Container Caching Optimization based on Explainable Deep Reinforcement Learning
Publication Date
1-1-2023
Document Type
Conference Proceeding
Publication Title
Proceedings - IEEE Global Communications Conference, GLOBECOM
DOI
10.1109/GLOBECOM54140.2023.10437757
First Page
7127
Last Page
7132
Abstract
Serverless edge computing environments use lightweight containers to run different services on a need basis. Container caching at edge nodes is an effective strategy to further reduce the startup latency related to the preparation of container images. However, the capacity limitation of the edge nodes requires an efficient caching strategy that can capture underlying service request patterns. Hence, this paper proposes an EXplainable Reinforcement Learning (XRL)-based container caching strategy to increase the hit rate of cached containers. While a few studies already proposed RL-based caching algorithms, our proposal focuses more on the explainability part of the caching decisions based on a causal graph. The generated explanations from our approach can indicate which caching actions specifically contribute to the increase in the hit rate, which implies the underlying request patterns. Our experiments in a simple network topology demonstrate the validity of the generated explanations.
Keywords
container caching, explainable reinforcement learning, serverless edge computing
Department
Computer Science
Recommended Citation
Divyashree Jayaram, Saad Jeelani, and Genya Ishigaki. "Container Caching Optimization based on Explainable Deep Reinforcement Learning" Proceedings - IEEE Global Communications Conference, GLOBECOM (2023): 7127-7132. https://doi.org/10.1109/GLOBECOM54140.2023.10437757
