Advanced Metering Infrastructure (AMI) networks in smart grids face evolving cybersecurity threats, with Distributed Denial of Service (DDoS) attacks posing critical risks to network availability and operational integrity. This paper presents a comprehensive evaluation of deep learning architectures for DDoS attack detection in AMI environments, focusing on Convolutional Neural Network (CNN), CNN-Long Short-Term Memory (CNN-LSTM), and CNN-Gated Recurrent Unit (CNN-GRU) hybrid approaches. Using a dataset of 72,007 AMI samples enhanced with realistic DDoS attack simulations covering six attack categories, we implemented extensive feature engineering generating 3,398 features optimized to 75 discriminative indicators. The methodology incorporates synthetic attack generation maintaining 30% attack ratio with stratified data partitioning for robust evaluation. The results gotten from experiments demonstrate that the CNN architecture achieves excellent performance with 86.52% accuracy, 91.08% precision, and 85.73% F1-score, requiring only 23.7 minutes training time and 291,841 parameters. The CNN-LSTM hybrid shows competitive performance with 85.82% accuracy and enhanced temporal modeling capabilities. Both architectures significantly outperform the more complex CNN-GRU variant, establishing CNN-based approaches as optimal for AMI security applications. This research contributes evidence-based architectural guidance for AMI threat detection systems, demonstrating practical deployment solutions that balance detection accuracy with computational efficiency for real-world utility environments.
S. Bassey, P. Asuquo, Victor Anaga et al.· E3S Web of Conferences· 0 citations
The integration of Internet of Things (IoT) systems with blockchain-based security mechanisms offers improved trust, auditability, and decentralization, but introduces significant challenges related to interoperability, transaction latency, and energy consumption at the network edge. Most existing blockchain-assisted intrusion detection systems (IDS) are limited to single-ledger deployments and rely on computationally intensive machine-learning inference, which restricts their applicability in resource-constrained IoT environments. Presented in the work is a cross-chain and energy-efficient intrusion detection framework that combines lightweight machine-learning–based anomaly detection with smart-contract–driven verification and interoperable blockchain communication. Intrusion detection models are optimized using pruning and INT8 quantization to reduce inference overhead on IoT gateways, while verified intrusion alerts are securely propagated across heterogeneous blockchain platforms through cross-chain messaging protocols. Smart contracts automate alert validation and response actions, enabling coordinated defense across multiple ledgers. Experimental evaluation using CICIDS2017 and BoT-IoT datasets, physical IoT gateway hardware, and a multi-chain blockchain testbed demonstrates that the proposed framework achieves a detection accuracy of 97.4%, reduces inference energy consumption by up to 56%, and improves alert propagation latency by 42% compared to single-chain baselines. These results indicate that decentralized, interoperable, and energy-aware intrusion detection is feasible for large-scale IoT deployments.
S. Bassey, Emmanuel Udoh, B. Stephen et al.· E3S Web of Conferences· 0 citations