Q-Learning Based Dynamic Task-Offloading Scheme to Improve QoE in Energy Harvesting IoT Edge Computing Environments 


Vol. 46,  No. 12, pp. 2212-2220, Dec.  2021
10.7840/kics.2021.46.12.2212


PDF
  Abstract

Typical IoT(Internet of things) devices have a limited lifetime because they use a battery as an energy source. To fundamentally solve this problem, various environmental energy harvesting IoT is being researched around solar energy. Meanwhile, many studies are attempting to improve the quality of experience (QoE) in terms of the energy problem and delay time of IoT devices. Many of these studies on QoE improvement are approaching it as a cost minimization problem, especially an energy use minimization problem. However, such an energy cost minimization approach due to limited energy is not appropriate for energy harvesting IoT devices, which can continuously harvest energy. Since many energy-harvesting IoT devices can continuously harvest energy, we should approach in the direction of cost optimization that can utilize energy to the maximum rather than cost minimization approach. This study proposes a reinforcement learning-based dynamic task offloading scheme that can enhance user QoE while maximizing the utilization of harvested energy in an energy harvesting IoT edge computing environment. The proposed scheme modeled Q-learning using the information of dynamically changing amount of energy harvesting and the information of IoT devices and edge nodes. It can perform very simple, yet efficiently operates compared to complex models of the conventional minimization problem.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

M. Kang, S. Lee, Y. Gong, Y. Kim, I. Yoon, D. K. Noh, "Q-Learning Based Dynamic Task-Offloading Scheme to Improve QoE in Energy Harvesting IoT Edge Computing Environments," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 12, pp. 2212-2220, 2021. DOI: 10.7840/kics.2021.46.12.2212.

[ACM Style]

Minjae Kang, Seungwoo Lee, Yujin Gong, Younghyun Kim, Ikjune Yoon, and Dong Kun Noh. 2021. Q-Learning Based Dynamic Task-Offloading Scheme to Improve QoE in Energy Harvesting IoT Edge Computing Environments. The Journal of Korean Institute of Communications and Information Sciences, 46, 12, (2021), 2212-2220. DOI: 10.7840/kics.2021.46.12.2212.

[KICS Style]

Minjae Kang, Seungwoo Lee, Yujin Gong, Younghyun Kim, Ikjune Yoon, Dong Kun Noh, "Q-Learning Based Dynamic Task-Offloading Scheme to Improve QoE in Energy Harvesting IoT Edge Computing Environments," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 12, pp. 2212-2220, 12. 2021. (https://doi.org/10.7840/kics.2021.46.12.2212)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880