Documents disponibles écrits par cet auteur

Design of an adaptive PSS based on recurrent adaptive control theory / Peng, Zhao in IEEE transactions on energy conversion, Vol. 24 N° 4 (Décembre 2009) 

Public ISBD [article]  in IEEE transactions on energy conversion > Vol. 24 N° 4 (Décembre 2009) . - pp. 884 - 892 Titre : Design of an adaptive PSS based on recurrent adaptive control theory Type de document : texte imprimé Auteurs : Peng, Zhao, Auteur ; Malik, O. P., Auteur Année de publication : 2010 Article en page(s) : pp. 884 - 892 Note générale : energy conversion Langues : Anglais (eng) Mots-clés : Adaptive  control;  neurocontrollers;  power  system  control;  power  system  stability;  recurrent  neural  nets Résumé : Inspired by observing the similarity between adaptive control systems and recurrent neural networks (RNNs), a new control scheme, the recurrent adaptive control (RAC), is presented in this paper. Back propagation through time (BPTT), a learning algorithm for RNNs, can be exploited in RAC. Application of truncated BPTT to RAC is also discussed. Further, a new control algorithm for RAC, termed recursive gradient (RG), is developed to improve the performance of the original and truncated BPTT algorithms. Effectiveness of the RG control algorithm as a power system stabilizer is demonstrated. En ligne : http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5336285&sortType%3Das [...] [article] Design of an adaptive PSS based on recurrent adaptive control theory [texte imprimé] / Peng, Zhao, Auteur ; Malik, O. P., Auteur . - 2010 . - pp. 884 - 892. energy conversion Langues : Anglais (eng) in IEEE transactions on energy conversion > Vol. 24 N° 4 (Décembre 2009) . - pp. 884 - 892 Mots-clés : Adaptive  control;  neurocontrollers;  power  system  control;  power  system  stability;  recurrent  neural  nets Résumé : Inspired by observing the similarity between adaptive control systems and recurrent neural networks (RNNs), a new control scheme, the recurrent adaptive control (RAC), is presented in this paper. Back propagation through time (BPTT), a learning algorithm for RNNs, can be exploited in RAC. Application of truncated BPTT to RAC is also discussed. Further, a new control algorithm for RAC, termed recursive gradient (RG), is developed to improve the performance of the original and truncated BPTT algorithms. Effectiveness of the RG control algorithm as a power system stabilizer is demonstrated. En ligne : http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5336285&sortType%3Das [...]