An Efficient Connected Swarm Deployment via Deep Learning

In this paper, an unmanned aerial vehicles (UAVs) deployment framework based on machine learning is studied. It aims to maximize the sum of the weights of the ground users covered by UAVs while UAVs forming a connected communication graph. We focus on the case where the number of UAVs is not necessarily enough to cover all ground users.We develop an UAV Deployment Deep Neural network (UD-DNNet) as a UAV’s deployment deep network method. Simulation results demonstrate that UDDNNet can serve as a computationally inexpensive replacement for traditionally expensive optimization algorithms in real-time tasks and outperform the state-of-the-art traditional algorithms.

[1]  Walid Saad,et al.  Efficient Deployment of Multiple Unmanned Aerial Vehicles for Optimal Wireless Coverage , 2016, IEEE Communications Letters.

[2]  Paulo Valente Klaine,et al.  Distributed Drone Base Station Positioning for Emergency Cellular Networks Using Reinforcement Learning , 2018, Cognitive Computation.

[3]  Dimitrios Zorbas,et al.  Modelling the mobile target covering problem using flying drones , 2016, Optim. Lett..

[4]  Michael Segal,et al.  Connected Ad-Hoc swarm of drones , 2020, DroNet@MobiSys.

[5]  Rui Zhang,et al.  Placement Optimization of UAV-Mounted Mobile Base Stations , 2016, IEEE Communications Letters.

[6]  Jian Li,et al.  Linear Time Approximation Schemes for Geometric Maximum Coverage , 2015, COCOON.

[7]  Chi Harold Liu,et al.  Energy-Efficient UAV Control for Effective and Fair Communication Coverage: A Deep Reinforcement Learning Approach , 2018, IEEE Journal on Selected Areas in Communications.

[8]  Luxi Yang,et al.  The multi-objective deployment optimization of UAV-mounted cache-enabled base stations , 2019, Phys. Commun..

[9]  Xiao Zhang,et al.  Fast Deployment of UAV Networks for Optimal Wireless Coverage , 2017, IEEE Transactions on Mobile Computing.

[10]  Haitao Zhao,et al.  Deployment Algorithms of Flying Base Stations: 5G and Beyond With UAVs , 2019, IEEE Internet of Things Journal.

[11]  Qiang Wang,et al.  A Fast Deployment Strategy for UAV Enabled Network Based on Deep Learning , 2020, 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications.

[12]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[13]  Mohammadreza Razzazi,et al.  The Most Points Connected-Covering Problem with Two Disks , 2018, Theory of Computing Systems.

[14]  Joseph S. B. Mitchell,et al.  Maximizing Covered Area in the Euclidean Plane with Connectivity Constraint , 2019, APPROX-RANDOM.

[15]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[16]  Michael Segal,et al.  Covering Users by a Connected Swarm Efficiently , 2020, ALGOSENSORS.

[17]  Mark de Berg,et al.  Covering Many or Few Points with Unit Disks , 2006, Theory of Computing Systems.

[18]  Eytan Modiano,et al.  Construction and Maintenance of Wireless Mobile Backbone Networks , 2009, IEEE/ACM Transactions on Networking.

[19]  Choong Seon Hong,et al.  Multi-UAVs Collaboration System based on Machine Learning for Throughput Maximization , 2019, 2019 20th Asia-Pacific Network Operations and Management Symposium (APNOMS).

[20]  N. Sidiropoulos,et al.  Learning to Optimize: Training Deep Neural Networks for Interference Management , 2017, IEEE Transactions on Signal Processing.

[21]  Liqun Fu,et al.  Placement Optimization of Aerial Base Stations with Deep Reinforcement Learning , 2020, ICC 2020 - 2020 IEEE International Conference on Communications (ICC).

[22]  Haitao Wang,et al.  Linear Time Approximation Schemes for Geometric Maximum Coverage , 2015, COCOON.

[23]  Kate Ching-Ju Lin,et al.  Maximizing Submodular Set Function With Connectivity Constraint: Theory and Application to Networks , 2013, IEEE/ACM Transactions on Networking.