Optimal 3D UAV Base Station Placement by Considering Autonomous Coverage Hole Detection, Wireless Backhaul and User Demand

다국어 초록 (Multilingual Abstract)

The rising number of technological advanced devicesmaking network coverage planning very challenging tasks for network operators. The transmission quality between the transmitterand the end users has to be optimum for the best performance outof any device. Besides, the presence of coverage hole is also an ongoing issue for operators which cannot be ignored throughout thewhole operational stage. Any coverage hole in network operators’coverage region will hamper the communication applications anddegrade the reputation of the operator’s services. Presently, thereare techniques to detect coverage holes such as drive test or minimization of drive test. However, these approaches have many limitations. The extreme costs, outdated information about the radioenvironment and high time consumption do not allow to meet therequirement competently. To overcome these problems, we take advantage of Unmanned aerial vehicle (UAV) and Q-learning to autonomously detect coverage hole in a given area and then deployUAV based base station (UAV-BS) by considering wireless backhaul with the core network and users demand. This machine learning mechanism will help the UAV to eliminate human-in-the-loop(HiTL) model. Later, we formulate an optimisation problem for3D UAV-BS placement at various angular positions to maximisethe number of users associated with the UAV-BS. In summary, wehave illustrated a cost-effective as well as time saving approach ofdetecting coverage hole and providing on-demand coverage in thisarticle.

참고문헌 (Reference)

1 Y. Zeng, "Wireless communications with unmanned aerial vehicles : Opportunities and challenges" 54 (54): 36-42, 2016

2 E. Kalantari, "User association and bandwidth allocation for terrestrial and aerial base stations with backhaul considerations" 1-6, 2017

3 "Understanding LTE Signal Strength Values"

4 H. Bayerlein, "Trajectory optimization for autonomous flying base station via reinforcement learning" 1-5, 2018

5 Scottish Government and Scottish Futures Trust, "Scottish 4G Infill Programme Consultation: Request For Information"

6 R. S. Sutton, "Reinforcement learning: An introduction" MIT press 2018

7 W. Koch, "Reinforcement learning for UAV attitude control" 3 (3): 22-, 2019

8 A. Nandy, "Reinforcement Learning: With Open AI, TensorFlow and Keras Using Python" Apress 2017

9 P. V. Klaine, "Reinforcement Learning Enabled Unmanned Aerial Vehicles in Pop-Up Cellular Networks"

10 R. Amorim, "Radio channel modeling for uav communication over cellular networks" 6 (6): 514-517, 2017

11 Z. Yijing, "Q learning algorithm based UAV path learning and obstacle avoidence approach" 3397-3402, 2017

12 Evolved Universal Terrestrial Radio Access (E-UTRA), "Overall description;Stage 2, 3GPP"

13 D. Wang, "Optimized link distribution schemes for ultra reliable and low latent communications in multi-layer airborne networks" 16 (16): 2019

14 A. Al-Hourani, "Optimal LAP altitude for maximum coverage" 3 (3): 569-572, 2014

15 E. Kalantari, "On the number and 3D placement of drone base stations in wireless cellular networks" 1-6, 2016

16 "New map shows Germany’s mobile ’dead zones’" The Local

17 A. Al-Hourani, "Modeling cellular-to-UAV path-loss for suburban environments" 7 (7): 82-85, 2017

18 A. Al-Hourani, "Modeling air-toground path loss for low altitude platforms in urban environments" 2898-2904, 2014

19 T. Ebuchi, "KDDI and Rakuten to help eliminate cellular dead zones by 2024" Nikkei Asian Review

20 R. Jurdi, "Identifying coverage holes: Where to densify?" 1417-1421, 2017

21 I. Akbari, "How reliable is MDT-based autonomous coverage estimation in the presence of user and BS positioning error?" 5 (5): 196-199, 2016

22 E. Teng, "Holes-in-the-Sky: A field study on cellular-connected UAS" 1165-1174, 2017

23 T. Jones, "Germany’s 4G mobile network one of worst in Europe" DW

24 N. A. Ali, "General expressions for downlink signal to interference and noise ratio in homogeneous and heterogeneous LTE-Advanced networks" 7 (7): 923-929, 2016

25 R. Sharma, "Fuzzy Q learning based UAV autopilot" 29-33, 2014

26 M. Alzenad, "FSObased vertical backhaul/fronthaul framework for 5G+ wireless networks" 56 (56): 218-224, 2018

27 R. Ghanavi, "Efficient 3D aerial base station placement considering users mobility by reinforcement learning" 1-6, 2018

28 R. Ghanavi, "Efficient 3D aerial base station placement considering users mobility by reinforcement learning" 1-6, 2018

29 R. I. Bor-Yaliniz, "Efficient 3-D placement of an aerial base station in next generation cellular networks" 1-5, 2016

30 Y. Wang, "Detection and protection of macro-users in dominant area of co-channel CSG cells" 1-5, 2012

31 H. Xiao, "Coverage hole detection in cellular wireless network"

32 H.-W. Liang, "Coverage hole detection in cellular networks with deterministic propagation model" 1-6, 2016

33 E. Kalantari, "Backhaul-aware robust 3D drone placement in 5G+ wireless networks" 109-114, 2017

34 H. X. Pham, "Autonomous UAV navigation using reinforcement learning"

35 A. Galindo-Serrano, "Automated coverage hole detection for cellular networks using radio environment maps" 35-40, 2013

36 A. Gomez Andrades, "A method of assessment of LTE coverage holes" 2016 : 236-, 2016

37 S. A. W. Shah, "A distributed approach for networked flying platform association with small cells in 5G+ networks" 2017

38 M. Mozaffari, "A Tutorial on UAVs for wireless networks: Applications, challenges, and open problems" CoRR

39 3GPP, "5G; NR; Base Station (BS) radio transmission and reception, Technical Specification (TS) 38.104" 3rd Generation Partnership Project (3GPP)

40 K. T. Feng, "3d on-demand flying mobile communication for millimeter-wave heterogeneous networks" 34 (34): 198-204, 2020

41 M. Alzenad, "3-D placement of an unmanned aerial vehicle base station (UAV-BS) for energyefficient maximal coverage" 6 (6): 434-437, 2017