论文信息 - APPLICATION OF MACHINE LEARNING TECHNIQUES ON THE DYNAMIC SECURITY OF ISOLATED POWER SYSTEMS WITH LARGE WIND POWER PENETRATION

APPLICATION OF MACHINE LEARNING TECHNIQUES ON THE DYNAMIC SECURITY OF ISOLATED POWER SYSTEMS WITH LARGE WIND POWER PENETRATION

In isolated power systems increased renewable power penetration with a high level of security can be achieved by the provision of advanced control tools to provide advice to the operators. The CARE system, an integrated control software that has been installed in the SCADA system of Crete includes on-line dynamic security assessment functions that supervise the security operating margins in case of pre-selected disturbances and are based on the application of Decision Trees and Neural Networks. In the paper the techniques applied for on-line dynamic security assessment are described and a preliminary evaluation of their application is provided.

E. S. Karapidakis | N. D. Hatziargyriou | Damianos Georgiadis

[1] J.A. Pecas Lopes,et al. Preliminary results from the More Advanced Control Advice Project for secure operation of isolated power systems with increased renewable energy penetration and storage , 2001, 2001 IEEE Porto Power Tech Proceedings (Cat. No.01EX502).

[2] J.A. Pecas Lopes,et al. Operation and control of island systems-the Crete case , 2000, 2000 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.00CH37077).

[3] Louis Wehenkel,et al. Automatic Learning Techniques in Power Systems , 1997 .

[4] Louis Wehenkel,et al. Decision tree approach to power systems security assessment , 1993 .

[5] João Peças Lopes,et al. Real time preventive actions for transient stability enhancement with a hybrid neural network-optimization approach , 1995 .