Chapter 21
Machine Learning for 5G System Optimization
First published: 16 February 2024
Summary
This chapter explores the application of machine learning (ML) in wireless systems, primarily focusing on opportunities in 5G-Advanced, although not exclusively so. The early sections deliver an introduction, highlighting the role of ML in the wireless technology domain, and an overview of training and inference of models in wireless systems is discussed. The chapter introduces selected examples of use cases in a broad area of wireless systems. Channel coding is a method that adds redundant information to a digital signal before it is passed onto the modulator and transmitted over the radio channel. In a wireless 3GPP-based mobile network, the Medium Access Control scheduler allocates radio resources in the cell within a carrier and between any aggregated carriers. Radio network planning involves designing the network and optimizing the placement of new base stations and wireless access points.
References
-
Cox , D.R.
(
1958
).
The regression analysis of binary sequences
.
Journal of the Royal Statistical Society: Series B: Methodological
20
(
2
):
215
–
232
.
https://doi.org/10.1111/j.2517-6161.1958.tb00292.x
.
10.1111/j.2517?6161.1958.tb00292.x Google Scholar
-
Galton , F.
(
1894
).
Natural Inheritance, by Francis Galton
.
London
:
Macmillan and co.
https://doi.org/10.5962/bhl.title.46339
.
10.5962/bhl.title.46339 Google Scholar
- Cortes , C. and Vapnik , V. ( 1995 ). Support-vector networks . Machine Learning 20 ( 3 ): 273 – 297 . https://doi.org/10.1007/BF00994018 .
- Ho , T.K. ( 1995 ). ‘Random decision forests’ . In: Proceedings of 3rd International Conference on Document Analysis and Recognition , 278 – 282 . Montreal, Que., Canada : IEEE Comput. Soc. Press https://doi.org/10.1109/ICDAR.1995.598994 .
- LeCun , Y. et al. ( 1989 ). Backpropagation applied to handwritten zip code recognition . Neural Computation 1 ( 4 ): 541 – 551 . https://doi.org/10.1162/neco.1989.1.4.541 .
-
Sutton , R.S.
and
Barto , A.G.
(
1998
).
Reinforcement learning: an introduction
. In:
Adaptive Computation and Machine Learning
.
Cambridge, Mass
:
MIT Press
.
10.1109/TNN.1998.712192 Google Scholar
- Hinton , G.E. and Salakhutdinov , R.R. ( 2006 ). Reducing the dimensionality of data with neural networks . Science 313 ( 5786 ): 504 – 507 . https://doi.org/10.1126/science.1127647 .
- Mockus , J. ( 1989 ). Bayesian approach to global optimization: theory and applications . In: Mathematics and Its Applications . Soviet series. Dordrecht ; Boston : Kluwer Academic .
- Mkadem , F. and Boumaiza , S. ( 2011 ). Physically inspired neural network model for RF power amplifier behavioral modeling and digital predistortion . IEEE Transactions on Microwave Theory and Techniques 59 ( 4 ): 913 – 923 . https://doi.org/10.1109/TMTT.2010.2098041 .
-
Pihlajasalo , J.
et al. (
Sep. 2021
).
HybridDeepRx: Deep Learning Receiver for High-EVM Signals
. In:
2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)
,
622
–
627
.
Helsinki, Finland
:
IEEE
https://doi.org/10.1109/PIMRC50174.2021.9569393
.
10.1109/PIMRC50174.2021.9569393 Google Scholar
- Pihlajasalo , J. et al. ( 2023 ). Deep Learning OFDM Receivers for Improved Power Efficiency and Coverage . IEEE Transactions on Wireless Communications 1 – 1 . https://doi.org/10.1109/TWC.2023.3235059 .
- RP-213599, ‘New SI: Study on Artificial Intelligence (AI)/Machine Learning (ML) for NR Air Interface’ . 3GPP RAN Plenary #94e, Dec 2021.
