Conference PaperPDF Available

MmWave Vehicular Beam Training with Situational Awareness by Machine Learning

Authors:
MmWave Vehicular Beam Training with Situational
Awareness by Machine Learning
(Invited Paper)
Yuyang Wang
,Aldebaro Klautau
,Monica Ribero
,Murali Narasimha§
,and Robert W. Heath Jr.
Department of Electrical and Computer Engineering, The University of Texas at Austin, USA
Federal University of Para (UFPA), Belem, Brazil §Huawei Technologies, Rolling Meadows, USA
Email: {yuywang, rheath, mribero}@utexas.edu, aldebaro@ufpa.br, murali.narasimha@huawei.com
Abstract—Configuring beams in millimeter-wave (mmWave)
vehicular communication is a challenging task. Large antenna
arrays and narrow beams are deployed at transceivers to exploit
beamforming gain, which leads to significant system overhead if
an exhaustive beam search is adopted. In this paper, we propose
to learn the optimal beam pair index by exploiting the locations
and sizes of the receiver and its neighboring vehicles (parts
of the situational awareness for automated driving), leveraging
machine learning tools with the past beam training records.
MmWave beam selection is formulated as a classification problem
based on situational awareness. We provide a comprehensive
comparison of different classification models and various levels of
situational awareness. Practical issues are considered in realistic
implementations, including GPS inaccuracies, out-dated locations
due to fixed location reporting frequencies and missing features
with limited connected vehicles penetration rate. The result shows
that we can achieve up to 86%of alignment probability with ideal
assumptions.
I. INTRODUCTION
With the huge frequency resources available, mmWave
is the only viable approach to support the massive sensor
data sharing in emerging vehicular applications [1]. MmWave
communication employs large antenna arrays to compensate
for the small antenna aperture and the penetration loss in case
of blockage [2]. With the narrow beams used in mmWave
with analog beamforming and high mobility in the vehicular
context, current beam training solutions based on exhaustive
search are inapplicable in most vehicular applications due to
the overhead and latency.
Wireless cellular communication systems have access to
vast data resources – yet untapped – which can make beam
training more efficient. At every base station (BS), sector,
and radio frequency channel, hundreds of pilot signals are
sent between the base station and users in its coverage area
to measure the propagation channel every second. With the
same cadence, the users send feedback to the BS about the
measured channel, for the infrastructure to select transmis-
sion parameters accordingly. Remarkably, this information is
leveraged only over a fraction of a second and then discarded.
This “data collection - discard” mode in the wireless industry
may be explained at lower frequencies due the presence of
more propagation paths in the channel, the variability in phone
handset movement, and limitations in sensing capabilities of
phones.
Data-driven beam training is the right approach for
mmWave vehicular systems. Wireless systems are becoming
too complicated to be fit in stochastic mathematical models.
MmWave channels are more deterministic given environment
geometries. Hence, beam information can be learned from the
geometry of surrounding objects, since they serve as reflectors
and can change directions of the beams. Also, vehicles travel
along roads in predictable ways, following certain patterns
e.g., higher density or slower speed during rush hour, which
makes it easier for mobility modeling. Vehicles are also
being equipped with sensors like satellite navigation, radar,
LiDAR, and cameras which can be used to localize vehicles
and sense the environment [1], [3]. With the availability of
sensors, vehicle locations can be shared to make everything
connected. Lastly, the BS is well equipped with the capability
to accommodate the needs for data-driven solutions. It has
access to cloud and edge computing capability; it is the natural
data fusion hub for data generated by various types of sensors
on a vehicle; it can also monitor current transmission status
and has capacity to cache the useful transmission records [4],
[5].
There are several papers proposing alternative data-driven
mmWave vehicular beam training solutions with side in-
formation, e.g., radar, cameras, etc [3]. In [6], the paper
proposed to recommend mmWave vehicular beams based on
the receiver location, with past transmission histories. The
proposed solution [6] might work well in line-of-sight (LOS)
dominant scenarios. It is very likely to fail, however, when
abundant blockages are present in the dataset, since the beams
could be highly random and large numbers of beams will
be recommended in order to guarantee alignment probability.
In [7], the paper presented a 5G-MIMO dataset of vehicular
channel and beam statistics with temporally-correlated vehicle
trajectories. An initial investigation was provided to solve the
mmWave beam selection problem when all the vehicle ge-
ometries instead of only the receiver location are incorporated
in the feature. In addition to beam pair index prediction, it
was shown in [8] that vehicles’ situational awareness can also
be used to predict the beam power to reduce overheads and
automate vehicular beam training.
In this paper, we propose a comprehensive investigation
of an efficient machine learning framework with situational
awareness in Section II. Aside from using the receiver lo-
cation, we propose to locations and sizes of vehicles in
the environment to predict the optimal beam pair index. In
Section II-C and II-D, we apply three different approaches, in
Cartesian coordinates, polar coordinates and occupancy grids,
with appropriate feature ordering. In Section IV, we compare
different classification methods to predict the optimal beam
pair index based on the situational features. Furthermore, we
show the significant improvement of prediction accuracy when
a richer set of vehicles locations are included in the prediction.
Since the model relies on the vehicle locations, location errors
in realistic implementations are considered, including GPS
inaccuracies, vehicle location reporting frequency and different
penetration rates of connected vehicles.
