Tiny-scale Internet of Things (IoT) deployments increasingly rely on multihop mesh networking, yet their performance remains highly sensitive to wireless link variability caused by interference, mobility, and environmental fluctuations. Existing linkquality estimation techniques offer limited early-warning capability, and reactive routing protocols often incur costly route repairs, leading to packet loss, unstable forwarding paths, and excessive control overhead. To address these constraints, this work introduces TinyHeal, a fully on-device TinyML-assisted self-healing communication framework that predicts link degradation before failures occur and proactively stabilizes routing decisions. The proposed design integrates lightweight temporal feature extraction, micro-model inference, and a prediction-driven routing state machine engineered for microcontrollerclass IoT nodes. Extensive experiments on four real-world and large-scale datasets—Intel Lab, GreenOrbs, FIT IoT-LAB, and IoT-RPL—demonstrate that TinyHeal achieves higher prediction accuracy, reduces parent-switch frequency, improves packet delivery ratio by up to 18%, and lowers control overhead by more than 50% compared with state-of-the-art LQE and ML-based baselines. A robustness and sensitivity analysis further confirms that TinyHeal maintains strong reliability-energy tradeoffs across a wide range of operating parameters, validating its suitability for resource-constrained and dynamically varying IoT mesh environments.
- Open Access
- Article
TinyHeal: TinyML-Assisted Predictive Link Degradation Recovery for Self-Healing IoT Mesh Networks
- James Miller
Author Information
Received: 08 Dec 2025 | Revised: 12 Jan 2026 | Accepted: 29 Jan 2026 | Published: 31 Mar 2026
Abstract
Keywords
TinyML | IoT mesh networks | self-healing communications | link-quality prediction | proactive routing | wireless sensor networks
References
- 1.
Chai, Y.; Zeng, X.J.; Liu, Z. The future of wireless mesh network in next-generation communication: A perspective overview. Evol. Syst. 2024, 15, 1635–1648.
- 2.
Chai, Y.; Zeng, X.J. The development of green wireless mesh network: A survey. J. Smart Environ. Green Comput. 2021, 1, 47–59.
- 3.
Wong, A.W.L.; Goh, S.L.; Hasan, M.K.; et al. Multi-hop and mesh for LoRa networks: Recent advancements, issues, and recommended applications. Acm Comput. Surv. 2024, 56, 136.
- 4.
Gupta, M.; Jain, K. A Comprehensive Survey of Aerial Mesh Networks (AMN): Characteristics, Application, Open Issues, Challenges, and Research Directions. Wirel. Pers. Commun. 2024, 138, 333–368.
- 5.
Alameri, I.A.S. Modification of the AODV Routing Discovery Mechanism in Wireless Mesh Networks. Ph.D. Thesis, Univerzita Pardubice, Pardubice, Czech Republic, 2023.
- 6.
Alsayyed, M.M.; Manickam, S.; Wulandari, E.R.N.; et al. A Review of Applicable Technologies, Routing Protocols, Requirements, and Architecture for Disaster Area Networks. IEEE Access 2025, 13, 91129–91160.
- 7.
Johnphill, O.; Sadiq, A.S.; Al-Obeidat, F.; et al. Self-Healing in Cyber–Physical systems using machine learning: A critical analysis of theories and tools. Future Internet 2023, 15, 244.
- 8.
Sahin, A.; Arslan, H. A Self-Healing Mesh Network without Global-Time Synchronization. In Proceedings of the ICC 2024-IEEE International Conference on Communications, Denver, CO, USA, 9–13 June 2024; pp. 256–261.
- 9.
Aziz, A.N.A.A.; Rashid, R.A.; Nasir, M.N.M.; et al. ESP Mesh Network for Security Application. In Proceedings of the IEEE International Conference on Advanced Telecommunication and Networking Technologies (ATNT), Johor Bahru, Malaysia, 9–10 September 2024; Volume 1, pp. 1–4.
- 10.
Sanjay, T.; Muktha Sree, T. Self-Healing Blockchain Mesh: A Decentralized Cybersecurity Framework for Autonomous Vehicle Protection. In Proceedings of the ICNKAI—2 K 2 5: International Level Conference on the Nexus of Knowledge Using AI and IoT, Chennai, India, 11–12 April 2025.
- 11.
Lab, I.B.R. Intel Lab Data: Wireless Sensor Network Dataset. Online dataset. 2004. Available online: http://db.csail.mit.edu/labdata/labdata.html (accessed on 1 December 2025 ).
- 12.
Liu, Y. GreenOrbs: Lessons Learned from Extremely Large Scale Sensor Network Deployment. In International Conference on Database Systems for Advanced Applications; Springer: Berlin/Heidelberg, Germany, 2011; pp. 402–402.
- 13.
Adjih, C.; Baccelli, E.; Fleury, E.; Het al. FIT IoT-LAB: A large scale open experimental IoT testbed. In Proceedings of the 2015 IEEE 2nd World Forum on Internet of Things (WF-IoT), Milan, Italy, 14–16 December 2015; pp. 459–464.
- 14.
Al Sawafi, Y.; Touzene, A.; Hedjam, R. Hybrid deep learning-based intrusion detection system for RPL IoT networks. J. Sens. Actuator Netw. 2023, 12, 21.
- 15.
Winter, T.; others. RPL: IPv6 Routing Protocol for Low-Power and Lossy Networks. 2012. Available online: https://www.rfceditor.org/rfc/rfc6550.html (accessed on 12 December 2025).
- 16.
Winter, T.; Thubert, P.; Brandt, A.; et al. The Triangle Metric: Fast Link Quality Estimation for Mobile Wireless Sensor Networks. In Proceedings of the 19th International Conference on Computer Communications and Networks, Zurich, Switzerland, 2–5 August 2010.
- 17.
Luo, X.; Liu, L.; Shu, J.; et al. Link Quality Estimation Method forWireless Sensor Networks Based on Stacked Autoencoder. IEEE Access 2019, 7, 21572–21583.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com