Reconfigurable intelligent surface passive beamforming enhancement using unsupervised learning

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 13, No. 1, February 2023, pp. 493~501
ISSN: 2088-8708, DOI: 10.11591/ijece.v13i1.pp493-501  493
Journal homepage: http://ijece.iaescore.com
Reconfigurable intelligent surface passive beamforming
enhancement using unsupervised learning
Intisar Al-Shaeli, Ismail Sharhan Hburi, Ammar A. Majeed
Department of Electrical Engineering, Faculty of Engineering, Wasit University, Wasit Province, Iraq
Article Info ABSTRACT
Article history:
Received Feb 25, 2022
Revised Sep 2, 2022
Accepted Sep 20, 2022
Reconfigurable intelligent surfaces (RIS) is a wireless technology that has
the potential to improve cellular communication systems significantly. This
paper considers enhancing the RIS beamforming in a RIS-aided multiuser
multi-input multi-output (MIMO) system to enhance user throughput in
cellular networks. The study offers an unsupervised/deep neural network
(U/DNN) that simultaneously optimizes the intelligent surface beamforming
with less complexity to overcome the non-convex sum-rate problem
difficulty. The numerical outcomes comparing the suggested approach to the
near-optimal iterative semi-definite programming strategy indicate that the
proposed method retains most performance (more than 95% of optimal
throughput value when the number of antennas is 4 and RIS’s elements are
30) while drastically reducing system computing complexity.
Keywords:
6G networks
Beamforming neural network
Massive multi-input multi-
output
Reconfigurable intelligent
surfaces
Unsupervised learning
This is an open access article under the CC BY-SA license.
Corresponding Author:
Intisar Al-Shaeli
Department of Electrical Engineering, Faculty of Engineering, Wasit University
Hay Al-Rabea Road, Al-Kut District, Wasit Province, Iraq
Email: intisark302@uowasit.edu.iq
1. INTRODUCTION
Reconfigurable intelligent surface )RIS( has been intended as a potentially transformative
technology capable of lowering power usage and enhancing network throughput by artificially altering the
propagation environment of electromagnetic waves (EM) [1]. RISs possess the enormous prospective to
change wireless network design and enable the creation of intelligent radio environments [2]. This ability
occurs when merged with other fifth-generation prospective technologies, such as non-orthogonal multiple
access (NOMA) systems [3], terahertz cellular systems, multi-input multi-output )MIMO( systems [4], and
wireless networks powered by artificial intelligence (AI) [5], [6]. Several essential characteristics that
distinguish RIS from recent technologies are highlighted in [7]. These characteristics contain specific design
constraints imposed by the RIS elements’ near-passive nature. These qualities open up new possibilities for
modifying the wireless environment, boosting the efficiency of radio wave use, extending coverage,
transferring energy, locating, and enhancing spatial capacity density [8] while improving energy
consumption [9]. Simultaneously, these characteristics introduce new difficulties in designing RIS-aided
cellular networks, including the transmission of information inside a RIS-enabled environment, enhancement
of the RIS configuration with restricted information, resource allocation, and the optimization of the network
in such cellular systems, as provided in [10].
Furthermore, machine learning (ML) techniques and deep learning (DL) have emerged as valuable
tools for dealing with massive amounts of data [11], exponential non-convex challenges that are
mathematically difficult, and computationally intensive challenges [12], [13]. DL-based techniques have
been employed in various cellular systems, including physical layer communications [14] and “resource
allocation” [15]. Inspired by the prospect of using DL for complex maximization problems, in study [1] the

