Machine Learning and Data Segmentation for Building Energy Use Prediction—A Comparative Study
| Autor: | Huda Dawood, William Mounter, Chris Ogwumike, Nashwan Dawood |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Technology
Control and Optimization Computer science Energy Engineering and Power Technology Machine learning computer.software_genre data segmentation support vector regression Electrical and Electronic Engineering Engineering (miscellaneous) Polynomial regression Data processing Artificial neural network Renewable Energy Sustainability and the Environment business.industry prediction buildings Data segment Support vector machine Mean absolute percentage error polynomial regression Artificial intelligence business artificial neural networks computer Energy (signal processing) Predictive modelling energy Energy (miscellaneous) |
| Zdroj: | Energies Volume 14 Issue 18 Energies, Vol 14, Iss 5947, p 5947 (2021) |
| ISSN: | 1996-1073 |
| DOI: | 10.3390/en14185947 |
| Popis: | Advances in metering technologies and emerging energy forecast strategies provide opportunities and challenges for predicting both short and long-term building energy usage. Machine learning is an important energy prediction technique, and is significantly gaining research attention. The use of different machine learning techniques based on a rolling-horizon framework can help to reduce the prediction error over time. Due to the significant increases in error beyond short-term energy forecasts, most reported energy forecasts based on statistical and machine learning techniques are within the range of one week. The aim of this study was to investigate how facility managers can improve the accuracy of their building’s long-term energy forecasts. This paper presents an extensive study of machine learning and data processing techniques and how they can more accurately predict within different forecast ranges. The Clarendon building of Teesside University was selected as a case study to demonstrate the prediction of overall energy usage with different machine learning techniques such as polynomial regression (PR), support vector regression (SVR) and artificial neural networks (ANNs). This study further examined how preprocessing training data for prediction models can impact the overall accuracy, such as via segmenting the training data by building modes (active and dormant), or by days of the week (weekdays and weekends). The results presented in this paper illustrate a significant reduction in the mean absolute percentage error (MAPE) for segmented building (weekday and weekend) energy usage prediction when compared to unsegmented monthly predictions. A reduction in MAPE of 5.27%, 11.45%, and 12.03% was achieved with PR, SVR and ANN, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |