Skip to main content

Deep Reinforcement Learning Based Autonomous Network Traffic Management and Optimization Framework

Anushree M R

St Joseph Engineering (Autonomous) College, Vamanjoor, Mangalore, India

Abstract

The rapid growth of modern communication technologies such as cloud computing, Internet of Things (IoT), 5G networks, and multimedia applications has significantly increased the complexity of network traffic management. Traditional traffic engineering methods rely on static routing protocols and predefined policies that are unable to efficiently adapt to dynamic network conditions, resulting in congestion, packet loss, and reduced Quality of Service (QoS). This research proposes a Deep Reinforcement Learning (DRL)-based autonomous network traffic management and optimization framework designed to improve network performance through intelligent and adaptive decision-making. The framework integrates Software-Defined Networking (SDN) architecture with DRL algorithms including Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) to optimize routing paths, bandwidth allocation, congestion control, and load balancing in real time. The proposed system continuously learns from network states and traffic patterns using reward-based optimization mechanisms. Simulation experiments are conducted using Mininet, NS-3, and SDN controllers to evaluate throughput, delay, packet loss, and bandwidth utilization. Experimental results demonstrate that the DRL-based framework significantly outperforms traditional traffic management approaches by reducing latency, minimizing congestion, and improving overall network efficiency. The study contributes toward the development of intelligent, scalable, and self-adaptive communication infrastructures for future autonomous networks

Article Information

Journal

International Journal of Emerging Trends in Engineering and Management Research

Volume (Issue)

Vol. 3 No. 1 (2018): International Journal of Emerging Trends in Engineering and Management Research (IJETEMR)

DOI

https://doi.org/10.15662/ijetemr.2018.0301001

Pages

2921-2930

Published

January 11, 2018
Copyright

Open Access

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

How to Cite

Anushree M R (%2018). Deep Reinforcement Learning Based Autonomous Network Traffic Management and Optimization Framework. International Journal of Emerging Trends in Engineering and Management Research , Vol. 3 No. 1 (2018): International Journal of Emerging Trends in Engineering and Management Research (IJETEMR) , pp. 2921-2930. https://doi.org/10.15662/ijetemr.2018.0301001

