A hybrid functional link extreme learning machine for Maximum Power Point Tracking of partially shaded Photovoltaic array

For maximum utilization of Photovoltaic (PV) system the Maximum Power Point tracking (MPPT) is necessary. This paper presents three novel intelligence techniques named Trigonometric Functional Link Artificial Neural Network (TFLANN), Ridge Extreme Learning Machine (RELM) and RELM with trigonometric functional expansion block (FEB) under partial shaded condition to predict the voltage at Maximum Power Point (MPP). Here the proposed techniques are compared and the results show that RELM with FEB is more efficient as compared to other two techniques in partial shaded conditions. The efficiency of the proposed methods is observed in terms of Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE) as discussed in result analysis. The RELM with FEB is less complex and takes less time for execution as compared to RELM and TFLANN method. The proposed PV system is being implemented MATLAB/SCRIPT environment.