應用類神經網路進行解制電業市場中可利用傳輸能力之估測

Available Transfer Capability Estimation in Deregulated Power Markets Using Artificial Neural Network

蕭芥陽(Chieh-Yang Hsiao)

指導教授 ： 洪穎怡

中原大學/工學院/電機工程研究所/碩士(2004年)

https://doi.org/10.6840/cycu200400135

摘要

摘 要

隨著電力市場的解制後，電力市場由獨佔壟斷轉變成自由競爭之市場，因此允許民營電廠加入參與供電。由於民營電廠本身並未擁有輸電網路，故得藉由擁有輸電網路之電力公司代為輸送其電力，因此有了轉供問題的產生，其中以輸電線可利用傳輸能力(Availability Transfer Capability, ATC)之計算為主要的問題。本論文利用類神經網路提出一個估測解制電業市場中可利用傳輸能力的方法。
本論文利用DC電力潮流及電力轉移分配因子(Power Transfer Distribution Factor, PTDF)求得可利用傳輸能力，並且考慮系統中各匯流排負載的變化與傳輸線路發生跳線時，對可利用傳輸能力之影響。然後利用倒傳遞網路進行訓練與預測，同時我們也結合發電機相移因子(Generation Shift Factor, GSF)、跳線轉移分佈因子(Outage Transfer Distribution Factor, OTDF)及主要成份分析網路之方法，以縮短倒傳遞網路之訓練時間。
本論文使用PowerWorld模擬軟體進行六個匯流排系統及IEEE 30匯流排系統之測試，然後利用NeuroSolution產生所提出的類神經網路方法進行可利用傳輸能力之預測，並計算實際值與預測值兩者之誤差量及相關係數，以證實本論文所提方法之可行性。

關鍵字

類神經網路 ； 解制 ； 轉供 ； 可利用傳輸能力

並列摘要

Abstract

The structure of the power industry has being changed from monopoly to competition due to the deregulation in the electricity market. Thus, the Independent Power Producer (IPP) is permitted to join providing electricity. Due to most IPPs don’t have transmission networks themselves, they must depend on the power utility who has a transmission network to deliver their power. Therefore, a wheeling problem was araised. The calculation of Availability Transfer Capability is a main problem. This thesis presents a method using the Artificial Neural Network (ANN) for estimating the ATC.
“DC power flow” and “Power Transfer Distribution Factor” are employed in calculating ATC in this thesis. When any load is changed and taking the system contingencies into account, ATC will be influenced. Then the Back-Propagation Network was employed in training and forecasting ATC. Generation Shift Factor, Outage Transfer Distribution, and Principal Component Analysis Network are also incorporated to reduce the training time.
This thesis employs a 6-bus system and the IEEE 30-bus systems, which were simulated by PowerWorld, to serve as test systems for ATC forecasting by the proposed artificial intelligence method which were simulated by NeuroSolutions. The errors and correlation between the realistic and forecasting data were given for showing the applicability.

並列關鍵字

Wheeling ； Deregulated Market ； Availability Transfer Capability ； Artificial Intelligence Network

參考文獻

[2] Y. R. Sood, N. P. Padhy, and H. O. Gupta, “Wheeling of Power Under Deregulated Environment of Power System─A Bibliographical Survey, ”IEEE Transactions On Power Systems, Vol.17, No. 3, pp. 870-878, August 2002.

[5] Y. Ou, C. Singh, “Assessment of Available Transfer Capability and Margins, ”IEEE Transactions on Power Systems, Vol.17,No. 2,pp. 463-468, May 2002.

[22] Allen J. Wood and Bruce F. Wollenberg, “Power Generation, Operation and Control, “John wiley&Sons, NEW YORK, 1996.

[23] R. D. Christie and B. F. Wollenberg, “Transmission Management in the Dergulated Environment” Proceedings of the IEEE, Vol. 88, No.2, pp. 170-195, February 2000.

[24] H. H. Yan, “PTDF And TLR From A Power Marketer’s Perspective, ”Power Engineering Society Summer Meeting, 1999. IEEE, Vol. 1, pp. 156-161, July 1999.