Continuous Monitoring meets Synchronous Transmissions and In-Network Aggregation

Abstract

Continuously monitoring sensor readings is an important building block for many IoT applications. The literature offers resourceful methods that minimize the amount of communication required for continuous monitoring, where Geometric Monitoring (GM) is one of the most generally applicable ones. However, GM has unique communication requirements that require specialized network protocols to unlock the full potential of the algorithm. In this work, we show how application and protocol codesign can improve the real-life performance of GM, making it an application of practical value for real IoT deployments. We orchestrate the communication of GM to utilize the properties of a state-of-the-art wireless protocol (Crystal) that relies on synchronous transmissions and is designed for aperiodic traffic, as needed by GM. We bridge the existing gap between the capabilities of the protocol and the requirements of GM, especially in the case of periods of heavy communication. We do so by introducing an in-network aggregation technique relying on latent opportunities for aggregation that we exploit in Crystal's design, allowing us to reliably monitor duplicatesensitive aggregate functions, such as sum, average or variance. Our results from testbed experiments with a publicly available dataset show that the combination of GM and Crystal results in a very small duty-cycle, a 2.2x-3.2x improvement compared to the baseline and up to 10x compared to previous work. We also show that our in-network aggregation technique reduces the duty-cycle by up to 1.38x.

Shadow-based Hand Gesture Recognition in one Packet

“…As mentioned in the introduction, our work is related to efforts that reduce data to be transmitted such as compression [21], [22], [34], in-network processing [15], [19], [30], and data prediction algorithms [24], [26]. While these methods aim for high accuracy between sensed values and approximated values in low sampling frequency applications, we target high sampling frequency applications and only keep the interesting features of the sensed values.…”

“…To avoid streaming sensor readings and to reduce the amount of sensor data that needs to be transmitted, previous work has proposed novel data compression mechanisms [21], [22], [34], in-network processing (i.e., data aggregation) [15], [19], [30], and data prediction algorithms [24], [26]. These approaches are primarily focused on monitoring the environment and therefore require a low sampling frequency.…”