II. BEAM SELECTION USING MACHINE LEARNING
A. Problem formulation
In mmWave vehicle-to-infrastructure (V2I) communica-
tions, road-side units (RSU) are deployed at a low height
(generally collocated with the lamp) on the road side, to
support data showering for the passing vehicles. Multiple
reflections might happen on the objects in the environment,
e.g., the road-side buildings, vehicles, pedestrians, etc, before
the beams reach the receiver. Among the different types
of reflecting objects, buildings (or roads) are stationary and
pedestrians are small in size which have negligible impacts
on the channel. This makes the vehicles the most important
dynamic factors in affecting the channel. We divide the set of
environment information Eto several categories: 1) stationary
objects in the environment as S(e.g., buildings, roads, other
infrastructures), 2) mobile vehicles as V, and 3) other objects
small in size (e.g., pedestrians, foliage) as N. There exists
a function f(·)that can map the set of the full environment
information Eto the beam information B, with some negligible
error η, i.e.,
f(·), s.t., f(E) = f(S,V,N) = B+η, (1)
where ηis due to some random disturbances in the model and
is very small.
Assuming the effect of Non the beam is negligible, and
Sis identical as S=S0for different data samples for the
current urban canyon, (1) can be further simplified to
f(·), s.t., f (V,S=S0,N)fS0(V)≈ B.(2)
Hence, we propose to learn the optimal beam pair index by
leveraging all vehicles’ locations and sizes. Specifically, the
beam selection will be formulated as a classification problem.
In Section II-B - II-D, we will respectively explain the details
of channel modeling, optimal beam index calculation, and how
to encode vehicle geometries with appropriate feature format.
B. Data collection and channel model
Since there are no testbeds available for mmWave V2I
communications, we utilize a ray tracing simulator to establish
the dataset. Ray tracing simulation has been widely adopted in
both industry and academia for channel measurements [9], [10]
and modeling [11]. We use a commercial ray tracing simulator
- Wireless Insite, from Remcom [12]. We consider a two-lane
straight street in urban canyon as shown in Fig. 1. Buildings
modeled by cubes are located on the two road sides with
random sizes. We consider two types of vehicles, respectively
large trucks, with length, width, height =T`, Tw, Thand
low height cars (sedans) of size C`, Cw, Ch. All vehicles
are modeled as cubes with material exteriors and randomly
dropped on the two lanes based on some certain distribution.
Ray tracing simulation outputs the Lstrongest paths from
the given configurations of geometry, transceiver, etc. Since
the path directions span a three-dimensional space, the output
angles are formatted in a spherical coordinate. In particular,
each path includes: 1) arrival azimuth angle φA, 2) arrival ele-
vation angle θA, 3) departure azimuth angle φD, 4) departure
elevation angle θD, 5) path gain αewith φas the phase, and
6) time of arrival τ. Due to the sparsity of mmWave channel,
we assume that parameters above are enough to approximate
the channels. Let’s denote the number of transmit antenna as
Ntand that of receive antenna as Nr. The wide-band channel
H[n]with Lctaps can be calculated as below [6]
H[n] =pNtNr
L
X
`=1
g(nT τ`)ar(φA
`)a
t(φD
`)α`e`,
0nLc1,(3)
where g(·)is the pulse shaping factor, at(·)and ar(·)are
the steering vectors, and Tis the sampling period. Uniform
planar arrays (UPA) are applied at both the transmitter and the
receiver. We apply DFT codebook Wand Ffor the precoder
and combiner and assume Nt=Nr=Ny×Nx= 4 ×2=8.
Therefore, there is a total of NB=NtNr= 64 different
beam pairs in our dataset. The received power of all the NB
beam pairs in the k-th sample is represented as a vector yk.
Assuming the i-th beam pair, (wi,fi), i ∈ {1,2,· · · , NB}, is
selected from the codebook, the received power of the i-th
beam pair yk[i]can be calculated as
yk[i] =
Lc1
X
n=0
w
iH[n]fi
2.(4)
and the optimal beam index skcan be obtained by
sk= arg max
i∈{1,2,··· ,|W×F |}{yk[i]},(5)
Fig. 1. Illustration of the deployment of ray tracing simulation. Receivers are
mounted on top of the low vehicles (denoted by the yellow boxes) and the
RSU is denoted by the green box.
Fig. 2. Illustration for encoding the environment with a Cartesian coordinate.
The origins lies at the left boundary of the simulation road side at the bottom.
And the each feature of the vehicle location is encoded as [horizontal location,
lane index].
Fig. 3. Illustration for encoding the environment with a polar coordinate.
The origins lies at RSU. Vehicle location is encoded as (r, φ), where φis the
angle between the point and the x-axis.
where |·| denotes the cardinality of the set.
C. Encoding vehicle geometry
To properly encode the locations of multiple vehicles,
we propose to format the features in Cartesian, polar, and
occupancy grids.
1) Cartesian coordinate: The first approach is by represent-
ing the simulation area in a Cartesian coordinate, as shown in
Fig. 2. We are considering a two-lane street and the cars are
assumed to be traveling in the center of each lane. Categorical
variables 1 or 2 are used to denote the lane index. Each
vehicle’s location is represented by (horizontal location, lane
index).
2) Polar coordinate: Cartesian coordinate gives a way to
encode the environment in a lossless way. It includes the
accurate location of every vehicle in the environment. Another
lossless option is to use polar coordinate to encode. Beam
training is in essence a problem to find the beam angles. In the
LOS links, polar coordinates give direct ways of interpreting
angles of the paths. To capture this angle correlation, the origin
is set at the RSU, as shown in Figure 3. And each location is
given by (distance to the origin, angular coordinate).
