The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Reinforcement Learning Based Energy Control Method for Smart Energy Buildings Integrated with V2G Station

강화학습 기반 V2G Station 연계형 스마트 에너지 빌딩 전력 제어 기법

  • Seok-Min Choi ;
  • Sun-Yong Kim (Dept. of Software, Dongseo University)
  • 최석민 (동서대학교) ;
  • 김선용 (동서대학교 소프트웨어학과)
  • Received : 2024.04.23
  • Accepted : 2024.06.12
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Energy consumption is steadily increasing, and buildings in particular account for more than 20% of the total energy consumption around the world. As an effort to cost-effectively manage the energy consumption of buildings, many research groups have recently focused on Smart Building Energy Management Systems (BEMS), which are deepening the research depth by applying artificial intelligence(AI). In this paper, we propose a reinforcement learning-based energy control method for smart energy buildings integrated with V2G station, which aims to reduce the total energy cost of the building. The results of performance evaluation based on the energy consumption data measured in the real-world building shows that the proposed method can gradually reduce the total energy costs of the building as the learning process progresses.

전 세계적으로 전력 소비량이 꾸준히 증가하고 있으며, 특히 빌딩의 전력 소비 비율은 세계 전력 소비 비율의 20% 이상을 차지할 만큼 그 비중이 크다. 이에 따라 빌딩에서의 전력 소비를 효율적으로 관리하는 빌딩 에너지 관리 시스템(BEMS, Building Energy Management System)의 연구 및 개발이 활발히 진행되고 있으며, 특히 최근에는 인공지능 기술의 발달로 인해 Smart BEMS 연구가 주목받고 있다. 본 논문에서는 강화학습 기반 V2G(Vehicle-to-Grid) Station 연계형 스마트 에너지 빌딩 전력 제어 기법을 제안한다. 실제 빌딩의 전력량 데이터 기반 성능평가 결과, 학습이 진행됨에 따라 빌딩에서의 전력 요금이 감축하는 것을 확인하였다.

Keywords

Acknowledgement

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (No.2022R1G1A1011513)

References

  1. Q. Abu Al-Haija, "A Stochastic Estimation Framework for Yearly Evolution of Worldwide Electricity Consumption," Forecasting, vol. 3, no. 2, 2021, pp. 256-266.
  2. S. Kim and H. Lim, "Reinforcement Learning Based Energy Management Algorithm for Smart Energy Buildings," Energies, vol. 11, no. 8, 2018, pp. 2010.
  3. K. Moncef and A. Mohammad, "Review analysis of COVID-19 impact on electricity demand for residential buildings," Renewable and Sustainable Energy Reviews, vol. 143, 2021, pp. 110888.
  4. A. Allouhi, Y. El Fouih, T. Kousksou, A. Jamil, Y. Zeraouli, and Y. Mourad, "Energy consumption and efficiency in buildings: current status and future trends," J. of Cleaner production, vol. 109, 2015, pp. 118-130.
  5. H. Kang, J. Park, J. Park, and C. Kim, "A Study on Energy Management System for Energy Saving in Building," J. of Institute of Korean Electrical and Electronics Engineers, vol. 10, no. 7, 2015, pp. 787-792.
  6. L. H. Jose, S. Roberto, C. Alvaro, P. Ricardo, and L. Isabel, "A Fuzzy-Based Building Energy Management System for Energy Efficiency," Buildings, vol. 8, no. 2, 2018, pp. 14-23.
  7. K. Park, Y. Kim, S. Kim, K. Kim, W. Lee, and H. Park, "Building Energy Management System based on Smart Grid," In Proceedings of the 2011 IEEE 33rd International Telecommunications Energy Conference, Amsterdam, Netherlands, 2011, pp. 1-4.
  8. T. Mazhar, M. A. Malik, I. Haq, I. Rozeela, I. Ullah, M. A. Khan, D. Adhikari, M. T. Ben Othman, and H. Hamam, "The Role of ML, AI and 5G Technology in Smart Energy and Smart Building Management," Electronics, vol. 11, no. 23, 2022, pp. 3960.
  9. J. Kim and S. Kim, "Reinforcement Learning-Based Illuminance Control method for Building Lighting System," J. of Institute of Korean Electrical and Electronics Engineers, vol. 26, no. 1, 2022, pp. 56-61.
  10. C. White and J. N. Gilmore, "Imagining the thoughtful home: Google Nest and logics of domestic recording," Critical Studies in Media Communication, vol. 40, no. 1, 2023, pp. 6-19.
  11. S. Choi, S. Lee, and S. Kim, "Building-Integrated V2G Station Scheduling Algorithm based on Reinforcement Learning," In Proceedings of Symposium of the Korean Institute of communications and Information Sciences, Jeju, Korea, 2023, pp. 393-393.
  12. H. Noh and Y. Lim, "Comparative Analysis of Battery Optimization in Grid Considering Consumption Patterns," J. of the Korea Institute of Electronic Communication Science, Vol. 30, no. 2, 2023, pp. 549-552.
  13. S. Lee, "A routing algorithm based on deep reinforcement learning in SDN," J. of the Korea Institute of Electronic Communication Science, vol. 16, no. 6, 2021, pp. 1153-1160.
  14. Z. Zhang, A. Chong, Y. Pan, C. Zhang, and K. P. Lam, "Whole building energy model for HVAC optimal control: A practical framework based on deep reinforcement learning," Energy and Buildings, vol. 199, 2019, pp. 472-490.
  15. Y. Zhao, S. Cen, S. Seong, J. Hur, and C. Lim, "Path Planning with Obstacle Avoidance Based on Double Deep Q Networks," J. of the Korea Institute of Electronic Communication Science, vol. 18, no. 2, 2023, pp. 231-240.