Congestion avoidance by dynamically cache placement method in named data networking.

In recent years, a new paradigm of Content-Centric Networks has emerged, which employs the prefix content name for addressing in the context of Named Data Networking (NDN). In conventional networks, subscribers send interest packets, and publishers generate related content and publish it to the requesters. In NDN, Caching Routers (CRs), as well as publishers, can also propagate data packets toward the requesters. The NDN network flow has two opposite sides: (1) the interest packet flow, known as interest forwarding on the upstream side, (2) the content flow, known as data publishing, on the downstream side. High traffic volume can be created by the increasing number of requested packets and associated data that are leading to bottlenecks in some parts of the networks. Therefore, congestion control and avoidance are significant issues in NDN. A considerable number of congestion control methods employ forwarding interest rate adjustment coming through the forwarding side. Nevertheless, the congestion can be prevented on the data publishing side using an efficient cache placement method. Congestion avoidance is a process for controlling congestion and balancing traffic loads to make the network effective. In this paper, a Dynamic Cache Placement (DCP) method is proposed to provide congestion avoidance by dynamically relocating the content of the CRs according to the traffic volume pattern and the link capacity. The DCP method distributes the popular data to the network regions with less traffic load and more accessible routers to balance the congested routers' traffic load. The DCP is implemented in the ndnSIM network simulator, and its performance is compared to the conventional method. Simulation results show that DCP is a fair and robust cache placement design, which successfully avoids congestion inflows with highly varying traffic demand. The proposed techniques employed in the DCP method improve the network performance in dynamic circumstances of the network. [ABSTRACT FROM AUTHOR]