Distributed Uplink Beamforming in Cell-Free Networks Using Deep Reinforcement Learning

The emergence of new wireless technologies together with the requirement of massive connectivity results in several technical issues such as excessive interference, high computational demand for signal processing, and lengthy processing delays. In this work, we propose several beamforming techniques for an uplink cell-free network with centralized, semi-distributed, and fully distributed processing, all based on deep reinforcement learning (DRL). First, we propose a fully centralized beamforming method that uses the deep deterministic policy gradient algorithm (DDPG) with continuous space. We then enhance this method by enabling distributed experience at access points (AP). Indeed, we develop a beamforming scheme that uses the distributed distributional deterministic policy gradients algorithm (D4PG) with the APs representing the distributed agents. Finally, to decrease the computational complexity, we propose a fully distributed beamforming scheme that divides the beamforming computations among APs. The results show that the D4PG scheme with distributed experience achieves the best performance irrespective of the network size. Furthermore, the proposed distributed beamforming technique performs better than the DDPG algorithm with centralized learning only for small-scale networks. The performance superiority of the DDPG model becomes more evident as the number of APs and/or users increases. Moreover, during the operation stage, all DRL models demonstrate a significantly shorter processing time than that of the conventional gradient descent (GD) solution.

[1]  Emil Björnson,et al.  Scalable Cell-Free Massive MIMO Systems , 2019, IEEE Transactions on Communications.

[2]  Shi Jin,et al.  Channel Estimation for Cell-Free mmWave Massive MIMO Through Deep Learning , 2019, IEEE Transactions on Vehicular Technology.

[3]  Matthew W. Hoffman,et al.  Distributed Distributional Deterministic Policy Gradients , 2018, ICLR.

[4]  Yuval Tassa,et al.  Continuous control with deep reinforcement learning , 2015, ICLR.

[5]  Emil Björnson,et al.  Centralized and Distributed Power Allocation for Max-Min Fairness in Cell-Free Massive MIMO , 2019, 2019 53rd Asilomar Conference on Signals, Systems, and Computers.

[6]  Mérouane Debbah,et al.  Uplink Power Control in Cell-Free Massive MIMO via Deep Learning , 2019, 2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP).

[7]  Shree Krishna Sharma,et al.  Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future , 2019, IEEE Access.

[8]  Erik G. Larsson,et al.  Cell-Free Massive MIMO: Uniformly great service for everyone , 2015, 2015 IEEE 16th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[9]  Emil Björnson,et al.  Ubiquitous cell-free Massive MIMO communications , 2018, EURASIP Journal on Wireless Communications and Networking.

[10]  Alister G. Burr,et al.  On the Uplink Max–Min SINR of Cell-Free Massive MIMO Systems , 2019, IEEE Transactions on Wireless Communications.

[11]  Osvaldo Simeone,et al.  A Very Brief Introduction to Machine Learning With Applications to Communication Systems , 2018, IEEE Transactions on Cognitive Communications and Networking.

[12]  Bhaskar D. Rao,et al.  Precoding and Power Optimization in Cell-Free Massive MIMO Systems , 2017, IEEE Transactions on Wireless Communications.

[13]  Ekram Hossain,et al.  Multiple Access in Dynamic Cell-Free Networks: Outage Performance and Deep Reinforcement Learning-Based Design , 2020, ArXiv.

[14]  Vincent K. N. Lau,et al.  Joint BS-User Association, Power Allocation, and User-Side Interference Cancellation in Cell-free Heterogeneous Networks , 2017, IEEE Transactions on Signal Processing.

[15]  Mohammad M. Mansour,et al.  Efficient Angle-Domain Processing for FDD-Based Cell-Free Massive MIMO Systems , 2020, IEEE Transactions on Communications.

[16]  Emil Björnson,et al.  Dynamic Resource Allocation in Co-Located and Cell-Free Massive MIMO , 2019, IEEE Transactions on Green Communications and Networking.

[17]  Rudolf H. Riedi An Introduction to Statistical Signal Processing , 2006 .

[18]  Chong-Yung Chi,et al.  QoS-Based Transmit Beamforming in the Presence of Eavesdroppers: An Optimized Artificial-Noise-Aided Approach , 2011, IEEE Transactions on Signal Processing.

[19]  David Gesbert,et al.  A Coordinated Approach to Channel Estimation in Large-Scale Multiple-Antenna Systems , 2012, IEEE Journal on Selected Areas in Communications.

[20]  Guy Lever,et al.  Deterministic Policy Gradient Algorithms , 2014, ICML.

[21]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[22]  Mohammad M. Mansour,et al.  Angle-Based Multipath Estimation and Beamforming for FDD Cell-free Massive MIMO , 2019, 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[23]  Erik G. Larsson,et al.  Cell-Free Massive MIMO Versus Small Cells , 2016, IEEE Transactions on Wireless Communications.

[24]  Jing Wang,et al.  Distributed wireless communication system: a new architecture for future public wireless access , 2003, IEEE Commun. Mag..

[25]  Dong In Kim,et al.  Generalized Coordinated Multipoint (GCoMP)-Enabled NOMA: Outage, Capacity, and Power Allocation , 2019, IEEE Transactions on Communications.

[26]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[27]  Petar Popovski,et al.  5G Wireless Network Slicing for eMBB, URLLC, and mMTC: A Communication-Theoretic View , 2018, IEEE Access.

[28]  Jingxian Wu,et al.  Max-Min Optimal Beamforming for Cell-Free Massive MIMO , 2020, IEEE Communications Letters.

[29]  Rasoul Nikbakht,et al.  Unsupervised-Learning Power Control for Cell-Free Wireless Systems , 2019, 2019 IEEE 30th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC).

[30]  Emil Björnson,et al.  Making Cell-Free Massive MIMO Competitive With MMSE Processing and Centralized Implementation , 2019, IEEE Transactions on Wireless Communications.

[31]  Angel Lozano,et al.  Modified Conjugate Beamforming for Cell-Free Massive MIMO , 2019, IEEE Wireless Communications Letters.

[32]  Ekram Hossain,et al.  The D-OMA Method for Massive Multiple Access in 6G: Performance, Security, and Challenges , 2019, IEEE Vehicular Technology Magazine.

[33]  Guillem Femenias,et al.  Cell-Free Millimeter-Wave Massive MIMO Systems With Limited Fronthaul Capacity , 2019, IEEE Access.