CN116979505A - Power grid short-term load prediction method and system - Google Patents

Power grid short-term load prediction method and system Download PDF

Info

Publication number
CN116979505A
CN116979505A CN202310749489.1A CN202310749489A CN116979505A CN 116979505 A CN116979505 A CN 116979505A CN 202310749489 A CN202310749489 A CN 202310749489A CN 116979505 A CN116979505 A CN 116979505A
Authority
CN
China
Prior art keywords
load
short
environmental information
load prediction
environmental
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310749489.1A
Other languages
Chinese (zh)
Inventor
朱伟
赵丹
郭强
高超
颜子龙
张亚南
袁志艺
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qufu Power Supply Co Of State Grid Shandong Electric Power Co
Jining Power Supply Co
Original Assignee
Qufu Power Supply Co Of State Grid Shandong Electric Power Co
Jining Power Supply Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qufu Power Supply Co Of State Grid Shandong Electric Power Co, Jining Power Supply Co filed Critical Qufu Power Supply Co Of State Grid Shandong Electric Power Co
Priority to CN202310749489.1A priority Critical patent/CN116979505A/en
Publication of CN116979505A publication Critical patent/CN116979505A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • G06N3/048—Activation functions
    • 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
    • G06N3/0499—Feedforward networks
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • 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
    • 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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Human Resources & Organizations (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • Probability & Statistics with Applications (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Power Engineering (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a power grid short-term load prediction method and system, and belongs to the technical field of short-term load prediction. Acquiring historical load data and corresponding environmental information according to a preset time granularity, and calculating correlation coefficients between environmental factors and loads in the environmental information; determining key features affecting the load according to the correlation coefficient; clustering key features based on the historical load data and corresponding environmental information to generate similar data samples; based on the environment accumulation effect, correcting the environment information in the similar data samples to obtain characteristic samples; and inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result. The influence of different environmental factors on the short-term load prediction can be fully considered, the accuracy of the short-term load prediction is improved, and the operation amount is reduced; the problem that the accuracy of short-term load prediction is influenced by excessive load-related influencing factors in the prior art is solved.

