An Incremental Learning Based Edge Caching System: From Modeling to Evaluation

Abstract

Caches are widely applied to improve data delivery performance in distributed systems like edge networks and content delivery networks (CDNs). We consider caching mechanism in those networks that deliver contents to end users. The challenge comes from the dynamic content distribution problem. The distribution of data popularity is highly skewed and changing over time. Besides, the access pattern of the user requests also varies over time. Some learning algorithms for edge caching problems need to rebuild a new model periodically to adapt to system dynamics, where the knowledge learned from the past is discarded. Besides, each model updating needs a large amount of data, leading to outdated models for consecutive user requests. Inspired by the success of incremental learning approaches in processing massive data in real time, we propose an incremental learning based framework at an edge caching server. The incremental learning algorithm is used to preserve valuable knowledge and to adapt to dynamic workloads faster. We implement our incremental learning based cache system prototype and evaluate its performance under various real-world workloads. The experimental results show that our algorithm can boost cache hit ratio for dynamic workloads compared with the state-of-the-art caching algorithms. INDEX TERMS Edge caching, incremental learning, system dynamics.

RevOPT: An LSTM-based Efficient Caching Strategy for CDN

“…Their proposal aims to provide an efficient caching scheme and at the same time to preserve the users' privacy by avoiding the centralization of their data for training purposes thanks to the use of the Federated Learning (FL) approach. In [17], Xu et al present an incremental learning-based framework for data caching in edge networks and CDNs. In their proposal and instead of rebuilding a new caching model each time the system dynamics are changed, the valuable knowledge gathered from the previous models are preserved and the same model is incrementally improved to adapt faster and efficiently to the dynamic workloads.…”