Page 188 - Kaleidoscope Academic Conference Proceedings 2020
P. 188
2020 ITU Kaleidoscope Academic Conference
by more than 1/4, while the average RSRP is only reduced REFERENCES
by 3%.
[1] “Study on New Radio (NR) to support non terrestrial
networks”, 3GPP TR 38.811, Jun. 2018.
[2] M. Gkizeli, R. Tafazolli and B. Evans, “Modeling
handover in mobile satellite diversity based systems”,
in Proc. 54th Vehicular Technology Conference,2001,
pp. 131-135.
[3] E. Del Re, R. Fantacci and G. Giambene, “Handover
queuing strategies with dynamic and fixed channel
allocation techniques in low Earth orbit mobile satellite
systems”, IEEE Transactions on Communications, vol.
47, no. 1, pp. 89-102, Jan. 1999.
[4] E. Del Re, R. Fantacci and G. Giambene, “Efficient
dynamic channel allocation techniques with handover
queuing for mobile satellite networks”, IEEE Journal
on Selected Areas in Communications, vol. 13, no. 2,
Figure 8 – The cumulative distribution function of handover pp. 397-405, Feb. 1995.
number for different handover optimization methods
[5] Z. Wu, F. Jin, J. Luo, Y. Fu, J. Shan and G.
Hu, “A Graph-Based Satellite Handover Framework
for LEO Satellite Communication Networks”, IEEE
Communications Letters, vol. 20, no. 8, pp. 1547-1550,
Aug. 2016.
[6] V. Yajnanarayana, H. Rydén and L. Hévizi,
“5G Handover using Reinforcement Learning”,
arXiv:1904.02572, 2019.
[7] Y. Chen, X. Lin, T. Khan and M. Mozaffari, “Efficient
Drone Mobility Support Using Reinforcement
Learning”, arXiv:1911.09715, 2019.
[8] M. Chen, Y. Zhang, Y. Teng, B. Liu and L. Zhang,
“Reinforcement Learning Based Signal Quality Aware
Handover Scheme for LEO Satellite Communication
Networks”, in HCC 2019. Lecture Notes in Computer
Science, vol 11956. Springer, Cham
Figure 9 – Average RSRP during simulation for different
handover optimization methods [9] A. Alkhateeb, I. Beltagy and S. Alex, “Machine learning
for reliable mmwave systems:blockage prediction and
proactive handoff”, in Proc. IEEE Global Conference
on Signal and Information Processing, 2018, pp.
5. CONCLUSION 1055-1059.
This paper proposes a CNN based handover optimization [10] N. Aljeri and A. Boukerche, “An Efficient Handover
method for LEO satellite network. The CNN structure is Trigger Scheme for Vehicular Networks Using
customized based on LeNet-5 and is used to extract the hidden Recurrent Neural Networks”, in Proc. 15th ACM
information in the historical RSRP. In order to produce the International Symposium on QoS and Security for
training data for CNN, a novel directed graph based model Wireless and Mobile Networks, 2019, pp. 85-91.
is proposed to find the optimal handover strategy when the
UE knows its future RSRP. After the training, the CNN can [11] “Solutions for NR to support non-terrestrial networks
be used to find a suboptimal handover decision based on (NTN)”, 3GPP TR 38.821, Mar. 2019.
its historical RSRP. In the simulation, the CNN is verified
to be effective in handover optimization. The number of [12] Y. Lecun, L. Bottou, Y. Bengio and P. Haffner,
handovers is significantly reduced while the average RSRP is “Gradient-based learning applied to document
only reduced by 3%. recognition”, Proceedings of the IEEE, vol. 86, no. 11,
pp. 2278-2324, Nov. 1998.
[13] “On beam layout definition for NTN system level
simulations”, Thales R1-1907087, Mar. 2019.
– 130 –