Optimizing Container Caching in Serverless Edge Computing with Scalable Reinforcement Learning
Publication Date
3-9-2026
Document Type
Conference Proceeding
Publication Title
2026 International Conference on Computing Networking and Communications Icnc 2026
DOI
10.1109/ICNC68183.2026.11416936
First Page
37
Last Page
41
Abstract
Serverless edge computing realizes low latency and resource-efficient function calls for responsive computing. In cloud-based serverless computing, it is a common practice to cache sufficiently many function containers for future reuse to reduce the overhead of container initiation. In contrast, the capacity limitation of edge nodes poses a complex problem of cache selection in serverless edge computing. In this paper, we propose a scalable container caching agent based on Deep Reinforcement Learning (DRL) to improve the training efficiency and caching performance under dynamic request arrivals. We propose to apply action masking, which eliminates inauspicious caching actions from the DRL exploration and concentrates computing resources on more promising actions, to achieve scalability. Our proposal is evaluated through comparative analysis in simulations with both real and synthetic datasets in terms of the latency and cache efficiency. Our results suggest that DRL with action masking can efficiently solve the combinatorial optimization of container caching.
Keywords
Container Caching, Deep Reinforcement Learning, Scalable Learning, Serverless Edge Computing
Department
Computer Science
Recommended Citation
Manikanta Sanjay Veera, Faiz Sameer Ahmed, and Genya Ishigaki. "Optimizing Container Caching in Serverless Edge Computing with Scalable Reinforcement Learning" 2026 International Conference on Computing Networking and Communications Icnc 2026 (2026): 37-41. https://doi.org/10.1109/ICNC68183.2026.11416936
