Authors:
B. Gunapriya, N. Samanvita, Thirumalraj Karthikeyan, S. Venkatasubramanian
Addresses:
Department of Electrical and Electronics Engineering, New Horizon College of Engineering, Bengaluru, Karnataka, India. Department of Electrical and Electronics Engineering, Nitte Meenakshi Institute of Technology (NMIT), Bengaluru, Karnataka, India. Department of Artificial Intelligence, Trichy Research Labs, Quest Technologies, Tiruchirappalli, Tamil Nadu, India. Department of Computer Science and Business Systems, Saranathan College of Engineering, Tiruchirappalli, Tamil Nadu, India.
Abstract:
During times of heavy demand, a Virtual Power Plant (VPP) coordinates power sources, load centres, and energy storage to provide effective power distribution. Mobile robots and electric vehicles (EVs) are essential for maintaining equilibrium between supply and demand. It is still difficult to guarantee a safe connection between end users and VPP aggregators, nevertheless. This study presents a novel method for integrating electric vehicles (EVs) with deep learning algorithms for smart grid power management. The main function of the system is to provide a reliable EV fleet platform by forecasting EV charging trends using SoftMax regression and a deep autoencoder. It was surprising to learn that the eating habits of bottlenose dolphins in the mud rings off the coast of Florida served as inspiration for the deep autoencoders. Inspired by the way dolphins graze on mud rings, the novel Mud Ring Algorithm (MRA) fine-tunes these deep autoencoders for global optimisation. This method outperformed conventional training models, achieving an impressive 98.50% accuracy. This discovery enables strategic power distribution from the EV network as required, reducing power fluctuations and greatly improving smart grid power management. This invention has the potential to improve power grid stability and reliability while optimising EV use.
Keywords: Virtual Power Plant; Mud Ring Algorithm; Electric Vehicles; SoftMax Regression; Deep Autoencoder; Smart Grid Management; Power Consumption; Internal Combustion Engine.
Received: 24/11/2024, Revised: 12/01/2025, Accepted: 01/03/2025, Published: 09/12/2025
DOI: 10.64091/ATIEL.2025.000189
AVE Trends in Intelligent Energy Letters, 2025 Vol. 1 No. 2 , Pages: 100-114