises the following steps:
extracting data key features based on clustered historical load data;
load prediction is carried out according to the key characteristics of the data;
and obtaining a power load prediction result.
The above modules are the same as examples and application scenarios implemented by the corresponding steps, but are not limited to what is disclosed in the first embodiment. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
The foregoing embodiments are directed to various embodiments, and details of one embodiment may be found in the related description of another embodiment.
The proposed system may be implemented in other ways. For example, the system embodiments described above are merely illustrative, such as the division of the modules described above, are merely a logical function division, and may be implemented in other manners, such as multiple modules may be combined or integrated into another system, or some features may be omitted, or not performed.
Example III
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a power load prediction method as described in the above embodiment one.
Example IV
The present embodiment provides a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps in a power load prediction method according to the above embodiment when executing the program.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (10)
1. A method of predicting an electrical load, comprising:
acquiring historical load data and various associated influence factors at corresponding moments and preprocessing;
clustering the preprocessed historical load data by an improved spectral clustering algorithm based on various associated influence factors; the improved spectral clustering algorithm is improved based on a synchronous back-substitution elimination method of the kanto ovich distance;
fusing the clustered historical load data according to a time sequence to obtain fused historical load data;
based on the fused historical load data, carrying out load prediction by utilizing a pre-trained power load prediction model to obtain a power load prediction result;
the load prediction is performed by using a pre-trained power load prediction model to obtain a power load prediction result, which specifically comprises the following steps:
extracting data key features based on clustered historical load data;
load prediction is carried out according to the key characteristics of the data;
and obtaining a power load prediction result.
2. The method for predicting electric power load according to claim 1, wherein the steps of obtaining and preprocessing the historical load data and various associated influencing factors at corresponding moments are as follows:
acquiring historical load data and various associated influence factors at corresponding moments;
performing data complement on the historical load data;
normalizing the completed historical load data;
and obtaining the preprocessed historical load data.
3. A method of predicting electrical loads as recited in claim 1 in which said historical load data includes load characteristic indicators over a set acquisition period.
4. The method of claim 1, wherein the associated influencing factors include environmental factors, social factors, and power policies.
5. The power load prediction method according to claim 1, wherein the preprocessed historical load data is clustered by an improved spectral clustering algorithm based on various associated influence factors, specifically:
classifying according to the related influence factors based on the preprocessed historical load data;
selecting a set of historical load data for each associated influencing factor;
constructing a similar matrix for each set of historical load data;
constructing a similarity matrix according to the similarity matrix;
calculating the eigenvalues of the similarity matrix, and arranging the eigenvalues in descending order;
calculating an intrinsic gap sequence of a similarity matrix and automatically determining cluster data;
calculating the eigenvalue of the normalized Laplace matrix, and arranging the eigenvalue according to ascending order;
selecting a feature vector corresponding to a first k minimum feature value of the normalized Laplace matrix to construct a feature vector space, wherein k is an integer and is larger than 0;
clustering data points in the feature vector space by using a synchronous back-substitution elimination method based on kanto ovich distance;
and mapping the obtained result back to the original sample set to obtain a clustering result of each group of history load.
6. The power load prediction method according to claim 1, wherein the training process of the power load prediction model is specifically:
acquiring historical load sample data and associated influence factors of corresponding moments;
calculating the correlation degree of the historical load sample data and the correlation influence factors of the corresponding moments;
influence factor data with the correlation degree larger than a threshold value is reserved and used as training factor data;
training a convolutional neural network model based on the correlation between the historical load sample data and the training factor data;
taking the classification loss of the historical load sample data and the classification loss of the training factor data as total loss, and repeating the training process until convergence conditions are reached;
and saving the network model with the minimum loss value as a final training result.
7. The power load prediction method according to claim 1, wherein the clustered historical load data is fused according to time sequence to obtain fused historical load data, specifically:
acquiring a time sequence mark in clustered historical load data;
the historical load data which are clustered and returned are ordered one by one based on the sequence of the time sequence marks;
and obtaining the fused historical load data.
