Effective Sizing and Optimisation of Hybrid Renewable Energy Sources for Micro Distributed Generation System

In the modern world, Renewable Energy Sources (RES) play a crucial role in resolving the fossil fuel issues. It supports maintaining the sustainability of the environment by reducing air pollution. Predominantly, Hybrid Renewable Energy System (HRES) is the ideal mechanism that integrates diverse RES for enhancing energy efficiency and reliability in Microgrids (MGs). Conversely, the integration of HRES with MGs faces challenging issues, such as energy management, load demand, efficiency, and reliability. Several research plans have been devised to attain enhanced HRES in MGs, but such schemes lack efficiency, reliability, and accuracy. To solve this problem, the proposed model implemented a specialized set of procedures to control load demand and decrease the cost of HRES in MGs. Accordingly, the respective model used the Ant Lion Colony Optimization with Particle Swarm Optimization (ALCO-PSO) for the Maximum Power Point Tracking (MPPT) mechanism for enhancing power efficiency. The Ant Colony Optimization (ACO) algorithm is utilized because it has the advantages of higher efficiency, better global search, and distributed nature. The classical research identified that it is limited due to computational complexity, premature convergence, etc. To resolve the issue, the Lion Optimization Algorithm (LOA) is combined with the ACO mechanism for ability to handle premature convergence, enhance complexity, sensitivity on parameter setting, etc. Conversely, ALCO is lacking certain factors such as limited scalability, global search capability, and other issues. To tackle the limitations, the PSO is incorporated with ALCO to improve accuracy through the ability to handle limited scalability and global search capability. Besides, direct current fault detection functions with the Artificial Neural Network (ANN) algorithm for improving the system’s performance with solar data. Finally, the performance of the projected system is calculated with specific performance metrics such as power, voltage, and power quality. The accuracy achieved by the model is 99.56%, the faster convergence (FC) obtained is 0.11 s, and the oscillation around (OA) gained by the model is 4.25 W. The tracking time is 0.2 s, the interruptible load is 0.009%, the cost of energy (COE) is 0.0413 $/kWh, and the penalty is 0.94 $/kWh.