Analysis of deep learning models for estimation of MPP and extraction of maximum power from hybrid PV-TEG: A step towards cleaner energy production

Abstract

The Hybrid Photovoltaic-Thermoelectric generation system (PV-TEG) exhibits immense potential for effectively harnessing solar energy. However, the overall effectiveness of the hybrid PV-TEG system is hindered by the relatively low efficiency of both PV and thermoelectric generation (TEG). To overcome this limitation, this research investigates the application of an evolutionary Neural Network (NN)-based Maximum Power Point Tracking (MPPT) control technique. This proposed control technique utilizes a Growth Optimizer Algorithm (GO-algorithm) to optimize the weights and biases of a Deep Neural Network (DNN), enabling real-time tracking of the global maximum power point (GMM). Furthermore, to fortify the robustness of the MPPT control, a modified Fractional Order Proportional-Integral-Derivative (FOPID) controller is used whose gains are tuned using the GO-algorithm (GO-FOPID). Experimental evaluations conclusively demonstrate the efficacy of the evolutionary NN-based MPPT control technique in enhancing the generation efficiency of hybrid PV-TEG systems. The effectiveness of the proposed MPPT technique is validated through a comparative analysis with other MPPT techniques. The GO-DNN-based MPPT controller excels in its real-time global maxima tracking capability, exhibiting minimal power oscillations with average efficiency of 99.928% and an exceptionally low tracking time of less than 5ms. This superior performance is verified by comparative, simulation, quantitative, and statistical analyses, thereby highlighting the efficiency, tracking time, stability, and fault detection capabilities of the GO-DNN and GO-FOPID controllers across various practical scenarios.