3) Occupancy grid: Another approach is to encode the
environment in either two-dimensional or three-dimensional
occupancy grids. This approach, though encoding the data in
a lossy way due to the quantization, can be more flexible in
including a wide category of urban canyons with different sizes
of vehicles and could be more resilient to potential feature
noises. The idea is to quantize the locations in a regular-
sized grid with a certain granularity dg, which is quantified
Fig. 4. Illustration for encoding the environment in regular-sized grids. The
origin lies at the left bottom of the simulation area. The x-axis direction is
quantized to different grids to encode the data.
by the distance between two adjacent grids. The size of the
simulation area horizontally is Dh. In our model, there are
in total of 3types of target vehicles, respectively neighboring
trucks,neighboring cars, and the receiver car, represented as
1, 2, 3. An illustration is provided in Fig. 4. The grids on the
first and second lanes will be represented by two vectors g1
and g2of length Dh
dg. If nothing lies inside the i-th grid of
the j-th lane (j= 1,2), we indicate the value gj[i] = 0; if
part of the truck lies inside the grid, gj[i] = 1; if part of a
car (excluding the receiver) lies inside the grid, gj[i]=2; if
the receiver lies inside the grid, gj[i] = 3. Finally, the vehicle
geometry vector in the occupancy grid gis concatenated by
the two vectors on the first and second lanes into one vector
g= [g1,g2].
D. Ordering the location features
Now each vehicle is encoded in a certain format by the
three coordinates discussed in Section II-C, properly ordering
the multiple vehicles in the feature array is still required in
Cartesian and polar coordinates. Similarly as Section III-A in
[8], vehicles are ordered based on the relative distance of the
vehicle to the receiver, the type of vehicle, the lane the vehicle
is located on, etc. In brief, the feature vin each of the data
sample is a one-dimensional vector and can be represented by
v= [r,t1,t2,c1,c2].(6)
In (6), ris the location of the RSU (in the Cartesian coordi-
nate) or the location of the receiver (in the polar coordinate).
The vector tand crepresent the set of locations of trucks
and the low cars, where the subscripts 1and 2denote the lane
index. In each t1,t2,c1and c2, the vehicles are ordered based
on their relative distance to the receiver, where the details are
referred to [8].
III. PRACTICAL IMPLEMENTATIONS
The proposed beam training approach relies on a “fully
connected vehicles” assumption, i.e., we assume all vehicles
are equipped with communicating transceivers, corresponding
protocols and high-resolution GPS, which enable them to
report real-time GPS locations to infrastructures. Each time
when a vehicle initializes a beam training request, the infras-
tructure will be able to construct a real-time map of all vehicles
in the site and formulate the corresponding feature to predict
the beam based on the trained model after offline learning.
In reality, however, a lot of factors could lead to inaccurate
or missing vehicle locations in the feature. In particular,
we exemplify three important sources for noisy features as
follows.
A. GPS inaccuracy
GPS is a satellite-based radio navigation system, where
GPS satellites broadcast their signals in space with a cer-
tain accuracy. Generally, the accuracy depends on a lot of
additional factors, e.g., satellite geometry, signal blockage,
atmospheric conditions, etc [13]. Particularly in the vehicular
urban canyon with frequent signal blockages and reflections,
the GPS inaccuracy can be a big issue.
Since the vehicles are traveling along the center of the lanes
and lane index is simply a categorical variable, the lane index
is assumed to correct all the time. Hence, the GPS location
error is modeled by a Gaussian distribution with zero mean,
and variance of σ2. Consistently, the GPS inaccuracies will be
modeled in both the training datasets and the testing datasets,
affecting all vehicles in the features.
B. Location updating frequency
In addition to the inherent inaccuracy with the vehicle
GPS, the randomness of vehicle mobility can introduce extra
errors to the vehicle locations. Generally, vehicles report
their locations to the infrastructures every ttime. With
mobility, however, the locations of vehicles stored in the
infrastructure soon become out-dated. Vehicles hence have
to report locations to the infrastructures frequently, so as to
guarantee a low level of vehicle location errors. Particularly,
given some initial setting of velocity v(t)and a(t)at t, in
the time interval [t, t + ∆t], the maximum location error is
¯x=v(t)∆t+1
2a(t)∆2
t. For simplicity, we assume the same
velocities and accelerations for all vehicles in the simulation.
The location error ¯xis applied to both training and testing
datasets.
One alternative is to pack more information in the ve-
hicles’ report to infrastructure. Connected vehicles are built
around the SAE protocol J2735 basic safety message (BSM),
which incorporates information of vehicle locations, and other
mobility related information, such as velocities and acceler-
ations [14]. With full BSM feedback, vehicle locations can
be predicted based on simple equations of motion, given the
previous state of the mobility parameters. For example, given
the vehicle’s location, velocity and acceleration at time of tas
x(t), v(t), a(t), at any time during ˜
t[t, t + ∆t], the updated
location can be approximated by
x(˜
t)x(t) + v(t)(˜
tt) + 1
2a(t)(˜
tt)2.(7)
As long as the reporting interval tis small enough, during
which the acceleration remains stable, (7) will keep track of the
vehicle’s location precisely during the time interval [t, t +t].
Hence, the key is simply to capture the appropriate time
interval within which the acceleration remains. The required
reporting interval is now converted to the scale of transporta-
tion, which is several orders of the time scale of that in
communication. Also, it should be noted that exhaustive beam
search, in most of the times, cannot capture beam changes on
time, since the beam training only happens at fixed time slots
t=τB,2τB,· · · (τBis the interval of conducting beam search
in traditional mmWave systems). Our model will be flexible
enough to predict any potential changes of beams, since now
we have continuous interpretation of vehicle locations and
tracking of the beams based on the locations.
C. Penetration rate
Another important issue in practical implementations is
the non-ideal penetration rate of the connected vehicles.
The penetration rate defines the percentage of the vehicles
with connected devices, whose locations are known to the
infrastructures. Fully connected vehicles are not a realistic
assumption in the current state of art. Low or not 100%
penetration rate might have significant impacts on our model
since the features have to be properly selected and ordered
correspondingly based on the locations as shown in Section
II-C and II-D. In this case, the vehicle locations might be
missing and the features might be misaligned. In particular, it
is assumed that only the low cars connected will initiate beam
training request within the proposed framework. Therefore,
among the data samples, we randomly select trucks as being
connected based on Bernoulli distribution with probability ppr,
where ppr is the penetration rate pre-defined. Trucks who are
not connected will be invisible to the infrastructure and the
locations will be missing in the feature.
