Using deep reinforcement learning for mmWave real-time scheduling

Gahtan B, Cohen R, Bronstein AM, Kedar G. 2023. Using deep reinforcement learning for mmWave real-time scheduling. 14th International Conference on Network of the Future. NoF: Conference on Network of the Future, 71–79.

Download (ext.)

Conference Paper | Published | English

Scopus indexed
Author
Gahtan, Barak; Cohen, Reuven; Bronstein, Alex M.ISTA ; Kedar, Gil
Abstract
We study the problem of real-time scheduling in a multi-hop millimeter-wave (mmWave) mesh. We develop a model-free deep reinforcement learning algorithm called Adaptive Activator RL (AARL), which determines the subset of mmWave links that should be activated during each time slot and the power level for each link. The most important property of AARL is its ability to make scheduling decisions within the strict time frame constraints of typical 5G mmWave networks. AARL can handle a variety of network topologies, network loads, and interference models, it can also adapt to different workloads. We demonstrate the operation of AARL on several topologies: a small topology with 10 links, a moderately-sized mesh with 48 links, and a large topology with 96 links. We show that for each topology, we compare the throughput obtained by AARL to that of a benchmark algorithm called RPMA (Residual Profit Maximizer Algorithm). The most important advantage of AARL compared to RPMA is that it is much faster and can make the necessary scheduling decisions very rapidly during every time slot, while RPMA cannot. In addition, the quality of the scheduling decisions made by AARL outperforms those made by RPMA.
Publishing Year
Date Published
2023-11-01
Proceedings Title
14th International Conference on Network of the Future
Publisher
IEEE
Page
71-79
Conference
NoF: Conference on Network of the Future
Conference Location
Izmir, Turkiye
Conference Date
2023-10-04 – 2023-10-06
eISSN
IST-REx-ID

Cite this

Gahtan B, Cohen R, Bronstein AM, Kedar G. Using deep reinforcement learning for mmWave real-time scheduling. In: 14th International Conference on Network of the Future. IEEE; 2023:71-79. doi:10.1109/nof58724.2023.10302794
Gahtan, B., Cohen, R., Bronstein, A. M., & Kedar, G. (2023). Using deep reinforcement learning for mmWave real-time scheduling. In 14th International Conference on Network of the Future (pp. 71–79). Izmir, Turkiye: IEEE. https://doi.org/10.1109/nof58724.2023.10302794
Gahtan, Barak, Reuven Cohen, Alex M. Bronstein, and Gil Kedar. “Using Deep Reinforcement Learning for MmWave Real-Time Scheduling.” In 14th International Conference on Network of the Future, 71–79. IEEE, 2023. https://doi.org/10.1109/nof58724.2023.10302794.
B. Gahtan, R. Cohen, A. M. Bronstein, and G. Kedar, “Using deep reinforcement learning for mmWave real-time scheduling,” in 14th International Conference on Network of the Future, Izmir, Turkiye, 2023, pp. 71–79.
Gahtan B, Cohen R, Bronstein AM, Kedar G. 2023. Using deep reinforcement learning for mmWave real-time scheduling. 14th International Conference on Network of the Future. NoF: Conference on Network of the Future, 71–79.
Gahtan, Barak, et al. “Using Deep Reinforcement Learning for MmWave Real-Time Scheduling.” 14th International Conference on Network of the Future, IEEE, 2023, pp. 71–79, doi:10.1109/nof58724.2023.10302794.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 2210.01423

Search this title in

Google Scholar
ISBN Search