Economic analysis of a hybrid intelligent optimization-based renewable energy system using smart grids

Abstract

Renewable energy has seen a substantial increase in deployment as an alternative to traditional power sources. However, two fundamental constraints exist that preclude widespread adoption: the availability of the generated power and the expense of the equipment. One of the most critical difficulties with this sort of hybrid system is to appropriately design the Hybrid Renewable Energy System (HRES) elements so that they fulfill all load requirements while requiring the least amount of investment and running expenditures. This research proposes a novel technique for evaluating the optimal smart grid linking Hybrid Renewable Energy (Solar photovoltaic and wind) with battery, to increase profitability, dependability, and feasibility. A multiobjective function is suggested and constructed to be optimized utilizing two optimization algorithms: Enhanced Particle Swarm Optimization (EPSO) and Harris Hawks Optimization (HHO) algorithm with Fuzzy-Extreme Learning Machine (ELM). The primary goal for the HRES is to operate optimally to reduce the cost of energy generat ion through hourly day-ahead. Here, the Fuzzy-ELM is utilized to predict the required load of the smart grid-connected system and hybrid EPSO-HHO, which are introduced to solve the problem of HRES economic analysis. Finally, the suggested EPSO-EHO method is implemented in the MATLAB software, and its performance comparison is made with other existing methods such as PSO, WOA, and HHO. The simulation result shows that the cost of the newly suggested EPSO-HHO technique-based Hybrid Renewable Energy System is less than PSO, WOA, and HHO by 4.89 %, 4.51 %, and 4.05 %, respectively.