Multi-region short-term load forecasting in consideration of Heat Index and load/weather diversity

This paper proposes a multi-region short-term load forecasting methodology, taking into account the Heat Index, a human-perceived equivalent temperature, to improve the load forecasting accuracy in Taiwan Power Company's (Taipower's) system. With the distinct climate characteristics due to Taiwan's long and narrow topography, it is difficult to obtain satisfactory load forecasting results by treating the whole island as one single region. Therefore, the multi-region load forecasting that factors in the load/weather diversity is applied to enhance the forecasting accuracy. Besides, such weather factors as temperature, relative humidity, and the Heat Index are also considered to examine the prediction accuracy. The results show that adopting the Heat Index as a parameter can effectively improve the accuracy if the temperature of the region under investigation is above 27°C/80°F. By considering both the load/weather diversity and the Heat Index, the further improvement of the load forecasting for the Taipower system in summer can be effectively achieved.