Online MLP/HDD-based automation-oriented cyber-resilient flexible DSSE under coordinated FDI cyberattacks with resource-aware guarantees

This paper proposes a novel cyber-resilient Distribution System State Estimation (DSSE) framework based on an integrated Multi-Layer Perceptron (MLP) and Hybrid Detection-Decision (HDD) mechanism. The proposed method is designed to operate under coordinated False Data Injection (FDI) cyberattacks while ensuring real-time performance and computational efficiency. The main contributions of this work are threefold: (i) development of an MLP-based DSSE model capable of accurate state estimation under normal and adversarial conditions, (ii) integration of a hybrid HDD module for real-time detection and mitigation of coordinated cyberattacks, and (iii) a resource-aware framework ensuring scalability and low-latency operation suitable for real-time distribution system applications. Extensive simulation results on benchmark distribution systems demonstrate that the proposed approach significantly improves estimation accuracy and robustness compared to conventional and learning-based DSSE methods, particularly under varying levels of cyberattacks and measurement noise.