Application of Artificial Neural Networks to solve the problem of Power Flow in Electrical Energy Systems

• Autores: Paucar, Leonor, Rider, Marcos J.
• Formato: artículo
• Fecha de Publicación: 2000
• Institución: Universidad Nacional de Ingeniería
• Repositorio: Revistas - Universidad Nacional de Ingeniería
• Lenguaje: español
• OAI Identifier: oai:oai:revistas.uni.edu.pe:article/464
• Enlace del recurso: https://revistas.uni.edu.pe/index.php/tecnia/article/view/464
• Nivel de acceso: acceso abierto

This article proposes the use of artificial neural networks (ANN) to solve the power flow problem in electrical energy systems. Power flow calculates the steady state of an electrical power system (SEP) and is a fundamental tool for the planning, operation and control of modern SEPs. The mathematical model of the power flow corresponds to a set of nonlinear algebraic equations that can be solved conventionally with the iterative Newton-Raphson (NR) method or with its decoupled versions. Currently, there are various commercial computer programs that use such methods. Among the objectives of the solution of the ANN-based power flow problem proposed here, its potential application stands out to solve problems that require a large computational effort such as online static security analysis and contingency analysis. The proposed methodology was applied to the 6-bar Ward-Hale and 14-bar IEEE (IEEE-14) test systems, observingsuccessful results in terms of arithmetic precision and processing time, compared to other conventional methods.