EV charging and fuel cell vehicle refuelling with distributed energy resources using hybrid approach.
Saved in:
| Title: | EV charging and fuel cell vehicle refuelling with distributed energy resources using hybrid approach. |
|---|---|
| Authors: | Senthilkumar, M.1 (AUTHOR) senthilkumar@psgitech.ac.in, Prabhu, Sandeep2 (AUTHOR) sprabhu@sidtm.edu.in, Arun Kumar, U.3 (AUTHOR) arun.udayakumarn@gmail.com, Krishnakumar, R.4 (AUTHOR) krishnakumar.ramasamy@srec.ac.in |
| Source: | Environment, Development & Sustainability. Feb2026, Vol. 28 Issue 2, p4309-4331. 23p. |
| Subject Terms: | *Distributed resources (Electric utilities), *Optimization algorithms, *Electric vehicle charging stations, *Energy storage, *Metaheuristic algorithms, *Artificial neural networks, *Fuel cells, *Cost control |
| Abstract: | This manuscript proposes a hybrid technique for Electric Vehicle (EV) charging and Fuel Cell vehicle refuelling with distributed energy resources. The proposed hybrid approach, known as the BWO-CCG-DLNN method, combines the Beluga Whale Optimization (BWO) algorithm with the Cascade-Correlation Growing Deep Learning Neural Network (CCG-DLNN). The primary goal of the proposed strategy is to reduce reliance on the utility grid while simultaneously reducing the overall cost of distributed energy resources by using battery storage for peak shaving. The EV charging's cost is reduced using the proposed BWO approach, and the ideal outcome of the system is predicted using the CCG-DLNN approach. The proposed strategy is implemented into use on the MATLAB platform, and it is contrasted with current strategys, including the Cuckoo Search Algorithm Color Harmony Algorithm, and Particle Swarm Optimization, The proposed method demonstrates the lowest mean (1.0936) and median (1.0158), indicating its effectiveness. The standard deviation (0.1505) suggests relatively consistent results. The proposed method shows better result when compared to other methods. When compared to other existing approaches, the proposed approach has a high efficiency of 98% and a low cost of 200 ($/kW). [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | This manuscript proposes a hybrid technique for Electric Vehicle (EV) charging and Fuel Cell vehicle refuelling with distributed energy resources. The proposed hybrid approach, known as the BWO-CCG-DLNN method, combines the Beluga Whale Optimization (BWO) algorithm with the Cascade-Correlation Growing Deep Learning Neural Network (CCG-DLNN). The primary goal of the proposed strategy is to reduce reliance on the utility grid while simultaneously reducing the overall cost of distributed energy resources by using battery storage for peak shaving. The EV charging's cost is reduced using the proposed BWO approach, and the ideal outcome of the system is predicted using the CCG-DLNN approach. The proposed strategy is implemented into use on the MATLAB platform, and it is contrasted with current strategys, including the Cuckoo Search Algorithm Color Harmony Algorithm, and Particle Swarm Optimization, The proposed method demonstrates the lowest mean (1.0936) and median (1.0158), indicating its effectiveness. The standard deviation (0.1505) suggests relatively consistent results. The proposed method shows better result when compared to other methods. When compared to other existing approaches, the proposed approach has a high efficiency of 98% and a low cost of 200 ($/kW). [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 1387585X |
| DOI: | 10.1007/s10668-024-05138-8 |
