QHRMOF: A Quantum-Inspired hybrid Multi-Objective framework for Energy-Efficient task scheduling and load balancing in cloud computing

The swift expansion of cloud computing services has resulted in a notable increase in energy consumption, presenting challenges for sustainability and effective resource management in cloud data centres. This paper introduces a novel Quantum-Inspired Hybrid Reinforcement Learning and Multi-Objective Optimization Framework (QHRMOF) designed to optimize task scheduling, dynamic load balancing, and server consolidation while minimizing power consumption and enhancing system performance. QHRMOF integrates three fundamental techniques: Quantum-Inspired Evolutionary Algorithm (QIEA) employs quantum principles like superposition and entanglement to improve solution space exploration and mitigate local optima; Hybrid Deep Reinforcement Learning (HDRL) integrates convolutional neural networks (CNNs) and Long Short-Term Memory (LSTM) to forecast workloads and dynamically categorize virtual machines (VMs) into overloaded and underloaded states for efficient task migration and load balancing; and Multi-Objective Optimisation (MOO) reconciles multiple conflicting objectives, including minimizing energy consumption and makespan while maximizing resource utilization and system scalability. QHRMOF minimizes unnecessary migrations and overhead through informed decision-making and adaptive resource management, all while maintaining optimal system performance. Simulations performed on the CloudSim platform utilizing real-world datasets, including those from NASA, HPC2N, and Google workloads, indicate that the proposed framework surpasses leading methodologies such as Multi-objective Genetic Algorithm (MOGA), Particle Swarm Optimization (PSO), Deep Reinforcement Learning for Load Balancing (DRL-LB), and Ant Colony Optimization (ACO). The findings indicate that QHRMOF attains a maximum reduction of 18.76% in makespan, a 22.84% decrease in energy consumption, a 19.52% enhancement in resource utilization, a 25.39% improvement in load balancing efficiency, and a 12.67% reduction in failure rates. These findings confirm the efficacy of QHRMOF in enhancing resource management, augmenting system reliability, and fostering energy-efficient cloud computing operations.