查詢結果分析
相關文獻
- 應用類神經網路評估及預測饋線日負載
- 結合乏晰理論及類神經網路作短期負載預測
- 預測方法之比較--以臺灣電力負載預測為例
- Short Term Load Forecasting Using Fuzzy ARMAX Models
- 人工神經網路在區域一次變電所負載預測之應用研究
- 利用類神經網路作短期負載預測
- 應用灰色一次累加生成於類神經網路短期電力負載預測
- 類神經網路應用於醫院空調耗電特性模擬之研究
- 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
頁籤選單縮合
題名 | 應用類神經網路評估及預測饋線日負載=Investigate the Daily Feeder Load Forecasting by Artificial Neural Networks |
---|---|
作者 | 曾燕明; 康渼松; 曾本立; | 書刊名 | 高苑學報 |
卷期 | 7:1 1998.02[民87.02] |
頁次 | 頁71-80 |
分類號 | 448.115 |
關鍵詞 | 類神經網路; 負載預測; 負載曲線; Artificial neural network; Load forecasting; Load pattern; |
語文 | 中文(Chinese) |
中文摘要 | 類神經網路對模型辨識具有良好適應性,將其應用於饋線出口日負載各小時實功 值預測。本文建構一監督式人工類神經網路 -- 函數連接式網路,經過訓練資料練網路收斂 後,再利用回想範例饋入收斂類神經預測饋線負載;以預測後之準確度為基準,加以探討饋 線變數加入後對饋線負載預測有何效應並加以評估,前後共改良四種類神經網路預測模式並 加以探討,經饋線負載預測準確度之評估結果,饋線負載預測不僅受溫度、濕度之影響,亦 受饋線鄰近歷史相同日型態負載曲線影響。 |
英文摘要 | It is to apply the methodologies to hourly feeder load forecasting with the well adaptive pattern recognize by artificial neural networks. In this paper, the back propagation with functional link is trained by historical feeder loading data (training data) until converged, then fed to the converged networks by recall sets to achieve the forecasting values. Based on the forecasting accuracy to enhance the networks by adding the depend variable to the training sets to accomplish certain accuracy or error, it is found the feeder load forecasting accuracy can be affected not only by temperature or humidity but also by the same day type historical daily load pattern. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。