Bayesian-Optimized Deep Learning for Adaptive Real-Time FDIA Detection in Smart Grid Demand Response Systems

Abstract

Smart grid demand response (DR) systems face escalating threats from False Data Injection Attacks (FDIAs), which corrupt load forecasts to distort real-time pricing, destabilize supply– demand equilibrium, and precipitate cascading grid failures. These intrusions manifest as multi-scale temporal anomalies from transient spikes to prolonged distortions in severely imbalanced datasets. We propose an adaptive deep learning architecture integrating: (i) a variance-adaptive 1D convolutional neural network (CNN) with dynamic kernel scaling to magnify anomalies while attenuating noise; (ii) a temporal-attention bidirectional LSTM (BiLSTM) to resolve forward–backward dependencies; and (iii) Bayesian optimization (BO) with Matérn kernels to jointly optimize accuracy–latency trade-offs under strict computational constraints. An Enhanced SMOTE-RUS scheme synthesizes minority-class attacks while preserving appliance-level periodicity. Evaluated on 377k half-hourly forecasts from 290 U.S. households, the framework attains 99.26% accuracy, 93.16% F1-score, and 1.2 ms per-sample inference, exceeding the strongest baseline by 21.4%.