Special features of energy forecast methodology in fast growing countries

An accurate load-forecast is essential for developing a power supply strategy, and system development plan, especially for developing countries where the demand is increased with high growth rate. Forecasting demand and energy for power systems in fast developing countries is however a difficult task; the difficulty arises from the limited historical data, and/or its uncertainty as well as the high growth rate of electric demand. This paper, thus presents a unified forecasting methodology with special features based on the decomposition of loads into several sectorial components for a fast-growing power system. The model has been applied to a typical fast growing system, the Saudi power system, as compared with the conventional method of forecasting the total energy. Further, this paper applies energy forecast models using artificial neural networks (ANN) with multilayer perceptron (MLP) and back propagation (BP) learning algorithm on such a fast growing system. ANN is implemented to support the choice of the most suitable load-forecasting model for long term power system planning. This technique demonstrates the accuracy of the proposed method among the three forecast models and shows that the suggested forecast model based on the ANN technique is simplest with high accuracy. To carry out this task with the various methods, it was necessary to perform data mining for the available historical data. Hence, it could be possible to forecast the peak load forecast assuming the historical data for the load factor.