DEVELOPMENT OF A DLNN MODEL FOR TRANSIENT STABILITY ASSESSMENT OF NIGERIA 28 BUS SYSTEMS

This article proposed using a deep learning neural network (DLNN) approach to forecast transient stability. Transient Stability Assessments (TSA) have long been acknowledged as being crucial for maintaining the reliable and protect operations of power systems. The complexity of power system dynamic features has increased because to the introduction of new components like power electronics, electric vehicles, and renewable energy sources, raising severe concerns among TSA. The development of renewable energy sources is currently having an impact on the reliability and security of the electrical network. Wide area monitoring systems have been used in the electrical system, producing large amounts of data that have ushered in new approaches to resolving these problems. Transient stability issues are attracting the attention of a wide range of stakeholders due to the potential for catastrophic outages. The goal of this project is to use data collection and DLNN to look for TSA problems in the electrical system. Data from the National Control Center (NCC) Oshogbo was used to mimic the Nigerian 28 Bus system in the DIgSILENT environment. In a Python context, a feature selection pipeline is built using the Relief-F feature selection method. To forecast transient stability on Python, the chosen feature will be fed into a particular form of DLNN. The DLNN reduces the time complexity of TSA, increasing accuracy. The accuracy value produced for the Nigeria 28 bus system is 90.16 percent once the system converges after 31 epochs. The IEEE 9 bus test system is used to validate the DLNN approach, which is used to evaluate transient stability. The outcome of this work is compared with similar work in the conclusion in terms of some evaluation performance.