考慮氣象因素之分區負載預測

Multi-region Short-term Load Forecasting with Consideration of Weather Factors

徐正威(Jeng-Wei Xu)

指導教授 ： 朱文成

大同大學/電機資訊學院/電機工程學系所/碩士(2008年)

摘要

由於台灣為狹長地形，各地氣候差異甚大，加以負載結構及特性不同，因此本論文擬以分區方式進行負載預測，取代以往整區的傳統作法，以提高預測結果之準確度。此外，由於台灣為亞熱帶海洋型氣候，全年炎熱潮溼的日子佔有相當比例，因此本文首例採用酷熱指數(Heat Index, HI)為負載預測之參數，以期更進一步提高某些時段之預測準確度。前述負載預測均採用類神經網路方式予以實現，並引用台電公司負載資料和氣象局氣溫及溼度紀錄予以模擬計算，其結果證實確為可行。

關鍵字

酷熱指數(Heat Index ； 負載預測 ； HI) ； 類神經網路(ANN)

並列摘要

Because Taiwan is a longitudinal island resulting in the different climate and load characteristics in the different areas, this paper performs multi-region load forecasting to replace the tradition method which treats the whole system as one region to improve the accuracy. Meanwhile, due to the sub-tropic climate in Taiwan, the weather is hot and humid in most of the days of a year. For this reason, this paper proposes to use Heat Index (HI) as a parameter for load forecasting in order to improve the accuracy furthermore in some specific periods. The foregoing description of the load forecasting applies artificial neural networks (ANN) to implement. Based on the load and the weather factor data recorded by Taiwan Power Company and Central Weather Bureau, the results justify that the short-term multi-region load forecasting with parameter of HI is feasible.

並列關鍵字

artificial neural networks (ANN). ； heat index(HI) ； load forecasting

參考文獻

[2] N. Amjady, “Short-Term Hourly Load Forecasting Using Time-Series Modeling with Peak Load Estimation Capability,” IEEE Transactions on Power Systems, Volume 16, No. 3, pp.498 – 505, Aug. 2001.

[3] K. B. Song, S. K. Ha, J. W. Park, D. J. Kweon, and K. H. Kim, “Hybrid Load Forecasting Method with Analysis of Temperature Sensitivities,” IEEE Transactions on Power Systems, Volume 21, No. 2, pp. 869 – 876, May 2006.

[4] K. B. Song, Y. S. Baek, D. H. Hong, and G. Jang, “Short-Term Load Forecasting for the Holidays Using Fuzzy Linear Regression Method,” IEEE Transactions on Power Systems, Volume 20, No. 1, pp. 96 – 101, Feb. 2005.

[5] M. S. S. Rao, S. A. Soman, B. L. Menezes, P. Chawande, P. Dipti, and T. Ghanshyam, “An Expert System Approach to Short-Term Load Forecasting For Reliance Energy Limited, Mumbai,” IEEE Power India Conference, 10-12 April 2006.

[6] S. Fan, K. Methaprayoon, and W. J. Lee, “Short-term Multi-Region Load Forecasting Based on Weather and Load Diversity Analysis,” 39th North American Power Symposium, pp.562 – 567, 30 Sept. – 2 Oct. 2007.