Abstract: Different aspects of reactive power regulation problem in wind farms are presented in this paper. In the first part some background of the reactive power control in Wind Park is presented, including motivations for its use and methods that can be used. In general, there are active (wind generator, compensator) and passive methods (L, C) of reactive power compensation. The wind park model ( the model of doubly fed induction generator (DFIG) based wind turbines, crowbar circuit, battery storage system, transformers, cable lines between wind farm and PCC, control system) has been shown in the proposed methods. In wind farm the crowbar protection, changes from reactive power source to reactive power load with the rise of low voltage and then burden of fault power system is aggravated. In order to solve the problem a new strategy is formed where a new real time coordinate control system (RTCCS) is built. Based on reactive power compensator the STATCOM synchronizes with wind power system and

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1847-3-948
• Views: 0
• Downloads: 0

Abstract: Neural networks have been proved as an important and useful tool for solving a wide variety of practical and real-world problems. Huge research in this field alleviated in understanding and finding new and effective methods to address different problems. However, selection of apposite combination of training and transfer function for a particular problem is a cumbersome task. But, this can be ascertained through research experiences and outcomes. The objective of this work is to compare the performances of three transfer functions in tandem with fourteen training functions used for backpropagation training of neural network for recognition of power quality (PQ) disturbance signatures. The comparison is shown on the basis of Lowest MSE, number of epochs, convergence time, and accuracy. It is shown that among three transfer functions namely “logsig”, “purelin”, and “tansig”; the overall performance of “tansig” was superior and the accuracy of BR training function was 100 % with all the t

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1847-3-954
• Views: 0
• Downloads: 0