IV. PER FO RM AN CE EVAL UATION
In this section, we provide a comprehensive evaluation
of the proposed beam selection approach. We mainly focus
on the two performance metrics: alignment probability and
the achieved throughput. Let max{·} denote the maximum
element of the vector (·), and (·)is the indicator function.
Given the real power y1,· · · ,ym, the real optimal beam
pair index s1, s2,· · · , smand the predicted beam pair index
ˆs1,ˆs2,· · · ,ˆsmof the msamples, the alignment probability
can be formulated as
PA=1
m
m
X
i=1
si=si),(8)
and the achieved throughput ratio RTis
RT=Pm
i=1 log2(1 + yisi])
Pm
i=1 log2(1 + max{yi}),(9)
We start with comparing the beam selection performance
with different machine learning models. Then we evaluate
the prediction performance with different levels of situational
awareness by adding in different numbers of vehicle in the
feature. Lastly, some realistic issues of noisy features in
implementations are discussed as in Section III.
A. Learning models
For fair comparison, we start with applying a simple feature
set encoded in a Cartesian coordinate as in Section II-C, with
TABLE I
ALIGNMENT PROBABILITY AND ACHIEVED THROUGHPUT RATIO OF BEAM
SELECTION WITH DIFFERENT CLASSIFIERS.
PA(%)RT(%)
Naive-Bayes 59.31 91.14
AdaBoost 45.80 75.05
RBF-SVM 55.89 89.32
Gradient Boosting 69.05 96.49
Random forest 85.14 98.32
no GPS errors. The used classifiers are listed in Table I. From
the result, it is shown that random forest outperforms the
other classifiers, and it achieves 85.14%alignment probability.
Another important observation is that the achieved through-
put does not scale with the alignment probability. Despite
the fact that random forest achieves much higher alignment
probability compared to the classifiers such as Naive-Bayes or
gradient-boosting, there are no significant differences among
their achieved throughput. The reason is the strongest several
beams’ powers are close. Therefore, even if the classifier
cannot predict the exact optimal beam pair index, as long
as the selected one is among one of those top beams, the
throughput will not be too bad. The conclusion reveals the fact
that alignment probability might not be the best performance
metric for evaluation. Even though the model cannot guar-
antee 100% alignment probability, it could still be accurate
enough to identify those “good beams”. This is important
for mmWave vehicular system design, since it is beneficial
to sacrifice some optimality to achieve low overheads. Some
sub-optimality is introduced in the prediction accuracy, but
the overheads can be largely reduced which can still provide
significant improvement over the system performance.
B. Different levels of situational awareness
In this part, we evaluate and compare the system per-
formance with different levels of situational awareness. The
red curve in Fig. 5 plots the alignment probability with
different number of vehicles modeled in the feature. The
vehicle locations are ordered correspondingly based on relative
distance to the receiver as in Section II-D. When the feature
only includes the receiver location, an alignment probability
of around 62%. is achieved. After adding in first lane truck
locations, the alignment probability is improved to 82%. From
the curve, it can be concluded that most of the enhancement is
contributed by the closest trucks’ (around only 2-3) locations.
Similar observations can be obtained by adding in second
lane trucks. When including low vehicles into the features,
the alignment probability remains stable which implies that
low vehicles have negligible impacts in mmWave vehicular
channels and are not very useful in predicting the beams.
Furthermore, we reduce the feature set by only keeping the
locations of vehicles that improve the alignment probability on
the red curve. Specifically, the reduced feature set becomes:
[receiver location, closest three trucks on the first lane, closest
0 5 10 15 20 25 30 35 40 45
Number of Vehicle Locations in the Feature
0.6
0.65
0.7
0.75
0.8
0.85
0.9
Alignment Probability
Increasing feature
Reduce feature
Adding low-height carsAdding 2nd lane truck
Adding 1st lane trucks
(Nveh = 10)
Only RX location
Fig. 5. Alignment probability adding in different number of vehicle locations
in the feature. We start with only using the receiver location of the feature and
add on the first lane truck, second lane truck, first lane cars, second lane cars
correspondingly based on the vehicle order in Section II-D. The blue curve
is the alignment probability by only including part of the vehicle locations in
the feature, e.g., the closest several trucks and cars on each lane.
012345678910
Variance of Gaussian error
0.55
0.6
0.65
0.7
0.75
0.8
0.85
Alignment probability
0.89
0.9
0.91
0.92
0.93
0.94
0.95
0.96
0.97
0.98
0.99
Throughput
Cartesian
Polar
Grids
Fig. 6. Comparison of alignment probability and achieved throughput with
different distributions of GPS location error. Results of Cartesian coordinates,
polar coordinates and occupation grid are compared in the figure.
truck on the second lane]. Blue curve shows the alignment
probability of around 86%when this reduced feature set is
used.
C. Noisy features
In this section, noisy location features are included in the
model. The inaccuracies of the location can come from three
parts: 1) inherent GPS inaccuracy, 2) out-dated locations due
to vehicle mobility and fixed location reporting interval, 3)
missing features due to limited penetration rate.
Alignment probability and achieved throughput are com-
pared in Fig. 6, with different GPS inaccuracies and encodings
of vehicle geometries. It is shown that location inaccuracy can
make a big difference on the prediction accuracy, even when
GPS error variance is very small. When the GPS error grows
large, the prediction accuracy falls below 60%. Therefore, one
limitation of our model is that it heavily relies on exact feed-
back of vehicle locations provided by GPS, whose accuracy
cannot be guaranteed, at least in the state-of-art. Also, it can
0 0.2 0.4 0.6 0.8 1
Penetration rate
0.6
0.65
0.7
0.75
0.8
0.85
0.9
Alignment probability
0 penetration rate (no situational awareness)
Full penetration rate
(full situational
awareness)
Fig. 7. Comparison of alignment probability with different penetration rates
with Cartesian coordinates.
0 100 200 300 400 500 600 700 800 900 1000
Reporting interval (ms)
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
Alignment probability
a = 0, 2, 5, 10 m/s2
v = 30km/h
v = 60km/h
v = 120km/h
Fig. 8. Comparison of alignment probability with different vehicle velocities,
accelerations and location reporting intervals. Here we assume identical
uniformly accelerated motion for all vehicles and there are no GPS errors
modeled in either the training or the testing datasets for fair comparison.
be observed that Cartesian and polar coordinates achieve better
performance than the occupancy grids.
Fig. 8 demonstrates how the performance is affected when
a longer location reporting interval is applied with vehicle
mobility. We assume uniformly accelerated rectilinear motion
for all vehicles. A combination of parameters v= 30,60,120
km/h and a= 0,2,5,10 m/s2is used and a fixed location error
¯x=vt+1
2a2
tis added to all features. For fair comparison,
no GPS errors are included in the datasets. It is shown
that if only the locations are reported to the infrastructures,
the alignment probability degrades very fast with a longer
reporting interval, even at a relatively low speed. Particularly,
using reporting interval of around 200 ms, the alignment
probability decreases from 86%to around 70%at v= 30km/h.
The different values of acceleration rates, however, do not have
a significant impact on the alignment probability. Therefore, if
the velocities can be fed back to the infrastructure along with
the locations, the updated locations can largely be predicted
and the model’s accuracy can be guaranteed, with negligible
extra overheads of feedback required.
Fig. 7 plots the alignment probability with different pene-
tration rates (of trucks). Since it is assumed that all the low
vehicles report locations to the infrastructure and only trucks
might be disconnected from the network, 0penetration rate
indicates the case without situational awareness, while full
penetration rate is equivalent to the full situational awareness
case as discussed in Section IV-B. It is shown that alignment
probability scales proportionally with the penetration rate and
even at very low penetration rate of around 20%, there is still
prominent improvement of the performance compared to the
no situational awareness case.
V. ACKNOWLEDGMENT
This research was partially supported by a gift from Huawei
through UT Situation-Aware Vehicular Engineering Systems
(UT-SAVES), by the U.S. Department of Transportation
through the Data-Supported Transportation Operations and
Planning (D-STOP) Tier 1 University Transportation Center
and the Communications and Radar-Supported Transportation
Operations and Planning (CAR-STOP) project funded by the
Texas Department of Transportation.
REFERENCES
[1] J. Choi, V. Va, N. Gonzalez-Prelcic, R. Daniels, C. R. Bhat, and R. W.
Heath, “Millimeter-wave vehicular communication to support massive
automotive sensing,IEEE Commun. Mag., vol. 54, no. 12, pp. 160–
167, 2016.
[2] Y. Wang, K. Venugopal, A. F. Molisch, and R. W. Heath, “Blockage
and coverage analysis with mmwave cross street BSs near urban
intersections,” in Proc. Int. Conf. Commun. (ICC), pp. 1–6, IEEE, 2017.
[3] N. Gonz´
alez-Prelcic, A. Ali, V. Va, and R. W. Heath, “Millimeter-wave
communication with out-of-band information,” IEEE Commun. Mag.,
vol. 55, no. 12, pp. 140–146, 2017.
[4] Y. Wang, K. Venugopal, R. W. Heath, and A. F. Molisch, “Mmwave
vehicle-to-infrastructure communication: Analysis of urban microcellu-
lar networks,” IEEE Trans. on Veh. Technol., pp. 1–1, 2018.
[5] M. Peng, Y. Li, J. Jiang, J. Li, and C. Wang, “Heterogeneous cloud radio
access networks: A new perspective for enhancing spectral and energy
efficiencies,IEEE Wireless Commun., vol. 21, no. 6, pp. 126–135, 2014.
[6] V. Va, J. Choi, T. Shimizu, G. Bansal, and R. W. Heath, “Inverse
multipath fingerprinting for millimeter wave V2Ibeam alignment,IEEE
Trans. Veh. Technol., vol. 67, pp. 4042–4058, May 2018.
[7] A. Klautau, P. Batista, N. G. Prelcic, Y. Wang, and R. W. Heath, “5G
MIMO data for machine learning: Application to beam-selection using
deep learning,” in Proc. Inf. Theory and Appl. Workshop (ITA), pp. 1–6,
Jan. 2016.
[8] Y. Wang, M. Narasimha, and R. W. Heath, Jr, “MmWave Beam
Prediction with Situational Awareness: A Machine Learning Approach,”
ArXiv e-prints, May 2018.
[9] S. Hur, S. Baek, B. Kim, J. Park, A. F. Molisch, K. Haneda, and M. Peter,
“28 GHz channel modeling using 3D ray-tracing in urban environments,
in Proc. European Conf. Antennas and Propagation (EuCAP), pp. 1–5,
IEEE, 2015.
[10] K. Haneda, L. Tian, H. Asplund, J. Li, Y. Wang, D. Steer, C. Li,
T. Balercia, S. Lee, Y. Kim, et al., “Indoor 5G 3GPP-like channel models
for office and shopping mall environments,” in Proc. Int. Conf. Commun.
Workshops, pp. 694–699, IEEE, 2016.
[11] V. Degli-Esposti, F. Fuschini, E. M. Vitucci, M. Barbiroli, M. Zoli,
L. Tian, X. Yin, D. A. Dupleich, R. M¨
uller, C. Schneider, et al., “Ray-
tracing-based mm-wave beamforming assessment,IEEE Access, vol. 2,
pp. 1314–1325, 2014.
[12] https://www.remcom.com/wireless-insite-em- propagation-software/.
[13] https://www.gps.gov/.
[14] Y. Zhang, G. W. Gantt, M. J. Rychlinski, R. M. Edwards, J. J.
Correia, and C. E. Wolf, “Connected vehicle diagnostics and prognostics,
concept, and initial practice,” IEEE Trans. on Reliability, vol. 58, no. 2,
pp. 286–294, 2009.
... RL is an area of ML used to maximize the notion of growing reward. In [7], taking maximum advantage of ML with previous beam training information using locations, nearest vehicles, and sizes of the receiver were used to learn the optimal beam pair index. For research into mmWave or massive MIMO antennas, a dataset is needed, so in [18], the dataset for mmWave or massive MIMO antennas has been described. ...
... The database used contains a large number of snapshots for training sets used in machine learning methodologies [7,28]. In the dataset, a DNN (deep neural network) based beam selection algorithm is used, which is a machine learning algorithm. ...
... Beam selection alignment probability and achieved throughput ratio with different classifiers[7]. ...
Article
Full-text available
The next generation of wireless communication networks will rely heavily on machine learning and deep learning. In comparison to traditional ground-based systems, the development of various communication-based applications is projected to increase coverage and spectrum efficiency. Machine learning and deep learning can be used to optimize solutions in a variety of applications, including antennas. The latter have grown popular for obtaining effective solutions due to high computational processing, clean data, and large data storage capability. In this research, machine learning and deep learning for various antenna design applications have been discussed in detail. The general concept of machine learning and deep learning is introduced. However, the main focus is on various antenna applications, such as millimeter wave, body-centric, terahertz, satellite, unmanned aerial vehicle, global positioning system, and textiles. The feasibility of antenna applications with respect to conventional methods, acceleration of the antenna design process, reduced number of simulations, and better computational feasibility features are highlighted. Overall, machine learning and deep learning provide satisfactory results for antenna design.
... For example, an inverse fingerprinting method that uses past received power characteristics at UE locations has been shown to reduce beam training overhead in vehicular communications [6]. Machine learning (ML) approaches based on neural networks (NNs) have also been used in this context to learn the complex mapping between UE positions and optimal beam indices [7], [8]. The authors in [9] also included the orientation of the UE antenna array as an input in their ML model, in addition to the UE position. ...
Preprint
Full-text available
Millimeter-wave (mmWave) MIMO systems rely on highly directional beamforming to overcome severe path loss and ensure robust communication links. However, selecting the optimal beam pair efficiently remains a challenge due to the large search space and the overhead of conventional methods. This paper proposes a probabilistic position-aided beam selection approach that exploits the statistical dependence between user equipment (UE) positions and optimal beam indices. We model the underlying joint probability mass function (PMF) of the positions and the beam indices as a low-rank tensor and estimate its parameters from training data using Bayesian inference. The estimated model is then used to predict the best (or a list of the top) beam pair indices for new UE positions. The proposed method is evaluated using data generated from a state-of-the-art ray tracing simulator and compared with neural network-based and fingerprinting approaches. The results show that our approach achieves a high data rate with fewer training samples and a significantly reduced beam search space. These advantages render it a promising solution for practical mmWave MIMO deployments, reducing the beam search overhead while maintaining a reliable connectivity.
Article
Effective beam alignment is essential for vehicle-to-infrastructure (V2I) millimeter wave (mmWave) communication systems, particularly in high-mobility vehicle scenarios. This paper explores a three-dimensional (3D) vehicle environment and introduces a novel deep learning (DL)-based beam search method that incorporates an image-based coding (IBC) technique. The mmWave beam search is approached as an image processing problem based on situational awareness. We propose IBC to leverage the locations, sizes, and information of vehicles, and utilize convolutional neural network (CNN) to train the image dataset. Consequently, the optimal beam pair index(BPI)can be determined. Simulation results demonstrate that the proposed beam search method achieves satisfactory performance in terms of accuracy and robustness compared to conventional methods.
Article
Full-text available
This paper presents a novel artificial intelligence (AI)-based phase shift system in a beamforming system implemented with field programmable gate array (FPGA)-based hardware by integrating a conventional convolutional neural network (CNN) algorithm. The position of the target can be determined through a phase shifter in a beamforming system using artificial intelligence. In a system that emits a beam from a radio frequency (RF) transmitter and receives a beam from an RF receiver, artificial intelligence can control the phase. It controls the phase of the transmitter for beam scanning and the phase to optimize the signal-to-noise ratio (SNR) of the receiver. The position of the target was detected by learning the signal input data from the receiver. Targets were detected through two-beam scanning processes in a 3D space. The first is a coarse process of detecting the approximate position of the target in the entire space, and the second is a fine process of detecting the area in detail after detecting the first approximate position. The phases of the individual antennae should be controlled for optimal beamforming based on the 5×5 antenna, and the phase is detected at high speed by holding the phase large in the first coarse tuning. The second scan entails a narrow range scan with a small phase to detect it at a high speed accurately. This study shows that with FPGA, AI beamforming can be implemented through two scanning methods without image sensors. Based on the receiver’s 5×5 antenna, the CNN input feature consisted of 35×35 classifies the class with high accuracy.
