Dynamic Mirror Placement for Reducing Inter-AS Traffic in NDN
Xuheng Cao, Noriaki Kamiyama · 2024
With the widespread adoption of social networking services (SNS) and streaming, the volume of traffic on the Internet has seen a rapid increase. Traditionally, to ensure the delivery of high-quality network services, mitigation strategies such as Content Delivery Networks (CDNs) have been proposed. How-ever, the underlying TCP/IP focuses on packet transfer based on the content's delivery source, the host, which may not be crucial content for users. In response to this, Named Data Networking (NDN) has been introduced as a new network architecture to efficiently deliver content. NDN incorporates features to deliver content from caches within the network. Nevertheless, a challenge persists when the content cache is not available nearby, requiring content retrieval from a distant location. Therefore, this paper proposes a method aiming to reduce inter-autonomous system (AS) traffic by dynamically generating copies, i.e., mirrors, of content at its origin. Additionally, to reflect a more realistic scenario, the proposed method is evaluated through computer simulations considering fluctuations in the popularity of real-world content. The numerical results confirm the effectiveness of the proposed approach.