http://hdl.handle.net/10453/148699 2026-06-06T00:28:35Z http://hdl.handle.net/10453/195195 Title: Cyber–physical resilience and security strategies for renewable energy-driven IoT power grids Authors: Li, TT; Huang, Y; Hua, Y; Hu, T; Yang, H; Alhazmi, M; Alsaif, S; Liu, G Abstract: The increasing penetration of renewable energy resources, coupled with the rapid proliferation of Internet of Things (IoT) technologies, has transformed the architecture of modern power grids into highly interconnected and intelligent systems. While these advances improve sustainability, flexibility, and operational efficiency, they also expand the attack surface, exposing critical infrastructures to sophisticated cyber and physical threats. This paper proposes a cyber–physical resilience and security framework designed to safeguard IoT-enabled power grids under adversarial conditions. First, a vulnerability assessment methodology is developed that integrates renewable generation variability, IoT communication dependencies, and network topology to identify systemic weak points across both cyber and physical domains. Second, resilient control strategies are introduced by combining distributionally robust optimization with multi-agent reinforcement learning to achieve secure energy allocation, adaptive task scheduling, and rapid system recovery under uncertainty. Third, a set of security strategies is proposed, including blockchain-based authentication for trustworthy data exchange, lightweight cryptographic techniques for IoT nodes, and deep learning-driven intrusion detection to counter evolving attack patterns. This study highlights the necessity of integrating optimization, learning-based control, and secure system design to enable the next generation of cyber–physically resilient renewable energy-driven IoT power grids. 2025-12-01T00:00:00Z http://hdl.handle.net/10453/195185 Title: AI-based Adaptive Overcurrent Protection for Load-side Relays in Offshore DC Microgrids Authors: Sheina, A; Zamora, R; Than Oo, AM; Gunawardane, K Abstract: The integration of renewable energy sources RES such as solar wind wave and tidal power through microgrids is gaining interest globally particularly for offshore applications In these circumstances DC microgrids are preferred over AC counterparts due to their suitability for islanded operation and their ability to simplify the integration of RES and energy storage systems ESS DC systems also mitigate common AC challenges such as frequency deviations harmonic distortion and voltage imbalance Despite these advantages DC microgrids face significant protection challenges primarily due to the absence of natural zero crossing rapid fault current rise and limited availability of standardized DC protection devices and schemes To address the need for more responsive protection mechanisms that can accommodate varying RES ESS and load conditions this paper proposes an adaptive overcurrent protection approach based on artificial intelligence AI The adaptive scheme employs an Adaptive Neuro Fuzzy Inference System ANFIS trained on data from diverse operating scenarios including normal loading fault events and renewable intermittency The model enables real time adjustment of relay settings on the load side ensuring accurate fault detection and improving system reliability A DC microgrid protection model is developed in MATLAB Simulink in which current measurements obtained under different operating conditions are used for training and validation The ANFIS based method achieved 99 41 prediction accuracy over 1 35 million samples and the Opal RT real time simulation confirmed its effectiveness with circuit breaker tripping times of 130 milliseconds for overcurrent faults and 20 milliseconds for short circuit faults 2026-02-17T00:00:00Z http://hdl.handle.net/10453/195167 Title: HiFi-XAI: A Fidelity-Aware, LLM-Powered Framework for Trustworthy Intrusion Detection Authors: Awasthi, A; Vediya, P; Miranka, H; Battula, RB; Nanda, P Abstract: The increasing deployment of complex "black box"AI models in anomaly-based Intrusion Detection Systems (IDS) for future networks has opened up a trust gap that requires human-interpretable explanations in order for analysts to feel confident in acting on alerts. Current approaches to Explainable AI (XAI), such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations), do not properly address the challenges inherent in the problem domain. These techniques fundamentally fail from a fidelity standpoint due to their incorrect assumption of independence between features that results in untrustworthy explanations, which are fundamentally based on correlated network data. We address these shortcomings by proposing HiFi-XAI, which leverages a new, novel framework to provide faithful and semantically rich explanations. HiFi-XAI introduces a model-agnostic Conditional Value Attribution Explanation (CVAE), a method based on probabilistic Shapley values that models feature dependencies to ensure explanations are derived from plausible data distributions. These high-fidelity attributions are then translated into actionable, natural-language narratives by a fine-tuned Large Language Model (LLM). We validate our framework through allaware scenario feature ablation studies on the CICIDS2017 and CICIOT2023 datasets. This demonstrates that CVAE consistently identifies more impactful features than SHAP and LIME across five anomaly-based IDS models. Furthermore, we deploy the HiFi-XAI to prove its practical feasibility and test it on a resource-constrained Raspberry Pi 4. Our work presents a complete, end-to-end solution for building trust in AI-driven IDS. 2025-01-01T00:00:00Z http://hdl.handle.net/10453/195166 Title: Protocol-Aware Hybrid Clustering for IoT: Adaptive Reconfiguration and Secure Communication with MQTT/CoAP Integration Authors: Dighriri, OM; Nanda, P; Mohanty, M; Alrashed, B; Haddadi, I Abstract: The fast evolution of Internet of Things (IoT) is placing increased demands on network infrastructures to be versatile and robust, especially in dynamic, heterogeneous, and resource-limited environments. Existing cluster-based and communication protocols struggle with protocol rigidity, insufficient integrated security, and limited reconfigurability. This paper proposes a novel security-aware hybrid clustering framework integrating BIRCH-DBSCAN algorithms, MQTT/CoAP switching adaptively, and AES-128 encryption with session-based key rotation for end-to-end confidentiality. By featuring a three-layer architecture designed with autonomous cluster recovery, layered verification, and a reconfiguration system upon performance, energy, and mobility changes. Evaluated and tested on ContikiNG simulation, the approach provides 43.3% latency reduction, 22.8 % energy efficiency improvement, 99.91 % delivery reliability, and zero breaches over 39 adaptive switches with just 4.2% overhead. The results attest to the platform's strength and viability for future IoT deployments for efficient and responsive communications in changing conditions. 2025-01-01T00:00:00Z