A Gradient Descent Approach for Maximum Power Point Tracking in Solar PV Systems Networks
— The intermittent nature of solar irradiation makes it necessary to continuously track the irradiation and change the orientation of the solar panels so as to maximize the PV output. Since the nature of solar irradiation data is both extremely random and complex, hence classical statistical techniques render inaccuracies in the predicted values. Therefore, machine learning based approaches are needed for the estimation or forecasting of the PV output. The proposed approach employs the gradient descent-based approach for attaining the condition of maximum power point tracking (MPPT). The performance of the system has been evaluated in terms of the mean absolute percentage error and accuracy. It has been shown that the proposed system attains an accuracy of 96.31% with an MAPE of 3.69%.