Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

How to Cache Important Contents for Multi-modal Service in Dynamic Networks: A DRL-based Caching Scheme

Zhe Zhang, Marc St-Hilaire, Xin Wei, Haiwei Dong, Abdulmotaleb El Saddik

TL;DR

A content importance-based caching scheme which consists of a content importance evaluation model and a caching model that can adaptively evaluate contents' importance in dynamic networks is proposed.

Abstract

With the continuous evolution of networking technologies, multi-modal services that involve video, audio, and haptic contents are expected to become the dominant multimedia service in the near future. Edge caching is a key technology that can significantly reduce network load and content transmission latency, which is critical for the delivery of multi-modal contents. However, existing caching approaches only rely on a limited number of factors, e.g., popularity, to evaluate their importance for caching, which is inefficient for caching multi-modal contents, especially in dynamic network environments. To overcome this issue, we propose a content importance-based caching scheme which consists of a content importance evaluation model and a caching model. By leveraging dueling double deep Q networks (D3QN) model, the content importance evaluation model can adaptively evaluate contents' importance in dynamic networks. Based on the evaluated contents' importance, the caching model can easily cache and evict proper contents to improve caching efficiency. The simulation results show that the proposed content importance-based caching scheme outperforms existing caching schemes in terms of caching hit ratio (at least 15% higher), reduced network load (up to 22% reduction), average number of hops (up to 27% lower), and unsatisfied requests ratio (more than 47% reduction).

How to Cache Important Contents for Multi-modal Service in Dynamic Networks: A DRL-based Caching Scheme

TL;DR

A content importance-based caching scheme which consists of a content importance evaluation model and a caching model that can adaptively evaluate contents' importance in dynamic networks is proposed.

Abstract

With the continuous evolution of networking technologies, multi-modal services that involve video, audio, and haptic contents are expected to become the dominant multimedia service in the near future. Edge caching is a key technology that can significantly reduce network load and content transmission latency, which is critical for the delivery of multi-modal contents. However, existing caching approaches only rely on a limited number of factors, e.g., popularity, to evaluate their importance for caching, which is inefficient for caching multi-modal contents, especially in dynamic network environments. To overcome this issue, we propose a content importance-based caching scheme which consists of a content importance evaluation model and a caching model. By leveraging dueling double deep Q networks (D3QN) model, the content importance evaluation model can adaptively evaluate contents' importance in dynamic networks. Based on the evaluated contents' importance, the caching model can easily cache and evict proper contents to improve caching efficiency. The simulation results show that the proposed content importance-based caching scheme outperforms existing caching schemes in terms of caching hit ratio (at least 15% higher), reduced network load (up to 22% reduction), average number of hops (up to 27% lower), and unsatisfied requests ratio (more than 47% reduction).
Paper Structure (30 sections, 12 equations, 8 figures, 3 tables, 1 algorithm)

This paper contains 30 sections, 12 equations, 8 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Video Content Caching Schemes
  4. Haptic Content Caching Schemes
  5. Multi-modal Content Caching Schemes
  6. AI-based Caching Schemes
  7. Shortcomings of Existing Works
  8. System Model
  9. Network Model
  10. User Request Model
  11. Content Importance Model
  12. Caching Model
  13. Proposed DRL-based Caching Scheme
  14. Content Importance Evaluation Model
  15. Problem Formulation
  16. ...and 15 more sections

Figures (8)

  • Figure 1: Network model (end users retrieve multi-modal contents from multi-modal service providers through the networks, an SDN controller is implemented in the edge networks to manage and monitor the networks)
  • Figure 2: Framework of the proposed DRL-based caching scheme
  • Figure 3: Pattern of user requests
  • Figure 4: Impact of cache size of edge nodes on average number of hops
  • Figure 5: Impact of cache size of edge nodes on hit ratio
  • ...and 3 more figures