TY - JOUR
T1 - Deep Reinforcement Learning for 5G Networks
T2 - Joint Beamforming, Power Control, and Interference Coordination
AU - Mismar, Faris B.
AU - Evans, Brian L.
AU - Alkhateeb, Ahmed
N1 - Publisher Copyright:
© 1972-2012 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - The fifth generation of wireless communications (5G) promises massive increases in traffic volume and data rates, as well as improved reliability in voice calls. Jointly optimizing beamforming, power control, and interference coordination in a 5G wireless network to enhance the communication performance to end users poses a significant challenge. In this paper, we formulate the joint design of beamforming, power control, and interference coordination as a non-convex optimization problem to maximize the signal to interference plus noise ratio (SINR) and solve this problem using deep reinforcement learning. By using the greedy nature of deep Q-learning to estimate future rewards of actions and using the reported coordinates of the users served by the network, we propose an algorithm for voice bearers and data bearers in sub-6 GHz and millimeter wave (mmWave) frequency bands, respectively. The algorithm improves the performance measured by SINR and sum-rate capacity. In realistic cellular environments, the simulation results show that our algorithm outperforms the link adaptation industry standards for sub-6 GHz voice bearers. For data bearers in the mmWave frequency band, our algorithm approaches the maximum sum rate capacity, but with less than 4% of the required run time.
AB - The fifth generation of wireless communications (5G) promises massive increases in traffic volume and data rates, as well as improved reliability in voice calls. Jointly optimizing beamforming, power control, and interference coordination in a 5G wireless network to enhance the communication performance to end users poses a significant challenge. In this paper, we formulate the joint design of beamforming, power control, and interference coordination as a non-convex optimization problem to maximize the signal to interference plus noise ratio (SINR) and solve this problem using deep reinforcement learning. By using the greedy nature of deep Q-learning to estimate future rewards of actions and using the reported coordinates of the users served by the network, we propose an algorithm for voice bearers and data bearers in sub-6 GHz and millimeter wave (mmWave) frequency bands, respectively. The algorithm improves the performance measured by SINR and sum-rate capacity. In realistic cellular environments, the simulation results show that our algorithm outperforms the link adaptation industry standards for sub-6 GHz voice bearers. For data bearers in the mmWave frequency band, our algorithm approaches the maximum sum rate capacity, but with less than 4% of the required run time.
KW - Reinforcement learning (RL)
KW - beamforming
KW - deep learning
KW - millimeter wave (mmWave)
KW - power control
UR - http://www.scopus.com/inward/record.url?scp=85082170447&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082170447&partnerID=8YFLogxK
U2 - 10.1109/TCOMM.2019.2961332
DO - 10.1109/TCOMM.2019.2961332
M3 - Article
AN - SCOPUS:85082170447
SN - 0090-6778
VL - 68
SP - 1581
EP - 1592
JO - IEEE Transactions on Communications
JF - IEEE Transactions on Communications
IS - 3
M1 - 8938771
ER -