Article
Full-text available
Beamforming using highly directional antennas is inevitable to compensate the propagation losses and enable communication in the millimeter wave (mmWave) band. However, this directivity makes mmWave links fragile and sensitive to environment dynamics and blockage. Consequently, initial access and management of the mmWave links in dynamic environments turns to be a big challenging issue, especially in dense network scenarios. In particular, a massive amount of beamforming training (BT) overhead with high delay is needed to establish the mmWave link between a user device (UD) and the deployed small cells (SCs). The consequences are become more severe in case of mobility, since frequent handovers (HOs) between different beams/SCs is needed to preserve the connection with moving UDs. Inspired by the fact that directionality makes the mmWave communications to be geometry and location driven, this paper proposes a geometry-based schemes for the initial access and management of mmWave links. In the proposed schemes, geometric information of the target area including the UDs locations, SCs coordinates and the target area maps are exploited to alleviate the complexity of the exhaustive-based BT. The high impact of the proposed mmWave link initial access and management schemes over the conventional ones in different terms such as BT complexity and total energy consumption rates is proved via simulation analysis.
Article
Digital twins are an important technology for advancing mobile communications, specially in use cases that require simultaneously simulating the wireless channel, 3D scenes and machine learning. Aiming at contributing towards a solution to this demand, this work describes a modular co-simulation methodology called CAVIAR, for implementing the virtual counterpart of a digital twin system. Here, CAVIAR is upgraded to support a message passing library and facilitate using different 6G-related simulators. The main contributions of this work are the detailed description of different CAVIAR architectures, the implementation of this methodology to assess a 6G use case of UAV-based search and rescue mission (SAR), and the generation of benchmarking data about the computational resource usage. For executing the SAR co-simulation we adopt five open-source solutions: the physical and link level network simulator Sionna, the simulator for autonomous vehicles AirSim, scikit-learn for training a decision tree for MIMO beam selection, Yolov8 for the detection of rescue targets and NATS for message passing. Results for the implemented SAR use case suggest that the methodology can run in a single machine, with the main demanded resources being the CPU processing and the GPU memory.
Conference Paper
The rapid development of 6G millimeter-wave (mmWave) networks has introduced new challenges for network security. Adversarial attacks on beamforming algorithms in these networks can lead to severe communication performance degradation. This paper proposes an optimization framework for Deep Learning (DL) hyperparameters that enhances adversarial security in 6G mmWave networks through beam prediction. We develop a robust DL model that can adapt to various adversarial attacks and maintain high prediction accuracy. The proposed framework optimizes hyperparameters using hybrid Particle Swarm Optimization (PSO) with Multi-Verse Optimizer (MVO) for improved security. The framework is evaluated through extensive simulations, demonstrating its effectiveness in improving network security and robustness against adversarial attacks. Under normal conditions, the optimized model achieves the lowest mean squared error (MSE) of 9.4410E – 05 for beamforming codeword predictions. Subjected to Fast Gradient Sign Method (FGSM) adversarial attacks, the optimized model maintains the lowest MSE of 2.2910E – 03, indicating greater resilience against adversarial perturbations. With adversarial training, the optimized model achieves the lowest MSE of 2.7110E – 03, demonstrating the most robust defense against adversarial attacks. In contrast, the non-optimized model suffers significant performance degradation under adversarial and defended conditions. The source code is available at [1].
Article
Vehicles today are equipped with different sensors, such as GPS, camera, and LiDAR. We propose Omni-CNN, a machine-learning (ML) based framework that accepts one or more of such available sensor inputs to speed up beam selection in vehicular networks, instead of performing an exhaustive search among all possible beams. Omni-CNN proposes a modality-agnostic approach, where a single shared model can accommodate any combination of these sensor inputs but with appropriate weight-selection masks specific to each modality. In Omni-CNN, we first use the residual capacity of the shared model to learn the predictive task for the current modality. Second, we propose an adaptive algorithm to calculate the required capacity on a per-layer basis and release the excess capacity for the next modalities. In our design, we use the gradients to identify the sparsity constraints that result in minimum capacity usage, while maintaining the accuracy. Third, given the sparsity constraints, we solve an optimization problem to select modality-specific sub-models using Alternating Directions-Method of Multipliers (ADMM) algorithm. Finally, we include decision level aggregation to handle scenarios, where more than one modality is present. Results on a challenging real-world dataset reveal that Omni-CNN reduces the overall model size by 91.4%, while achieving 80.89% accuracy in the prediction of the optimal beam. Furthermore, it reduces the beam selection overhead by 99.37% while retaining 93.34% of the throughput, compared to the 802.11ad standard.
Conference Paper
Full-text available
Millimeter wave (mmWave) communication offers Gbps data transmission, which can support massive data sharing in vehicle-to-infrastructure (V2I) networks. In this paper, we analyze the blockage effects among different vehicles and coverage probability of a typical receiver, considering cross street BSs near urban intersections in a multi-lane mmWave vehicular network. First, a three-dimensional model of blockage among vehicles on different lanes is considered. Second, we compute the coverage probability considering the interference of cross street base stations. Incorporating the blockage effects, we derive an exact and semi closed-form expression of the cumulative distribution density (CDF) of the association link path gain. Then, a tight approximation of the coverage probability is computed. We provide numerical results to verify the accuracy of the analytic results. We demonstrate the effects of blockage and the cross street interference. Also, we compare coverage probability with different BSs intensities under various street settings. It is shown that in multi-lane V2I networks, blockage among vehicles is not significant. Also, deploying more BSs does not increase coverage probability efficiently in ultra-dense streets.
Article
Full-text available
Efficient beam alignment is a crucial component in millimeter wave systems with analog beamforming, especially in fast-changing vehicular settings. This paper uses the vehicle's position (e.g., available via GPS) to query the multipath fingerprint database, which provides prior knowledge of potential pointing directions for reliable beam alignment. The approach is the inverse of fingerprinting localization, where the measured multipath signature is compared to the fingerprint database to retrieve the most likely position. The power loss probability is introduced as a metric to quantify misalignment accuracy and is used for optimizing candidate beam selection. Two candidate beam selection methods are derived, where one is a heuristic while the other minimizes the misalignment probability. The proposed beam alignment is evaluated using realistic channels generated from a commercial ray-tracing simulator. Using the generated channels, an extensive investigation is provided, which includes the required measurement sample size to build an effective fingerprint, the impact of measurement noise, the sensitivity to changes in traffic density, and a beam alignment overhead comparison with IEEE 802.11ad as the baseline. Using the concept of beam coherence time, which is the duration between two consecutive beam alignments, and parameters of IEEE 802.11ad, the overhead is compared in the mobility context. The results show that while the proposed approach provides increasing rates with larger antenna arrays, IEEE 802.11ad has decreasing rates due to the larger beam training overhead that eats up a large portion of the beam coherence time, which becomes shorter with increasing mobility.
Article
Full-text available
Configuring the antenna arrays is the main source of overhead in millimeter wave (mmWave) communication systems. In high mobility scenarios, the problem is exacerbated, as achieving the highest rates requires frequent link reconfiguration. One solution is to exploit spatial congruence between signals at different frequency bands and extract mmWave channel parameters from side information obtained in another band. In this paper we propose the concept of out-of-band information aided mmWave communication. We analyze different strategies to leverage information derived from sensors or from other communication systems operating at sub-6 GHz bands to help configure the mmWave communication link. The overhead reductions that can be obtained when exploiting out-of-band information are characterized in a preliminary study. Finally, the challenges associated with using out-of-band signals as a source of side information at mmWave are analyzed in detail.
Article
Full-text available
Vehicle-to-infrastructure (V2I) communication may provide high data rates to vehicles via millimeter-wave (mmWave) microcellular networks. This paper uses stochastic geometry to analyze the coverage of urban mmWave microcellular networks. Prior work used a pathloss model with a line-of-sight probability function based on randomly oriented buildings, to determine whether a link was line-of-sight or non-line-of-sight. In this paper, we use a pathloss model inspired by measurements, which uses a Manhattan distance model and accounts for differences in pathloss exponents and losses when turning corners. In our model, users and base stations (BSs) are randomly located on a network formed by a two dimensional Poisson line process. Our model is well suited for urban microcellular networks where the base stations are deployed at street level. Based on this new approach, we derive the coverage probability under certain BS association rules to obtain closed-form solutions without much complexity. In addition, we draw two main conclusions from our work. First, non-line-of-sight BSs are not a major benefit for association or source of interference. Second, there is an ultradense regime where deploying (active) BSs does not enhance coverage.
Article
Full-text available
Future mobile communications systems are likely to be very different to those of today with new service innovations driven by increasing data traffic demand, increasing processing power of smart devices and new innovative applications. To meet these service demands the telecommunications industry is converging on a common set of 5G requirements which includes network speeds as high as 10 Gbps, cell edge rate greater than 100 Mbps, and latency of less than 1 msec. To reach these 5G requirements the industry is looking at new spectrum bands in the range up to 100 GHz where there is spectrum availability for wide bandwidth channels. For the development of new 5G systems to operate in bands up to 100 GHz there is a need for accurate radio propagation models which are not addressed by existing channel models developed for bands below 6 GHz. This paper presents a preliminary overview of the 5G channel models for bands up to 100 GHz in indoor offices and shopping malls, derived from extensive measurements across a multitude of bands. These studies have found some extensibility of the existing 3GPP models to the higher frequency bands up to 100 GHz. The measurements indicate that the smaller wavelengths introduce an increased sensitivity of the propagation models to the scale of the environment and show some frequency dependence of the path loss as well as increased occurrence of blockage. Further, the penetration loss is highly dependent on the material and tends to increase with frequency. The small-scale characteristics of the channel such as delay spread and angular spread and the multipath richness is somewhat similar over the frequency range, which is encouraging for extending the existing 3GPP models to the wider frequency range. Further work will be carried out to complete these models, but this paper presents the first steps for an initial basis for the model development.
Article
Full-text available
The use of large-size antenna arrays to implement pencil-beam forming techniques is becoming a key asset to cope with the very high throughput density requirements and high path-loss of future millimeter-wave gigabit-wireless applications. Sub-optimal beamforming strategies based on search on discrete set of beams (steering vectors) are proposed and implemented in present standards and applications. The potential of fully-adaptive advanced beamforming strategies that will become possible in the future, thanks to the availability of accurate localization and powerful distributed computing, is evaluated in this work through system simulation. After validation and calibration against mm-wave directional indoor channel measurements, a 3D ray tracing model is used as a propagation-prediction engine to evaluate performance in a number of simple, reference cases. Ray tracing itself however is proposed and evaluated as a real-time prediction tool to assist future beamforming techniques.
Article
As driving becomes more automated, vehicles are being equipped with more sensors generating even higher data rates. Radars (RAdio Detection and Ranging) are used for object detection, visual cameras as virtual mirrors, and LIDARs (Light Detection and Ranging) for generating high resolution depth associated range maps, all to enhance the safety and efficiency of driving. Connected vehicles can use wireless communication to exchange sensor data, allowing them to enlarge their sensing range and improve automated driving functions. Unfortunately, conventional technologies, such as dedicated short-range communication (DSRC) and 4G cellular communication, do not support the gigabit-per-second data rates that would be required for raw sensor data exchange between vehicles. This paper makes the case that millimeter wave (mmWave) communication is the only viable approach for high bandwidth connected vehicles. The motivations and challenges associated with using mmWave for vehicle-to-vehicle and vehicle-to-infrastructure applications are highlighted. A solution to one key challenge - the overhead of mmWave beam training - is proposed. The critical feature of this solution is to leverage information derived from the sensors or DSRC as side information for the mmWave communication link configuration. Examples and simulation results show that the beam alignment overhead can be reduced by using position information obtained from DSRC.