Container Caching Optimization based on Explainable Deep Reinforcement Learning
Authors:
- 4 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7127-7132
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
This publication has 11 references indexed in Scilit:
- Retention-Aware Container Caching for Serverless Edge Computing2022
- Deep Reinforcement Learning for QoS-Aware Package Caching in Serverless Edge Computing2021
- FaaS and Curious: Performance Implications of Serverless Functions on Edge Computing Platforms2021
- FaasCache: keeping serverless computing alive with greedy-dual caching2021
- A Decentralized Framework for Serverless Edge Computing in the Internet of ThingsIEEE Transactions on Network and Service Management, 2020
- Deep Reinforcement Learning-Based Edge Caching in Wireless NetworksIEEE Transactions on Cognitive Communications and Networking, 2020
- An execution model for serverless functions at the edge2019
- Deep Reinforcement Learning for Mobile Edge Caching: Review, New Features, and Open IssuesIEEE Network, 2018
- Proactive retention aware caching2017
- Human-level control through deep reinforcement learningNature, 2015