본문 바로가기
  • Home

Efficient Resource Allocation for Energy Saving with Reinforcement Learning in Industrial IoT Network

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2024, 29(9), pp.169-177
  • DOI : 10.9708/jksci.2024.29.09.169
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : July 17, 2024
  • Accepted : August 26, 2024
  • Published : September 30, 2024

Dongyeong Seo 1 Kwansoo Jung ORD ID 2 Kwansoo Jung ORD ID 3

1한국전자통신연구원
2대전대학교
3순천향대학교

Accredited

ABSTRACT

Industrial Wireless Sensor Network (IWSN) is a key feature of Industrial IoT that enables industrial automation through process monitoring and control by connecting industrial equipment such as sensors, robots, and machines wirelessly, and must support the strict requirements of modern industrial environments such as real-time, reliability, and energy efficiency. To achieve these goals, IWSN uses reliable communication methods such as multipath routing, fixed redundant resource allocation, and non-contention-based scheduling. However, the issue of wasting redundant resources that are not utilized for communication degrades not only the efficiency of limited radio resources but also the energy efficiency. In this paper, we propose a scheme that utilizes reinforcement learning in communication scheduling to periodically identify unused wireless resources and reallocate them to save energy consumption of the entire industrial network. The experimental performance evaluation shows that the proposed approach achieves about 30% improvement of resource efficiency in scheduling compared to the existing method while supporting high reliability. In addition, the energy efficiency and latency are improbed by more than 21% and 38%, respectively, by reducing unnecessary communication.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.