- Ye , H. , Li , G.Y. , and Juang , B.-H. ( 2018 ). Power of deep learning for channel estimation and signal detection in OFDM systems . IEEE Wireless Communications Letters 7 ( 1 ): 114 – 117 . https://doi.org/10.1109/LWC.2017.2757490 .
-
J. Long
,
E. Shelhamer
, and
T. Darrell
, ‘
Fully convolutional networks for semantic segmentation
’,
2014
,
https://doi.org/10.48550/ARXIV.1411.4038
.
10.48550/ARXIV.1411.4038 Google Scholar
- Honkala , M. , Korpi , D. , and Huttunen , J.M.J. ( 2021 ). DeepRx: fully convolutional deep learning receiver . IEEE Transactions on Wireless Communications 20 ( 6 ): 3925 – 3940 . https://doi.org/10.1109/TWC.2021.3054520 .
-
Korpi , D.
,
Honkala , M.
,
Huttunen , J.M.J.
, and
Starck , V.
(
Jun. 2021
).
DeepRx MIMO: convolutional MIMO detection with learned multiplicative transformations
. In:
ICC 2021 – IEEE International Conference on Communications
,
1
–
7
.
Montreal, QC, Canada
:
IEEE
https://doi.org/10.1109/ICC42927.2021.9500518
.
10.1109/ICC42927.2021.9500518 Google Scholar
-
Aoudia , F.A.
and
Hoydis , J.
(
2021
).
Trimming the fat from OFDM: pilot- and CP-less communication with end-to-end learning
. In:
2021 IEEE International Conference on Communications Workshops (ICC Workshops)
,
1
–
6
.
Montreal, QC, Canada
:
IEEE
https://doi.org/10.1109/ICCWorkshops50388.2021.9473605
.
10.1109/ICCWorkshops50388.2021.9473605 Google Scholar
- Farhadi , H. et al. ( 2023 ). Deliverable D4.3: AI-driven communication & computation co-design: final solutions . Hexa-X, Apr. 30 : [Online]. Available: https://hexa-x.eu/wp-content/uploads/2023/05/Hexa-X_D4.3_v1.0.pdf .
- Marzetta , T.L. ( 2015 ). Massive MIMO: an introduction . Bell Labs Technical Journal 20 : 11 – 22 . https://doi.org/10.15325/BLTJ.2015.2407793 .
- J. M. J. Huttunen , D. Korpi , and M. Honkala , ‘ DeepTx: Deep Learning Beamforming with Channel Prediction ’, 2022 , https://doi.org/10.48550/ARXIV.2202.07998 .
-
L. Maggi
,
R. Koblitz
,
Q. Zhu
, and
M. Andrews
, ‘
Tracking the Best Beam for a Mobile User via Bayesian Optimization
’,
2023
,
https://doi.org/10.48550/ARXIV.2303.17301
.
10.1109/VTC2023-Spring57618.2023.10200730 Google Scholar
- Arikan , E. ( 2009 ). Channel polarization: a method for constructing capacity-achieving codes for symmetric binary-input memoryless channels . IEEE Transactions on Information Theory 55 ( 7 ): 3051 – 3073 . https://doi.org/10.1109/TIT.2009.2021379 .
- Gallager , R. ( 1962 ). Low-density parity-check codes . IRE Transactions on Information Theory 8 ( 1 ): 21 – 28 .
-
E. Nachmani
,
Y. Beery
, and
D. Burshtein
, ‘
Learning to Decode Linear Codes Using Deep Learning
’,
2016
,
https://doi.org/10.48550/ARXIV.1607.04793
.
10.1109/ALLERTON.2016.7852251 Google Scholar
-
O'Shea , T.J.
,
Karra , K.
, and
Clancy , T.C.
(
Dec. 2016
).
Learning to communicate: channel auto-encoders, domain specific regularizers, and attention
. In:
2016 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)
,
223
–
228
.
