Analyzing Effects of Electricity Subsidy on Social Welfare in Iran by Integrated System Approach and Artificial Neural Network

Nowadays, many researches are made to estimate some of socio-economic variables in which methods such as regression, time series (ARIMA, AR and etc.), Artificial Neural Networks (ANN) and so on are used. In this paper integrated System Approach and ANN are applied for estimating affects of subsidy on electricity consumption and social welfare. Actual electricity price is estimated by ANN, which has been effectively used for price forecasting recently. Forecasted electricity demand and also historical data of weighted average prices in electricity market are used to train Neural Networks. System approach are very successful in estimating qualitative variable in socio-economic, human factors and policy government, hence System Dynamics (SD) method is employed to analyze effects of electricity subsidy for residential sector. Indeed in this study ANN outputs are used as exogenous variable to develop SD model. Three scenarios for electricity pricing are presented to investigate electricity consumption and social welfare. In the first scenario subsidy is not considered, in the second affects of subsidy is added and for the third one different types of subsidy is analyzed. The results of three scenarios confirm that the performance of different electricity subsidy is closest to the goal of social welfare in Iran.