Description

Power grid short-term load prediction method and system
Technical Field
The invention relates to the technical field of short-term load prediction, in particular to a power grid short-term load prediction method and system.
Background
The statements in this section merely relate to the background of the present disclosure and may not necessarily constitute prior art.
The whole of the power substation and the power transmission and distribution line of various voltages in the power system is called a power grid. The power transformation, transmission and distribution system comprises three units. The task of the power grid is to deliver and distribute electrical energy, changing the voltage. The short-term load prediction mainly refers to daily load prediction and weekly load prediction, provides reference basis for hydropower scheduling, unit start-stop, water-fire coordination and the like, and is basic work required by daily operation of a power grid.
At present, the traditional short-term load prediction method generally trains and verifies a neural network model for prediction by using historical load data, and outputs a short-term load prediction result by using nonlinear characteristics of the neural network model.
However, it is worth noting that the external influence factors of load prediction are many and complex, not all factors can play a role in short-term load prediction, and the types of influence factors and the importance of influence on load prediction cannot be fully considered only by means of a neural network model, so that the prediction precision cannot be guaranteed; and the historical load data are more and messy, so that the operation amount is extremely large, and the robustness of the neural network model is influenced.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a power grid short-term load prediction method and system, environmental information influencing short-term load prediction is screened out, the environmental information is corrected by considering the influence of environmental information change on electricity consumption behaviors of people, then short-term load prediction is carried out, and the efficiency and accuracy of power grid short-term load prediction are improved.
In a first aspect, the invention provides a method for predicting short-term load of a power grid;
a method of grid short-term load prediction, comprising:
according to the preset time granularity, historical load data and corresponding environment information are obtained, and correlation coefficients between each environment factor and load in the environment information are calculated; determining key features affecting the load according to the correlation coefficient;
clustering key features based on the historical load data and corresponding environmental information to generate similar data samples; based on the environment accumulation effect, correcting the environment information in the similar data samples to obtain characteristic samples;
and inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result.
Further, calculating the correlation coefficient between each environmental factor and the load in the environmental information, and determining the key feature affecting the load according to the correlation coefficient includes:
carrying out normalization processing on the historical load data and the corresponding environmental information, calculating the correlation coefficient of each environmental factor and the load data, and obtaining a correlation coefficient set;
determining a threshold according to the correlation coefficient set; and screening the environmental factors as key features influencing the load according to the threshold and the corresponding correlation coefficient of each environmental factor.
Further, the correlation coefficient is expressed as:
wherein L is a correlation coefficient, x is an environmental factor, y is a load, cov is a covariance, σ x Standard deviation, sigma, of environmental factors y Is the standard deviation of the load.
Further, the clustering the key features, generating similar data samples includes:
based on historical load data and corresponding environmental information, clustering key features through a K-means algorithm, calculating similarity between the key features and other environmental information, and obtaining a similar data sample;
the similar data samples comprise historical load data, corresponding key features and other environmental information with high similarity to the key features.
Further, the correcting the environmental information in the similar data sample based on the environmental cumulative effect includes:
screening according to the load information in the similar data samples to obtain similar load information; according to the similar load information, screening the environmental information in the continuous time period, and judging whether the environmental information corresponding to a certain time granularity has mutation or not;
if yes, determining a correction coefficient according to the environmental information in the continuous time period;
and acquiring the corrected environmental information based on the environmental information in the continuous time period and the environmental information corresponding to a certain time granularity according to the correction coefficient.
Preferably, the modified environmental information is expressed as:
wherein E' is the corrected environmental information, E n K is the actual environment information on the nth day n-t For correction factor on day n-t, E n-t Is the actual environmental information on the n-t th day.
Further, before calculating the correlation coefficient between each environmental factor and the load in the environmental information, the method further comprises:
screening abnormal values in the historical load data, and correcting the abnormal values; missing values in the historical load data are screened and filled in using an average over a continuous period of time.
Preferably, the filtering the abnormal value in the historical load data, and the correcting the abnormal value specifically includes: and processing the abnormal value by means of mean value filtering.
Further, the short-term load prediction model is a BP neural network model.
In a second aspect, the invention provides a power grid short-term load prediction system;
a power grid short-term load prediction system, comprising:
the key feature selection module is configured to: according to the preset time granularity, historical load data and corresponding environment information are obtained, and correlation coefficients between each environment factor and load in the environment information are calculated; determining key features affecting the load according to the correlation coefficient;
an environmental information correction module configured to: clustering key features based on the historical load data and corresponding environmental information to generate similar data samples; based on the environment accumulation effect, correcting the environment information in the similar data samples to obtain characteristic samples;
a short-term load prediction module configured to: and inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the technical scheme provided by the invention, the environmental factors with the greatest influence on the load are found out through calculation of the correlation coefficient, the environmental factors are clustered and identified, the environmental information similar to the key features is determined, the data sample containing the key features and the environmental information similar to the key features is screened out, and then short-term load prediction is carried out; on one hand, factors with larger influence on the short-term load are clarified, the influence of other interference factors on the short-term load prediction is reduced, and the accuracy of the short-term load prediction and the robustness of a short-term load prediction model are improved; on the other hand, the calculation amount of the model is reduced, and the efficiency and the instantaneity of short-term load prediction are improved.
2. According to the technical scheme provided by the invention, the influence of the abnormal condition of the collected historical data and the environmental information change degree on the electricity consumption behavior of people is fully considered, the environmental information is corrected by combining the environmental accumulation effect, the electricity consumption behavior and the electricity consumption habit of people are more accurately reflected, the situation that the short-term load prediction is wrongly indicated by the data with small load information change due to environmental mutation is avoided, the prediction authenticity of the short-term load prediction is influenced, and the prediction precision is effectively 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 schematic flow chart of a power grid short-term load prediction method according to an embodiment of the present invention;