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 1, February 2023: 493-501
494
authors used the DL technique to construct the RIS beamforming matrices with restricted channel state
information (CSI). The active/passive beamforming was intended to enhance the secrecy performance of
reflective RIS-assisted MIMO networks with a single genuine receiver and a single eavesdropper in [16],
[17]. In the scope of RIS-aided communication systems, authors in references [18], [19] proposed a
supervised learning strategy in which a deep neural network (DNN) is learned offline to demonstrate an
implicit connection among both measured coordinate information and the RIS’s phase configuration.
However, a significant difficulty for supervised learning is obtaining labels. Gao et al. [20] achieved the ideal
labels using extensive search, which is cost-prohibitive in practice, especially when many training examples
are necessary. Gao et al. [20] introduced a modified DNN for single-user RIS-assisted MIMO networks
trained offline using the unsupervised learning approach. This study produces a structure that can estimate
real-time when utilized online. They showed through simulation that the proposed mechanism significantly
decreases computation complexity in comparison to the traditional suboptimal scheme that employs a semi-
definite relaxation method. Song et al. [21] introduced a novel two-stage structure to optimize the transmit
beamforming and the RIS phase shift matrix together and, consequently, the sum rate of all users. Based on
the characteristics of this problem, they carefully customized network layers, features, and loss functions.
The current study proposed an efficient and low-cost DNN structure to improve the passive
beamforming vectors in RIS-assisted MIMO systems with a power limitation target. A particular emphasis is
placed on developing a customized DNN construction for the RIS beamforming design challenge and
selecting a set of specific characteristics for the training process. To eliminate the labeling complexity
associated with supervised learning, we suggest using the “unsupervised learning” technique for RIS
beamforming design in this study, like [22], [23]. Different from the work in [20], the suggested structure of
the neural network can deal with more complicated multiuser scenarios to optimize the system throughput
under the constraint of the access point (AP) maximum allowed transmitting power. In addition, different
from the approach employed in [21], our proposed architecture considers three channels at the network input
instead of two-channel. These are direct, reflected, and AP_RIS channels which make the scheme appropriate
for more realistic environments and improve the feature extraction of the network.
The following summarizes the study contributions. At the start point, the study offers a framework
for the multiantenna method that utilizes a DNN to select a beamformer with the optimal spectral
performance while minimizing transmission power. Following that, numerical experiments were undertaken
to test the suggested system performance, which revealed that the proposed design offers a critical
performance boost compared to standard beamforming approaches. This article was structured: section 1
introduction. Section 2 system model and formulation of the problem. Section 3 DNN structure. In section 4,
numerical results were discussed. Conclusion the paper is done in section 5. Notations: the capital letters like
(M, N) denote scalar constants. Small latter like (k,…r) denote scalar variables. Vectors are represented by
bold small latter like (h), where the hk means the kth
element of h. Capital bold latter implies matrix-like F.
Diag (·) denotes the diagonal operation. We use tr (.), (.) H, 𝐶, indicates the matrixes’ trace, conjugate
transpose (Hermitian), and complex matrix, respectively.
2. SYSTEM MODEL AND FORMULATION OF THE PROBLEM
Based on our previous work in [24], which depends on the traditional iterative approach to cope
with the transmission/reflection beamforming design problem, the current work follows an entirely different
simple path to meet the proposed goal of this study by employing an artificial neural approach. Specifically,
we consider a RIS-enhanced multiuser MIMO wireless system, as shown in Figure 1. that consists of
|Ap| numbers of APs configured with M antenna elements servicing the downlink of single-antenna K users.
The AP is aided by R numbers of RIS, each containing N reflective elements. Without losing of generality,
we consider that all channels’ channel state information (CSI) is precisely known at the AP and RIS. The
direct path to the Kth
user is expressed through a channel matrix with complex vectors, Fa,k ∈ ℂ N×K.
Without lossing of generality, we consider that all channels’ CSI is precisely known at the AP and RIS. The
surface-user path is implied by hr,k ∈ ℂ N×1, while the MIMO AP-RIS links channel matrix is denoted as
Ga,r ∈ ℂ M×N. Diagonal matrix 𝛷r ∈ ℂ N×N is the received signal phase shift at the RIS, where 𝜱r=√𝜂
diag (𝚽 r1,… 𝚽 rn), ∀r ∈ Ɍ. Theoretically, an element’s reflection amplitude can be tuned for diverse tasks,
e.g., performance optimization and channel acquisition [25]. Nevertheless, in practice, it is expensive to
consider an independent controller of the phase shift and amplitude of the reflection simultaneously.
Consequently, an individual element is typically considered to optimize the signal reflection as
simplicity. For the motive of the simplicity of practical execution, we assume a discrete value (finite-number)
for the RIS’s element phase shifts. It is worth noting that the discrete phase shifter’s quantization loss
significantly grows as N increases. For scenarios with a big N, we choose high-order quantization to reduce

