Load prediction method based on dynamic time warping and long-short time memory

A dynamic time warping, short-term load forecasting technology, applied in forecasting, neural learning methods, instruments, etc., can solve the problem of different exact times, and achieve the effect of reducing the number, reducing the complexity, and improving the generalization ability.

Active Publication Date: 2019-05-14
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A load profile is a 24-hour record of a household's energy consumption, and while consumer behavior indicates

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
  • Load prediction method based on dynamic time warping and long-short time memory
  • Load prediction method based on dynamic time warping and long-short time memory
  • Load prediction method based on dynamic time warping and long-short time memory

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0051] Such as figure 1 As shown, the present invention discloses a load forecasting method based on dynamic time warping and long and short time memory. The idea of ​​the present invention is to first cluster power users based on dynamic time warping similarity, and gather users with similar power usage habits. Into one category. Then perform random pooling operations on users of the same category to increase the scale and diversity of training data to increase the generalization ability of the prediction model. Then, the pooled user data sets are respectively established based on long and short-term memory load forecasting models. The proposed method has better engineering adaptability.

[0052] Because the user's load curve has the characteristics of multilaterality and time delay, there is a certain deviation in the clustering of load users based on Euclidean distance, which cannot be judged. Dynamic Time Warping (DTW, dynamic time warping) is a method to measure the simila...

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 load prediction method based on dynamic time warping and long-short time memory, and the method comprises the following steps: S1, obtaining the basic data required for short-term load prediction of a user from a power system; S2, carrying out the clustering of users with similar power utilization behaviors through employing a dynamic time warping method according to thehistorical load data of the user; S3, performing pooling processing on the user data of the same category; S4, selecting training data, preprocessing the training data and using the preprocessed training data as input; and S5, constructing a short-term load prediction method based on the deep long-term and short-term memory recurrent neural network, and verifying the effectiveness. According to the method, the users with similar electricity consumption behaviors are clustered according to the characteristic of large cardinal number of the to-be-predicted users, so that the prediction efficiency is improved. Meanwhile, through pooling processing on the data in the same category, the diversity of the training data is increased, the short-term load prediction precision is improved, and certain engineering application significance is achieved.

Description

technical field [0001] The invention relates to a short-term load forecasting method for electric power system residents, in particular to a short-term load forecasting method for electric power system residents, which is used for predicting electric power system load and belongs to the technical field of pattern recognition and image processing. Background technique [0002] Residential load forecasting in the power system is based on the historical load change law, combined with meteorological, economic and other factors to scientifically predict the load for the next few days or hours. Accurate load forecasting is an important decision-making basis for arranging power production scheduling and equipment maintenance planning. Therefore, it is necessary to study new methods and new technologies for residents' load forecasting in order to improve the accuracy and reliability of load forecasting and meet the requirements of engineering technology. [0003] In recent years, w...

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): G06Q10/04G06Q50/06G06N3/04G06N3/08G06K9/62
CPCY04S10/50
Inventor 王堃王振宇孙雁飞亓晋岳东
Owner NANJING UNIV OF POSTS & TELECOMM
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