ALCoD: An Adaptive Load-Aware Approach to Load Balancing for Containers in IoT Edge Computing
Dignde Jiang, Bowen Zhu, Xinhui Liu, Shahid Mumtaz
Abstract
Container technologies promise efficient deployment of distributed services, but their potential is hampered by suboptimal resource utilization and network congestion stemming from initial placement decisions made without knowledge of future demands. Existing container cluster management strategies lack robust adaptive capabilities to efficiently balance load as workloads evolve unpredictably over time. This article puts forth the Adaptive Load-aware Container Deployment (ALCoD), a novel container cluster management approach integrating worst fit decreasing heuristic placement with deep Reinforcement Learning (RL)-based migration optimization. ALCoD adapts to fluctuating resource availability and service demands by leveraging the complementary strengths of each technique. The worst fit decreasing approach allows rapid initial cluster deployment when resources are abundantly available, while the deep RL policy orchestrates intelligent container migrations to optimize load balancing during times of resource scarcity, maintaining service availability throughout. Comprehensive evaluations verified that compared to state-of-the-art strategies, ALCoD reduces system response times by 29.19%, improves load balancing by 51.31%, and decreases bandwidth usage by 27.4% under real-world conditions. Beyond these raw performance improvements, ALCoD demonstrates the potential of hybrid algorithms that blend complementary techniques to match the intrinsic dynamics of container clusters. This pioneering approach establishes a solid foundation for realizing the full promise of containerized services through reliable, responsive delivery even as operating conditions continuously evolve.