02102nas a2200265   4500000000100000000000100001008004100002260001200043653003100055653004300086653004500129653002900174653004900203100001600252700002100268700001700289700001900306700001600325245009400341856010000435300001200535490000600547520126900553022001401822       2019                            d  c12/201910aArtificial Neural Networks10aDoubly Fed Induction Generator  (DFIG)10aSquirrel Cage Induction Generator (SCIG)10aCombined Wind Farm (CWF)10aStatic Synchronous Series Compensator (SSSC)1 aSalah Kamel1 aFrancisco Jurado1 aAhmed Rashad1 aYousry Ibrahim1 aLoai Nasrat00aPerformance Enhancement of Wind Farms Using Tuned SSSC Based on Artificial Neural Network  uhttps://www.ijimai.org/journal/sites/default/files/files/2019/05/ijimai20195_7_12_pdf_71211.pdf  a118-1240 v53 aRecently, power systems are confronting a lot of challenges. Increasing the dependence on renewable energy sources especially wind energy and its impact on the stability of electrical systems are the most important challenges. Flexible alternating current transmission systems (FACTS) can be used to improve the relationship between wind farms and electrical grids. The performance of these FACTS depends on the parameters of its control system. These parameters can be tuned using modern methods like Artificial Neural Network (ANN). In this paper, ANN is used to improve the performance of static synchronous series compensator (SSSC) integrated into combined wind farm (CWF). This CWF is composed of squirrel cage induction generators (SCIG) and doubly fed induction generators (DFIG) wind turbines. This wind farm is collecting the advantage of SCIG and DFIG wind turbines. To view out the motivation of this paper, a comparison is done among the performances of combined wind farm (CWF) with ANN-SSSC, CWF with ordinary SSSC and CWF with SSSC tune by Multi-objective genetic algorithm (MOGA SSSC). The root mean square Error (RMSE) is used to evaluate the results. The results illustrate that the performance of CWF can be improved using SSSC adjusted by ANN.  a1989-1660