Abstract
Machine learning models have proven to be reliable methods in the forecasting of energy use in commercial and office buildings. However, little research has been done on energy forecasting in dwellings, mainly due to the difficulty of obtaining household level data while keeping the privacy of inhabitants in mind. Gaining insight into the energy consumption in the near future can be helpful in balancing the grid and insights in how to reduce the energy consumption can be received. In collaboration with OPSCHALER, a measurement campaign on the influence of housing characteristics on energy costs and comfort, several machine learning models were compared on forecasting performance and the computational time needed. Nine months of data containing the mean gas consumption of 52 dwellings on a one hour resolution was used for this research. The first 6 months were used for training, whereas the last 3 months were used to evaluate the models. The results showed that the Deep Neural Network (DNN) performed best with a 50.1 % Mean Absolute Percentage Error (MAPE) on a one hour resolution. When comparing daily and weekly resolutions, the Multivariate Linear Regression (MVLR) outperformed other models, with a 20.1 % and 17.0 % MAPE, respectively. The models were programmed in Python.
Highlights
In recent years the European Commission has set ambitious CO2 emission reduction targets
In comparison to Multivariate Linear Regression (MVLR), Deep Neural Network (DNN) outperformed MVLR because of its ability to adapt to non-linearities
A probable reason for Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) performing worse than expected is the presence of Not a Number (NaN) in the dataset
Summary
In recent years the European Commission has set ambitious CO2 emission reduction targets. The importance of diminishing natural gas consumption in dwellings is growing. Gaining insight in the prediction of gas consumption in dwellings is critical to meet the Dutch government requirements. A vast number of research has been conducted towards energy consumption prediction in commercial and office buildings [2, 3, 4, 5, 6]. Little research has been conducted to predict gas consumption on single household level due to the difficulty of obtaining the energy use data due to data privacy [7]. From commercial and office building energy forecasting research, Alberto Hernandez Neto [3] concluded that deep neural networks outperform physical simulation models by 3-6 %. This paper focusses on comparing the accuracy of widely discussed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
