An artificial intelligence approach to optimization of an off-grid hybrid wind/hydrogen system

Off-grid electrification of remote areas using a hybrid renewable energy scheme is a requirement to achieve the goals of sustainable development. However, the optimization and sizing for the capacity of such systems are challenging. In this regard, this study targets an improved optimization algorithm with high efficiency for optimization and longterm capacity planning of an off-grid hybrid renewable energy scheme composed of wind, fuel cell, and hydrogen storage schemes. The suggested methods are three improved versions of the global dynamic harmony search to do pitch adjustment mechanism. The objective function of this study is to reduce the total net annual cost of the system and the loss of power supply probability to a minimum. The performance of this hybrid system is examined via a simulation study, which had been performed on a remote area located in eastern Iran over a long period. The results of the three improved proposed algorithms are compared with the original global dynamic harmony search algorithm. Also, sensitivity analysis is proposed to showcase the influence of uncertainties on the system and input parameters on the algorithm. The simulation results indicate that three improved versions of the global dynamic harmony search algorithm find more promising results than the original algorithm, and confirm the superior accuracy, convergence speed, and robustness of the global dynamic harmony search-II. Also, reliability level and iteration values have a ? Three improved versions of global dynamic harmony search (GDHS) are presented in term of best fitness function. ? GDHS-II yields the most promising results in terms of convergence speed, robustness, and accuracy. ? Off-grid hybrid system based on wind and hydrogen energy reduces system costs and increase reliability. ? Reliability level and iteration values have a considerable impact on each component and TNAC of the optimal hybrid system. Off-grid electrification of remote areas using a hybrid renewable energy scheme is a requirement to achieve the goals of sustainable development. However, the optimization and sizing for the capacity of such systems are challenging. In this regard, this study targets an improved optimization algorithm with high efficiency for optimization and long -term capacity planning of an off-grid hybrid renewable energy scheme composed of wind, fuel cell, and hydrogen storage schemes. The suggested methods are three improved versions of the global dynamic harmony search to do pitch adjustment mechanism. The objective function of this study is to reduce the total net annual cost of the system and the loss of power supply probability to a minimum. The performance of this hybrid system is examined via a simulation study, which had been performed on a remote area located in eastern Iran over a long period. The results of the three improved proposed algorithms are compared with the original global dynamic harmony search algorithm. Also, sensitivity analysis is proposed to showcase the influence of uncertainties on the system and input parameters on the algorithm. The simulation results indicate that three improved versions of the global dynamic harmony search algorithm find more promising results than the original algorithm, and confirm the superior accuracy, convergence speed, and robustness of the global dynamic harmony search-II. Also, reliability level and iteration values have a considerable impact on the total net annual cost of the optimal hybrid energy system based on wind and hydrogen energy. (c) 2021 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

Automated summary

Off-grid electrification of remote areas using a hybrid renewable energy scheme is essential for sustainable development goals, but optimizing system capacity is challenging. This study introduces an improved optimization algorithm for long-term planning of a hybrid system with wind, fuel cell, and hydrogen storage. The three enhanced global dynamic harmony search algorithms show superior performance in reducing costs and increasing reliability compared to the original algorithm. Moreover, reliability levels and iterations significantly influence the total net annual cost of the optimal hybrid energy system.