A novel on intelligent energy control strategy for micro grids with renewables and EVs

• Published in: Energy strategy reviews 2024-03, Vol.52, p.101306, Article 101306
• Main Authors: CH, Hussaian Basha, K, Ramakrishna Reddy, C, Dhanamjayulu, Kamwa, Innocent, Muyeen, S.M.
• Format: Article
• Language: English
• Subjects: Battery degradation; Electric vehicles; EV fleet and power loss; G2V; Intelligent CNN RES; Microgrid
• ISSN: 2211-467X; 2211-467X
• DOI: 10.1016/j.esr.2024.101306

Energy management in Micro Grids (MG) has become increasingly difficult as stochastic Renewable Energy Sources (RES) and Electric Vehicles (EV) have become more prevalent. Even more challenging is autonomous MG operation with RES since prompt frequency control is required. We provide an innovative Energy Management Strategy (EMS) for MG with grid support in this academic publication. By integrating RES and EV storage, we seek to decrease reliance on the grid. The EMS consists of three execution phases: Ranking for EV Recommendation (RER), Optimal Power Allocation (OPA) for Fleet, and EV Storage Allocation (OAES). The aim of slicing the time in to smaller in intervals is to update the energy and power scheduling in shorter intervals as per the changes are going on in the system. The period of 24 h is divided into 96 intervals (t) and storage requirements (kWh/t) are estimated based on the estimated load and RES together with the necessary storage volume. We employ three approaches that are frequently used for communication channel power allocation optimization to accomplish OAES. With two objectives: minimum network power loss plus voltage fluctuations, the Multi-Objective Optimization Problem (MOOP) is solved for each 't' based on OAES to provide the Optimal Power Flow (OPF). The Pareto-front is used to calculate the best amount of power from each fleet in each 't'. The data received from the fuzzy rule base is used in the third stage to train an intelligent Convolutional Neural Network (CNN), which has rank of EV as an output and four decision variables as inputs. The main goals in this stage are to minimize battery degradation and to make the most of it for MG support. With the aid of a MATLAB-based simulation setup and heterogeneous entities, the primary goal of EMS is examined and put into practice in an On-grid MG. •In this scholarly article present a pioneering Energy Management Strategy (EMS) for MG with grid support.•To reduce grid dependency by utilizing RES and EV storage. The EMS comprises three stages of execution: Optimal Allocation EV Storage (OAES), Optimal Power Allocation (OPA) for Fleet, and Ranking for EV Recommendation (RER)•The key objectives in this stage are: min, the battery's degradation, and maximize its utilization for MG support.