2025 ASEE Annual Conference & Exposition

In this research, Cyber-physical attacks on power grid networks, particularly false data injection attacks (FDIAs), have increased, leading to power outages and significant economic losses. These attacks pose a serious threat to smart grid load flow monitoring systems. This research explores advanced approaches using machine learning models and simulation case studies focused on mitigating FDIAs in smart grids. The study emphasizes resilience, traceability, and mitigation of these attacks through innovations in power load flow monitoring. The methodology involves advanced simulations with minimal programming technologies to decompose multi-node bus power grid generation and address false data load flow issues. A core objective is to standardize effective mitigation strategies to prevent power load flow disruptions, enhance resilience in critical data protection, and embedded blockchain technology for secure transaction management templates within the grid. A virtual platform for smart contracts is developed, facilitating load flow transactions securely. Additionally, a machine learning model is integrated to analyze, train, test, and forecast load flow data, enabling future predictions and improving the smart grid's resilience mechanisms against FDIAs.