Data prediction + synchronous transmissions =ultra-low power wireless sensor networks

Data prediction in wireless sensor networks replaces the com-monly used (periodic) data reporting with a model, updated (infrequently) at the sink to accurately reproduce real data trends. This technique abates up to 99% of application mes-sages; yet, recent work has shown it achieves \only" up to a 7x lifetime improvement when executed atop a mainstream network stack (e.g., CTP + BoX-MAC), as the idle listen-ing and topology maintenance in the latter are ill-suited to the sparse trafic induced by data prediction. This paper presents a novel network stack designed for data prediction, Crystal, that exploits synchronous transmissions to quickly and reliably transmit model updates when these occur (in-frequently but often concurrently), and minimizes overhead during the (frequent) periods with no updates. Based on 90-node experiments in the Indriya testbed and with 7 public datasets, we show that Crystal unleashes the full poten-tial of data prediction, achieving per-mille duty cycle wit...