A Survey on Artificial Intelligence Techniques for Improved Rich Media Content Delivery in a 5G and Beyond Network Slicing Context
Fazal E Subhan, Abid Yaqoob, Cristina Hava Muntean, Gabriel‐Miro Muntean
Abstract
Network slicing is an emerging paradigm driven by an objective to provide support for personalized services in the highly evolving and dynamic 5G and beyond network environment. The management of network functions and resources under network slicing architecture for rich media content delivery is a challenging task that requires an efficient decision at all network levels to maintain the required Quality of Service (QoS) and Quality of Experience (QoE). Integrating Artificial Intelligence (AI) in the network slice architecture for taking efficient network decision is one of the potential solutions to the problem. In this paper, we summarize the network slicing enabling technologies such as Software Defined Network (SDN), Network Function Virtualization (NFV), Multi-access Edge Computing (MEC) in the context of AI for improving the rich media content delivery. In addition, we present a comprehensive survey on content-centric networking and delivery solutions based on network slicing technologies i.e., MPEG-DASH-enabled Information Centric Networking (ICN) and Content Delivery Network (CDN) for intelligent rich media content caching and prefetching, predictive analysis, content preference optimization, secure resource allocation, and dynamic traffic steering. Several standardization and orchestration mechanisms of 5G network slicing proposed by 3GPP are then presented. Finally, the challenges of AI-enabled 5G network slicing for immersive content delivery are outlined with potential solutions and future research opportunities.