Clock Synchronization Based on Non-Parametric Estimation Considering Dynamic Delay Asymmetry

Precise time protocol is widely used to enable devices to have unified time in the industrial scene. Due to unknown delay asymmetry affecting the synchronization accuracy, numerous researches focus on parameter estimation methods for compensation. However, the fixed delay is difficult to determine in practical, and network dynamics aggravate delay asymmetry, which reduces the actual effect of synchronization. In this paper, a non-parametric estimation method is introduced into synchronization process modeling, which can fit the timestamp data well without fixed delay value. A double-layer clock synchronization method is proposed to estimate the clock skew and offset, where sparse support vector regression and stochastic gradient descent method are combined to improve the operational efficiency and adaptability to network dynamics. Simulation results based on actual measured data show that the proposed method has better performance in both static and dynamic networks than traditional methods.