Efficient Routing for Software-Defined Wireless Sensor Networks: A Naïve Bayes Approach

Document Type

Article

Source of Publication

IEEE Access

Publication Date

12-3-2025

Abstract

Wireless Sensor Networks (WSNs) form the backbone of Internet of Things (IoT) applications. Software-Defined Networking (SDN) is an emerging networking paradigm that extends the lifetime of WSNs by transferring the resource-intensive routing task from sensor nodes to a centralized controller. However, many SDN-based routing schemes for WSNs employ inefficient algorithms at the controller. Traditional shortest-path methods often create traffic imbalances across neighboring nodes, while Reinforcement Learning (RL)-based approaches typically generate excessive control traffic. Both issues accelerate energy depletion and reduce network lifetime. Moreover, existing algorithms frequently overlook critical factors, such as buffer occupancy, when selecting relay nodes, which can lead to congestion, packet loss, and increased latency. To address these limitations, this paper proposes NBSDN, a Naïve Bayes–based routing algorithm for SDN-enabled WSNs. NBSDN extends our earlier energy- and distance-aware solution (referred to as NB-SDWSN) by incorporating link quality and node buffer capacity into the routing decision process. The controller periodically rotates relay node assignments among neighboring nodes based on their residual energy, distance to the sink, link quality, and buffer occupancy, thereby balancing load and preventing congestion. Extensive simulations conducted in the COOJA environment demonstrate that NBSDN significantly outperforms benchmark algorithms—including the Dijkstra-based Shortest Path SDN (SPSDN), Energy-Aware SDN (EASDN), NB-SDWSN, and RL-based SDN (RLSDN) routing—in terms of network lifetime, control overhead, packet loss, latency, and throughput.

ISSN

2169-3536

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Volume

13

First Page

207277

Last Page

207302

Disciplines

Computer Sciences

Keywords

congestion avoidance, COOJA simulator, IoT, load balancing, Naïve Bayes algorithm, performance analysis, SDN, WSNs

Scopus ID

105023910290

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Indexed in Scopus

yes

Open Access

yes

Open Access Type

Gold: This publication is openly available in an open access journal/series

This document is currently not available here.

Share

COinS