Authors - L. Ciabattoni, G. Ippoliti, A. Benini, S. Longhi, M. Pirro
Abstract - In this paper the design and test of a home energy management system have been considered. The device, monitoring home loads, detecting and forecasting photovoltaic (PV) power production and home consumptions, informs and influence users behaviour on their energy demand.
A neural network based self-learning prediction algorithm is used to forecast the power production of the PV plant and the household consumptions over a determined time horizon. A semi auto active demand side management technique is used to maximize the amount of PV electricity directly used on-site. The proposed solution has been experimentally tested in 3 houses with 3.3 KWp PV plant.
This paper is available on Science Direct.