DOI QR코드

DOI QR Code

PCA 적용 데이터 차원 변화에 따른 LSTM 기반 건물 전력 소비량 예측 - 대전 캠퍼스 건물을 중심으로 -

LSTM-based Prediction of Building Power Consumption with PCA Based Data Dimension Change - Centered on a Campus Building in Daejeon -

  • 투고 : 2021.07.05
  • 심사 : 2021.09.06
  • 발행 : 2021.09.30

초록

Building energy demand currently accounts for 30% of the total energy consumption, which has a great influence on the planning and operation of the energy market managed by energy suppliers. Furthermore, its importance has increased significantly with the advent of smart grid. Variables affecting building energy consumption include identified various environmental conditions that cast sophisticated effect on the energy performance of the buildings. However, due to a large number of potentially associated environmental variables, it is needed to extract embedded features so as to improve building energy prediction capability through adopting Principle Component Analysis which could reduce input data dimension. The primary objective of this study is to propose a high-precision building energy demand prediction model by reducing the dimensionality through PCA. Machine learning is implemented by using LSTM model, and prediction accuracy and performance are verified through R2, RMSE, MAE, as well as computation time. The improvement ratio showed 14.93% increase when dimension-reduced dataset and normalized raw data were combined in comparison with the predicted case tested by using only normalized raw data. This study could support optimum building energy operation planning and design by promoting the creation and implementation of energy-efficient smart grid systems in the future.

키워드

과제정보

본 연구는 국토교통부 / 국토교통과학기술진흥원의 지원으로 수행되었으며(과제번호 21PIYR-B153277-03) 이 논문은 국토교통부의 스마트시티 혁신인재육성사업으로 지원되었습니다.

참고문헌

  1. Ministry of Land, Infrastructure and Transport. (2014). A study on the standarization of quantitive evaluation method of building energy performance.
  2. Al-Honmoud, M. S. (2001). Computer-aided building energy analysis techniques, Building and Environment.
  3. A.M. Castro Martinez., S.H. Mallidi & B.T. Meyer. (2017). On the relevance of auditory-based Gabor features for deep learning in robust speech recognition, Computer Speech & Language, 45, 21-38. https://doi.org/10.1016/j.csl.2017.02.006
  4. Kim, S., & Park, S. (2011). Multi-class classification of database workloads using PCA-SVM classifier, The Korean Institute of information Scientists and Engineers, 38(1), 1-8.
  5. Liang, C., Li, H., Lei, M., & Du, Q. (2018). Dongting lake water level forcast and its relationship with the three gorges dam based on a long short-term memory network, Water, 10(10), 1389. https://doi.org/10.3390/w10101389
  6. Seo, W., & Park, C. (2012). Issues and limitations in simulation application for building energy diagnosis, Architectural Institute of Korea.
  7. Tran, Q., & Song, S. (2017). Water level forecasting based on deep learning: A use case of trincity river-Texas-The United States, The Journal of Korean Institute of Information Scientists and Engineers, 44(6), 607-612.