A Hierarchical Multi-Agent Reinforcement Learning With a Heterogeneous Metaheuristic Aware Resource Allocation in Big Data-Cloud

Abstract

The rapid advancement of technology like Internet of Things (IoT) and Cloud computing (CC)based heterogeneous environment required dynamic resource management system. Thecomplexity of IoT-Cloud is increasing due to abundance of dynamic data dissemination thatcreate poor performance like high energy consumption (EC), workload imbalancing, pooradaptability, and fail to handle SLA violations. The two primary contributions of the proposedwork are the Optimized Priority-Aware Hierarchical Multi-Agent Deep Q Network (OPHMDQN)and the Adaptive Multi-Objective Dung Beetle Optimization Algorithm (ADBOA). Themulti-agent strategies increase the scalability and adaptability of resource managementthrough local and global hierarchies. The approach integrates information-based decisionmakingand priority-aware allocation while accounting for SLA requirements, systemconstraints, and job complexity to optimise resource generation, utilisation, allocation, andtask scheduling. In comparison to existing optimization and Reinforcement Learning (RL)techniques, experimental results show that the proposed OPHM-DQN-ADBOA frameworkconsistently reduces EC (up to 30 % lower), execution delay, and SLA violations whileimproving resource utilisation and LB. The ADBOA enhances the proposed model throughoptimal multi-objective training, reducing EC, SLA violation, and cost while improvingresource utilization and scheduling efficiency. As a results, the model achieves high scalabilityand adaptability in heterogeneous IoT-Cloud resource management.