ABSTRACTTo evaluate mobile communication systems, it is important to develop accurate and concise fading channel models. However, fading encountered in mobile communication is usually non‐stationary, and the existing methods can only model quasi‐stationary or piecewise‐stationary fading instead of general non‐stationary fading. To address this, this paper proposes an evolutionary spectrum (ES)‐based approach to modeling non‐stationary fading channels. Our ES approach is more general than the existing piecewise‐stationary models and is capable of characterizing a general non‐stationary fading channel that has an arbitrary ES (or time‐varying power spectral density); our ES approach is parsimonious and is also able to generate stationary fading processes. As an example, we show how to apply our ES approach to generating stationary and non‐stationary correlated Nakagami‐mfading channel processes. Simulation results show that the ES of the channel gain process produced by our ES‐based channel model agrees well with the user‐specified ES, indicating the accuracy of our ES‐based channel model. Copyright © 2011 John Wiley & Sons, Ltd.