Family houses energy consumption forecast tools for smart grid management

Abstract

This paper presents a short term (ST) load forecast (FC) using Artificial Neural Networks (ANNs) or Generalized Reduced Gradient (GRG). Despite the apparent natural unforeseeable behavior of humans, electricity consumption (EC) of a family home can be forecast with some accuracy, similarly to what the electric utilities can do to an agglomerate of family houses. In an existing electric grid, it is important to understand and forecast family house daily or hourly EC with a reliable model for EC and load profile (PF). Demand side management (DSM) programs required this information to adequate the PF of energy load diagram to Electric Generation (EG). In the ST, for load FC model, ANNs were used, taking data from a EC records database. The results show that ANNs or GRG provide a reliable model for FC family house EC and load PF. The use of smart devices such as Cyber-Physical Systems (CPS) for monitoring, gathering and computing a database, improves the FC quality for the next hours, which is a strong tool for Demand Response (DR) and DSM.