Joint Replica Server Placement, Content Caching, and Request Load Assignment in Content Delivery Networks

Abstract

With the explosive growth of information and communication technology and its services, some popular Websites currently generate an enormous amount of Internet traffic. A content delivery network (CDN) would then become imperative for supporting such services efficiently. In this paper, we propose joint optimizing approaches for replica server placement, content caching in selected servers, and content request load assignment among the servers, aiming to minimize the ratio of unserved content request load when the network resources and server capacity are both limited. For this, we develop a mixed integer linear programming (MILP) optimization model. To mitigate the computational complexity of the MILP model, we further decompose the optimization problem into three sub-problems, including: 1) choosing the replica server nodes optimally; 2) deciding the content items to be cached in the replica servers; and 3) allocating the content request loads from users onto different servers. For these sub-problems, we develop corresponding heuristic algorithms and show that the proposed approach is not only efficient but also performs very close to the MILP model. We also find that a number of system limitations, such as different numbers of replica servers placed, link capacity, server processing capacity, and server storage capacity, jointly affect the performance of the CDN. Saturation trends are observed on the performance, which indicate that as long as sufficient resources have already been provided, augmenting the resources further may only lead to marginal additional performance improvement.

Deep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless Networks

“…Usually, to solve the CDN in-network caching problem, routing policy to allocate users' requests to different servers needs to be addressed. Prior work [2], [3] has focused on jointly solving the caching and routing problems to minimize the service delay. Though the application of CDN has been shown to reduce the data traffic, it can hardly handle the growing mobile data traffic because it is inevitable that the content has to be transmitted through the CDN nodes before arriving at the user.…”

Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks

“…Aram et al [16] studied the problem of optimal replica server deployment and content placement in the urban content delivery network and proposed an optimization design to minimize the cost of server deployment. Xu et al [17] proposed a joint optimization method to reduce the request load of content distribution network. However, the above methods need to deploy a large number of edge servers with high cost.…”

A Dynamic Virtual Datacenter Selection Strategy for Integrated Cloud Service Platform Construction With Multiclouds

“…Among them, S. Jamin et al studied the performances of different placement strategies and found that increasing the number of mirror sites was effective in reducing client download time and server load [21]. K. Xu et al proposed joint optimizing approaches for replica server placement, content caching in selected servers, and content request load assignment among the servers to minimize the ratio of unserved content request load when the network resources and server capacity were both limited [22]. X. Yuan et al proposed a server placement model for peer-to-peer (P2P) live streaming systems that considered the Internet service provider friendship and peers' contribution [24].…”

“…Although the methods of these works are different from each other, most of them can be classified into two categories. One formulates the service node placement as a facility location problem with the aim of selecting M service nodes from N potential sites [21], [22], [24]. It passively selects its service nodes from a candidate node pool, constraining its scalability by the candidate node pool.…”