Int J Elec & Comp Eng ISSN: 2088-8708 
Reconfigurable intelligent surface passive beamforming enhancement using … (Intisar Al-Shaeli)
495
the discrete phase shifter’s quantization loss. If we employ b-bits to characterize the phase-shift levels, then
the number of these levels will be 2𝑏
[26]. For simplicity, we assume uniform-quantization for the discrete
phase-shifts levels in the range [0; 2π)]. To this end, at each RIS element, the discrete phase shift values set
will be,
𝜱𝑟,𝑛 ∈ {0,
𝜋
2𝑏−1 , … , (2𝑏
− 1)
𝜋
2𝑏−1}, ∀r ∈ R, ∀n ∈ N (1)
Figure 1. Model of the proposed multiple RISs schemes
At the AP, the transmitted baseband signals are represented,
𝑥 = ∑ 𝑽𝑎,𝑘 𝑆𝑘
𝐾
𝑘=1 (2)
where 𝑆k is the transmitted symbol to the k-th
user, (k=1, …. K) [9], and Va,k is a baseband beamformer vector
for the k-th
user, Va,k ∈ ℂ M×K
for m=1, …. M. Using the system model discussed above, the received signal at
the k-th
user can be described in the following manner,
𝑦𝑘 = ∑ 𝑭𝑎,𝑘
𝐻
𝑽𝑎,𝑘𝑆𝑘 + ∑ ∑ 𝑯𝑟,𝑘
𝐻
𝜱𝑟
𝐻
𝑮𝑎,𝑟𝑽𝑎,𝑘𝑆𝑘
𝑟∈|𝑅|
𝑎∈|𝐴𝑝|
𝑎∈|𝐴𝑝|
⏟
𝑢𝑠𝑒𝑓𝑢𝑙−𝑠𝑖𝑔𝑛𝑎𝑙
+
∑ ∑ 𝑭𝑎,𝑘
𝐻
𝑽𝑎,𝑖𝑆𝑖
𝑖∈|𝐾|
𝑖≠𝑘
𝑎∈|𝐴𝑝| + ∑ ∑ ∑ 𝑯𝑟,𝑘
𝐻
𝜱𝑟
𝐻
𝑮𝑎,𝑟
𝑽𝑎,𝑖𝑆𝑖
𝑟∈|𝑅|
𝑖∈|𝐾|
𝑖≠𝑘
𝑎∈|𝐴𝑝|
⏟
𝑖𝑛𝑡𝑒𝑟𝑓𝑒𝑟𝑒𝑛𝑐𝑒−𝑠𝑖𝑔𝑛𝑎𝑙
+ 𝒏𝑘 (3)
where 𝐧k ∼ CN (0, σ2
) is the additive white Gaussian noise at the receiver for the k-th user, and the
useful-signal includes both direct Ap-user and indirect AP-RIS-user paths. Next, if we use the symbols
𝚽, 𝐆𝑟 and 𝐕𝑘, for respectively, diag.{𝚽1, 𝚽2, … 𝚽𝑅}, 𝐆𝑟
𝑇
= [𝐆1,𝑟
𝑇
, 𝐆2,𝑟
𝑇
, … 𝐆𝐴𝑃,𝑟
𝑇
], and
𝐕𝑘
𝑇
= [𝐕1,𝑘
𝑇
, 𝐕2,𝑘
𝑇
, … 𝐕𝐴𝑃,𝑘
𝑇
], the last expression for the received signal yk in (3) may be simplified
into, ∑𝑎∈|𝐴𝑝| ∑𝑖∈|𝐾| (𝑭𝑎,𝑘
𝐻
+ 𝑯𝑘
𝐻
𝜱𝑟
𝐻
) 𝑽𝑖𝑆𝑎,𝑖 + 𝒏𝑘. In addition, if we use the notation 𝐐k to denote the
equivalent channel for the useful signal such that,
𝐐𝑘
𝐻
= 𝐅k
𝐻
+ ∑ 𝐇𝑘
𝐻
𝚽r
𝐻
𝐆r
r∈|𝑅| (4)
Then, the received signal and signal to interference plus noise ratio (SINR) at user k are expressed,
respectively,

