Intelligent Task Scheduling and Energy Optimization in Multi-Cloud Environments Using Hybrid Metaheuristic Algorithms

Abstract

The rapid growth of cloud computing technologies, distributed data centers, Internet of Things (IoT) infrastructures, artificial intelligence applications, and large-scale enterprise services has significantly increased the complexity of resource management and task scheduling in multi-cloud environments. Modern cloud ecosystems frequently consist of heterogeneous computational infrastructures distributed across multiple public, private, and hybrid cloud platforms. These environments continuously process massive computational workloads requiring efficient task allocation, adaptive resource utilization, energy-aware optimization, and latency-sensitive scheduling. Traditional cloud scheduling techniques often struggle to optimize computational performance and energy efficiency simultaneously because of dynamic workloads, heterogeneous infrastructure configurations, communication overhead, and varying service-level requirements. As energy consumption and operational costs continue to increase in large-scale cloud systems, intelligent scheduling and energy-efficient optimization have become critical research challenges in next-generation distributed cloud computing environments. This research proposes an Intelligent Task Scheduling and Energy Optimization Framework in Multi-Cloud Environments Using Hybrid Metaheuristic Algorithms. The proposed framework integrates hybrid metaheuristic optimization techniques, deep reinforcement learning, adaptive workload balancing, graph neural resource coordination, and predictive cloud analytics to support scalable and energy-aware multi-cloud intelligence.