Summary form only given as follows. This paper presents a new approach for real-time tuning the parameters of a conventional power system stabilizer (PSS) using a radial basis function (RBF) network. The RBF network is trained using an orthogonal least squares (OLS) learning algorithm. Investigations reveal that the required number of RBF centers depends on spread factor, /spl beta/ and the number of training patterns. Studies show that a parsimonious RBF network can be obtained by presenting a relatively smaller number of training patterns, generated randomly and spreadover the entire operating domain. Investigations reveal that the dynamic performance of the system with an RBF network adaptive PSS (RBFAPSS) is virtually identical to that of an artificial neural network based adaptive PSS (ANNAPSS). The dynamic performance of the system with RBFAPSS is quite robust over a wide range of loading conditions and equivalent reactance X/sub c/.