Summer daily peak load forecasting considering accumulation effect and abrupt change of temperature

For the distinctive power load and resource characteristics in an area, the relationship is analyzed between regional peak load and typical meteorological factors in summer. The forecasting model for daily peak load in summer is established, considering not only the general meteorological factors such as season, temperature, humidity, precipitation and the continuous sunny days, but also the persistent drought, the average temperature difference, the atmospheric conditions, human comfort and other factors. Particularly, due to the prolonged heat or abrupt change, the forecasting model is revised using the accumulation effect with high temperature and substitute average value for the abrupt change temperature. The calculated results show that the revised forecasting model is more accurate and feasible.

[1]  Ying Chen,et al.  Short-Term Load Forecasting: Similar Day-Based Wavelet Neural Networks , 2010, IEEE Transactions on Power Systems.

[2]  Sanjay V. Dudul,et al.  Short-term load prediction with a special emphasis on weather compensation using a novel committee of wavelet recurrent neural networks and regression methods , 2010, 2010 Joint International Conference on Power Electronics, Drives and Energy Systems & 2010 Power India.

[3]  W. Zalewski.  Comparison of the fuzzy regression analysis and the least squares regression method to the electrical load estimation , 1998, MELECON '98. 9th Mediterranean Electrotechnical Conference. Proceedings (Cat. No.98CH36056).

[4]  Shuang Liu,et al.  Short-term load forecasting based on chaos theory and RBF neural network , 2011, ICNC.

[5]  Vassilis S. Kodogiannis,et al.  Load forecasting using fuzzy wavelet neural networks , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[6]  Nima Amjady,et al.  Short-term hourly load forecasting using time-series modeling with peak load estimation capability , 2001 .