Dynamic Load Balancing in SDN Using Machine Learning

DOI

10.2991/978-94-6239-674-6_18How to use a DOI?

Keywords

Software-Defined Networking; Dynamic Load Balancing; Traffic Optimization; Network Congestion Control

Abstract

SDN is a centralized traffic management model with the separation between the control and data planes. Dynamic traffic undermines the conventional load-balancing methods and this brings congestion and underutilization of available bands. This paper provides an outline of a framework that uses the power of Machine Learning (ML) to forecast a congestion problem, as well as maximizing resource utilization. Compared to the reactive methods, the ML model evaluates the past and actual traffic statistics to discover trends and preset routing. It enhances throughput, reduces latency and its allocation effectively resources within the network. Actually, the assessment outcomes demonstrate 20 percent achievement of throughput, 15 percent decrease in latency and 30 percent dropped packets as compared to the traditional methods. These are accompanied by difficulties, such as computing costs and security threats. The future work is thus on reinforcement learning to solve autonomous traffic engineering and maximizing the ML inference in real-time. As cloud computing, IoT, and 5G ecosystems have to scale under any conditions, irrespective of their complexities, the work is one of the steps to develop AI-based networking.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sonam Sharma
AU  - Gagandeep Singh
AU  - Shubham Kumar
PY  - 2026
DA  - 2026/05/28
TI  - Dynamic Load Balancing in SDN Using Machine Learning
BT  - Proceedings of the International Conference on Sustainable Computing and Artificial Intelligence (ICSCAI 2025)
PB  - Atlantis Press
SP  - 207
EP  - 218
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-674-6_18
DO  - 10.2991/978-94-6239-674-6_18
ID  - Sharma2026
ER  -