A Physical Model-Based Data-Driven Approach to Overcome Data Scarcity and Predict Building Energy Consumption
Open Access
- 2 August 2022
- journal article
- research article
- Published by MDPI AG in Sustainability
- Vol. 14 (15) , 9464
Abstract
Predicting building energy consumption needs to be anticipated to save building energy and effectively control the predictions. This study depicted the target building as a physical model to improve the learning performance in a data-scarce environment and proposed a model that uses simulation results as the input for a data-driven model. Case studies were conducted with different quantities of data. The proposed hybrid method proposed in this study showed a higher prediction accuracy showing a cvRMSE of 22.8% and an MAE of 6.1% than using the conventional data-driven method and satisfying the tolerance criteria of ASHRAE Guideline 14 in all the test cases.Keywords
Funding Information
- Korea Agency for Infrastructure Technology Advancement (22CTAP-C164158-02)
This publication has 23 references indexed in Scilit:
- Quantification of electricity flexibility in demand response: Office building case studyEnergy, 2019
- A Comparison of ARIMA and LSTM in Forecasting Time Series2018
- An architecture for emergency event prediction using LSTM recurrent neural networksExpert Systems with Applications, 2018
- Energy simulation for a high-rise building using IDA ICE: Investigations in different climatesBuilding Simulation, 2016
- A hybrid model approach for forecasting future residential electricity consumptionEnergy and Buildings, 2016
- Practical options for selecting data-driven or physics-based prognostics algorithms with reviewsReliability Engineering & System Safety, 2015
- A review on the basics of building energy estimationRenewable and Sustainable Energy Reviews, 2014
- The impact of place-based affiliation networks on energy conservation: An holistic model that integrates the influence of buildings, residents and the neighborhood contextEnergy and Buildings, 2012
- Characteristics of infrared sky radiation in the United StatesSolar Energy, 1984
- Solar and terrestrial radiation dependent on the amount and type of cloudSolar Energy, 1980