Bulletin of Electrical Engineering and Informatics · 2022 · 11 citations · 29 references
EngineeringElectrical EngineeringElectric MachinesEnergy SystemsRenewable Energy SystemsInduction MachinesNeural Control SystemsRenewable Energy Power ConversionRenewable Energy TechnologyWind Energy SystemsWind Turbine TechnologyNeural Network ControlSliding Mode ControlWind Farm Electrical SystemsWind Power SystemsWind Turbine Control Systems
This study aims to propose a robust hybrid sliding mode artificial neural network control (SM-ANN) scheme for controlling the stator power (active/reactive) of a doubly fed induction generator (DFIG)-based direct drive vertical axis wind turbine (VAWT) power system under a real-world scenario wind speed that will be installed in the Adrar region (Saharan zone) of Algeria. The SM-ANN scheme will control the stator power of the direct drive VAWT power. The chattering phenomenon is the most significant disadvantage associated with sliding mode control (SMC). In order to find a solution to this issue, the artificial neural network (ANN) method was applied to pick the appealing part of the SMC. MATLAB/Simulink is used to do an evaluation, after which the SM-ANN controller being suggested is compared to both traditional sliding mode (SM) and proportional-integral (PI) controllers. The results of the simulation demonstrated that the recommended SM-ANN controller has good performance in terms of enhancing the quality of energy that is delivered to the power network. This is in comparison to the traditional SM and PI controllers, which both have a long history of use. Notwithstanding the fact that there is DFIG parameter fluctuation present.
29
Belkacem Belabes, Abdelkader Youcefi, Ouahiba Guerri et al. · Renewable and Sustainable Energy Reviews · 2015 · 88 citations