Natural Gas Load Forecasting Based on Improved Back Propagation Neural Network

To suit for the condition that the relative error is more popular than the absolute error, and overcome the shortcoming of the traditional Back propagation neural network, this paper proposed an improved Back propagation algorithm with additional momentum item based on the sum of relative error squa...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied Mechanics and Materials Ročník 563; číslo Sensors and Materials: Advanced Researches; s. 312 - 315
Hlavní autor: Jiang, Yu Lian
Médium: Journal Article
Jazyk:angličtina
Vydáno: Zurich Trans Tech Publications Ltd 01.05.2014
Témata:
Algorithms
Back propagation
Back propagation algorithms
Computer simulation
Errors
Natural gas
Neural networks
Training
Back Propagation Neural Network
Forecasting
Additional Momentum Item
Relative Error
ISBN:9783038351191, 3038351199
ISSN:1660-9336, 1662-7482, 1662-7482
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To suit for the condition that the relative error is more popular than the absolute error, and overcome the shortcoming of the traditional Back propagation neural network, this paper proposed an improved Back propagation algorithm with additional momentum item based on the sum of relative error square. The improved algorithm was applied to the example of the natural gas load forecasting, simulations showed that the improved algorithm has faster training speed than the traditional algorithm, and has higher accuracy as while.
Bibliografie:Selected, peer reviewed papers from the 2014 International Conference on Sensors and Materials Manufacturing Science (ICSMMS 2014), April 11-12, 2014, Hangzhou, China
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISBN:9783038351191
3038351199
ISSN:1660-9336
1662-7482
1662-7482
DOI:10.4028/www.scientific.net/AMM.563.312