Short-Term Load Forecasting For Jordan's Power System

• Published in: I-Manager's Journal on Electrical Engineering Vol. 2; no. 4; pp. 78 - 83
• Main Author: Al-Tallaq, Kamel N. A.
• Format: Journal Article
• Language: English
• Published: Nagercoil iManager Publications 01.04.2009
• Subjects: Electric power generation; Electricity consumption; Forecasting; Learning theory; Mathematical models; Neural networks; Peak load; Time series
• ISSN: 0973-8835; 2230-7176
• DOI: 10.26634/jee.2.4.224

One of the requirements for the operation and planning activities of an electrical utility is the prediction of load for the next hour to several days out, known as Short Term Load Forecasting (STLF). Artificial neural network (ANN) techniques have been applied to various subjects in the electrical power system area including electric load forecasting. This paper presents an application of (ANN) to the weekly load forecast problem of Jordan National Power System (JNPS). The ANN is trained with the load patterns corresponding to the forecasting hours and the forecasted load is obtained. Time Series Regression (TSR) modifies the initial forecasted load. A Neural Network (NN) model for the prediction of the seven-day ahead peak load of Jordan power system is developed. For the purpose, Nonlinear Autoregressive (AR) modeling, using simple Back-propagation NNs architecture, is used. This model was trained using two weeks data window for the most recent daily peak loads. The model treated the peak load at weekdays and weekends altogether. The results showed that the model has satisfactory results for one hour up to a week prediction of JNPS load. The average absolute percent error for the generated forecasts using this model was 0.5%.