Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ニューラルネットワークによる負荷予測方法及び装置
Document Type and Number:
Japanese Patent JP7412423
Kind Code:
B2
Abstract:
Disclosed are a load prediction method and apparatus based on a neural network. The method comprises: receiving a time period to be predicted (S202); inputting the time period into a neural network model for predicting an energy load, wherein the neural network model is a radial-basis neural network obtained by means of training based on a hybrid particle swarm optimization algorithm (S204); and using the neural network model to predict an energy load value in the time period (S206). The method solves the technical problem in the prior art of low accuracy when a single load prediction algorithm is used for predicting an energy load.

Inventors:
Hwang Xin
Shengwei Liu
Application Number:
JP2021514399A
Publication Date:
January 12, 2024
Filing Date:
September 25, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ENNEW DIGITAL TECHNOLOGY CO., LTD.
International Classes:
G06N3/08
Foreign References:
CN103729685A
Other References:
RAZA, M. Q. et al.,"A review on short term load forecasting using hybrid neural network techniques",2012 IEEE International Conference on Power and Energy (PECon) [online],IEEE,2012年12月,p. 846-851,[2023年08月22日検索],インターネット,Electronic ISBN:978-1-4673-5019-8,DOI: 10.1109/PECon.2012.6450336
LU, Ning et al.,"Particle Swarm Optimization-Based RBF Neural Network Load Forecasting Model",2009 Asia-Pacific Power and Energy Engineering Conference [online],IEEE,2009年03月,[2023年08月22日検索],インターネット,Electronic ISSN: 2157-4847,DOI: 10.1109/APPEEC.2009.4918588
花田一磨,"ラジアル基底関数ネットワークを用いた八戸工業大学の毎時電力需要予測",電気学会全国大会講演論文集,2010年03月05日,Vol. 6,p. 70
Attorney, Agent or Firm:
Momoko Arima