A multi Adaptive Neuro Fuzzy Inference System for short term load forecasting by using previous day features

Author

Souzanchi-K, Zohreh ; Fanaee-T, Hadi ; Yaghoubi, Mahdi ; Akbarzadeh-T, Mohammad-R

Author_Institution

Dept. of Artificial Intell., Islamic Azad Univ., Mashhad, Iran

Volume

2

fYear

2010

fDate

1-3 Aug. 2010

Abstract

In this paper, the use of Adaptive Neural-Fuzzy Inference System (ANFIS) to study the design of Short-Term Load Forecasting (STLF) systems for the east of Iran was explored. This paper forecasts consumed load by using multi ANFIS. Entries of the presented model are into the multi ANFIS including the date of the day, temperature maximum and minimum, climate condition and the previous days consumed load and its exit is forecasting of power load consumption of every season. Previous days contain 2,7,14 day before, and 2, 3, 4 day before. The results show that temperature and the features of 2, 7 and 14 day ago have an important role in load forecast.

Keywords

fuzzy neural nets; fuzzy reasoning; load forecasting; power engineering computing; power system planning; Iran; multiANFIS; multiadaptive neuro fuzzy inference system; power load consumption; short term load forecasting system; Adaptation model; Artificial neural networks; Autoregressive processes; Forecasting; Load forecasting; Load modeling; Predictive models; Adaptive Neural-Fuzzy Inference System; Load forecasting; Multi ANFIS; Previous Day Features;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics and Information Engineering (ICEIE), 2010 International Conference On

Conference_Location

Kyoto

Print_ISBN

978-1-4244-7679-4

Electronic_ISBN

978-1-4244-7681-7

Type

conf

DOI

10.1109/ICEIE.2010.5559714

Filename

5559714