A Multi-objective Evolutionary Approach to Data Compression in Wireless Sensor Networks

Energy is a primary constraint in the design and deployment of wireless sensor networks (WSNs) since sensor nodes are typically powered by batteries with a limited capacity. Since radio communication is, in general, the most energy hungry operation in a sensor node, most of the techniques proposed to extend the lifetime of a WSN have focused on limiting transmission/reception of data, for instance, through data compression. Since sensor nodes are equipped with limited computational and storage resources, enabling compression requires specifically designed algorithms. In this paper, we propose a lossy compressor based on a differential pulse code modulation scheme with quantization of the differences between consecutive samples. The quantization parameters, which allow achieving the desired trade-off between compression performance and information loss, are determined by a multi-objective evolutionary algorithm. Experiments carried out on three datasets collected by real WSN deployments show that our approach can achieve significant compression ratios despite negligible reconstruction errors.