References

1. El Sallab, A., Abdou, M., Perot, E., & Yogamani, S. (2017). Deep reinforcement learning framework for autonomous driving. Proceedings of the Electronic Imaging Conference on Autonomous Vehicles and Machines, 70–76.
2. Gao, J., Shen, Y., Liu, J., Ito, M., & Shiratori, N. (2017). Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network. arXiv preprint arXiv:1705.02755.
3. Kashihara, K. (2017). Deep Q learning for traffic simulation in autonomous driving at a highway junction. 2017 IEEE International Conference on Systems, Man, and Cybernetics, 984–988.
4. Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.
5. Mousavi, S., Schukat, M., Corcoran, P., & Howley, E. (2017). Traffic light control using deep policy-gradient and value-function based reinforcement learning. IET Intelligent Transport Systems, 11(7), 417–423.
6. Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. MIT Press.
7. Stampa, G., Arias, M., Sanchez-Charles, D., Muntés-Mulero, V., & Cabellos, A. (2017). A deep-reinforcement learning approach for software-defined networking routing optimization. arXiv preprint arXiv:1709.07080.
8. Wu, C., Parvate, K., Kheterpal, N., Dickstein, L., Mehta, A., Vinitsky, E., & Bayen, A. (2017). Framework for control and deep reinforcement learning in traffic. 2017 IEEE 20th International Conference on Intelligent Transportation Systems, 1–8.
9. Wu, C., Kreidieh, A. R., Parvate, K., Vinitsky, E., & Bayen, A. M. (2017). Flow: Architecture and benchmarking for reinforcement learning in traffic control. arXiv preprint arXiv:1710.05465.
10. Yu, C., Lan, J., Guo, Z., & Hu, Y. (2017). DROM: Optimizing the routing in software-defined networks with deep reinforcement learning. IEEE Access, 1–12.
11. He, Y., Yu, F. R., Zhao, N., Yin, H., & Leung, V. C. M. (2017). DRL-based resource management in software-defined and virtualized vehicular ad hoc networks. Proceedings of the 13th International Conference on Wireless Algorithms, Systems, and Applications, 1–6.
12. Mathew, A., & Asari, V. K. (2014, March). Rotation-invariant histogram features for threat object detection on pipeline right-of-way. In Video Surveillance and Transportation Imaging Applications 2014 (Vol. 9026, pp. 19-26). SPIE.
13. Sugumar, R., Rengarajan, A., & Jayakumar, C. (2015). Design a Weight Based Sorting Distortion Algorithm for Privacy Preserving Data Mining. Middle-East Journal of Scientific Research, 23(3), 405-412.
14. Karthika, V., Brijet, Z., & Bharathi, N. (2012). Design of optimal controller for fluid catalytic cracking unit. Procedia Engineering, 38, 1150-1160.
15. Amutha, M., & Sugumar, R. (2015). A survey on dynamic data replication system in cloud computing. International Journal of Innovative Research in Science, Engineering and Technology, 4(4), 1454-1467.
16. Sugumar, R. B., & Anandharaj, K. (2016). Assessment of Bacterial Load in the Fresh Water Lake System of Tamil Nadu. Interl J Curr Microbiol App Sci, 5(6), 236-246.
17. Rengarajan, R. S. A. (2016). Secure verification technique for defending IP spoofing attacks.
18. Mathew, A. R., & Al Hajj, A. (2017). Secure communications on IoT and big data. Indian Journal of Science and Technology, 10(11).
19. Alex, A. T., Asari, V. K., & Mathew, A. (2012, October). Gradient feature matching for expression invariant face recognition using single reference image. In 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC) (pp. 851-856). IEEE.
20. Sasidevi, J., Sugumar, R., & Priya, P. S. (2015). New-Multi-Phase Distribution Network Intrusion Detection. International Journal, 5(3).
21. Mathew, A., & Asari, V. K. (2013, March). Tracking small targets in wide area motion imagery data. In Video Surveillance and Transportation Imaging Applications (Vol. 8663, pp. 69-78). SPIE.
22. Sudhan, S. K. H. H., & Kumar, S. S. (2016). Gallant Use of Cloud by a Novel Framework of Encrypted Biometric Authentication and Multi Level Data Protection. Indian Journal of Science and Technology, 9, 44.
23. Alex, A. T., Asari, V. K., & Mathew, A. (2013, March). Gradient feature matching for in-plane rotation invariant face sketch recognition. In Image Processing: Machine Vision Applications VI (Vol. 8661, pp. 46-58). SPIE.
24. Natarajan, R., & Sugumar, R. (2014). A survey on attacks in web usage mining. International Journal of Innovative Research in Computer and Communication Engineering, 2(5), 4470-5.
25. Satyanarayana, D., Mathew, A. R., & Sathyashree, S. (2016). An Architecture for Wireless Communication Systems using Li-Fi technology. In 8th International Conference on Latest Trends in Engineering and Technology (ICLTET’2016) (pp. 37-41).
26. Mathew, A. R. (2017). Cloud Technology and the Challenges for Forensics Investigators. DEStech Transactions on Computer Science and Engineering.
27. Begum, R. S., & Sugumar, R. (2015). A Conceptual Comparison of Artificial Bee Colony and Particle Swarm Optimization.
28. Soundappan, S. J., & Sugumar, R. (2016). Optimal knowledge extraction technique based on hybridisation of improved artificial bee colony algorithm and cuckoo search algorithm. International Journal of Business Intelligence and Data Mining, 11(4), 338-356.
29. Singh, T. J., & Sugumar, R. (2012, December). An extensibility of THEMIS billing system for the cloud computing environment. In 2012 Fourth International Conference on Advanced Computing (ICoAC) (pp. 1-6). IEEE.
30. Sugumar, R., Rengarajan, A., & Jayakumar, C. (2018). Trust based authentication technique for cluster based vehicular ad hoc networks (VANET). Wireless Networks, 24(2), 373-382.
31. Sudhan, S. K. H. H., & Kumar, S. S. (2015). An innovative proposal for secure cloud authentication using encrypted biometric authentication scheme. Indian Journal of Science and Technology, 8(35), 1-5.
32. Priya, P. S., & Sugumar, R. (2014). Multi Keyword Searching Techniques over Encrypted Cloud Data. In IJSR.
33. Chiranjeevi, K. G., Latha, R., & Kumar, S. S. (2016). Enlarge Storing Concept in an Efficient Handoff Allocation during Travel by Time Based Algorithm. Indian Journal of Science and Technology, 9, 40.
34. Amutha, M., & Sugumar, R. (2015). A survey on dynamic data replication system in cloud computing. International Journal of Innovative Research in Science, Engineering and Technology, 4(4), 1454-1467.
35. Sugumar, R. (2014). A technique to stock market prediction using fuzzy clustering and artificial neural networks.
36. Brijet, Z., Kumar, B. S., & Bharathi, N. (2017). Vehicle anti-theft system using fingerprint recognition technique. Open Academic Journal of Advanced Science and Technology, 1(1), 36-41.
37. Z. Brijet, N. Bharathi, G. Shanmugapriya. (2015). Design of Model Predictive Controller for Fluid Catalytic Cracking Unit. Fluid-IJCTA, 8(5), 1917-1926