Limassol, Cyprus
:
IEEE
https://doi.org/10.1109/ISSPIT.2016.7886039
.
10.1109/ISSPIT.2016.7886039 Google Scholar
-
Kela , P.
,
Puttonen , J.
,
Kolehmainen , N.
et al. (
May 2008
).
Dynamic packet scheduling performance in UTRA Long Term Evolution downlink
. In:
in 2008 3rd International Symposium on Wireless Pervasive Computing
,
308
–
313
.
Santorini, Greece
:
IEEE
https://doi.org/10.1109/ISWPC.2008.4556220
.
10.1109/ISWPC.2008.4556220 Google Scholar
-
Van Hasselt , H.
,
Guez , A.
, and
Silver , D.
(
2016
).
Deep Reinforcement Learning with Double Q-Learning
.
Proceedings of the AAAI Conference on Artificial Intelligence
30
(
1
):
https://doi.org/10.1609/aaai.v30i1.10295
.
10.1609/aaai.v30i1.10295 Google Scholar
-
Calabrese , F.D.
,
Rosa , C.
,
Anas , M.
et al. (
Sep. 2008
).
Adaptive Transmission Bandwidth Based Packet Scheduling for LTE Uplink
. In:
in 2008 IEEE 68th Vehicular Technology Conference
,
1
–
5
.
Calgary, Canada
:
IEEE
https://doi.org/10.1109/VETECF.2008.316
.
10.1109/VETECF.2008.316 Google Scholar
- J. Hoydis , F. A. Aoudia , A. Valcarce , and H. Viswanathan , ‘ Toward a 6G AI-Native Air Interface’, ArXiv201208285 Cs Math , Apr. 2021, Accessed: May 07, 2021. [Online]. Available: http://arxiv.org/abs/2012.08285
-
Reunanen , J.
,
Salo , J.
, and
Luostari , R.
(
2015
). ‘
LTE Key Performance Indicator Optimization
’. In:
LTE Small Cell Optimization
(ed.
H. Holma
,
A. Toskala
, and
J. Reunanen
),
195
–
248
.
Chichester, UK
:
John Wiley & Sons Ltd
https://doi.org/10.1002/9781118912560.ch12
.
10.1002/9781118912560.ch12 Google Scholar
-
Reunanen , J.
,
Luostari , R.
, and
Holma , H.
(
2015
).
Capacity Optimization
. In:
LTE Small Cell Optimization
(ed.
H. Holma
,
A. Toskala
, and
J. Reunanen
),
249
–
292
.
Chichester, UK
:
John Wiley & Sons Ltd
https://doi.org/10.1002/9781118912560.ch13
.
10.1002/9781118912560.ch13 Google Scholar
-
Luostari , R.
,
Salo , J.
,
Reunanen , J.
, and
Holma , H.
(
2015
).
VoLTE Optimization
. In:
LTE Small Cell Optimization
(ed.
H. Holma
,
A. Toskala
, and
J. Reunanen
),
293
–
331
.
Chichester, UK
:
John Wiley & Sons Ltd
https://doi.org/10.1002/9781118912560.ch14
.
10.1002/9781118912560.ch14 Google Scholar
- Alliance , O.-R.A.N. ( Mar. 2021 ). O-RAN Near-RT RAN Intelligent Controller Near-RT RIC Architecture 2.00 . O-RAN Alliance [Online]. Available: https://www.o-ran.org/specifications .
-
Han , S.
,
Mao , H.
, and
Dally , W.J.
(
2015
).
Deep compression: compressing deep neural networks with pruning
.
Trained Quantization and Huffman Coding
https://doi.org/10.48550/ARXIV.1510.00149
.
10.48550/ARXIV.1510.00149 Google Scholar
- G. Hinton , O. Vinyals , and J. Dean , ‘ Distilling the Knowledge in a Neural Network ’, 2015 , https://doi.org/10.48550/ARXIV.1503.02531 .
