Design of advanced artificial intelligence protection technique based on low voltage ride-through grid code for large-scale wind farm generators: a case study in Egypt

Abstract

This paper proposes an advanced artificial intelligence protection technique based on low voltage ride-through (LVRT) for a large-scale doubly fed induction generator (DFIG) wind farm. The proposed protection technique consists of two dependant approaches. The first approach is fault detector algorithm that using adaptive neuro fuzzy inference system as an artificial intelligence technique to detect the fault occurrence and its location. The second approach is implementation of Egyptian LVRT grid code to discriminate between tripping or not tripping decision for faulted wind turbine generators based on fault conditions such as its duration and voltage level. The proposed protection technique is applied on a simulation model of 200 MW Gabal El-Zayt wind farm, which located in Red Sea region and connected to Egyptian electrical grid. The studied wind farm consists of 100 DFIG wind turbines, and each generator has a capacity of 2 MW. The simulation model of studied wind farm is implemented by using MATLAB/SIMULINK toolboxes to demonstrate the performance of proposed protection technique. The impacts of fault duration, fault type, internal and external fault locations on the behaviour of studied wind farm equipped with the proposed protection technique are investigated. Also, the impacts of grid voltage sag and different ground transition resistances on the performance of proposed protection technique are investigated. The simulation results show that, the proposed protection technique can detect and isolate the faulted area according to Egyptian LVRT grid code requirements for enhancement the stability of studied wind farm.