Citation

Babu, Tina and Nair, Rekha R. and Balusamy, Balamurugan and Yogarayan, Sumendra (2026) H-CLAS: A Hybrid Continual Learning Framework for Adaptive Fault Detection and Self-Healing in IoT-Enabled Smart Grids. IoT, 7 (1). p. 12. ISSN 2624-831X

Text IoT-07-00012.pdf - Published Version Restricted to Repository staff only Download (958kB)

Abstract

The rapid expansion of Internet of Things (IoT)-enabled smart grids has intensified the need for reliable fault detection and autonomous self-healing under non-stationary operating conditions characterized by frequent concept drift. To address the limitations of static and single-strategy adaptive models, this paper proposes H-CLAS, a novel Hybrid Continual Learning for Adaptive Self-healing framework that unifies regularization-based, memorybased, architectural, and meta-learning strategies within a single adaptive pipeline. The framework integrates convolutional neural networks (CNNs) for fault detection, graph neural networks for topology-aware fault localization, reinforcement learning for selfhealing control, and a hybrid drift detection mechanism combining ADWIN and Page– Hinkley tests. Continual adaptation is achieved through the synergistic use of Elastic Weight Consolidation, memory-augmented replay, progressive neural network expansion, and Model-Agnostic Meta-Learning for rapid adaptation to emerging drifts. Extensive experiments conducted on the Smart City Air Quality and Network Intrusion Detection Dataset (NSL-KDD) demonstrate that H-CLAS achieves accuracy improvements of 12–15% over baseline methods, reduces false positives by over 50%, and enables 2–3× faster recovery after drift events. By enhancing resilience, reliability, and autonomy in critical IoT-driven infrastructures, the proposed framework contributes to improved grid stability, reduced downtime, and safer, more sustainable energy and urban monitoring systems, thereby providing significant societal and environmental benefits.

Item Type:	Article
Uncontrolled Keywords:	Convolutional neural networks, graph neural networks
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	04 May 2026 05:36
Last Modified:	04 May 2026 05:36
URII:	http://shdl.mmu.edu.my/id/eprint/15883

Downloads

Edit (login required)