查詢結果分析
來源資料
相關文獻
- Establishment of a Evaluation System for Photovoltaic Power Generation Using Neural Network
- 製程間具相關數據之趨勢模型偵測探討
- 類神經網路應用於臺灣股市預測:統合基本面與技術面資訊
- 類神經網路在集水區降雨逕流模擬之應用
- 類神經網路於製程管制之應用:具相關性數據特性模型之偵測與分析
- 類神經網路應用於臺灣股市預測
- 應用類神經網路與遺傳演算法建構小汽車跟車模式之研究
- A Neural Network Approach to Sewing Time Prediction
- 以XOR問題探討倒傳遞網路收斂情況的影響因素及改進方法
- 應用監督性類神經網路於衛星影像分類技術之探討
頁籤選單縮合
題名 | Establishment of a Evaluation System for Photovoltaic Power Generation Using Neural Network=以類神經網路建置太陽光能發電量之預估系統 |
---|---|
作者 | 余定中; 石金福; 張孝澤; Yu, Ting-chung; Shih, Chin-fu; Chang, Hsiao-tse; |
期刊 | 龍華科技大學學報 |
出版日期 | 20130600 |
卷期 | 33 2013.06[民102.06] |
頁次 | 頁51-60 |
分類號 | 448.167、448.167 |
語文 | eng |
關鍵詞 | 太陽能發電系統; 類神經網路; 倒傳遞網路; Photovoltaic system; Neural network; Back propagation network; |
中文摘要 | 本論文的目的在以類神經網路的方法來預估桃園縣迴龍地區太陽能的發電量及電流,利用影響太陽能發電量的各種參數及先前實際量測到的發電量值,來建立出一個資料庫,以供發電量預估使用。本文使用Matlab/Simulink 軟體來建置一個類神經網路模 型,並使用類神經網路中的倒傳遞網路(back-propagation network)來預估太陽能發電系統的發電量。此外,本論文亦實現類神經網路的參數最佳化以得到最準確的預估發電量數值。藉由預估結果的比較,本文所建立的類神經網路模型可以準確的預估出各種天候狀況下的發電量及輸出電流,驗證了本文所建置類神經網路預估系統的可行性。 |
英文摘要 | The purpose of this paper is to evaluate the electrical energy generated by photovoltaic systems (PV system) using the method of neural network. A database, which includes the practical measured electrical energy and the parameters of weather conditions that can affect the electrical energy generated by the PV systems, is established in advance in order to be used in electrical energy evaluations. The Matlab/Simulink software is used in this paper to set up a neural network model with the learning algorithm of back-propagation network in order to evaluate the generated electrical energy of the PV system. An optimization of the network parameters is also performed to find the best solutions of the energy estimation. After observing the results of electrical energy forecast and divergence evaluation, it can be found that the proposed back propagation network model can accurately predict the generated electrical power and output current under different weather conditions. The feasibility and accuracy of the proposed evaluation system is then validated. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。