Non-Linear Time Varying Modeling for Phase Noise in Oscillators Based On a Discrete Recursive Approach

Abstract

<p> A unique approach for the modeling of phase noise is examined in this thesis. In previous work regarding phase noise theory, the memory property of phase is virtually ignored. The thesis introduces the Discrete Recursive Procedure (DRP): a systematic approach or methodology to predict phase noise using a discrete recursive algorithm taking into account the memory property of phase. This discrete recursive algorithm is a general extension of the Linear Time Varying (LTV) model and is referred to as the NonLinear Time Varying (NLTV) model. </p> <p> Simulations are performed using the DRP method. Phase fluctuation comparisons are made between the LTV and the NLTV models for an ideal oscillator. The simulation results show that the NLTV model taking into account the memory property of phase makes more realistic phase noise predictions than the LTV model for asymmetrical Impulse Sensitivity Function (ISF) cases. Phase noise simulation results using the NLTV model are given for a modified 810-MHz CMOS cross-coupled LC oscillator design. At 90kHz offset, the simulation prediction (-89 dBc/Hz) and the measurement readings (-93 dBc/Hz) are closely matched with a difference of approximately 4 dBc/Hz while the CAD simulation prediction ( -101. 8) has a difference of 9 dBc/Hz from the measurements. In the phase noise simulation for the 62-MHz BIT Colpitts oscillator design, the NLTV model predicts a -26 dBc/decade and -19.5 dBc/decade for the flicker noise and thermal noise regions in accordance with the theoretical -30 dBc/decade and -20 dBc/decade slopes. </p>