Electricity Demand Estimation Using an Adaptive Neuro-Fuzzy Network: A Case Study from the

Electricity is one of the energy types that have attracted a lotof interest due to its versatility.Rigorous analysis of the determinants of electricity demand as well as its accurate forecasting are of vital importance in the design of an effective energy policy to deal with current and future electricity needs.Several load forecasting models have been used inelectric power systems for achieving accuracy. Most studies have focused on the relationship between electricity demand and economicparameters such as gross domestic product (GDP), Gross National Product (GNP), national income, and the rate of employment as well as unemployment. Various studies have investigated the influence of ambient airtemperature, most times represented by heating and coolingdegree-days, on electrical energy consumption. Many studies have been conducted on short/long term electricity demand/load forecasting, but application of neuro fuzzy logic for forecasting electricity demand based on combined economic and climate conditions is still unexplored. In this paper, an ANFIS network (adaptive neuro fuzzy inference system) was designed to map six parameters as input data for State of Johor, Malaysia including four demographic & economic parameters (i.e. Employment, GDP, Industry Efficiency and Population), and two meteorological parameters related to annual weather temperature (i.e. minimum and maximum average annual temperature).to electricity demand as output variable. Keywords:Electricity demand; Neuro-Fuzzy; ANIFS; Forecastin