8. An electrical load prediction system, comprising:
the data acquisition module is configured to acquire historical load data and various associated influence factors at corresponding moments and perform preprocessing;
the data clustering module is configured to cluster the preprocessed historical load data through an improved spectral clustering algorithm based on various associated influence factors, wherein the improved spectral clustering algorithm is improved based on a synchronous back-substitution elimination method of a kanto ovich distance;
the data fusion module is configured to fuse the clustered historical load data according to time sequence to obtain fused historical load data;
the power load prediction module is configured to perform load prediction by utilizing a pre-trained power load prediction model based on the fused historical load data to obtain a power load prediction result;
the load prediction is performed by using a pre-trained power load prediction model to obtain a power load prediction result, which specifically comprises the following steps:
extracting data key features based on clustered historical load data;
load prediction is carried out according to the key characteristics of the data;
and obtaining a power load prediction result.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of a power load prediction method as claimed in any one of claims 1-7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of a power load prediction method as claimed in any one of claims 1 to 7 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311557589.0A CN117277316B (en) | 2023-11-22 | 2023-11-22 | Power load prediction method, system, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311557589.0A CN117277316B (en) | 2023-11-22 | 2023-11-22 | Power load prediction method, system, medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117277316A true CN117277316A (en) | 2023-12-22 |
| CN117277316B CN117277316B (en) | 2024-04-09 |
Family
ID=89216411
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311557589.0A Active CN117277316B (en) | 2023-11-22 | 2023-11-22 | Power load prediction method, system, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117277316B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117833243A (en) * | 2024-03-06 | 2024-04-05 | 国网山东省电力公司信息通信公司 | Method, system, equipment and medium for predicting short-term demand of electric power |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400009A (en) * | 2013-08-07 | 2013-11-20 | 华北电力大学 | Wind electric field dynamic equivalence method based on split level semi-supervised spectral clustering algorithm |
| CN106447091A (en) * | 2016-09-09 | 2017-02-22 | 国网安徽省电力公司电力科学研究院 | Regional meteorological condition similarity-based large power network load prediction method |
| US20190081476A1 (en) * | 2017-09-12 | 2019-03-14 | Sas Institute Inc. | Electric power grid supply and load prediction |
| US20210209467A1 (en) * | 2018-09-25 | 2021-07-08 | Ennew Digital Technology Co., Ltd. | Method and device for predicting thermal load of electrical system |
| CN113128574A (en) * | 2021-03-31 | 2021-07-16 | 国网河北省电力有限公司电力科学研究院 | Scene reduction method and device and terminal equipment |
| CN113379564A (en) * | 2021-04-08 | 2021-09-10 | 国网河北省电力有限公司营销服务中心 | Power grid load prediction method and device and terminal equipment |
| CN115526420A (en) * | 2022-10-19 | 2022-12-27 | 宁波市电力设计院有限公司 | Power load prediction method and system based on relevance of external influence factors |
| CN116186548A (en) * | 2023-05-04 | 2023-05-30 | 广州三晶电气股份有限公司 | Power load prediction model training method and power load prediction method |
| CN116979505A (en) * | 2023-06-25 | 2023-10-31 | 国网山东省电力公司曲阜市供电公司 | Power grid short-term load prediction method and system |
-
2023
- 2023-11-22 CN CN202311557589.0A patent/CN117277316B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400009A (en) * | 2013-08-07 | 2013-11-20 | 华北电力大学 | Wind electric field dynamic equivalence method based on split level semi-supervised spectral clustering algorithm |
| CN106447091A (en) * | 2016-09-09 | 2017-02-22 | 国网安徽省电力公司电力科学研究院 | Regional meteorological condition similarity-based large power network load prediction method |
| US20190081476A1 (en) * | 2017-09-12 | 2019-03-14 | Sas Institute Inc. | Electric power grid supply and load prediction |
