Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64252
Volume:
10 |
5 |
May 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science and Engineering
Ashokrao Mane Group of Institutions
Department of Computer Science and Engineering
Ashokrao Mane Group of Institutions
Department of Computer Science and Engineering
Ashokrao Mane Group of Institutions
Department of Computer Science and Engineering
Ashokrao Mane Group of Institutions
Department of Computer Science and Engineering
Ashokrao Mane Group of Institutions
Department of Computer Science and Engineering
Ashokrao Mane Group of Institutions
The rapid growth of cloud computing, IoT devices, and large-scale internet services has increased the demand for efficient network traffic management techniques. Traditional networking approaches suffer from static configurations and inefficient resource utilization under dynamic traffic conditions. To overcome these limitations, this project proposes an Artificial Intelligence-Based Load Balancer using Software Defined Networking (SDN). The system integrates machine learning techniques with SDN architecture to intelligently distribute network traffic across multiple servers or network paths. The proposed framework improves network performance, minimizes congestion, reduces latency, and enhances resource utilization through centralized and programmable traffic control.
KEYWORDS
The proposed AI-based SDN Load Balancer provides an intelligent and adaptive solution for modern network traffic management. By integrating Software Defined Networking with Artificial Intelligence techniques such as TFT-based traffic prediction and DQN-based routing, the system efficiently distributes network traffic and reduces congestion. The implementation using Mininet, OpenFlow, and the Ryu Controller demonstrates improved throughput, reduced delay, lower packet loss, and better resource utilization compared to traditional load balancing methods. The real-time monitoring dashboard further enhances network visibility and management, making the proposed system suitable for next-generation cloud, IoT, and data center networks.
1. IBM Think, "What Is Software-Defined Networking (SDN)?", https://www.ibm.com/think/topics/sdn 2. Open Networking Foundation, "OpenFlow Switch Specification Version 1.3.0", https://www.cs.yale.edu/homes/yu-minlan/teach/csci599-fall12/papers/openflow-spec-v1.3.0.pdf 3. Ryu SDN Framework, https://ryu-sdn.org/ 4. Mininet Overview, https://mininet.org/overview/ 5. PyTorch Tutorials, "Saving and Loading Models", https://docs.pytorch.org/tutorials/beginner/saving_loading_ models.html 6. PyTorch Tutorials, "Save and Load the Model",https://docs.pytorch.org/tutorials/beginner/basics/saveloadr un_tutorial.html 7. Flask Documentation, "Blueprints and Views",https://flask.palletsprojects.com/en/stable/tutorial/views/ 8. Chart.js Documentation, "Line Chart" and "Bar Chart",https://www.chartjs.org/docs/latest/charts/line.html and https://www.chartjs.org/docs/latest/charts/bar.html 9. Lim, Arik, Loeff, Pfister, "Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting", https://arxiv.org/abs/1912.09363 10. Mnih et al., "Human-level control through deep reinforcement learning", Nature, https://www.nature.com/articles/nature14236 11. Faezi and Shirmarz, "A Comprehensive Survey on Machine Learning using in Software Defined Networks (SDN)", https://link.springer.com/article/10.1007/s44230-023-00025-3
Publication Date
5/29/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...