An Overview of a New Statistical Non-Intrusive Load Monitoring (NILM) Analysis and Recognition Approach for Domestic Environments: DENARDO
IP devices are ubiquitously spread, for both residential and industrial purposes, thanks to the low integration costs and rapid development cycle of all-IP-based 5G+ technologies. As a consequence, the engineering community now considers their automatization and energy scheduling/management as relevant research fields. These topics have a striking relevance also for the development of smart city networks. As a drawback, most ID-device applications produce a large amount of data (high-frequency complexity), requiring supervised machine learning algorithms to be properly analyzed. In this research, we focus on the performance of vehicular mobility and imaging systems, recognizing scenarios (with powered-on devices) in real-time, with the help of a simple convolutional neural network, proving the effectiveness of such an innovative low-cost approach.