| US20210209467A1 (en) * | 2018-09-25 | 2021-07-08 | Ennew Digital Technology Co., Ltd. | Method and device for predicting thermal load of electrical system |
| CN113128574A (en) * | 2021-03-31 | 2021-07-16 | 国网河北省电力有限公司电力科学研究院 | Scene reduction method and device and terminal equipment |
| CN113379564A (en) * | 2021-04-08 | 2021-09-10 | 国网河北省电力有限公司营销服务中心 | Power grid load prediction method and device and terminal equipment |
| CN115526420A (en) * | 2022-10-19 | 2022-12-27 | 宁波市电力设计院有限公司 | Power load prediction method and system based on relevance of external influence factors |
| CN116186548A (en) * | 2023-05-04 | 2023-05-30 | 广州三晶电气股份有限公司 | Power load prediction model training method and power load prediction method |
| CN116979505A (en) * | 2023-06-25 | 2023-10-31 | 国网山东省电力公司曲阜市供电公司 | Power grid short-term load prediction method and system |
Non-Patent Citations (1)
| Title |
|---|
| C. DINESH, S. MAKONIN AND I. V. BAJIĆ: "Residential Power Forecasting Based on Affinity Aggregation Spectral Clustering", IEEE ACCESS, 27 May 2020 (2020-05-27), pages 99431 - 99444 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117833243A (en) * | 2024-03-06 | 2024-04-05 | 国网山东省电力公司信息通信公司 | Method, system, equipment and medium for predicting short-term demand of electric power |
| CN117833243B (en) * | 2024-03-06 | 2024-05-24 | 国网山东省电力公司信息通信公司 | Method, system, equipment and medium for predicting short-term demand of electric power |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117277316B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Deng et al. | Multi-scale convolutional neural network with time-cognition for multi-step short-term load forecasting | |
| CN117277316B (en) | Power load prediction method, system, medium and equipment | |
| CN108734355B (en) | Short-term power load parallel prediction method and system applied to power quality comprehensive management scene | |
| CN108694673A (en) | A kind of processing method, device and the processing equipment of insurance business risk profile | |
| CN105184402B (en) | A kind of personalized user short-term load forecasting algorithm based on decision tree | |
| CN108921358B (en) | Prediction method, prediction system and related device of power load characteristics | |
| CN116186548B (en) | Power load prediction model training method and power load prediction method | |
| CN116890689B (en) | Charging control method, device, equipment and storage medium based on vehicle identification | |
| CN109636010A (en) | Provincial power network short-term load forecasting method and system based on correlative factor matrix | |
| CN109325631A (en) | Electric car charging load forecasting method and system based on data mining | |
| CN113706151A (en) | Data processing method and device, computer equipment and storage medium | |
| CN113862691B (en) | Control method and device for photovoltaic hydrogen production, storage medium and electronic equipment | |
| CN114358449A (en) | Electric vehicle charging load space-time distribution prediction method based on graph neural network | |
| CN109583503A (en) | A kind of interruptible load prediction technique | |
| CN111932302B (en) | Method, device, equipment and system for determining number of service sites in area | |
| CN116109007B (en) | Power generation power determination method, server and storage medium | |
| CN113095680A (en) | Evaluation index system and construction method of electric power big data model | |
| Rouwhorst et al. | Improving Clustering-Based Forecasting of Aggregated Distribution Transformer Loadings With Gradient Boosting and Feature Selection | |
| Cai et al. | Short-term load forecasting for city holidays based on genetic support vector machines | |
| CN106845763B (en) | Power grid reliability analysis method and device | |
| Mao et al. | Naive Bayesian algorithm classification model with local attribute weighted based on KNN | |
| CN111144652B (en) | Tour comfort algorithm and trend prediction based method, system and device | |
| CN109598508B (en) | Identification method and device, computing equipment and storage medium | |
| CN111783827A (en) | Enterprise user classification method and device based on load data | |
| Koban et al. | A remark on forecasting spikes in electricity prices |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |