Crossover-BPSO Driven Multi-Agent Technology for Managing Local Energy Systems

TL;DR

This paper introduces a hybrid crossover binary particle swarm optimization algorithm integrated with multi-agent technology to optimize resource allocation in local energy systems, significantly reducing costs and improving service quality.

Contribution

The paper presents a novel hybrid algorithm (crBPSO) combined with a multi-agent architecture for efficient local energy management, outperforming existing methods in cost reduction.

Findings

21% cost reduction compared to existing algorithms

Effective maintenance of energy demand satisfaction

Improved quality of service in local energy systems

Abstract

This article presents a new hybrid algorithm, crossover binary particle swarm optimization (crBPSO), for allocating resources in local energy systems via multi-agent (MA) technology. Initially, a hierarchical MA-based architecture in a grid-connected local energy setup is presented. In this architecture, task specific agents operate in a master-slave manner. Where, the master runs a well-formulated optimization routine aiming at minimizing costs of energy procurement, battery degradation, and load scheduling delay. The slaves update the master on their current status and receive optimal action plans accordingly. Simulation results demonstrate that the proposed algorithm outperforms selected existing ones by 21\% in terms average energy system costs while satisfying customers' energy demand and maintaining the required quality of service.