 ISSN: 2088-8708
496
𝑦𝑘 = ∑𝑘
𝑖=1 𝑸𝑘
𝐻
𝑽𝑖𝑆𝑖 + 𝒏𝑘 (5)
𝛤
𝑘(𝜱, 𝑽) =
𝑽𝑘
𝐻
𝑸𝑘𝑸𝑘
𝐻
𝑽𝑘
∑𝑖∈|𝐾|
𝑖≠𝑘
𝑽𝑖
𝐻𝑸𝑘𝑸𝑘
𝐻𝑽𝑖+𝒏𝑘
(6)
To this end, the sum rate (Nat/s/Hz) per user k is shown as (7),
Rt=∑𝑘∈𝑘 ln (1+Γk) (7)
The main objective is to enhance the RISs reflection-beamforming Φ, as well as AP-transmission
beamforming V to maximize channel throughput while adhering to the total power constraint. The
transmission/reflection beamforming design problem can be stated,
Ƥ0: max
𝚽,𝐕
∑𝑘∈|𝐾| ln(1 + Γk) (8)
s.t: 𝜱𝑟,𝑛 ∈ {0,
𝜋
2𝑏−1 , … ,
(2𝑏−1)𝜋
2𝑏−1 } , ∀𝑟 ∈ 𝑅, ∀𝑛 ∈ 𝑁 (8a)
tr (𝐕k 𝐕k
H
) ≤ Pmax (8b)
where Pmax denotes the AP maximum allowed transmitting power. The reflecting element phase shift
limitation is specified in the constraint of (8a). Owing to the restrictions in (8a) and (8b), the optimization
issue presented in (8) is a significant complicated problem challenge; therefore, in the proposed scheme, and
for the sake of simplification, we consider the maximum-ratio transmission for the actively transmit
beamforming [27], [28].
𝐕𝑇
=
(𝐆𝚽𝐇 +𝐅 )𝐻
‖𝐆𝚽𝐇 +𝐅 ‖
(9)
Up to this end, Ƥ0 can be modified to the following problem,
Ƥ1: max
𝚽
‖𝐆𝚽𝐇 + 𝐅 ‖2
(10)
s.t: 𝜱𝑟,𝑛 ∈ {0,
𝜋
2𝑏−1 , … ,
(2𝑏−1)𝜋
2𝑏−1 } , ∀r ∈ R, ∀n ∈ N (10a)
tr (𝐕k 𝐕k
H
) ≤ Pmax (10b)
3. DEEP NEURAL NETWORK STRUCTURE
The beamforming neural network (BF-Net) is trained to solve the transmitting beamforming
problem directly (no iteration) to enhance the system’s throughput. The training data sets are compiled via an
exhaustive search (offline phase) of each channel realization to select a RIS beamforming vector that
maximizes the entire system’s throughput. After training, the scheme will be ready to guess the passive
beamforming vector for any given input channel gains. The suggested structure for this beamforming neural
network (abbreviated BF-Net for convenience of notation) consists of multiple layers, as illustrated in
Figure 2.
The structure has 10 layers and preserves data at the dim, NM × 𝐾 × 3 input layer while recurring a
dim, 1×K vector at the output. Each neural network input utilizes the real/imaginary portions of the wireless
channel. Convolutional layers (layers 2 and 5) are being used to extract the characteristics hidden in the
network input data, including 16 filters totaling 3×3 pixels in size. The bias and weights are propagated
through the layer to extract features. Following these layers (i.e., convolutional layers), we already have
normalization and activation layers, which provide a faster learning rate through normalization and optimal
converging. On the other hand, the normalization layers, similar to dropout-layers, can moderate the
over-fitting opportunity by offering some noise to the convolution layer. Next, the flattened layer will flatten
the output of the convolutional layers to harvest a single feature vector of dim |K|. A rectified-linear unit
activation function (ReLU) can be employed for the intermediate layers. In contrast, the last layer prefers the
soft-max function to certify a good classification prediction.

