A Novel Methodology for Determining Steady-State Security Regions Using Artificial Neural Networks in Near Real-Time Applications

Abstract

The increasing penetration of variable renewable energy sources, such as photovoltaic and wind power, poses significant challenges to the real-time security assessment of power systems. In this context, the Steady-State Security Regions framework has emerged as a robust tool for voltage security assessment, providing valuable insights into the steady-state operating limits of electrical networks. However, the computational burden associated with determining these regions during system operation remains a major obstacle for current methodologies. This paper presents a novel approach for efficiently identifying these regions using artificial neural networks, enabling the fast and accurate delineation of security boundaries suitable for real-time and near-real-time applications. The methodology was validated on the IEEE 9-Bus and New England test systems, achieving accuracy comparable to conventional techniques while reducing computational time by up to 96%. The results underscore the potential of the proposed method as a scalable and effective tool to support operational decision-making in power systems with high shares of renewable generation.