A Hybrid Metaheuristic Approach for Multi-Objective Load Balancing in Digital Twin-Enabled Cloud Environment

The rapid growth of digital twin services is pushing computational resources requirements to unprecedented levels. While cloud computing provides the scalable infrastructure needed to support these computational demands. However, the critical challenge lies in intelligently distributing workloads across distributed cloud environments through advanced load balancing techniques, where traditional deterministic approaches struggle to find optimal solutions within polynomial time. Therefore, addressing such challenges this paper proposes an efficient service placement approach based on Modified Cuckoo Search Optimization called CSOT-PM to optimize dynamic resource allocation in cloud computing which supporting digital twin services. The proposed work is benchmarked against established algorithms like the Genetic Algorithm (GA) and Ant Colony Optimization (ACO), using performance metrics such as makespan time, resource utilization, energy consumption, and Service Level Agreement (SLA) violations. The proposed algorithm achieves a 30% reduction in energy consumption and an 11% improvement in SLA.