FLOPSYNC-QACS: Quantization-aware clock synchronization for wireless sensor networks

Abstract

Distributed real-time systems often rely on clock synchronization. However, the achievement of precise synchronization in Wireless Sensor Networks (WSNs) is hampered by competing design challenges, which finally causes many WSN hardware platforms to rely on low frequency clock crystal for local timebase provision. Although this solution is inexpensive and with a remarkably low energy consumption, it limits the resolution at which time can be measured. The FLOPSYNC synchronization scheme was then introduced to compensate for possible quartz crystal imperfections. The main limitation of FLOPSYNC is that it does not account for the effects of quantization. In this paper we propose a switched control variant of the base FLOPSYNC scheme to address quantization explicitly in the compensator design, providing clock synchronization in cost-sensitive WSN node platforms with a minimal additional overhead. Experimental evidence is given that the approach reaches a synchronization error of at most 1 clock tick in a real WSN

Overview of Time Synchronization for IoT Deployments: Clock Discipline Algorithms and Protocols

“…This approach has certain advantages compared to the batch least square based clock synchronization. Another control theoretical solution based on low-frequency oscillators is FLOPSYNC-QACS by Terraneo et al [ 74 ]. The authors present a control scheme that can be used when the quantization errors dominate the other time errors.…”

Jitter-Compensated VHT and Its Application to WSN Clock Synchronization

“…Although in this category solutions have been proposed to synchronize within one clock tick, like FLOPSYNC-QACS [7], the low resolution of the timebase inevitably results in a synchronization lower bound, that with the typically used 32 kHz crystals is of approximately 30.5µs.…”

“…We carry out the design in the continuous time domain, mainly because doing so allows to operate with frequency values directly, and independently of the adopted synchronization period. Putting model (7) in transfer function form and transforming to continuous time, we get E hl (s) = P(s) (U hl (s) + D hl (s)) , P(s)…”