Hybrid GWO-ANN Associated SMC based Boost Converter for MPPT of PV System under Partial Shading Conditions

Power generation from Photovoltaic (PV) modules is the best way to utilize the renewable energy in many places. The output of the PV modules will depends on many factors including changes in solar irradiance, temperature, partial shading conditions, operating voltage across terminals of module etc. Apart from operating voltage of PV modules, remaining all factors are depending on nature which we cannot change easily. Hence obtaining an effective voltage regulation of terminals to achieve maximum power from PV module is very important for best utilization. There are many existing maximum power point tracking (MPPT) mechanisms on PV systems but an effective integrating mechanism is required to achieve the best operation under all possible conditions. Artificial neural network (ANN) can able to produce best reference signal corresponding to maximum power location under various random changes very quickly. In other hand, sliding mode controller (SMC) is able to force the boost converter to deliver the best output voltage with fewer ripples under variable input voltage. Fastest response with fewer ripples in dc voltage can help to harvest maximum energy from PV panels. Therefore, integration of ANN with SMC can prepare the MPPT converter to deliver more energy under random changes in irradiance and temperature. The performance of ANN associated SMC for boost converter based MPPT of the PV system is presented in this paper. In order to obtain more realistic response, Hardware-in the-Loop (HIL) is established for proposed system with the help of two OPAL-RT modules. Extensive results by using HIL are presented and discussed under various case studies to enhance the proposed method.