Deep Reinforcement Learning-Based Content Migration for Edge Content Delivery Networks With Vehicular Nodes

Abstract

With the explosive demands for data, content delivery networks are facing ever-increasing challenges to meet end-users' quality-of-experience requirements, especially in terms of delay. Content can be migrated from surrogate servers to local caches closer to end-users to address delay challenges. Unfortunately, these local caches have limited capacities, and when they are fully occupied, it may sometimes be necessary to remove their lower-priority content to accommodate higher-priority content. At other times, it may be necessary to return previously removed content to local caches. Downloading this content from surrogate servers is costly from the perspective of network usage, and potentially detrimental to the end-user QoE in terms of delay. In this paper, we consider an edge content delivery network with vehicular nodes and propose a content migration strategy in which local caches offload their contents to neighboring edge caches whenever feasible, instead of removing their contents when they are fully occupied. This process ensures that more contents remain in the vicinity of end-users. However, selecting which contents to migrate and to which neighboring cache to migrate is a complicated problem. This paper proposes a deep reinforcement learning approach to minimize the cost. Our simulation scenarios realized up to a 70% reduction of content access delay cost compared to conventional strategies with and without content migration.

Deep Learning for Video Application in Cooperative Vehicle-Infrastructure System: A Comprehensive Survey

“…Malektaji et al [76] considered an edge content delivery network with ve and proposed using the DDQN model to solve the problem of content mig DQN model defined the state space as the priority information of the cont delivery status of the content, the actions are defined as migrating, caching a content and the reward is defined as the access delay. This model reduces co latency by 70% compared with traditional policies.…”

A Distributed Real-Time Transcoding CDN System Design and Performance Simulation Study

“…Paper [12] built a new framework based on Cloud Content Delivery Networks (CCDNs) to capture the dynamic characteristics and quantifies the node transmission efficiency. Malektaji et al proposed a deep reinforcement learning (DRL) content migration technique for a hierarchical edge-based CDN [13].…”

Proactive Network Fault Management for Reliable Subscribed Network Slicing in Software-Defined Mobile Data IoT Services

“…DQN approaches have been comprehensively intentioned in the mobility network resource allocation, offloading, and E2E network MANO [17][18][19]. DRL provides the ability to adapt to natural network environments to train the agents to handle network issues [19][20][21][22].…”