Integrating Deep Reinforcement Learning with NDN Simulators

Named Data Networking (NDN) is a transformative paradigm for future Internet architectures, shifting from traditional host-centric models to content-centric networking that prioritizes efficient data retrieval. As NDN evolves, optimizing its core operations, such as forwarding, security, and congestion control, becomes crucial. Deep Reinforcement Learning (DRL) has shown significant potential in addressing these challenges by enabling adaptive and intelligent decision-making. While previous studies have explored DRL integration within NDN simulators, further investigation is needed to assess its practical impact. This paper examines the application of DRL in the ndnSIM simulation environment, leveraging its learning capabilities to enhance forwarding efficiency. Experimental results indicate promising performance, reinforcing the feasibility of using DRL to optimize NDN forwarding strategies and improve overall network efficiency.