Previous Issues
Volume :2 Issue : 2 1995
Add To Cart
Download
An Intelligent Decision Support System For Electricity Peak-Load Forecasting for the United Arab Emirates
Auther : Masood Abdulla Badri
This study uses a variety of time series techniques to produce short-term forecasts (one year ahead) of monthly electricity peak-load for eight geographical areas in the UAE by analyzing the behavior of monthly peak-load. The study develops a time series based decision support system that integrates data management, model base management, simulation, graphic display, and statistical analysis to provide near optimal forecasting models. The system can work as an expert to automatically propose the optimal forecasting model. Results show that multiplicative winters models perform extremely well for most of the data. On the other hand, the Box Jenkins ARIMA models provided optimal fits for other time series cases. For each of the Emirates, a model is suggested to be used in forecasting short-term electricity load.