The wind energy conversion systems (WECS) suffer from an intermittent nature of source (wind) and the resulting disparity between power generation and electricity demand. Thus, WECS are required to be operated at maximum power point (MPP). This research paper addresses a sophisticated MPP tracking (MPPT) strategy to ensure optimum (maximum) power out of the WECS despite environmental (wind) variations. This study considers a WECS (fixed pitch, 3KW, variable speed) coupled with a permanent magnet synchronous generator (PMSG) and proposes three sliding mode control (SMC) based MPPT schemes, a conventional first order SMC (FOSMC), an integral back-stepping-based SMC (IBSMC) and a super-twisting reachability-based SMC, for maximizing the power output. However, the efficacy of MPPT/control schemes rely on availability of system parameters especially, uncertain/nonlinear dynamics and aerodynamic terms, which are not commonly accessible in practice. As a remedy, an off-line artificial function-fitting neural network (ANN) based on Levenberg-Marquardt algorithm is employed to enhance the performance and robustness of MPPT/control scheme by effectively imitating the uncertain/nonlinear drift terms in the control input pathways. Furthermore, the speed and missing derivative of a generator shaft are determined using a high-gain observer (HGO). Finally, a comparison is made among the stated strategies subjected to stochastic and deterministic wind speed profiles. Extensive MATLAB/Simulink simulations assess the effectiveness of the suggested approaches.