A Secure and Cached-Enabled NDN Forwarding Plane Based on Programmable Switches

Abstract

Recently, the rapid development of software-defined networking (SDN) and programming protocol-independent packet processors (P4) provides a potential possibility for the deployment of Named Data Networking (NDN), which has aroused tremendous attention in academia. Existing P4-based NDN solutions mainly focus on how to describe the stateful forwarding characteristics of NDN in a programmable switch environment. However, the existing solutions still face many challenges such as cache availability and data confidentiality and do not support retransmission of interest packets and multicast forwarding of data packets. In this paper, we propose a new NDN forwarding plane based on programmable switches to address the above challenges. We design a decoupled cache module to avoid a large impact on the data plane forwarding performance when the cache function is enabled. Also, we enhance the design of the existing P4-based NDN forwarding plane to support interest retransmission and multicast forwarding of data packets. In addition, with the advantage of network programmability of P4 technology, we extend the content permutation algorithm and integrate it into the NDN forwarding plane, which makes our scheme support lightweight secure forwarding. Finally, we evaluate our scheme in the prototype system and conduct comparative experiments with representative schemes. Experiment results show that our scheme outperforms it in terms of content retrieval latency and received throughput and can support lightweight secure forwarding with low cost.

Controller-driven vector autoregression model for predicting content popularity in programmable named data networking devices

“…In recent work ( Dudeja et al, 2022 ; Liu et al, 2022 ), an SDN-based secure content caching and forwarding approach was introduced. Routers maintain an index table in their cache memory with unique signatures for data.…”

“…However, the rigidity of fixed popularity threshold values may lead to an escalation in inter-exchange traffic ( Suksomboon et al, 2013 ; Bernardini, Silverston & Festor, 2013 ; Nguyen et al, 2019 ). Subsequently, specific popularity-aware caching approaches incorporate popularity and freshness metrics as decision factors ( Ong et al, 2014 ; Dudeja et al, 2022 ; Liu et al, 2022 ; Gupta et al, 2023 ). Unfortunately, they achieve suboptimal performance in maximizing cache hit rates because their caching decisions are primarily based on request rates, regardless of the network’s topological characteristics.…”