The modest changes in operating current and voltage of photovoltaic (PV) panel due to the temperature and radiation fluctuation constitute visible variations in the output power. In this paper, a hybrid method to optimize the performance of the maximum power point tracking (MPPT) controller for mitigating these variations and forcing the system to operate on maximum power point (MPP) is developed. The presented Hybrid MPPT method consists of two loops: (i) artificial neural network (ANN) based reference point setting loop and (ii) perturbation and observation (P&O) based fine tuning loop. To assess robustness of the proposed method, a comparison is performed using the conventional P&O, incremental conductance (INC) and ANN based MPPT methods under both rapidly changing radiation and partially shaded conditions by using PSCAD/EMTDC program. The results obtained from the test cases explicitly demonstrate that the presented MPPT method not only achieves an increase in speed of MPP tracking, but also reduces the steady state oscillations and prevents the possibility of the algorithm from confusing its perturbation direction. The system efficiency more than 98.26%, 120 ms improvement in convergence speed and 1.16 V decrease in the rate of overshoot are obtained with proposed Hybrid MPPT method under the rapidly changing environmental conditions. (C) 2017 Elsevier B.V. All rights reserved.