497
𝑅𝑒𝐿𝑈(𝑧) = 𝑀𝑎𝑥{0, 𝑧} (11)
𝑆𝑜𝑓𝑡𝑚𝑎𝑥(𝑧) =
𝑒𝑧𝑖
∑ 𝑒
𝑧𝑗
𝐾
𝑗=1
(12)
Where z is the layer input vector, this neural network is trained using "stochastic-gradient" descent (SG) for
the optimized solution algorithms. For the output layer, as a regression loss (unsupervised method), the
negative of the primary function in P1 (objective), which samples (S) of training, can be defined,
𝑙𝑜𝑠𝑠 = −
1
𝑆
∑𝑠∈|𝑆| ‖𝐆𝑠
𝚽𝑠
𝐇𝑠
+ 𝐅𝑠 ‖2
(13)
Figure 2. Structure of the proposed beamforming neural network
4. NUMERICAL RESULTS
Next, we will verify the proposed network’s performance through numerical simulation. All
parameters of the network and the baseline near-optimal algorithm for the sake of results comparison are
indicated in Table 1 (otherwise are specified within the figures caption). First, we examine the effect of the
RIS’s element count on the per-user performance. As shown in Figure 3, both techniques’ performance is
close to each other and increases with the deployment of RIS elements. This plot shows that increasing the
number of elements by 10 (from 20 up to 30) can improve the user throughput in the context by 18%. The
proposed method achieves more than 95% of the optimal throughput value for the number of antennas of 4
and 30 RIS’s elements at a low implementation cost compared to the optimal scheme.

 ISSN: 2088-8708
498
Table 1. System parameters values are applied in the simulation
Parameter Setting
Access point antenna number Mt = {2, 4, 6, 10}
RIS elements number N=8X8
Number of available users |K| = 4
The budget of the transmit power Pmax = 10 dB
AWGN noise power spectral density σn
2
= -174 dBm/Hz
Pathloss model Pl(dB)=-126.1+36.5 log10 (distance)
Small-scale fading channels Independent and identically distributed (i.i.d) Rayleigh
Train model of the neural network 0.001 learn rate Adam model
Epochs number 1,000
The benchmark scheme An iterative semi-definite [27].
Figure 3. The effect of the RIS’s element count on user throughput
Next, Figure 4 demonstrates the effect of the AP’s antenna count on per-user throughput. The
throughput of both methods rises with the amount of AP antenna and the development of RIS elements. Also,
Figure 5 put together the effect of the number of AP antennas and the RIS’s elements number on the user
throughput. As expected, the proposed system beamforming gets better with the deployment of more
elements of antennas and RIS reflectors. Also, it outperforms the benchmark performance overall in the
range of the x and y-axis. Lastly, Figure 6 introduces a compression between the proposed and the
benchmark schemes in terms of time-performance, i.e., the average time-complexity when there are 10
antenna elements at the AP. It is worth mentioning that the training stage of the proposed deep NN is carried
out offline. Hence, we emphasize the time-complexity results of the online prediction stage. In this regard,
the big-O symbol, i.e., “order of,” can be used to introduce the time-complexity of a specific procedure. Both
input and flatten layers have a simple complexity that can ignore the time cost. For filters of the dimension
𝑛𝑗 × 𝑛𝑗 in the j-th
convolution layer with convolution output size of 𝑥𝑗 × 𝑦𝑗 , there are the same number of
addition and multiplication where in this case the multiplication complexity is of the order,
𝑂(∑ 𝑛𝑗 𝑦𝑗 . 𝑛𝑗 𝑥𝑗 . 𝑓𝑗 𝑓𝑗−1
𝐿
𝑗=1 ) (14)
where 𝑓𝑗 𝑓𝑗−1 denote the number of the convolution filters in the j-th
and (j-1)-th
layers, respectively. In
addition, the complexity of additions is insignificant if compared to that associated with the multiplications.
Also, since the rectified linear activation function (ReLU) defines the input sample’s sign only, the
complexity can be neglected.
Yet, for the BN-layer and the total activation layers, the order is 𝑂(∑ 𝑦𝑗 𝑥𝑗 𝑓𝑗
𝐿
𝑗=1 ). Assuming that
FLC-layer has z-neurons, then the order will be as follows, 𝑂(∑ 𝑧 . 𝑦𝐹𝐿𝐶 𝑥𝐹𝐿𝐶 𝑓𝐹𝐿𝐶
𝐿
𝑗=1 ). We employ
zero-padding of size one for our proposed NN, and we have 16 convolution filters of dimension 3 × 3; then
the convolution output is of size 2 × 𝐾𝑁𝑀, and the total complexity will be approximate, of the order,
𝑂(𝐾𝑁𝑀). It is clear from Figure 6 the superior of the proposed scheme in compression to the great
complexity of the iterative sub-optimal precoding method, e.g., for 25 RIS’s elements, the average consumed

