Energy-Efficient Task Scheduling in Cloud Computing with EcoTaskOpt: A Hybrid Ant Colony and Particle Swarm Optimization Approach

Intelligent scheduling of heterogeneous cloud computing systems is the key to energy efficiency, optimal performance and cost and environmental impact reduction. In this paper, a novel ant colony inspired cooperative foraging behavior based meta-heuristic optimization framework named EcoTaskOpt is proposed for the efficient task scheduling among the heterogeneous cloud resources. EcoTaskOpt combines Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) algorithm in a hybrid model, where the updates of pheromone information and particle velocity are dynamically adjusted to achieve the optimization of task to resource mappings with the balance between exploration and exploitation in complex scheduling scenarios. For evaluation, a benchmark data set is created using CloudSim, including real-time Google Cluster traces, synthetic task graphs with different levels of computational complexity, server power profile and thermal dynamics related to workload intensity. Simulation results show that compared with the conventional heuristics, deep reinforcement learning and hybrid evolutionary algorithms, EcoTaskOpt reduces energy consumption by up to 42%, reduces makespan by up to 18%, improves resource utilization by up to 21%. It also has good performance under different load conditions, which is robust, scalable, and adaptive. The main contributions of this work are: (1) hybrid ACO-PSO algorithm for energy- and thermal-aware task scheduling (2) realistic evaluation using diverse cloud workloads & server dynamics and (3) empirical validation for the achieved massive energy efficiency & performance improvements and a sustainable solution for modern cloud computing.