The cutting-edge electrical utility industry is quick advancing into a keen blend of best-in-class digital advancements with the actual foundation, famously alluded to as cyber-physical system (CPS). These CPSs, which depend entirely on an extensive intelligent computing algorithm-based communication network, are vulnerable to digital assaults and are likewise touchy to various technical and socioeconomic variables trading off its stability. Evaluation and forecast of the stability of these CPSs are fundamental in this unique situation. Figuring such countless variables while designing a framework of stability assessment is humanly inconceivable and hence deployment of cutting-edge computational methods, for example, the machine learning-based model, is found generally reasonable for such purposes. In this work, a novel improved genetic algorithm (GA)-based extreme learning machine (ELM) model for smart-grid-CPS stability forecast has been proposed. The exploratory outcome in regards to the proposed model is then contrasted with other contemporary AI and profound learning models.
Elsevier, Electric Power Systems Resiliency: Modelling, Opportunity and Challenges, 2022, Pages 149-163