499
time is about 0.851 × 10−3
𝑠𝑒𝑐, while for the baseline algorithm, the average required time is about 4.862 ×
10−3
𝑠𝑒𝑐.
Figure 4. The effect of the number of AP antennas on user throughput
Figure 5. The effect of both AP antennas number/RIS’s elements number on the user throughput
Figure 6. The average time required by the algorithms concerning the number of RIS items

 ISSN: 2088-8708
500
5. CONCLUSION
We consider optimizing RIS beamforming to increase the users’ throughput in this study. We offer
unsupervised/deep neural network (U/DNN) based on convolutional neural networks (CNNs) to reduce the
training weights and number to deal with the non-convexity issue. By engaging with the wireless
communication environment and obtaining real-time data, the RIS controller developed a policy for
optimizing the RIS’s phase shift. The simulation results show that both techniques’ performance is close to
each other while increasing with the deployment of RIS passive elements and AP antenna numbers. The
average consumed time when the AP has 10 antenna elements, it is evident that the technique is better in
compression with the iterative sub-optimal precoding strategy’s excessive complexity.
REFERENCES
[1] A. Taha, M. Alrabeiah, and A. Alkhateeb, “Enabling large intelligent surfaces with compressive sensing and deep learning,” IEEE
Access, vol. 9, pp. 44304–44321, 2021, doi: 10.1109/ACCESS.2021.3064073.
[2] M. Di Renzo et al., “Smart radio environments empowered by reconfigurable AI meta-surfaces: an idea whose time has come,”
EURASIP Journal on Wireless Communications and Networking, no. 1, Dec. 2019, doi: 10.1186/s13638-019-1438-9.
[3] F. Keti, S. M. Atroshey, and J. A. Hamadamin, “Spectral and energy efficiencies maximization in downlink NOMA systems,”
Bulletin of Electrical Engineering and Informatics, vol. 11, no. 3, pp. 1449–1459, Jun. 2022, doi: 10.11591/eei.v11i3.3654.
[4] D. P. Mishra, K. K. Rout, and S. R. Salkuti, “Compact MIMO antenna using dual-band for fifth-generation mobile
communication system,” Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), vol. 24, no. 2,
pp. 921–929, Nov. 2021, doi: 10.11591/ijeecs.v24.i2.pp921-929.
[5] H. F. Rashag and M. H. Ali, “Optimization of transmission signal by artificial intelligent,” International Journal of Advances in
Applied Sciences, vol. 8, no. 4, pp. 290–292, Dec. 2019, doi: 10.11591/ijaas.v8.i4.pp290-292.
[6] A. M. Elbir, A. Papazafeiropoulos, P. Kourtessis, and S. Chatzinotas, “Deep channel learning for large intelligent surfaces aided
mm-wave massive MIMO systems,” IEEE Wireless Communications Letters, vol. 9, no. 9, pp. 1447–1451, Sep. 2020, doi:
10.1109/LWC.2020.2993699.
[7] C. Huang et al., “Holographic MIMO surfaces for 6G wireless networks: opportunities, challenges, and trends,” IEEE Wireless
Communications, vol. 27, no. 5, pp. 118–125, Oct. 2020, doi: 10.1109/MWC.001.1900534.
[8] D. Dardari, “Communicating with large intelligent surfaces: fundamental limits and models,” IEEE Journal on Selected Areas in
Communications, vol. 38, no. 11, pp. 2526–2537, Nov. 2020, doi: 10.1109/JSAC.2020.3007036.
[9] C. Huang, A. Zappone, G. C. Alexandropoulos, M. Debbah, and C. Yuen, “Reconfigurable intelligent surfaces for energy
efficiency in wireless communication,” IEEE Transactions on Wireless Communications, vol. 18, no. 8, pp. 4157–4170, Aug.
2019, doi: 10.1109/TWC.2019.2922609.
[10] M. A. ElMossallamy, H. Zhang, L. Song, K. G. Seddik, Z. Han, and G. Y. Li, “Reconfigurable intelligent surfaces for wireless
