Presentation 1999/12/17
Next Day Electric Peak Load Forecasting Using Two Types of Neural Networks
Hiroyasu Konishi, Masanori Izumida, Kenji Murakami,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Using two types of neural networks, we have forecasted a next day electric peak load in Shikoku area. First neural network uses learning data that are past 10 days of the target day. Second neural network uses those of last year. Then we get the forecasted results that are the weighted sum of the forecasted results by the first neural network and the forecasting results by the second neural network. In addition, at the first neural network, we use the learning method, which uses learning data with priority. In the method, learning data close to the target day has high priority. Moreover, we have studied suitable input features. Using those methods, we have reduces the forecasting error.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / Electric load forecasting / Input features / Weights of input data
Paper # PRMU99-177
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/12/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Next Day Electric Peak Load Forecasting Using Two Types of Neural Networks
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) Electric load forecasting
Keyword(3) Input features
Keyword(4) Weights of input data
1st Author's Name Hiroyasu Konishi
1st Author's Affiliation Shikoku Research Institute inc.()
2nd Author's Name Masanori Izumida
2nd Author's Affiliation Ehime univ.
3rd Author's Name Kenji Murakami
3rd Author's Affiliation Ehime univ.
Date 1999/12/17
Paper # PRMU99-177
Volume (vol) vol.99
Number (no) 515
Page pp.pp.-
#Pages 8
Date of Issue