Channel-State-Aware Deep Reinforcement Learning for Adaptive Routing in Wireless Mesh Networks
DOI:
https://doi.org/10.31838/NJAP/08.01.03Keywords:
Wireless Mesh Networks (WMNs), Deep Reinforcement Learning (DRL), Channel State Information (CSI), Adaptive Routing, Deep Q-Network (DQN), Signal-to-Noise Ratio (SNR), Link Stability, Interference Management, Cognitive Routing, Dynamic Network OptimizationAbstract
In the given paper a Channel-State-Aware Deep Reinforcement Learning (CSA-DRL) method of adaptive and intelligent routing in dynamic Wireless Mesh Networks (WMNs) modification is proposed. The proposed system is centered around a Deep Q-Network (DQN) that can utilize a multi-dimensional state vector based on real-time physical-layer measurements such as Signal-to-Noise Ratio (SNR), Signal-to-Interference-plus-Noise Ratio (SINR), Received Signal Strength Indicator (RSSI), link stability, interference index and local buffer occupancy. These metrics enable the agent to develop a rich context account of wireless environment, which enables it to take proactive decisions, working with non-deterministic and highly dynamic network conditions. The major contribution in this work is that one explicitly considers effects of antenna beamwidth and gain, which is incorporated in DRL-based mesh routing framework. Observing the properties of directional antennas in the channel metrics, e.g., radiation pattern, gain distribution, and beam orientation, the CSA-DRL agent is able to learn the signal propagation patterns and shape the routing policies accordingly. The antenna-aware improvement allows better modeling RSSI and SINR which are orientation and interference area-sensitive. The success of the method can be proved by using simulations with directional antenna modules with the NS-3 simulator, showing that the CSA-DRL model outperforms traditional routing protocols and baseline DRL models in most indicators of performance, such as packet delivery ratio, average throughput, route stability and latency. The system is demonstrated to be both scale-able and resilient to dense and sparse node topology as well as differing conditions of small-scale fading including Rayleigh and Nakagami-m, thus making it a robust system. In addition, because it aligns with physical-layer realities, the CSA-DRL frame work forms a basis of a future RF-aware and beam-adaptive routing that can be deployed in next-generation wireless networks, such as 6G, vehicular ad hoc networks, and edge-based smart infrastructure. On the whole, the proposed work shows an innovative and feasible contribution to the development of the field of smart wireless communication based on reinforcement learning in the form of an antenna.
References
1. Pragadeswaran, S., Subha, N., Varunika, S., Moulishwar, P., Sanjay, R., Karthikeyan, P., Aakash, R., & Vaasavathathaii, E.
(2024). Energy efficient routing protocol for security analysis scheme using homomorphic encryption. Archives for Technical Sciences, 2(31), 148–158. https://doi.org/10.70102/afts.2024.1631.148
2. Perkins, C. E., & Royer, E. M. (1999). Ad-hoc on-demand distance vector routing. In Proceedings of the 2nd Workshop on Mobile Computing Systems and Applications (pp. 90–100).
3. Clausen, T., & Jacquet, P. (2003). Optimized link state routing protocol (OLSR). RFC 3626, Internet Engineering Task Force (pp. 1–53).
4. De Couto, D. S. J., Aguayo, D., Bicket, J., & Morris, R. (2003). A high-throughput path metric for multi-hop wireless routing. In Proceedings of the 9th Annual International Conference on Mobile Computing and Networking (MobiCom) (pp. 134–146). ACM. 38
5. Papadopoulos, N. A., & Konstantinou, E. A. (2025). SoC solutions for automotive electronics and safety systems for revolutionizing vehicle technology. Journal of Integrated VLSI, Embedded and Computing Technologies, 2(2), 36–43. https://doi.org/10.31838/JIVCT/02.02.05
6. Hemalatha, P., & Kamalanathan, C. (2025). AS2ICRL: Energy management model using inverse constrained reinforcement learning based adaptive sleep scheduling in wireless sensor networks. Journal of Internet Services and Information Security, 15(2), 964–984. https://doi.org/10.58346/JISIS.2025.I2.064
7. Boyan, J. A., & Littman, M. L. (1994). Packet routing in dynamically changing networks: A reinforcement learning
approach. In Advances in Neural Information Processing Systems (NIPS) (pp. 671–678).
8. Khoeurt, S., So-In, C., Musikawan, P., & Aimtongkham, P. (2023). Multidirectional trust-based security mechanisms for sinkhole attack detection in the RPL routing protocol for internet of things. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 14(3), 48–76. https://doi.org/10.58346/ JOWUA.2023.I3.005
9. Prasath, C. A. (2023). The role of mobility models in MANET routing protocols efficiency. National Journal of RF Engineering and Wireless Communication, 1(1), 39–48. https://doi.org/10.31838/RFMW/01.01.05
10. Chen, X., Wu, C., Li, Z., & Lau, F. C. M. (2021). Deep reinforcement learning for routing optimization in SDN. ACM
Transactions on Networking, 29(2), 770–783. https://doi.org/10.1109/TNET.2021.3061406
11. Giji Kiruba, D., Benita, J., & Rajesh, D. (2023). A proficient obtrusion recognition clustered mechanism for malicious sensor nodes in a mobile wireless sensor network. Indian Journal of Information Sources and Services, 13(2), 53–63. https://doi.org/10.51983/ijiss-2023.13.2.3793
12. Srilakshmi, K., Preethi, K., Afsha, M., Pooja Sree, N., & Venu, M. (2022). Advanced electricity billing system using Arduino Uno. International Journal of Communication and Computer Technologies, 10(1), 1–3.
13. Prakash, M., & Prakash, A. (2023). Cluster head selection and secured routing using glowworm swarm algorithm and hybrid security algorithm for over IoT-WSNs. International Academic Journal of Innovative Research, 10(2), 01–09.
https://doi.org/10.9756/IAJIR/V10I2/IAJIR1004
14. Liu, J., Shi, Y., Yang, L., & Cai, L. (2009). Channel-aware routing for wireless mesh networks based on link SNR. In Proceedings of Vehicular Technology Conference – spring (pp. 1–5).
15. Vijay, V., Chaitanya, K., Pittala, C. S., Ajitha, G., Susri Susmitha, S., Tanusha, J., Venkateshwarlu, S. C., & Vallabhuni, R. R. (2022). Physically unclonable functions using two-level finite state machine. Journal of VLSI Circuits and Systems, 4(1), 33–41. https://doi.org/10.31838/jvcs/04.01.06
16. Zeng, Y., Chen, B., Zhang, Y., & Yang, D. (2012). Delay-aware routing using reinforcement learning in multi-hop wireless networks. In Proceedings of Global Communications Conference (GLOBECOM) (pp. 1005–1010).
17. Sindhu, S. (2025). Mathematical analysis of vibration attenuation in smart structures using piezoelectric layers. Journal of Applied Mathematical Models in Engineering, 1(1), 26–32.
18. Ramasamy, V. (2023). Analytic approaches of various routing protocols in WSN-Comparative study. Wireless Personal Communications, 133(2), 1031–1053.
19. Muralidharan, J. (2024). Compact reconfigurable antenna with frequency and polarization agility for cognitive radio
applications. National Journal of RF Circuits and Wireless Systems, 1(2), 16–26.
20. Mao, M., Leng, S., Yang, K., & Zhang, Y. (2019). A deep reinforcement learning approach for intelligent resource
management in wireless networks. Transactions on Wireless Communications, 18(7), 3686–3696. https://doi.org/10.1109/TWC.2019.2919647
