Generalized regression neural network and fitness dependent optimization: Application to energy harvesting of centralized TEG systems

The thermoelectric generator (TEG) system has attracted extensive attention because of its applications in centralized solar heat utilization and recoverable energy. operating efficiency the TEG is highly affected by conditions. In a series-parallel structure, due to diverse temperature differences, modules show non-linear performance. Due non-uniform distribution (NUTD) condition, several maximum power points (MPPs) appear on P/V curve. multiple MPPs, true global (GMPP) are very important for optimum action. existing conventional technologies have slow tracking speed, low productivity, unwanted fluctuations voltage curves. To overcome behavior shortcomings, A novel control technology proposed, which utilizes improved generalized regression neural network fitness dependent optimization (GRNNFDO) track GMPP under dynamic Conventional techniques not likely trace GMPP. Our GRNNFDO can NUTD varying conditions this article, some major contributions area systems investigated solving issues such as maxima tracking, module mismatch, oscillations around point. results compared with Cuckoo-search algorithm (CSA), grasshopper (GHO) particle swarm (PSO) algorithm. Results verified experiments authenticated MATLAB/SIMULINK. proposed technique generates up 7% more energy than PSO 60% fast-tracking meta-heuristic algorithms.