Wireless Power Control via Counterfactual Optimization of Graph Neural Networks

We consider the problem of downlink power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium. To mitigate the interference among concurrent transmissions, we leverage the network topology to create a graph neural network architecture, and we then use an unsupervised primal-dual counterfactual optimization approach to learn optimal power allocation decisions. We show how the counterfactual optimization technique allows us to guarantee a minimum rate constraint, which adapts to the network size, hence achieving the right balance between average and 5th percentile user rates throughout a range of network configurations.

[1]  Navid Naderializadeh,et al.  ITLinQ: A New Approach for Spectrum Sharing in Device-to-Device Communication Systems , 2013, IEEE Journal on Selected Areas in Communications.

[2]  Ashwin Sampath,et al.  Cell Association and Interference Coordination in Heterogeneous LTE-A Cellular Networks , 2010, IEEE Journal on Selected Areas in Communications.

[3]  Zhu Han,et al.  Game-theoretic resource allocation for full-duplex communications , 2016, IEEE Wireless Communications.

[4]  Syed Ali Jafar,et al.  On the Optimality of Treating Interference as Noise , 2015, IEEE Transactions on Information Theory.

[5]  Zhi-Quan Luo,et al.  An iteratively weighted MMSE approach to distributed sum-utility maximization for a MIMO interfering broadcast channel , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Geoffrey Ye Li,et al.  Graph Embedding-Based Wireless Link Scheduling With Few Training Samples , 2019, IEEE Transactions on Wireless Communications.

[7]  Wei Yu,et al.  FPLinQ: A cooperative spectrum sharing strategy for device-to-device communications , 2017, 2017 IEEE International Symposium on Information Theory (ISIT).

[8]  Tony Q. S. Quek,et al.  Deep Learning for Distributed Optimization: Applications to Wireless Resource Management , 2019, IEEE Journal on Selected Areas in Communications.

[9]  Alejandro Ribeiro,et al.  Optimal Wireless Resource Allocation With Random Edge Graph Neural Networks , 2019, IEEE Transactions on Signal Processing.

[10]  Alejandro Ribeiro,et al.  Learning Optimal Resource Allocations in Wireless Systems , 2018, IEEE Transactions on Signal Processing.

[11]  Geoffrey Ye Li,et al.  Deep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks , 2019, Proceedings of the IEEE.

[12]  Wei Yu,et al.  Ieee Transactions on Wireless Communications, Accepted for Publication 1 Multicell Coordination via Joint Scheduling, Beamforming and Power Spectrum Adaptation , 2022 .

[13]  Ya-Feng Liu,et al.  On the Complexity of Joint Subcarrier and Power Allocation for Multi-User OFDMA Systems , 2012, IEEE Transactions on Signal Processing.

[14]  Meryem Simsek,et al.  When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework , 2019, ArXiv.

[15]  Sanjay Shakkottai,et al.  FlashLinQ: A synchronous distributed scheduler for peer-to-peer ad hoc networks , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[16]  Jeffrey G. Andrews,et al.  Are we approaching the fundamental limits of wireless network densification? , 2015, IEEE Communications Magazine.

[17]  Xiaojing Huang,et al.  The simulation of independent Rayleigh faders , 2002, IEEE Trans. Commun..

[18]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[19]  Alejandro Ribeiro,et al.  Counterfactual Programming for Optimal Control , 2020, L4DC.

[20]  Zhi-Quan Luo,et al.  Dynamic Spectrum Management: Complexity and Duality , 2008, IEEE Journal of Selected Topics in Signal Processing.

[21]  Yuanming Shi,et al.  A Graph Neural Network Approach for Scalable Wireless Power Control , 2019, 2019 IEEE Globecom Workshops (GC Wkshps).

[22]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[23]  Giuseppe Caire,et al.  ITLinQ+: An improved spectrum sharing mechanism for device-to-device communications , 2015, 2015 49th Asilomar Conference on Signals, Systems and Computers.

[24]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[25]  Meryem Simsek,et al.  Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning , 2020, 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[26]  Jeffrey G. Andrews,et al.  Downlink Cellular Network Analysis With Multi-Slope Path Loss Models , 2014, IEEE Transactions on Communications.