Power load prediction method and device

A technology of power load and forecasting method, which is applied in the field of power load forecasting methods and devices, and can solve problems such as large time and resources, low forecasting accuracy and authenticity, and costly power load forecasting methods, so as to avoid data loss and waste Effects of time and resources

Pending Publication Date: 2020-10-30
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] The technical problem to be solved by the present invention is that the prior art power load forecast

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Power load prediction method and device
  • Power load prediction method and device
  • Power load prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] Such as figure 1 Shown, a kind of electric load forecasting method, described method comprises:

[0086] Step S1: Input the original data set into the BP neural network, traverse and search to obtain the location of the missing data, use the BP neural network to use the load data at three time points before and after the missing data point as input features, output the missing data value, and fill in the missing data. Obtain a complete data set; among them, the original data set is a data set directly obtained from the data source without any processing, which includes weather data for a period of time: temperature, humidity, wind speed, and corresponding power load data.

[0087] Such as figure 2 As shown, the step S1 includes:

[0088] Step 101: Construct a BP neural network, wherein the input layer is 6 neurons, the middle layer is 13 neurons, the output layer is 1 neuron, and the activation function uses the sigmoid function;

[0089] Step 102: search and read a...

Embodiment 2

[0126] Corresponding to Embodiment 1 of the present invention, Embodiment 2 of the present invention also provides a power load forecasting device, which includes:

[0127] The missing data processing module is used to input the original data set into the BP neural network, traverse and search to obtain the position of the missing data, use the BP neural network to use the load data of three time points before and after the missing data point as the input feature, and output the missing data value, and carry out Fill in missing data to obtain a complete data set;

[0128] The parameter optimization module is used to optimize the parameters of the complete data set, and output the optimal hyperparameter to generate the optimal hyperparameter vector;

[0129] The model training module is used to construct the LSTM neural network using the optimal hyperparameter vector, and input the training data to train the LSTM neural network to obtain the LSTM model;

[0130] The test modul...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a power load prediction method and device. The method comprises the steps of inputting an original data set into a BP neural network, performing traversal search to obtain positions of missing data, outputting missing data values, and performing missing data filling to obtain a complete data set; performing parameter optimization on the complete data set, and outputting anoptimal hyper-parameter to generate an optimal hyper-parameter vector; constructing an LSTM neural network by using the optimal hyper-parameter vector, and inputting training data to train the LSTM neural network to obtain an LSTM model; inputting test data, and testing the LSTM model; inputting characteristic values into the LSTM model passing the test, and carrying out power load prediction, wherein the characteristic values comprise air temperature, humidity, wind speed, historical data and prediction time points. The method has the advantages that the time and resources are reduced, and the prediction precision and authenticity are improved.

Description

technical field [0001] The present invention relates to the field of electric load forecasting, and more particularly relates to a method and device for electric load forecasting. Background technique [0002] In the power system, there is simultaneity between grid power generation and power consumption. Therefore, the power grid management and dispatching department needs to make a power generation plan in advance. Therefore, power load forecasting has become an important research topic for power grid dispatching departments. The accuracy of Short Term Load Forecasting (STLF) is directly related to the operating costs of power companies. The change of electric load is random, but there is a certain regularity on the whole. Therefore, more and more scholars apply more intelligent nonlinear models to short-term load forecasting. Such as: long short-term memory artificial neural network (LSTM). [0003] LSTM is a special form of recurrent neural network (RNN). RNN is a t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q10/04G06Q50/06G06N3/04G06N3/08G06N3/12
CPCG06Q10/04G06Q50/06G06N3/049G06N3/084G06N3/126G06N3/044G06N3/045Y04S10/50
Inventor 仝青山
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap