没有合适的资源?快使用搜索试试~ 我知道了~
首页MassiveMIMONetworks_Spectral Energy andHardwareEfficiency[.pdf
资源详情
资源评论
资源推荐

Foundations and Trends
R
in Signal Processing
Massive MIMO Networks: Spectral,
Energy, and Hardware Efficiency
Suggested Citation:
Emil Björnson, Jakob Hoydis and Luca Sanguinetti (2017), “Massive
MIMO Networks: Spectral, Energy, and Hardware Efficiency”, Foundations and Trends
R
in Signal Processing: Vol. 11, No. 3-4, pp 154–655. DOI: 10.1561/2000000093.
Emil Björnson
Linköping University
emil.bjornson@liu.se
Jakob Hoydis
Bell Labs, Nokia
jakob.hoydis@nokia.com
Luca Sanguinetti
University of Pisa
luca.sanguinetti@unipi.it
This article may be used only for the purpose of research, teaching,
and/or private study. Commercial use or systematic downloading
(by robots or other automatic processes) is prohibited without ex-
plicit Publisher approval.
Boston — Delft

Contents
1 Introduction and Motivation 158
1.1 Cellular Networks . . . . . . . . . . . . . . . . . . . . . . 160
1.2 Definition of Spectral Efficiency . . . . . . . . . . . . . . . 167
1.3 Ways to Improve the Spectral Efficiency . . . . . . . . . . 173
1.4 Summary of Key Points in Section 1 . . . . . . . . . . . . 214
2 Massive MIMO Networks 216
2.1 Definition of Massive MIMO . . . . . . . . . . . . . . . . 216
2.2 Correlated Rayleigh Fading . . . . . . . . . . . . . . . . . 222
2.3 System Model for Uplink and Downlink . . . . . . . . . . 226
2.4 Basic Impact of Spatial Channel Correlation . . . . . . . . 228
2.5 Channel Hardening and Favorable Propagation . . . . . . . 231
2.6 Local Scattering Spatial Correlation Model . . . . . . . . . 235
2.7 Summary of Key Points in Section 2 . . . . . . . . . . . . 243
3 Channel Estimation 244
3.1 Uplink Pilot Transmission . . . . . . . . . . . . . . . . . . 244
3.2 MMSE Channel Estimation . . . . . . . . . . . . . . . . . 248
3.3 Impact of Spatial Correlation and Pilot Contamination . . 254
3.4 Computational Complexity and Low-Complexity Estimators 264
3.5 Data-Aided Channel Estimation and Pilot Decontamination 271

3.6 Summary of Key Points in Section 3 . . . . . . . . . . . . 274
4 Spectral Efficiency 275
4.1 Uplink Spectral Efficiency and Receive Combining . . . . . 275
4.2 Alternative UL SE Expressions and Key Properties . . . . . 301
4.3 Downlink Spectral Efficiency and Transmit Precoding . . . 316
4.4 Asymptotic Analysis . . . . . . . . . . . . . . . . . . . . . 335
4.5 Summary of Key Points in Section 4 . . . . . . . . . . . . 351
5 Energy Efficiency 353
5.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . 354
5.2 Transmit Power Consumption . . . . . . . . . . . . . . . . 357
5.3 Definition of Energy Efficiency . . . . . . . . . . . . . . . 362
5.4 Circuit Power Consumption Model . . . . . . . . . . . . . 375
5.5 Tradeoff Between Energy Efficiency and Throughput . . . 390
5.6 Network Design for Maximal Energy Efficiency . . . . . . . 395
5.7 Summary of Key Points in Section 5 . . . . . . . . . . . . 401
6 Hardware Efficiency 403
6.1 Transceiver Hardware Impairments . . . . . . . . . . . . . 404
6.2 Channel Estimation with Hardware Impairments . . . . . . 413
6.3 Spectral Efficiency with Hardware Impairments . . . . . . 419
6.4 Hardware-Quality Scaling Law . . . . . . . . . . . . . . . 439
6.5 Summary of Key Points in Section 6 . . . . . . . . . . . . 449
7 Practical Deployment Considerations 451
7.1 Power Allocation . . . . . . . . . . . . . . . . . . . . . . . 452
7.2 Spatial Resource Allocation . . . . . . . . . . . . . . . . . 468
7.3 Channel Modeling . . . . . . . . . . . . . . . . . . . . . . 482
7.4 Array Deployment . . . . . . . . . . . . . . . . . . . . . . 500
7.5 Millimeter Wavelength Communications . . . . . . . . . . 522
7.6 Heterogeneous Networks . . . . . . . . . . . . . . . . . . 527
7.7 Case Study . . . . . . . . . . . . . . . . . . . . . . . . . . 537
7.8 Summary of Key Points in Section 7 . . . . . . . . . . . . 546
Acknowledgements 548

Appendices 549
A Notation and Abbreviations 550
B Standard Results 558
B.1 Matrix Analysis . . . . . . . . . . . . . . . . . . . . . . . 558
B.2 Random Vectors and Matrices . . . . . . . . . . . . . . . 563
B.3 Properties of the Lambert W Function . . . . . . . . . . . 567
B.4 Basic Estimation Theory . . . . . . . . . . . . . . . . . . 567
B.5 Basic Information Theory . . . . . . . . . . . . . . . . . . 572
B.6 Basic Optimization Theory . . . . . . . . . . . . . . . . . 575
C Collection of Proofs 579
C.1 Proofs in Section 1 . . . . . . . . . . . . . . . . . . . . . 579
C.2 Proofs in Section 3 . . . . . . . . . . . . . . . . . . . . . 591
C.3 Proofs in Section 4 . . . . . . . . . . . . . . . . . . . . . 593
C.4 Proofs in Section 5 . . . . . . . . . . . . . . . . . . . . . 609
C.5 Proofs in Section 6 . . . . . . . . . . . . . . . . . . . . . 612
References 621

Massive MIMO Networks: Spectral,
Energy, and Hardware Efficiency
Emil Björnson
1
, Jakob Hoydis
2
and Luca Sanguinetti
3
1
Linköping University; emil.bjornson@liu.se
2
Bell Labs, Nokia; jakob.hoydis@nokia.com
3
University of Pisa; luca.sanguinetti@unipi.it
ABSTRACT
Massive multiple-input multiple-output (MIMO) is one of the
most promising technologies for the next generation of wireless
communication networks because it has the potential to provide
game-changing improvements in spectral efficiency (SE) and en-
ergy efficiency (EE). This monograph summarizes many years of
research insights in a clear and self-contained way and provides
the reader with the necessary knowledge and mathematical tools
to carry out independent research in this area. Starting from
a rigorous definition of Massive MIMO, the monograph covers
the important aspects of channel estimation, SE, EE, hardware
efficiency (HE), and various practical deployment considerations.
From the beginning, a very general, yet tractable, canonical system
model with spatial channel correlation is introduced. This model
is used to realistically assess the SE and EE, and is later extended
to also include the impact of hardware impairments. Owing to
this rigorous modeling approach, a lot of classic “wisdom” about
Massive MIMO, based on too simplistic system models, is shown
to be questionable.
The monograph contains many numerical examples, which can
be reproduced using Matlab code that is available online at
https://dx.doi.org/10.1561/2000000093_supp.
Emil Björnson, Jakob Hoydis and Luca Sanguinetti (2017), “Massive MIMO Networks:
Spectral, Energy, and Hardware Efficiency”, Foundations and Trends
R
in Signal
Processing: Vol. 11, No. 3-4, pp 154–655. DOI: 10.1561/2000000093.
剩余505页未读,继续阅读


















安全验证
文档复制为VIP权益,开通VIP直接复制

评论0