Forecasting of short-term lighting and plug load electricity consumption in single residential units: Development and assessment of data-driven models for different horizons

Abstract

Improving the management of electricity resources in residential buildings using intelligent control and energy scheduling requires sub-hourly and hourly predictions of the electricity consumption. However, literature currently provides little evidence and guidelines on the possibility to predict short-term non-HVAC electrical loads in single residential units. In this work, we compare data-driven forecasting models of increasing complexity for predicting lighting and plug load electricity demand in a dwelling over horizons ranging from 10 min to 24 h. Five data-driven approaches are analyzed: (i) persistence forecast, (ii) linear regression, (iii) Apriori algorithm, (iv) gradient boosted regression trees and (v) neural network. Data monitored in eight dwellings located in Quebec City (Canada) are used to train and test the models. For each horizon and for each dwelling, we selected the inputs required to make the best prediction based on Pearson correlation coefficients and we then optimized the hyperparameters of each data-driven method. Overall, the gradient boosted regression trees model yielded the best performance, but was followed closely by some of the other techniques depending on the residential unit and time horizon. With this prediction technique, we found root-mean square errors normalized by average consumption typically ranging from 20 to 100%, respectively for 24-hour and 10-minute horizons. The main contribution of this work is the assessment of the level of predictability and methods to forecast electrical loads of individual dwellings, over many horizons, and excluding space heating and domestic hot water production.