DQN-AF: Deep Q-Network based Adaptive Forwarding Strategy for Named Data Networking

TL;DR

This paper introduces a deep reinforcement learning-based adaptive forwarding strategy for Named Data Networking, improving performance by analyzing router metrics without signaling overhead or violating architecture principles.

Contribution

It presents a novel Deep Q-Network approach for adaptive forwarding in NDN, addressing limitations of standard strategies and enhancing network performance.

Findings

Significant performance improvements over standard strategies

No additional signaling overhead introduced

Effective adaptation to diverse communication scenarios

Abstract

NDN has gained significant attention due to the appearance of several unforeseen design flaws that became evident with new communication scenarios. Among its many features, the two standard NDN forwarding strategies are not adaptive, causing performance degradation in several scenarios. This paper proposes an adaptive forwarding strategy based on deep reinforcement learning with Deep Q-Network, which analyzes the NDN router interface metrics without creating signaling overhead or harming the design principles from the NDN architecture, besides showing significant performance gains compared to the standard strategies.