Compressed Sensing in Multi-Hop Large-Scale Wireless Sensor Networks Based on Routing Topology Tomography

TL;DR

This paper introduces a novel compressed sensing method for large-scale multi-hop wireless sensor networks that reduces data transmission and extends network lifetime by efficiently recovering data with minimal packets, leveraging routing topology and machine learning.

Contribution

It presents a resource-efficient compressed sensing approach that works with dynamic routing topology and employs machine learning to find suitable sparse representations for data recovery.

Findings

Reduces data recovery errors by an order of magnitude.

Significantly decreases wireless communication costs.

Validates effectiveness on real-world WSN deployment.

Abstract

Data acquisition from a multi-hop large-scale outdoor wireless sensor network (WSN) deployment for environmental monitoring is full of challenges. This is because the severe resource constraints on small battery-operated motes (e.g., bandwidth, memory, power, and computing capacity), the big data acquisition volume from the large-scale WSN,and the highly dynamic wireless link conditions in an outdoor communication environment. We present a novel compressed sensing approach which can recover the sensing data at the sink with high fidelity when very few data packets are collected, leading to a significant reduction of the net-work transmissions and thus an extension of the WSN lifetime. Interplaying with the dynamic WSN routing topology, the proposed approach is efficient and simple to implement on the resource-constrained motes without a mote's storing of any part of the random projection matrix, as opposed to other existing compressed sensing based schemes. We propose a systematic method via machine learning to find a suitable representation basis, for any given WSN deployment and data field, which is both sparse and incoherent with the random projection matrix in the compressed sensing for data acquisition. We validate our approach and evaluate its performance using a real-world multi-hop WSN testbed deployment in situ. The results demonstrate that our approach significantly outperforms existing compressed sensing approaches by reducing data recovery errors by an order of magnitude for the entire WSN observation field, while drastically reducing wireless communication costs at the same time.