fig. 2 is a schematic system architecture diagram of a power grid short-term load prediction system according to an embodiment of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary 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, unless the context clearly indicates otherwise, the singular forms also are intended to include the plural forms, and furthermore, it is to be understood that the terms "comprises" and "comprising" and any variations thereof are intended to cover non-exclusive inclusions, such as, for example, processes, methods, systems, products or devices that comprise a series of steps or units, are not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or inherent to such processes, methods, products or devices.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
In the prior art, a plurality of factors influencing load prediction are not distinguished according to the relevance of the factors influencing the load prediction, and abnormal information exists in the data due to faults or other factors in the process of collecting historical data, so that the accuracy of short-term load prediction is influenced; therefore, the embodiment provides a power grid short-term load prediction method.
Next, a method for predicting a short-term load of a power grid disclosed in this embodiment will be described in detail with reference to fig. 1. The power grid short-term load prediction method comprises the following steps:
s1, acquiring historical load data and corresponding environment information according to a preset time granularity, and calculating correlation coefficients between each environment factor and load in the environment information; and determining key characteristics affecting the load according to the correlation coefficient.
Exemplary, the historical load data and corresponding environmental information for month 6 to month 9 of 2022 are read, denoted as h= { H 1 ，h 2 ，h 3 ，h 4 ，h 5 -wherein the environmental information comprises an environmental temperature h 1 Relative humidity h 2 Wind speed h 3 And ambient air pressure h 4 ，h 5 Is the load. The specific flow is as follows:
s101, carrying out normalization processing on historical load data and corresponding environment information, calculating correlation coefficients of each environment factor and the load data, and obtaining phasesCoefficient set { L } i }(i＝1,2,3,4)。
The formula for the normalization process is expressed as follows:
wherein x' is the normalization result, x max Maximum value of non-normalized time variable, x min The minimum value of the variable when not normalized is given, and x is the variable to be normalized.
Further, the correlation coefficient of each environmental factor and the load data is calculated through the pearson correlation coefficient analysis, and the correlation coefficient is expressed as:
wherein L is a correlation coefficient, x is an environmental factor, y is a load, cov is a covariance, σ x Standard deviation, sigma, of environmental factors y Is the standard deviation of the load.
The value of the pearson correlation coefficient is between-1 and 1, and when L=0, the linear relation among variables is not shown; when L >0, the two variables are positively correlated, and the closer the value is to 1, the greater the positive correlation; when L <0, the two variables are inversely related, the closer their values are to-1, the greater the degree of negative correlation.
S102, according to a correlation coefficient set, taking the high correlation condition into consideration, setting a threshold alpha to be 0.8, and screening the environmental factors as key features affecting the load according to the threshold and the correlation coefficients corresponding to the environmental factors. The key features that have the most impact on the load are determined according to the following equation:
|L i |≥α
wherein L is i Is a correlation coefficient, and α is a threshold.
The calculated correlation coefficient set between each environmental factor (the environmental temperature, the relative humidity, the wind speed and the environmental air pressure) and the load is { -0.85,0.75, -0.25, -0.3}, and the environmental factor with the largest influence on the load is obtained according to the threshold value, namely the key feature.
Further, before S101, the method further includes: screening abnormal values in the historical load data, and correcting the abnormal values; missing values in the historical load data are screened and filled in using an average over a continuous period of time.
Specifically, the abnormal value is processed by means of mean filtering, which is expressed as:
max[|Y(d，t)-Y(d，t-1)|，|Y(d，t)-Y(d，t+1)|]>ε(t)
where ε (t) is a threshold value, t is a time, Y (d, t) is a load value at time t on day d, Y (d, t-1) is a load value at time t-1 on day d, t-1 is a previous time, Y (d, t+1) is a load value at time t+1 on day d, and t+1 is a subsequent time.
And S2, clustering key features based on the historical load data and corresponding environmental information to generate similar data samples.
The method comprises the steps of clustering key features through a K-means algorithm based on historical load data and corresponding environment information, calculating similarity between the key features and other environment information through calculation of Euclidean distances, and obtaining similar data samples; the similar data samples comprise historical load data, corresponding key features and other environmental information with high similarity to the key features.
And S3, correcting the environmental information in the similar data samples based on the environmental accumulation effect to obtain the characteristic samples.
When the environment is unchanged within a certain time and then suddenly changed, the environmental information felt by people is delayed from the change of the environment, and the electricity consumption behavior of people is regulated and controlled according to the feeling of people, namely the environment accumulation effect. For example, when cold weather occurs in a plurality of continuous days, even if the temperature rises suddenly in the next day, the power load does not rise suddenly; or in continuous overcast and rainy weather, even if the next day is a sunny day, the road is still muddy, and the electricity load cannot be changed obviously. In the collected historical data, the point is often ignored, so that the model ignores the influence of the mutation of the environmental information on the short-term load change; therefore, it is necessary to correct the environmental information so as to reflect the actual electricity consumption data and electricity consumption habits as much as possible.
The step S3 specifically comprises the following steps:
s301, screening according to load information in similar data samples to obtain similar load information; and screening the environmental information in the corresponding continuous time period according to the similar load information, and judging whether the environmental information corresponding to a certain time granularity has mutation or not. If yes, determining a correction coefficient according to the environmental information in the continuous time period.
Specifically, the value range of the correction coefficient is 0-1, the specific value of the correction coefficient is determined according to the change condition of the environmental information, the correction coefficient is in direct proportion to the stabilization time of the environmental information, and in inverse proportion to the mutation degree of the environmental information; for example, the longer the environment is kept at a low temperature, the smaller the amount of change in temperature, and the larger the value of the correction coefficient.
S302, according to the correction coefficient, based on the environment information in the continuous time period and the environment information corresponding to a certain time granularity, obtaining corrected environment information, and determining a characteristic sample. The corrected environmental information is expressed as:
wherein E' is the corrected environmental information, E n K is the actual environment information on the nth day n-t For correction factor on day n-t, E n-t Is the actual environmental information on the n-t th day.
S4, inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result.
In this embodiment, the short-term load prediction model is a BP neural network model, and the BP neural network is a multi-layer feedforward neural network that adjusts network parameters by inputting forward propagation signals and error back propagation. The network uses the steepest descent method, continuously adjusts the weight and the threshold value of the network through back propagation, so that the square sum of errors of the network is minimum, and the network has strong nonlinear fittingCapability. In the neuron model of the network, each neuron receives an input signal x of a previous layer of neurons i Each signal is passed through a filter with a weight w i Is passed on. The neuron gathers the input signal, compare with threshold value theta; and obtaining a final output y through a Sigmoid activation function.
Wherein y is the final output short-term load prediction result, w i Is weight, x i Is an input feature sample.
Example two
With reference to fig. 2, this embodiment discloses a power grid short-term load prediction system, including:
the key feature selection module is configured to: according to the preset time granularity, historical load data and corresponding environment information are obtained, and correlation coefficients between each environment factor and load in the environment information are calculated; determining key features affecting the load according to the correlation coefficient;
an environmental information correction module configured to: clustering key features based on the historical load data and corresponding environmental information to generate similar data samples; based on the environment accumulation effect, correcting the environment information in the similar data samples to obtain characteristic samples;
a short-term load prediction module configured to: and inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result.
It should be noted that the key feature selection module, the environment information correction module, and the short-term load prediction module correspond to the steps in the first embodiment, and the modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the disclosure 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 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 flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
The foregoing embodiments are directed to various embodiments, and details of one embodiment may be found in the related description of another embodiment.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A method for predicting short-term load of a power grid, comprising:
according to the preset time granularity, historical load data and corresponding environment information are obtained, and correlation coefficients between each environment factor and load in the environment information are calculated; determining key features affecting the load according to the correlation coefficient;
clustering key features based on the historical load data and corresponding environmental information to generate similar data samples; based on the environment accumulation effect, correcting the environment information in the similar data samples to obtain characteristic samples;
and inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result.
2. The method for predicting short-term load of power grid according to claim 1, wherein calculating the correlation coefficient between each environmental factor and load in the environmental information, and determining the key feature affecting the load according to the correlation coefficient comprises:
carrying out normalization processing on the historical load data and the corresponding environmental information, calculating the correlation coefficient of each environmental factor and the load data, and obtaining a correlation coefficient set;
determining a threshold according to the correlation coefficient set; and screening the environmental factors as key features influencing the load according to the threshold and the corresponding correlation coefficient of each environmental factor.
3. The grid short-term load prediction method according to claim 1, wherein the correlation coefficient is expressed as:
wherein L is a correlation coefficient, x is an environmental factor, y is a load, cov is a covariance, σ x Standard deviation, sigma, of environmental factors y Is the standard deviation of the load.
4. The grid short-term load prediction method of claim 1, wherein the clustering key features to generate similar data samples comprises:
based on historical load data and corresponding environmental information, clustering key features through a K-means algorithm, calculating similarity between the key features and other environmental information, and obtaining a similar data sample;
the similar data samples comprise historical load data, corresponding key features and other environmental information with high similarity to the key features.
5. The grid short-term load prediction method according to claim 1, wherein the modifying the environmental information in the similar data samples based on the environmental cumulative effect comprises:
screening according to the load information in the similar data samples to obtain similar load information; according to the similar load information, screening the environmental information in the continuous time period, and judging whether the environmental information corresponding to a certain time granularity has mutation or not;
if yes, determining a correction coefficient according to the environmental information in the continuous time period;
and acquiring the corrected environmental information based on the environmental information in the continuous time period and the environmental information corresponding to a certain time granularity according to the correction coefficient.
6. The grid short-term load prediction method according to claim 5, wherein the corrected environmental information is represented as:
wherein E' is the corrected environmental information, E n K is the actual environment information on the nth day n-t For correction factor on day n-t, E n-t Is the actual environmental information on the n-t th day.
7. The grid short-term load prediction method according to claim 1, further comprising, before calculating the correlation coefficient between each environmental factor and the load in the environmental information:
screening abnormal values in the historical load data, and correcting the abnormal values; missing values in the historical load data are screened and filled in using an average over a continuous period of time.
8. The power grid short-term load prediction method according to claim 7, wherein the filtering of the abnormal values in the historical load data, and the correcting of the abnormal values specifically comprises: and processing the abnormal value by means of mean value filtering.
9. The power grid short-term load prediction method according to claim 1, wherein the short-term load prediction model is a BP neural network model.
10. A power grid short-term load prediction system, comprising:
the key feature selection module is configured to: according to the preset time granularity, historical load data and corresponding environment information are obtained, and correlation coefficients between each environment factor and load in the environment information are calculated; determining key features affecting the load according to the correlation coefficient;
an environmental information correction module configured to: clustering key features based on the historical load data and corresponding environmental information to generate similar data samples; based on the environment accumulation effect, correcting the environment information in the similar data samples to obtain characteristic samples;
a short-term load prediction module configured to: and inputting the characteristic sample into a preset short-term load prediction model for processing, and obtaining a short-term load prediction result.
CN202310749489.1A 2023-06-25 2023-06-25 Power grid short-term load prediction method and system Pending CN116979505A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310749489.1A CN116979505A (en) 2023-06-25 2023-06-25 Power grid short-term load prediction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310749489.1A CN116979505A (en) 2023-06-25 2023-06-25 Power grid short-term load prediction method and system

