Open AccessA comparative Study of Forecasting the Electrical Demand in Basra city using Box-Jenkins and Modern Intelligent Techniques
Author(s) -
Khadeega Abd Al-zahra,
Khulood Moosa,
Basil H. Jasim
Publication year - 2015
Publication title -
iraqi journal for electrical and electronic engineering/al-maǧallaẗ al-ʻirāqiyyaẗ al-handasaẗ al-kahrabāʼiyyaẗ wa-al-ilikttrūniyyaẗ
Language(s) - English
Resource type - Journals
eISSN - 2078-6069
pISSN - 1814-5892
DOI - 10.37917/ijeee.11.1.12
Subject(s) - autoregressive integrated moving average , box–jenkins , time series , computer science , fuzzy logic , demand forecasting , autoregressive model , consumption (sociology) , artificial neural network , data mining , artificial intelligence , econometrics , operations research , engineering , machine learning , mathematics , social science , sociology
The electrical consumption in Basra is extremely nonlinear; so forecasting the monthly required of electrical consumption in this city is very useful and critical issue. In this Article an intelligent techniques have been proposed to predict the demand of electrical consumption of Basra city. Intelligent techniques including ANN and Neuro-fuzzy structured trained. The result obtained had been compared with conventional Box-Jenkins models (ARIMA models) as a statistical method used in time series analysis. ARIMA (Autoregressive integrated moving average) is one of the statistical models that utilized in time series prediction during the last several decades. Neuro-Fuzzy Modeling was used to build the prediction system, which give effective in improving the predict operation efficiency. To train the prediction system, a historical data were used. The data representing the monthly electric consumption in Basra city during the period from (Jan 2005 to Dec 2011). The data utilized to compare the proposed model and the forecasting of demand for the subsequent two years (Jan 2012-Dec 2013). The results give the efficiency of proposed methodology and show the good performance of the proposed Neuro-fuzzy method compared with the traditional ARIMA method.