An RBF neural network-based system for home smart metering

In the era of the Internet of Things (IoT), numerous application domains are emerging for a new generation of networked smart devices capable to process and communicate data over the Internet, for building a new smart world. While some large scale domains are certainly of a special interest, e.g., smart grid, some others small scale applications, e.g., smart home, give any user the chance to build his own IoT system. Thanks to the technological development, it is now possible to use and integrate cheap technologies to monitor the state of our homes. The paper is devoted to the implementation of an inexpensive system to measure the energy consumption of a home electrical appliances. An Arduino board equipped with a proper sensor is connected to the specific appliance one wants to monitor, and a web application running on a web server accessible through any device, i.e., pc, tablet or smartphone, makes it possible the real-time monitoring of the energy consumptions and to query for the historical energy rates. Moreover, a forecasting module based on a Radial Basis Function Neural Network trained, in the first layer, by a rough-fuzzy supervised clustering, provides future energy trends.