查詢結果分析
相關文獻
- Adaptive ARMA Model for Short-Term Load Forecasting
- 結合乏晰理論及類神經網路作短期負載預測
- 自我組織式模糊系統作短期電力負載預測
- A New Short-Term Load Forecasting Approach using Self-Organizing Fuzzy ARMAX Models
- 一群落估算法用於模糊模式鑑別的短期負載預測
- Time Series Analysis for Power System Short Term Load Forecasting
- 應用時間序列法及模糊系統法於短期負載預測
- 以進化規劃法作電力系統短期負載預測之研究
- Short Term Load Forecasting for Main Transformers and Feeders
- 以進化規劃法作電力系統短期負載預測之研究
頁籤選單縮合
題名 | Adaptive ARMA Model for Short-Term Load Forecasting=適應性自迴歸-移動平均模式之短期負載預測方法 |
---|---|
作者 | 黃昭明; 黃慶連; 陳建富; 楊宏澤; 王瑋民; |
期刊 | 高苑技術學報 |
出版日期 | 19930200 |
卷期 | 2 1993.02[民82.02] |
頁次 | 頁83-91 |
分類號 | 448.115 |
語文 | eng |
關鍵詞 | 適應性自迴歸-移動平均模式; 短期負載預測; |
中文摘要 | 本文提出一套適應性自迴歸-移動平均模式之短期負載預測方法,用於預測未來一週內每小時負載。在現有短期負載預測方法中,巴氏簡氏法被公認為最精確方法,但由於此法之模式及參數一經選定,並不能適時利用預測誤差更新其預測值,故在預測精確度上仍受極大限制。本文所提出之適應性方法是藉著最小均方誤差 (Minimum Mean Square Error) 理論推導誤差學習係數 (Error Learning Coefficient),再經由此誤差學習係數與第一小時之預測誤差修正原先之預測值。由於本法所俱有之適應性能力,對於系統之不正常狀況,亦能適時修正其預測值。本法不僅能精確預測一般工作天(週一至週五)負載,對於週末、日及例假日負載亦能作精確預測。本文中利用台電系統負載及氣象局溫度資料作測試,進行24小時 (24-hour ahead) 及一週 (one week ahead)之短期負載預測,結果顯示在精確度方面,本法優於傳統巴氏-簡氏及移轉函數法,特別是在24小時 (24-hour ahead) 負載預測週期,更能顯示本法之精確性。 |
英文摘要 | An adaptive ARMA model for short-team load forecasting of power system is proposed in this paper. For short-term load forecasting, the Box-Jenkins Transfer Function approach has been regarded as one of the most accurate methods. However, the Box-Jenkins approach could not adapt the available forecasting errors to update the forecast, the accuracy is limited. The proposed adaptive approach derives the error learning coefficients by virtue of minimum mean square error theory and then updates the forecasts based on the one-step ahead forecast errors and the coefficients. Due to its adaptive capability, the algorithm can deal with any unusual system condition. The proposed algorithm has been tested and compared with the Box-Jenkins approach by applying both to the same utility data. The results of 24-hour and one week ahead forecast show that our algorithm could be more accurate that the conventional Box-Jenkins approach in future application, especially for 24-hous ahead load forecasting. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。