Deep Reinforcement Learning Based Power Control for Wireless Multicast Systems

Raghu, R and Upadhyaya, P and Panju, M and Agarwal, V and Sharma, V (2019) Deep Reinforcement Learning Based Power Control for Wireless Multicast Systems. In: 57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019, 24-27 September 2019, Monticello, IL, USA, USA, pp. 1168-1175.

PDF ann_all_con_com_con_com_all_2019.pdf - Published Version Restricted to Registered users only Download (515kB) | Request a copy

Abstract

We consider a multicast scheme recently proposed for a wireless downlink 1. It was shown earlier that power control can significantly improve its performance. However for this system, obtaining optimal power control is intractable because of a very large state space. Therefore in this paper we use deep reinforcement learning where we use function approximation of the Q-function via a deep neural network. We show that optimal power control can be learnt for reasonably large systems via this approach. The average power constraint is ensured via a Lagrange multiplier, which is also learnt. In the longer version of the paper 2, we also demonstrate that our learning algorithm can be modified to allow the optimal control to track the time varying system statistics.

Item Type:	Conference Paper
Publication:	2019 57th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2019
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	Copyright of this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Deep neural networks; Lagrange multipliers; Learning algorithms; Machine learning; Multicasting; Quality control; Quality of service; Reinforcement learning; Time varying systems, Average power; Function approximation; Large system; Optimal controls; Optimal power control; Q-functions; Wireless downlink; Wireless multicast, Power control
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	17 Feb 2020 07:57
Last Modified:	17 Feb 2020 07:57
URI:	http://eprints.iisc.ac.in/id/eprint/64451

Actions (login required)

View Item