Bio-Inspired Edge Computing for Real-Time Energy Optimization in Smart Grids

Abstract

The number of energy requirements of the population and integration of the renewable sources have made modern power systems grow exponentially in terms of complexity. The traditional cloud-based solutions do not have the capability of processing large real-time data across the distributed nodes of the grid because of latency, scalability. The paper introduces a bio-inspired edge computing architecture that recreates self-organizing and adaptive nature of biology in optimization of energy in real time in the smart grids. Swarm intelligence, i.e. Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) is suggested to be employed in the system to dynamically optimize the loads and assign the energy to the edge nodes. It is 22 percent more energy efficient with 30 percent lower response latency according to the simulation results as compared to traditional cloud-based models. The framework demonstrates the fact that the next-generation smart grids can be driven by biologically inspired intelligence that is integrated into edge infrastructures. It is necessary to mention that such keywords as bio-inspired computing, Edge computing, Smart grids, Swarm intelligence, and Energy optimization are also available.