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

• Main Authors: Chieh-Yang Hsiao, 蕭芥陽
• Other Authors: Ying-Yi Hong
• Format: Others
• Language: zh-TW
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/45258872107632025431

碩士 === 中原大學 === 電機工程研究所 === 92 === 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.