Short Term Electrical Load Forecasting Using Time Series

Abstract

Electric load forecasting plays an important role in the planning and operation of the power system. Precise load forecasting helps the electric utility to make unit commitment decisions, reduces spinning reserve capacity and schedule device maintenance plan properly. It also reduces the generation cost and increases reliability of power systems. A short-term electrical peak load forecast for Sudan grid was carried out using time series and the result was compared with actual values of peak load. Historical peak load data was collected from the daily report of operation and control of Sudanese National Grid, the hourly data covers a period from January to January 2014. Mean absolute percentage error (MAPE) and correlation (R) were used as performance indices to test the accuracy of the forecasted load. Result obtained from the time series using GMDH gave a correlation (R) range between 0.896 and 0.982 and a mean absolute percentage error (MAPE) range between 1.07 % and 1.72%.Results obtained show the efficacy of the GMDH forecasting.