Deep Reinforcement Learning for Mode Optimization in RF-Powered Backscatter Cognitive Radio Networks 


Vol. 46,  No. 2, pp. 246-256, Feb.  2021
10.7840/kics.2021.46.2.246


PDF
  Abstract

In an RF-powered backscatter cognitive radio network, the secondary transmitter (ST) harvests energy or backscatters information when the primary channel is busy. Alternatively, the ST actively transmits data using the harvested energy when the primary channel becomes idle. It is critical to decide when to harvest, backscatter, and actively transmit to maximize the throughput of the secondary system under unpredictable primary channel states. In this paper, we propose a deep reinforcement learning-based mode optimization scheme in which the ST can learn the optimal policy through rewards obtained by interacting with the primary channel. To be more specific, the ST is required to perform harvesting mode to observe the reward. We formulate the proposed scheme with a Markov decision process and design a deep Q-network (DQN) for mode optimization. To accelerate the training process, we introduce a penalty for energy outage. The achievable throughput was validated through simulations by considering a greedy policy based on the trained DQN model. It was also compared to the ideal case when the complete information about the primary channel is provided.

  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]

S. Wu, M. Kwon, J. Y. Kim, Y. Shin, "Deep Reinforcement Learning for Mode Optimization in RF-Powered Backscatter Cognitive Radio Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 2, pp. 246-256, 2021. DOI: 10.7840/kics.2021.46.2.246.

[ACM Style]

Shanai Wu, Minhae Kwon, Jin Young Kim, and Yoan Shin. 2021. Deep Reinforcement Learning for Mode Optimization in RF-Powered Backscatter Cognitive Radio Networks. The Journal of Korean Institute of Communications and Information Sciences, 46, 2, (2021), 246-256. DOI: 10.7840/kics.2021.46.2.246.

[KICS Style]

Shanai Wu, Minhae Kwon, Jin Young Kim, Yoan Shin, "Deep Reinforcement Learning for Mode Optimization in RF-Powered Backscatter Cognitive Radio Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 2, pp. 246-256, 2. 2021. (https://doi.org/10.7840/kics.2021.46.2.246)