Unlock instant, AI-driven research and patent intelligence for your innovation.

Impact load prediction method considering improved spectral clustering and Bi-LSTM neural network

A neural network and load prediction technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem of ignoring the morphological characteristics of the load curve, and achieve the effect of improving the prediction accuracy

Inactive Publication Date: 2021-08-13
HEBEI UNIV OF TECH +1
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as the demand for finer classification of load curves increases, spectral clustering commonly uses Euclidean distance to measure the similarity of curves, ignoring the morphological characteristics of load curves

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
  • Impact load prediction method considering improved spectral clustering and Bi-LSTM neural network
  • Impact load prediction method considering improved spectral clustering and Bi-LSTM neural network
  • Impact load prediction method considering improved spectral clustering and Bi-LSTM neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0081] The embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0082] In order to describe the present invention more specifically, the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0083] In this embodiment, the structural diagram of the impact load prediction method is as follows figure 1 As shown, including processing the charging load data of electric vehicles, obtaining the daily load curve, and analyzing the characteristics of the curve, selecting the improved spectral clustering algorithm of DTW similarity measure to cluster the daily load curve, and clustering the daily load curve according to the load curve clustering results , respectively process the data of various groups and perform Bi-LSTM neural network training, so as to predict the charging load on the forecast day; the steps are a...

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 relates to an impact load prediction method considering improved spectral clustering and a Bi-LSTM neural network. According to the method, different electric vehicle charging load time sequence characteristics are considered, an improved spectral clustering and Bi-LSTM neural network impact load prediction method is adopted, an improved spectral clustering algorithm of DTW similarity measurement is selected to perform clustering processing on daily load curves, modeling analysis is performed on each type of clustered curves, therefore, the purpose of improving the overall load prediction precision is achieved. The method specifically comprises the following steps: processing electric vehicle charging load data to obtain a daily load curve, analyzing curve characteristics, selecting an improved spectral clustering algorithm for DTW similarity measurement to cluster the daily load curve, performing data processing on each group according to a load curve clustering result, and performing Bi-LSTM neural network training, and thus, charging load prediction is performed on the prediction day.

Description

technical field [0001] The invention belongs to the technical field of electric load forecasting, and relates to an impact load forecasting method considering improved spectrum clustering and Bi-LSTM neural network. Background technique [0002] Electric Vehicle (EV) is a new type of electric vehicle, its charging load accounts for an increasing proportion of the overall load in certain areas or periods, and the power changes greatly and lasts for a long time when connected to the grid. Long, belongs to a kind of energy impact load. In particular, electric buses and electric taxis have high charging frequency and high charging power, and the requirements for regional power supply capacity continue to increase. Therefore, it is of great significance to study the short-term charging load forecast of electric vehicles in the region for the precise dispatching of the power grid and the improvement of energy utilization. [0003] Among many load forecasting algorithms, deep lea...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06K9/62
CPCG06N3/084G06N3/044G06F18/23213
Inventor 李练兵李东颖张佳伟李脉董晓红李思佳李佳祺刘汉民刁嘉李明任杰王阳赵建华王海张文煜袁冬冬姚帅亮张海欣
Owner HEBEI UNIV OF TECH