ANN-Based STATCOM Tuning for Performance Enhancement of Combined Wind Farms

Ahmed Rashad, Salah Kamel, Francisco Jurado*, Mohamed Abdel-Nasser, Karar Mahmoud

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

7 Citations (Scopus)

Abstract

Although the wind farms based on squirrel cage induction generators (SCIG) is cheaper than the wind farms based on doubly fed induction generators (DFIG), it is always in desperate need for reactive power compensation. Nevertheless, the wind farms based on DFIG are expensive compared with the SCIG wind farm, it features by its ability to control the active power independent of reactive power. However, combined wind farm (CWF) has been developed to collect the benefits of SCIG and DFIG wind turbines in the same wind farm. In this article, artificial neural network (ANN) is used to evaluate gain parameters of static synchronous compensator (STATCOM) in order to improve the stability performance of CWF. The impact of tuned STATCOM on the performance of CWF during gust wind speed and during three-phase fault is comprehensively investigated. The performance of CWF with STATCOM tuned by ANN is compared with its performance when the STATCOM tuned by the multiobjective genetic algorithm (MOGA) and whale optimization algorithm (WOA). The results show that the performance of CWF can be enhanced using STATCOM tuned by ANN more than MOGA and WOA.

Original languageEnglish
Pages (from-to)10-26
Number of pages17
JournalELECTRIC POWER COMPONENTS AND SYSTEMS
Volume47
Issue number1-2
DOIs
Publication statusPublished - 20 Jan 2019
MoE publication typeA1 Journal article-refereed

Keywords

  • Artificial neural network
  • Combined wind farm
  • Doubly fed induction generators
  • Multiobjective genetic algorithm
  • Squirrel cage induction generators
  • STATCOM
  • Whale optimization algorithm

Fingerprint Dive into the research topics of 'ANN-Based STATCOM Tuning for Performance Enhancement of Combined Wind Farms'. Together they form a unique fingerprint.

Cite this