A Decision-making Framework Based on Artificial Neural Networks and Intelligent Agents for Transmission Grid Operation

Abstract

Security margins have been reduced in restructured and deregulated power systems, and as a result, these systems have been operated close to their security limits. Therefore, it is of utmost importance that power system operation be tracked in a real-time fashion, making decisions as fast as possible to ensure operating points within security limits. In this context, this article proposes a practical decision-making framework for transmission grid operation featuring artificial neural networks and intelligent agents. In this framework, the system operating point is tracked by means of voltage stability margins estimated by artificial neural networks,while the decision-making process is supported by means of intelligent agents. The output of this framework is a qualitative answer that supports system operators in making decisions to enhance security margins. A 6-bus test-system and the CIGRE 32-bus system were used for validating the neural network approach for voltage stability margin estimations; the proposed framework was validated with the IEEE 300-bus system. Results show that such a framework can be readily applied to support decisions aimed at ensuring secure system operating points.

Keywords:

• artificial neural network
• intelligent agents
• maximum loading
• transmission grid operation
• voltage stability

Additional information

Notes on contributors

Ricardo A. S. Fernandes

Ricardo A. S. Fernandes received his B.Sc. in electrical engineering from the Educational Foundation of Barretos in 2006. He received his M.Sc. and Ph.D. in electrical engineering from the São Carlos Engineering School, University of São Paulo, Brazil, in 2009 and 2011, respectively. As of 2013, he is an adjunct professor with the Electrical Engineering Department at the Federal University of São Carlos. His research interests are in the field of smart grids, power quality, and intelligent systems.

Guilherme G. Lage

Guilherme G. Lage received his B.Sc. and Ph.D. in electrical engineering from the São Carlos Engineering School, University of São Paulo, Brazil, in 2006 and 2013, respectively. In 2009–2010, he was a visiting scholar at the Electricity Markets Simulation and Optimization Laboratory, University of Waterloo, Canada. As of 2014, he is an adjunct professor with the Electrical Engineering Department at the Federal University of São Carlos, Brazil. His research interests are in power system operation, particularly in the modeling and application of optimization techniques to power systems planning.

Geraldo R. M. da Costa

Geraldo R. M. da Costa received his B.Sc. and M.Sc. in electrical engineering from the São Carlos Engineering School, University of São Paulo, and his Ph.D. from the University of Campinas, Brazil. Currently, he is a full professor with the Department of Electrical and Computer Engineering at the São Carlos Engineering School, University of São Paulo, Brazil. His research interests are in power system operation and planning, particularly in the application and development of optimization techniques to power systems.