Energy management of renewable-based micro-grids with electric vehicle aggregators: COA-CANN approach

This manuscript proposes a hybrid energy management of renewable-based micro grids (MGs) with Electric Vehicle (EV) aggregators. The proposed hybrid strategy is a combination of the Coati Optimization Algorithm (COA) and Constitutive Artificial Neural Networks (CANN), and the proposed technique is referred to as the COA-CANN technique. The proposed approach aims to lessen operational costs, maximize MG's social welfare, and utilization of renewable sources of energy. The integration of renewable energy and EVs in micro-grid systems presents unique challenges in terms of optimal energy allocation and load balancing. The COA is utilized to optimize energy allocation and load balancing, ensuring efficient utilization of resources. On the other hand, CANN is employed to accurately predict energy demand and supply, facilitating proactive decision-making in MG operations. The proposed strategy is done in MATLAB and its performance is in contrast to the present strategy. The proposed strategy is better than all currently used methods, including the Salp-Swarm Optimizer, Cuckoo Search Algorithm and Heap-Based Optimizer. The outcomes demonstrate that the proposed technique saves $800 in comparison to other existing techniques.