DOI QR코드

DOI QR Code

A Study on the Improvement of Heat Energy Efficiency for Utilities of Heat Consumer Plants based on Reinforcement Learning

강화학습을 기반으로 하는 열사용자 기계실 설비의 열효율 향상에 대한 연구

  • Kim, Young-Gon (Advanced Institutes of Convergence Technology(AICT) Seoul National University) ;
  • Heo, Keol (Advanced Institutes of Convergence Technology(AICT) Seoul National University) ;
  • You, Ga-Eun (Advanced Institutes of Convergence Technology(AICT) Seoul National University) ;
  • Lim, Hyun-Seo (Advanced Institutes of Convergence Technology(AICT) Seoul National University) ;
  • Choi, Jung-In (Advanced Institutes of Convergence Technology(AICT) Seoul National University) ;
  • Ku, Ki-Dong (Korea District Heating Corp.) ;
  • Eom, Jae-Sik (Korea District Heating Corp.) ;
  • Jeon, Young-Shin (Korea District Heating Corp.)
  • 김영곤 (서울대학교 차세대융합기술연구원) ;
  • 허걸 (서울대학교 차세대융합기술연구원) ;
  • 유가은 (서울대학교 차세대융합기술연구원) ;
  • 임현서 (서울대학교 차세대융합기술연구원) ;
  • 최중인 (서울대학교 차세대융합기술연구원) ;
  • 구기동 (한국지역난방공사 미래개발원) ;
  • 엄재식 (한국지역난방공사 미래개발원) ;
  • 전영신 (한국지역난방공사 미래개발원)
  • Received : 2018.05.16
  • Accepted : 2018.06.04
  • Published : 2018.06.30

Abstract

This paper introduces a study to improve the thermal efficiency of the district heating user control facility based on reinforcement learning. As an example, it is proposed a general method of constructing a deep Q learning network(DQN) using deep Q learning, which is a reinforcement learning algorithm that does not specify a model. In addition, it is also introduced the big data platform system and the integrated heat management system which are specialized in energy field applied in processing huge amount of data processing from IoT sensor installed in many thermal energy control facilities.

이 논문은 강화학습기반으로 지역난방 열사용자 기계실 설비의 열효율 향상을 시도하는 연구를 소개하며, 한 예시로서 모델을 특정하지 않는 강화학습 알고리즘인 딥큐러닝(deep Q learning)을 활용하는 학습 네트워크(DQN)를 구성하는 일반적인 방법을 제시한다. 또한 복수의 열에너지 기계실에 설치된 IoT 센서로부터 유입되는 방대한양의 데이터 처리에 있어 에너지 분야에 특화된 빅데이터 플랫폼 시스템과 열수요 통합관리시스템에 대하여 소개 한다.

Keywords

References

  1. K. Kwon., 2018, Multi Behavior Learning of Lamp Robot based on Q-learning, Journal of Digital Contents Society 19(1), pp. 35-41 https://doi.org/10.9728/DCS.2018.19.1.35
  2. Ki. Kim., 2018, Natural Behavior Learning Based on Deep Reinforcement Learning for Autonomous Navigation of Mobile Robots, Journal of Institute of Control, Robotics and Systems, 24(3), pp. 256-262 https://doi.org/10.5302/J.ICROS.2018.17.0230
  3. Y. Kong., 2017, Dynamic Obstacle Avoidance and Optimal Path Finding Algorithm for Mobile Robot Using Q-learning, Journal of Korean Institute of Information Technology, 15(9), pp. 57-62
  4. Apache Kafka, https://kafka.apache.org/
  5. Apache Hadoop. https://hadoop.apache.org/
  6. M. Song., 2017, Development of Big Data System for Energy Big Data, Journal of Korean Institute of Information Technology, 24(1), pp. 24-3
  7. M. Song., Development of Heat Demand Management System for District Heating based on Big Data Platform, Journal of Korean Institute of Information Technology, pp. 31-33
  8. Apache Spark. https://spark.apache.org/
  9. Apache Spark SQL, http://spark.apache.org/sql/
  10. Apache Flume, https://flume.apache.org/
  11. Apache Sqoop, https://sqoop.apache.org/