DEEPGRIDSHIELD: A DEEP LEARNING FRAMEWORK FOR REAL TIME ANOMALY DETECTION IN POWER DISTRIBUTION NETWORKS

Recent studies indicate that cyber-physical systems, especially those involving vehicular networks and industrial control systems, experience up to 35% of security breaches due to misclassified anomalies. Additionally, over 28% of attacks in power distribution and transport networks go undetected due to poor feature representation. Traditional classifiers, when used in isolation, demonstrate an average detection accuracy of only 85–88% in complex, multi-class intrusion scenarios. Existing manual analysis methods suffer from high dependence on rule-based signatures, which are often ineffective against novel or evolving attacks. They also require continuous human supervision, making real-time implementation impractical, and tend to misclassify low-frequency but critical anomaly patterns due to lack of robust learning mechanisms. To address these challenges, this work proposes a hybrid classification framework that integrates a Multilayer Perceptron (MLP)-based Deep Neural Network (DNN) with a Random Forest Classifier (RFC). The methodology leverages the MLP’s ability to learn high-dimensional, non-linear feature representations through dense layers, particularly extracting features from an intermediate latent layer termed the "feature layer." These features are then used as input for the RFC, which excels at ensemble-based decision-making and effectively mitigates overfitting by combining predictions from multiple decision trees. The complete model pipeline is optimized using early stopping and persistence strategies to enhance generalization and reusability. This hybrid approach not only improves classification accuracy and generalization but also ensures robustness across varied and imbalanced datasets, making it highly suitable for real-time anomaly detection in intelligent systems.