Reactive power transfer allocation method with the application of artificial neural network

• Main Authors: Mustafa, Mohd Wazir, Khalid, S.N., Shareef, Hussain, Khairuddin, Azhar
• Format: Article
• Published: Institution of Engineering and Technology 2008
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/7688/; http://ieeexplore.ieee.org/document/4505264/
• Institution: Universiti Teknologi Malaysia

A novel method to identify the reactive power transfer between generators and load using modified nodal equations is proposed. On the basis of the solved load flow results, the method partitions the Y-bus matrix to decompose the current of the load buses as a function of the generators' current and voltage. Then it uses the load voltages from the load flow results and decomposed load currents to determine reactive power contribution from each generator to loads. The validation of the proposed methodology is demonstrated by using a simple 3-bus system and the 25-bus equivalent system of south Malaysia. Next part here focuses on creating an appropriate artificial neural network (ANN) to solve the same problem in a simpler and faster manner. The basic idea is to use supervised learning paradigm to train the ANN. Most commonly used feedforward architecture has been chosen for the proposed ANN reactive power transfer allocation technique. Almost all system variables obtained from load flow solutions are utilised as an input to the neural network. Moreover, tan-sigmoid activation functions are incorporated in the hidden layer to realise the nonlinear nature of the reactive power transfer allocation. The targets of the ANN corresponding to the previously developed reactive power transfer allocation method. The 25-bus equivalent system of south Malaysia is utilised as a test system to illustrate the effectiveness of the ANN output compared with that of the modified nodal equations method. The ANN output provides promising results in terms of accuracy and computation time.