Predicting Future Hourly Residential Electrical Consumption: A Machine Learning Case Study

Journal Article · Sun Jan 01 04:00:00 UTC 2012 · Energy and Buildings

DOI:https://doi.org/10.1016/j.enbuild.2012.03.010· OSTI ID:1041424

Edwards, Richard E ^[1]; New, Joshua Ryan ^[1]; Parker, Lynne Edwards ^[1]

---

1. ORNL

Whole building input models for energy simulation programs are frequently created in order to evaluate specific energy savings potentials. They are also often utilized to maximize cost-effective retrofits for existing buildings as well as to estimate the impact of policy changes toward meeting energy savings goals. Traditional energy modeling suffers from several factors, including the large number of inputs required to characterize the building, the specificity required to accurately model building materials and components, simplifying assumptions made by underlying simulation algorithms, and the gap between the as-designed and as-built building. Prior works have attempted to mitigate these concerns by using sensor-based machine learning approaches to model energy consumption. However, a majority of these prior works focus only on commercial buildings. The works that focus on modeling residential buildings primarily predict monthly electrical consumption, while commercial models predict hourly consumption. This means there is not a clear indicator of which techniques best model residential consumption, since these methods are only evaluated using low-resolution data. We address this issue by testing seven different machine learning algorithms on a unique residential data set, which contains 140 different sensors measurements, collected every 15 minutes. In addition, we validate each learner's correctness on the ASHRAE Great Energy Prediction Shootout, using the original competition metrics. Our validation results confirm existing conclusions that Neural Network-based methods perform best on commercial buildings. However, the results from testing our residential data set show that Feed Forward Neural Networks, Support Vector Regression (SVR), and Linear Regression methods perform poorly, and that Hierarchical Mixture of Experts (HME) with Least Squares Support Vector Machines (LS-SVM) performs best - a technique not previously applied to this domain.

• Research Organization: Oak Ridge National Laboratory (ORNL)
• Sponsoring Organization: EE USDOE - Office of Energy Efficiency and Renewable Energy (EE)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1041424
• Journal Information: Energy and Buildings, Journal Name: Energy and Buildings Journal Issue: 0 Vol. 49; ISSN ENEBDR; ISSN 0378-7788
• Country of Publication: United States
• Language: English

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
ALGORITHMS
BUILDING MATERIALS
COMMERCIAL BUILDINGS
ENERGY CONSUMPTION
FORECASTING
LEARNING
METRICS
MIXTURES
NEURAL NETWORKS
RESIDENTIAL BUILDINGS
SENSORS
SIMULATION
SPECIFICITY
TESTING
VALIDATION
VECTORS