Improving performance of content-centric networks via decentralized coded caching for multi-level popularity and access

Abstract

Content-Centric Networking (CCN) offers a novel architectural paradigm that seeks to address the inherent limitations of the prevailing Internet Protocol (IP)-based networking model. In contrast to the host-centric communication approach of IP networks, CCN prioritizes content by enabling direct addressing and routing based on content identifiers. The potential performance improvements of CCN can be further amplified through optimized management of coded data storage and transmission strategies. Decentralized Coded Caching (DCC) emerges as a promising technique that harnesses the collective caching power of distributed network elements. By strategically pre-positioning frequently accessed content closer to potential consumers during periods of low network utilization, DCC has the potential to mitigate content transfer rates during peak traffic periods. This paper proposes a series of fundamental modifications to the CCN architecture by integrating DCC. The proposed framework incorporates differentiated coding strategies tailored to user access privileges, thereby eliminating the overhead associated with queue-based searching. Additionally, the framework facilitates recoding of uncoded data encountered along the content delivery path. These combined methodologies demonstrably enhance network throughput, elevate cache hit ratios, and consequently, reduce content delivery latency compared to conventional CCN implementations.