Collaborative Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud Network

• Published in: IEEE/ACM transactions on networking Vol. 31; no. 6; pp. 1 - 15
• Main Authors: Shen, Shihao, Han, Yiwen, Wang, Xiaofei, Wang, Shiqiang, Leung, Victor C. M.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cloud computing; Clustering algorithms; Computational modeling; Dynamic scheduling; Edge computing; Graph neural networks; Heuristic algorithms; IEEE transactions; kubernetes; Learning; Multiagent systems; reinforcement learning; Scheduling; scheduling algorithms; Throughput
• ISSN: 1063-6692; 1558-2566
• DOI: 10.1109/TNET.2023.3267168

Kubernetes ( k8s ) has the potential to coordinate distributed edge resources and centralized cloud resources, but currently lacks a specialized scheduling framework for edge-cloud networks. Besides, the hierarchical distribution of heterogeneous resources makes the modeling and scheduling of k8s -oriented edge-cloud network particularly challenging. In this paper, we introduce KaiS , a learning-based scheduling framework for such edge-cloud network to improve the long-term throughput rate of request processing. First, we design a coordinated multi-agent actor-critic algorithm to cater to decentralized request dispatch and dynamic dispatch spaces within the edge cluster. Second, for diverse system scales and structures, we use graph neural networks to embed system state information, and combine the embedding results with multiple policy networks to reduce the orchestration dimensionality by stepwise scheduling. Finally, we adopt a two-time-scale scheduling mechanism to harmonize request dispatch and service orchestration, and present the implementation design of deploying the above algorithms compatible with native k8s components. Experiments using real workload traces show that KaiS can successfully learn appropriate scheduling policies, irrespective of request arrival patterns and system scales. Moreover, KaiS can enhance the average system throughput rate by <inline-formula> <tex-math notation="LaTeX">15.9\%</tex-math> </inline-formula> while reducing scheduling cost by <inline-formula> <tex-math notation="LaTeX">38.4\%</tex-math> </inline-formula> compared to baselines.