Q-learning Based Downlink MIMO-NOMA Scheme for Vehicle Networks 


Vol. 44,  No. 8, pp. 1493-1503, Aug.  2019
10.7840/kics.2019.44.8.1493


PDF
  Abstract

As various services such as multimedia streaming are increasing in the vehicle networks, the demand for high-capacity of wireless communications is increasing. The multiple-input and multiple-output (MIMO) - non-orthogonal multiple access (NOMA) scheme is one of candidates that solve the problem. The road side unit (RSU), which operates as a base station in the vehicle network, allocates the transmission power to the vehicles according to the channel state of the vehicles. The conventional NOMA schemes have allocated the transmission power to the vehicles under the assumption that the RSU perfectly knows all the channel state of the vehicles. However, in the practical environments, it is impossible for the RSU to know all the channel state without error. In this paper, we develop a power allocation scheme under the assumption that a RSU imperfectly knows the channel state of the vehicles in the heterogeneous vehicle networks with the MIMO-NOMA based V2I communications and the orthogonal multiple access (OMA) based V2V communications. Moreover, we apply the Q-learning algorithm of the machine learning to the MIMO-NOMA scheme in order to allocate the transmit power. The proposed Q-learning based power allocation shows that the overall system throughput can converge within a short time.

  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]

J. Lee, G. Choi, J. So, "Q-learning Based Downlink MIMO-NOMA Scheme for Vehicle Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 8, pp. 1493-1503, 2019. DOI: 10.7840/kics.2019.44.8.1493.

[ACM Style]

Jaehee Lee, Giwook Choi, and Jaewoo So. 2019. Q-learning Based Downlink MIMO-NOMA Scheme for Vehicle Networks. The Journal of Korean Institute of Communications and Information Sciences, 44, 8, (2019), 1493-1503. DOI: 10.7840/kics.2019.44.8.1493.

[KICS Style]

Jaehee Lee, Giwook Choi, Jaewoo So, "Q-learning Based Downlink MIMO-NOMA Scheme for Vehicle Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 8, pp. 1493-1503, 8. 2019. (https://doi.org/10.7840/kics.2019.44.8.1493)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880