article
The integration of Software Defined Networking (SDN) and Network Function Virtualization (NFV) with the Internet of Things (IoT) offers scalable, programmable, and efficient network infrastructures. However, traditional routing mechanisms often fail to adapt to the dynamic and heterogeneous nature of large-scale IoT networks. This paper proposes a Deep Q-Network (DQN)-based routing optimization method within SDN/NFV architectures. Our approach considers real-time metrics including latency, bandwidth, memory availability, and processing load to make adaptive routing decisions. Simulation results on a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{2 0 0}$</tex>-node IoT topology demonstrate significant improvements in Packet Delivery Ratio (PDR), end-to-end latency, and load distribution compared to conventional routing algorithms. The paper also discusses limitations such as training complexity, scalability, and energy consumption, while proposing potential enhancements for future research.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/wincom65874.2025.11313390
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
