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.

A scoping review of deep neural networks for electric load forecasting

“…In demand-side management, the household's role is essential to ensure an efficient smart grid. The system can leverage demand-side management tactics based on household energy demand to shift loads, shave peaks or fill valleys (Rodrigues et al, 2017;Saatwong & Suwankawin, 2016). Further, the household energy demand is much more volatile than an aggregated load of multiple households, meaning researchers need to consider other external inputs such as occupancy behavior, building characteristics, and even income and employment status (Ramokone et al, 2020;Yuce et al, 2017).…”

Modeling System Based on Machine Learning Approaches for Predictive Maintenance Applications

“…The random variation is usually based on fluctuations observed in historical data for a selected period [15]. Depending on the data selected and used to train the model, two groups of approaches can be identified [16][17][18][19][20][21][22][23][24][25]: 3. Hybrid models: They represent any combination of two or more of the methods described above [17,25].…”