Electric power systems are often disturbed by several variations of the electrical load and peaks during the day. However, the anticipation of this change and especially peak loads must be controlled in order to keep the production-consumption equation in compliance with different standards to secure profitable operations of power system. Developing an accurate and robust peak load forecasting model provide electricity companies to make important decisions regarding generation scheduling and reduced significantly the cost of operating power systems. The objective of this study is to develop and to employ an artificial intelligence approach for performing the daily peak load prediction. The suitability and the performance of the proposed approach is illustrated and verified with simulations through an application to the Algerian peak load data, downloaded from OSE website.