Analysis of Power Flow of Power System Using Neural Network

• Main Authors: Pan, Kuan-Wei, 潘冠維
• Other Authors: Huang, Pei-Hwa
• Format: Others
• Language: zh-TW
• Published: 2018
• Online Access: http://ndltd.ncl.edu.tw/handle/2qy75h

碩士 === 國立臺灣海洋大學 === 電機工程學系 === 106 === The main purpose of this thesis is to analyze the maximum allowable capacity of interconnection point for the system by using Neural Network (NN). The maximum allowable capacity of interconnection point is analyzed according to current loading for the system with wind farm. According to the interconnection criteria, the current loadings are investigated to determine whether the system meets specifications. The NN method is used for analyzing the current loadings of each transmission line with different interconnection points and different capacities which are under the normal operation. Then it is decided whether the current loading is overloaded. If overloading occurs at the transmission line, then the capacity of interconnection point is reduced, so that the current loading of transmission lines meets the grid code. The maximum allowable capacity of the interconnection point is calculated. This thesis utilizes different interconnection points with different capacities to increase the number of the training samples, and analyzes transmission line which congestion occur easily by the system power flow, then samples of transmission line congestion are added to the training samples to improve the accuracy rate of NN. The simulation shows that the accuracy rate of the purpose method can reach 75%.