Research on Virtualized Cloud Computing Task Scheduling Based on Improved Ant Colony Algorithm

This study proposes an Improved Ant Colony Optimization (IACO) algorithm for cloud computing resource scheduling and constructs a model targeting minimized task completion time, balanced economic benefits, and load equilibrium. The algorithm introduces an S-shaped function to dynamically adjust transition probabilities, integrating constrained pheromone update, adaptive mechanisms, and elite solution reinforcement strategies to optimize global search capability. MATLAB simulations demonstrate that IACO significantly outperforms the traditional ant colony algorithm in task completion time, economic efficiency, and load balancing, particularly in large-scale resource allocation scenarios, providing an efficient solution for cloud task scheduling.