查詢結果分析
相關文獻
- 結合乏晰理論及類神經網路作短期負載預測
- 利用類神經網路作短期負載預測
- The Effect of Preprocessing on Neural Network for Short-Term Electricity Load Forecasting
- Forecast Improvement of Electricity Load Using a Model Integrating ARIMA and ANN
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
頁籤選單縮合
題名 | 結合乏晰理論及類神經網路作短期負載預測=Combined Fuzzy-Neural Network to Short-Term Load Forecasting |
---|---|
作者 | 梁瑞勳; 鄭清吉; Liang, Ruey-hsun; Cheng, Ching-chi; |
期刊 | 科技學刊 |
出版日期 | 19990700 |
卷期 | 8:3 1999.07[民88.07] |
頁次 | 頁193-203 |
分類號 | 448.115 |
語文 | chi |
關鍵詞 | 短期負載預測; 類神經網路; 皮爾森法; 乏晰推理機; Short-term load forecasting; Artificial neural network; Pearson method; Fuzzy inference machine; |
中文摘要 | 為了達成準確的負載預測,本文結合了乏晰理論及類神經網路來作短期負載預測 。在電力系統中,具有準確性的負載預測是相當重要的,它是經濟調度、水火力機組發電協 調、機組排程和系統安全性分析的基礎。 建立一個結合乏晰推論技術與類神經網路的方法是為了有效地得到短期負載預測的結果。近 幾年來,類神經網路已成為一有力的計算工具,且廣泛地應用在處理一個複雜的系統。乏晰 推理機則包含了許多語言變數與歸屬函數,及 IF-THEN 知識法則的型式。 在本文所提出的 方法中, 先應用皮爾森( Pearson )法來選擇兩日與預測日負載相關性較好之負載歷史資 料,連同預測日前兩日的氣候溫度與預測當日的預測溫度,經模糊化過程轉換後作為類神經 網路的輸入資料,應用倒傳遞神經網路優良的學習能力預測出一最初的預測負載值。乏晰推 理機應用所建立完成的法則與知識庫來推論出倒傳遞神經網路輸出經由解模糊化過程後的負 載與實際負載值之間的誤差量。網路所求得的最初預測負載值加上乏晰推理機所推論出的預 測誤差值便是最終之預測負載值。本文所使用的測試資料是以臺灣電力公司的實際資料作為 應用實例,包含整個電力系統負載、斗六變電所一號主變壓器及饋線(中華線)負載的預測 。預測所得的結果展現均比傳統類神經網路更能勝任。 |
英文摘要 | An approach based on combined fuzzy theory and artificial neural network is developed for short-term load forecasting. Accurate load forecasting is of great importance for power system operation. It is the basis of economic dispatch, hydrothermal coordination, unit commitment, and system security analysis among other functions. An approach, which combines the power of artificial neural networks and fuzzy theory, is developed in order to reach the desired short-term load forecasting in an efficient manner. Over the past few years, artificial neural networks have received a great deal of complexity of the system, and are now being proposed as a powerful computational tool. In the proposed approach, the Pearson analysis method is first applied to choose two load patterns of historical load records that are similar to forecasted load pattern. Then, these two load patterns and required weather parameters are fuzzified and input to a neural network for training or testing the network. We can apply the back-propagation neural network to find a preliminary forecasted load. In addition, the rule base of the fuzzy inference machine contains linguistic important attached to them in terms of membership functions with knowledge in the form of fuzzy IF-THEN rules. It makes the load correction inferences from historical information and past forecasted load errors to infer a forecasted load error. Adding the forecasted load error to the preliminary forecasted load, we can obtain the finial forecasted load. The effectiveness of the proposed approach to the short-term load forecasting problem is demonstrated by the practical data from Taiwan Power Company. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。