Publications (1)

Publication Number Publication Date
CN116979505A true CN116979505A (en) 2023-10-31

Family

ID=88470326

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310749489.1A Pending CN116979505A (en) 2023-06-25 2023-06-25 Power grid short-term load prediction method and system

Country Status (1)

Country Link
CN (1) CN116979505A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117277316A (en) * 2023-11-22 2023-12-22 国网山东省电力公司曲阜市供电公司 Power load prediction method, system, medium and equipment
CN117955094A (en) * 2024-01-10 2024-04-30 北京浩然五洲软件技术有限公司 Power load prediction method and system
CN118137492A (en) * 2024-04-30 2024-06-04 国网山东省电力公司泗水县供电公司 Short-term power load prediction method and system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117277316A (en) * 2023-11-22 2023-12-22 国网山东省电力公司曲阜市供电公司 Power load prediction method, system, medium and equipment
CN117277316B (en) * 2023-11-22 2024-04-09 国网山东省电力公司曲阜市供电公司 Power load prediction method, system, medium and equipment
CN117955094A (en) * 2024-01-10 2024-04-30 北京浩然五洲软件技术有限公司 Power load prediction method and system
CN117955094B (en) * 2024-01-10 2024-07-02 北京浩然五洲软件技术有限公司 Power load prediction method and system
CN118137492A (en) * 2024-04-30 2024-06-04 国网山东省电力公司泗水县供电公司 Short-term power load prediction method and system

Similar Documents

Publication Publication Date Title
CN116979505A (en) Power grid short-term load prediction method and system
US20190265768A1 (en) Method, system and storage medium for predicting power load probability density based on deep learning
CN110023850B (en) Method and control device for controlling a technical system
CN112215442B (en) Method, system, device and medium for predicting short-term load of power system
CN106971238A (en) The Short-Term Load Forecasting Method of Elman neutral nets is obscured based on T S
CN1274435A (en) Model-free adaptive process control
CN109615124B (en) SCADA master station load prediction method based on deep learning
CN113705929B (en) Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion
CN113675863B (en) Digital twin-based micro-grid frequency secondary cooperative control method
CN113743673A (en) Power load prediction method during typhoon
CN107871157B (en) Data prediction method, system and related device based on BP and PSO
CN115470862A (en) Dynamic self-adaptive load prediction model combination method
Vyalkova et al. Analysis of hybrid model error of short-term forecast of energy consumption in Moscow
CN111754029A (en) Community load prediction system
CN113177355A (en) Power load prediction method
CN113268929B (en) Short-term load interval prediction method and device
Osowski et al. Regularisation of neural networks for improved load forecasting in the power system
CN114240687A (en) Energy hosting efficiency analysis method suitable for comprehensive energy system
CN107862866B (en) Data noise point detection method based on average offset translation
Caihong et al. A study on quality prediction for smart manufacturing based on the optimized BP-AdaBoost model
Crispim et al. Prediction of the solar radiation evolution using computational intelligence techniques and cloudiness indices
CN113947007A (en) Energy load prediction method, device and equipment
KR20190071174A (en) Method and system for short-term wind speed prediction based on pressure data
CN115660898B (en) SVR-based classification type wind power short-term power prediction precision improving method and device
CN111967919A (en) System and method for analyzing electricity consumption behavior of residents based on autoregressive and adaptive boosting algorithm

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