communications: principles, challenges, and opportunities,” IEEE Transactions on Cognitive Communications and Networking,
vol. 6, no. 3, pp. 990–1002, Sep. 2020, doi: 10.1109/TCCN.2020.2992604.
[11] A. Kansal and P. Singh, “Performance improvement of MU-MIMO system by optimizing the K-Factor for the K-Mean user
grouping algorithm,” International Journal of Informatics and Communication Technology (IJ-ICT), vol. 5, no. 3, pp. 89–93, Dec.
2016, doi: 10.11591/ijict.v5i3.pp89-93.
[12] H. Huang, W. Xia, J. Xiong, J. Yang, G. Zheng, and X. Zhu, “Unsupervised learning-based fast beamforming design for downlink
MIMO,” IEEE Access, vol. 7, pp. 7599–7605, 2019, doi: 10.1109/ACCESS.2018.2887308.
[13] X. Li and A. Alkhateeb, “Deep learning for direct hybrid precoding in millimeter wave massive MIMO systems,” in 2019 53rd
Asilomar Conference on Signals, Systems, and Computers, Nov. 2019, pp. 800–805, doi:
10.1109/IEEECONF44664.2019.9048966.
[14] Z. Qin, H. Ye, G. Y. Li, and B.-H. F. Juang, “Deep learning in physical layer communications,” IEEE Wireless Communications,
vol. 26, no. 2, pp. 93–99, Apr. 2019, doi: 10.1109/MWC.2019.1800601.
[15] J. Gao, M. R. A. Khandaker, F. Tariq, K.-K. Wong, and R. T. Khan, “Deep neural network based resource allocation for V2X
communications,” in 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall), Sep. 2019, pp. 1–5, doi:
10.1109/VTCFall.2019.8891446.
[16] M. Cui, G. Zhang, and R. Zhang, “Secure wireless communication via intelligent reflecting surface,” IEEE Wireless
Communications Letters, vol. 8, no. 5, pp. 1410–1414, Oct. 2019, doi: 10.1109/LWC.2019.2919685.
[17] H. Shen, W. Xu, S. Gong, Z. He, and C. Zhao, “Secrecy rate maximization for intelligent reflecting surface assisted multi-antenna
communications,” IEEE Communications Letters, vol. 23, no. 9, pp. 1488–1492, Sep. 2019, doi:
10.1109/LCOMM.2019.2924214.
[18] H. Sun, X. Chen, Q. Shi, M. Hong, X. Fu, and N. D. Sidiropoulos, “Learning to optimize: training deep neural networks for
interference management,” IEEE Transactions on Signal Processing, vol. 66, no. 20, pp. 5438–5453, Oct. 2018, doi:
10.1109/TSP.2018.2866382.
[19] C. Huang, G. C. Alexandropoulos, C. Yuen, and M. Debbah, “Indoor signal focusing with deep learning designed reconfigurable
intelligent surfaces,” in 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications
(SPAWC), Jul. 2019, pp. 1–5, doi: 10.1109/SPAWC.2019.8815412.
[20] J. Gao, C. Zhong, X. Chen, H. Lin, and Z. Zhang, “Unsupervised learning for passive beamforming,” IEEE Communications
Letters, vol. 24, no. 5, pp. 1052–1056, May 2020, doi: 10.1109/LCOMM.2020.2965532.
[21] H. Song, M. Zhang, J. Gao, and C. Zhong, “Unsupervised learning-based joint active and passive beamforming design for
reconfigurable intelligent surfaces aided wireless networks,” IEEE Communications Letters, vol. 25, no. 3, pp. 892–896, Mar.
2021, doi: 10.1109/LCOMM.2020.3041510.
[22] W. Lee, M. Kim, and D.-H. Cho, “Transmit power control using deep neural network for underlay device-to-device
communication,” IEEE Wireless Communications Letters, vol. 8, no. 1, pp. 141–144, Feb. 2019, doi:
10.1109/LWC.2018.2864099.
[23] T. Lin and Y. Zhu, “Beamforming design for large-scale antenna arrays using deep learning,” IEEE Wireless Communications
Letters, vol. 9, no. 1, pp. 103–107, Jan. 2020, doi: 10.1109/LWC.2019.2943466.
[24] I. Al-Shaeli and I. Hburi, “An efficient beamforming design for reflective intelligent surface-aided communications system,” in

