Rate-Distortion Classification for Self-Tuning IoT Networks
This enables energy-efficient, self-tuning IoT networks by adapting compression protocols on-the-fly, though it is incremental as it applies existing ML methods to a specific domain.
The paper tackles the problem of dynamically tuning lossy compression in IoT networks by automatically assessing signal classes and their rate-distortion curves using machine learning, showing that these curves can be reliably estimated with 10-20 statistical features on small time windows.
Many future wireless sensor networks and the Internet of Things are expected to follow a software defined paradigm, where protocol parameters and behaviors will be dynamically tuned as a function of the signal statistics. New protocols will be then injected as a software as certain events occur. For instance, new data compressors could be (re)programmed on-the-fly as the monitored signal type or its statistical properties change. We consider a lossy compression scenario, where the application tolerates some distortion of the gathered signal in return for improved energy efficiency. To reap the full benefits of this paradigm, we discuss an automatic sensor profiling approach where the signal class, and in particular the corresponding rate-distortion curve, is automatically assessed using machine learning tools (namely, support vector machines and neural networks). We show that this curve can be reliably estimated on-the-fly through the computation of a small number (from ten to twenty) of statistical features on time windows of a few hundreds samples.