Anomaly Detection Algorithm Based on Hybrid Model for Establishing Appropriate Energy Baseline

Tae-Kyu Lee; Jeong-Uk Kim

doi:10.22696/jkiaebs.20240010

All Issue

2024 Vol.18, Issue 2 Preview Page Next Page

Research Article

Anomaly Detection Algorithm Based on Hybrid Model for Establishing Appropriate Energy Baseline 적정 에너지 베이스라인 구축을 위한 하이브리드 모델 기반 이상값 검출 알고리즘

30 April 2024. pp. 109-121

PDF XML

Abstract

This study explores the importance of establishing an appropriate energy baseline for the energy management of buildings and building complexes. The energy baseline serves as a benchmark for assessing a building’s energy consumption and accurately measuring the effects of energy-saving measures. With many buildings using energy inefficiently, accurately setting an energy baseline presents challenges. This research emphasizes the necessity of continuously monitoring a building’s energy consumption to establish a sustainable energy management strategy. The proper setting and management of an energy baseline play a crucial role in assessing the effectiveness of energy demand management projects. The study demonstrates that the energy baseline varies according to energy consumption behavior, revealing up to a 28% daily discrepancy in estimated energy baseline through the detection of anomaly data. These findings suggest difficulties in accurately determining an energy baseline, yet underline the need for appropriate criteria for judgment and the significance of constructing a proper baseline for accurately calculating the energy-saving effects from a demand management perspective. Future research aims to develop additional algorithms for analyzing energy consumption behavior and detecting anomalous data.

Keywords

Building energy

Energy saving

Energy baseline

Anomaly detection

키워드

건물에너지

에너지 절감

에너지 베이스라인

이상데이터 검출

References

Afroz, Z., Gunay, H.B., O'Brien, W., Newsham, G., Wilton, I. (2021). An inquiry into the capabilities of baseline building energy modelling approaches to estimate energy savings. Energy and Buildings, 244, 111054. DOI: https://doi.org/10.1016/j.enbuild. 2021.111054.

10.1016/j.enbuild.2021.111054

Díaz, J.A., Ramos, J.S., Delgado, M.C.G., García, D.H., Montoya, F.G., Domínguez, S.Á. (2018). A daily baseline model based on transfer functions for the verification of energy saving. A case study of the administration room at the Palacio de la Madraza, Granada. Applied Energy, 224, 538-549. DOI: https://doi.org/10.1016/j.apenergy.2018.04.060.

10.1016/j.apenergy.2018.04.060

Jung, Y.W., Kim, J.Y., Kim, J.U. (2020). Optimal Selection of Energy Baseline Through Analysis of Electrical Energy Consumption Statistics and Influence Factors of Office Buildings. Journal of Korean Institute of Architectural Sustainable Environment and Building Systems, 14(6), 601-612.

Kim, Y.M. (2021). Greenhouse Gas Reduction Targets for 2050 and Policy Instruments for Carbon Neutrality in the Building Sector. KRIHS, 479.

Kwak, R.Y. (2008). Questionnaire survey & Evaluation for Quality Level of Energy Management System in Buildings. Journal of the Architectural Institute of Korea Planning & Design, 24(12), 353-360.

Qaisar, I., Zhao, Q. (2022). Energy baseline prediction for buildings: A review. Results in Control and Optimization, 7, 100129. DOI: https://doi.org/10.1016/j.rico.2022.100129.

10.1016/j.rico.2022.100129

Sarmas, E., Forouli, A., Marinakis, V., Doukas, H. (2024). Baseline energy modeling for improved measurement and verification through the use of ensemble artificial intelligence models. Information Sciences, 654, 119879, DOI: https://doi.org/10.1016/j.ins. 2023.119879.

10.1016/j.ins.2023.119879

Seong, N.C., Hong, G.P. (2022). An Analysis of the Effect of the Data Preprocess on the Performance of Building Load Prediction Model Using Multilayer Neural Networks. Journal of Korean Institute of Architectural Sustainable Environment and Building Systems, 16(4), 273-284.

Srivastav, A., Tewari, A., Dong, B. (2013). Baseline building energy modeling and localized uncertainty quantification using Gaussian mixture models. Energy and Buildings, 65, 438-447. DOI: https://doi.org/10.1016/j.enbuild.2013.05.037.

10.1016/j.enbuild.2013.05.037

Wi, Y.M. (2017). A Study on the Baseline Load Estimation Method using Heating Degree Days and Cooling Degree Days Adjustment. The Transactions of the Korean Institute of Electrical Engineers, 66(5), 745-749.

10.5370/KIEE.2017.66.5.745

Yoon, Y.R., Lee, M.H., Moon, H.J. (2018). Comparison of Building Energy Prediction Models based on Machine Learning Algorithms for Hourly M&V Baseline. The Korean Society of Living Environmental System, 25(5), 595-602.

10.21086/ksles.2018.10.25.5.595

Cho, J.K. (2020). A Study on Evaluation Methodologies of Energy Efficiency Rating for Data Centers. 2020 SAREK Winter Annual Conference, 376-379.

Lee, T.W. (2022). Suggestions for supply expansion and industry activation of the building & energy management system. 2022 SAREK Winter Annual Conference, 173-176.

United Nations (UN). (2020). 2020 Global Status Report for Buildings and Construction; Towards a zero-emissions, efficient and resilient buildings and construction sector.

Information

Publisher :Korean Institute of Architectural Sustainable Environment and Building Systems
Publisher(Ko) :한국건축친환경설비학회
Journal Title :Journal of Korean Institute of Architectural Sustainable Environment and Building Systems
Journal Title(Ko) :한국건축친환경설비학회논문집
Volume : 18
No :2
Pages :109-121
Received Date : 2024-02-26
Revised Date : 2024-04-07
Accepted Date : 2024-04-18
DOI :https://doi.org/10.22696/jkiaebs.20240010

Journal of Korean Institute of Architectural Sustainable Environment and Building Systems ISSN:1976-6483(Print) 2586-0666(Online) 한국건축친환경설비학회논문집

All Issue