501
2022 International Conference on Computer Science and Software Engineering (CSASE), Mar. 2022, pp. 151–156, doi:
10.1109/CSASE51777.2022.9759797.
[25] Q. Wu and R. Zhang, “Towards smart and reconfigurable environment: intelligent reflecting surface aided wireless network,”
IEEE Communications Magazine, vol. 58, no. 1, pp. 106–112, Jan. 2020, doi: 10.1109/MCOM.001.1900107.
[26] I. Hburi, H. F. Khazaal, R. Fahdel, and H. Raadi, “Sub-array hybrid beamforming for sustainable largescale mmWave-MIMO
communications,” in 2021 International Conference on Advanced Computer Applications (ACA), Jul. 2021, pp. 101–106, doi:
10.1109/ACA52198.2021.9626806.
[27] I. S. Baqer, “A practical weighted sum rate maximisation for multi-stream cellular MIMO systems,” in 2018 International
Conference on Engineering Technology and their Applications (IICETA), May 2018, pp. 48–53, doi:
10.1109/IICETA.2018.8458083.
[28] D. Tse and P. Viswanath, Fundamentals of wireless communication. Cambridge University Press, 2005.
BIOGRAPHIES OF AUTHORS
Intisar AL-Shaeli received the B.Eng. degree in control and system engineering
from University of Technology, Iraq, in 2002. Currently, she is an MSc student at the
Department of Electrical Engineering, Wasit University. She is employee in the Ministry of
Communication in Iraq, Informatics and Telecommunications Public Company as chief
engineering officer. Here research interests in the field of wireless communication and
telecommunication in addition to computer control. She can be contacted at email:
intisark302@uowasit.edu.iq.
Ismail Sharhan Hburi received the B.Eng. and M.Sc. degrees from the
University of Technology, Baghdad, Iraq, in 1991 and 2007, respectively, the Ph.D. degree in
wireless communication from Brunel University London, U.K., in 2017. His current research
area is wireless communication, massive MIMO cellular networks, IoT, wireless sensor
networks. He can be contacted at email: isharhan@uowasit.edu.iq.
Ammar A. Majeed received the B.eng. degree in electrical engineering from
university of Wasit in 2016. Now, he is M.S student in the same university. He is a technical
engineer in Middle Technical University, Kut Technical Institute. His research field is wireless
communication systems, massive MIMO cellular systems. He can be connected at email:
ammara302@uowasit.edu.iq.

Reconfigurable intelligent surface passive beamforming enhancement using unsupervised learning

More Related Content

Similar to Reconfigurable intelligent surface passive beamforming enhancement using unsupervised learning (20)

More from IJECEIAES (20)

Recently uploaded (20)

Reconfigurable intelligent surface passive beamforming enhancement using unsupervised learning