The major concern for every electrical utility is the ability to provide reliable and uninterrupted service to their customers The challenge becomes more significant with the fast and sharp increasing need for electric energy in the fast developing countries such as Egypt. Load forecasting is mandatory for planning, operation and control of power system. This paper concerns with long term load forecasting. This study presents a comparison between two models when applied to the Egyptian unified network, these models are Artificial Neural Network (ANN) model and regression model. To improve forecasting accuracy of the model we apply data preprocessing techniques. Forecasting capability of each approach is evaluated by calculating two separate statistical evaluations of the Mean Absolute Percentage Error (MAPE) and the Average Absolute Percentage Error (AAVE) .