Effective Load Balancing is essential for maintaining performance and resource efficiency in cloud computing. This paper addresses the limitations of traditional methods like Round Robin (RR), which lack adaptability and fail under heterogeneous workloads. This study proposes Ant Colony Optimization (ACO) - based load balancing algorithm inspired by the foraging behavior of ants, where artificial agents dynamically distribute tasks using virtual pheromone trails. ACO optimized load balancing approach was benchmarked against Round Robin under varying virtual machine (VM) counts, RAM sizes, and cloudlet lengths. Experimental results show that the ACO algorithm improves performance significantly, achieving up to 118% higher request handling (RPS) and a 57% reduction in execution time compared to Round Robin using CloudSim. These improvements demonstrate ACO adaptability, scalability, and efficiency in managing dynamic cloud workloads. The study findings offer a promising direction for intelligent, bio-inspired balancing strategies in cloud infrastructures.