اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDeep Reinforcement Learning for Intelligent Reflecting Surface-assisted D2D Communications
165
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this paper, we propose a deep reinforcement learning (DRL) approach for solving the optimisation problem of the networks sum-rate in device-to-device (D2D) communications supported by an intelligent reflecting surface (IRS). The IRS is deployed to mitigate the interference and enhance the signal between the D2D transmitter and the associated D2D receiver. Our objective is to jointly optimise the transmit power at the D2D transmitter and the phase shift matrix at the IRS to maximise the network sum-rate. We formulate a Markov decision process and then propose the proximal policy optimisation for solving the maximisation game. Simulation results show impressive performance in terms of the achievable rate and processing time.
قيم البحث
اقرأ أيضاً
In this letter, we investigate an intelligent reflecting surface (IRS) aided device-to-device (D2D) offloading system, where an IRS is employed to assist in computation offloading from a group of users with intensive tasks to another group of idle us
ers. We propose a new two-timescale joint passive beamforming and resource allocation algorithm based on stochastic successive convex approximation to minimize the system latency while cutting down the heavy overhead in exchange of channel state information (CSI). Specifically, the high-dimensional passive beamforming vector at the IRS is updated in a frame-based manner based on the channel statistics, where each frame consists of a number of time slots, while the offloading ratio and user matching strategy are optimized relied on the low-dimensional real-time effective channel coefficients in each time slot. The convergence property and the computational complexity of the proposed algorithm are also examined. Simulation results show that our proposed algorithm significantly outperforms the conventional benchmarks.
In a practical massive MIMO (multiple-input multiple-output) system, the number of antennas at a base station (BS) is constrained by the space and cost factors, which limits the throughput gain promised by theoretical analysis. This paper thus studie
s the feasibility of adopting the intelligent reflecting surface (IRS) to further improve the beamforming gain of the uplink communications in a massive MIMO system. Under such a novel system, the central question lies in whether the IRS is able to enhance the network throughput as expected, if the channel estimation overhead is taken into account. In this paper, we first show that the favorable propagation property for the conventional massive MIMO system without IRS, i.e., the channels of arbitrary two users are orthogonal, no longer holds for the IRS-assisted massive MIMO system, due to its special channel property that each IRS element reflects the signals from all the users to the BS via the same channel. As a result, the maximal-ratio combining (MRC) receive beamforming strategy leads to strong inter-user interference and thus even lower user rates than those of the massive MIMO system without IRS. To tackle this challenge, we propose a novel strategy for zero-forcing (ZF) beamforming design at the BS and reflection coefficients design at the IRS to efficiently null the inter-user interference. Under our proposed strategy, it is rigorously shown that even if the channel estimation overhead is considered, the IRS-assisted massive MIMO system can always achieve higher throughput compared to its counterpart without IRS, despite the fact that the favorable propagation property no longer holds.
In the intelligent reflecting surface (IRS) assisted communication systems, the acquisition of channel state information (CSI) is a crucial impediment for achieving the passive beamforming gain of IRS because of the considerable overhead required for
channel estimation. Specifically, under the current beamforming design for IRS-assisted communications, $KMN+KM$ channel coefficients should be estimated if the passive IRS cannot estimate its channels with the base station (BS) and users due to its lack of radio frequency (RF) chains, where $K$, $N$ and $M$ denote the number of users, reflecting elements of the IRS, and antennas at the BS, respectively. This number can be extremely large in practice considering the current trend of massive MIMO (multiple-input multiple-output), i.e., a large $M$, and massive connectivity, i.e., a large $K$. To accurately estimate such a large number of channel coefficients within a short time interval, we devote our endeavour in this paper to investigating the efficient pilot-based channel estimation method in IRS-assisted uplink communications. Building upon the observation that the IRS reflects the signals from all the users to the BS via the same channels, we analytically verify that a time duration consisting of $K+N+max(K-1,lceil (K-1)N/M rceil)$ pilot symbols is sufficient for the BS to perfectly recover all the $KMN+KM$ channel coefficients in the case without noise. In contrast to the conventional uplink communications without IRS in which the minimum pilot sequence length for channel estimation is independent with the number of receive antennas, our study reveals the significant role of massive MIMO in reducing the channel training time for IRS-assisted communication systems.
In this paper, the minimum mean square error (MMSE) channel estimation for intelligent reflecting surface (IRS) assisted wireless communication systems is investigated. In the considered setting, each row vector of the equivalent channel matrix from
the base station (BS) to the users is shown to be Bessel $K$ distributed, and all these row vectors are independent of each other. By introducing a Gaussian scale mixture model, we obtain a closed-form expression for the MMSE estimate of the equivalent channel, and determine analytical upper and lower bounds on the mean square error. Using the central limit theorem, we conduct an asymptotic analysis of the MMSE estimate, and show that the upper bound on the mean square error of the MMSE estimate is equal to the asymptotic mean square error of the MMSE estimation when the number of reflecting elements at the IRS tends to infinity. Numerical simulations show that the gap between the upper and lower bounds are very small, and they almost overlap with each other at medium signal-to-noise ratio (SNR) levels and moderate number of elements at the IRS.
This paper investigates an intelligent reflecting surface (IRS) aided cooperative communication network, where the IRS exploits large reflecting elements to proactively steer the incident radio-frequency wave towards destination terminals (DTs). As t
he number of reflecting elements increases, the reflection resource allocation (RRA) will become urgently needed in this context, which is due to the non-ignorable energy consumption. The goal of this paper, therefore, is to realize the RRA besides the active-passive beamforming design, where RRA is based on the introduced modular IRS architecture. The modular IRS consists with multiple modules, each of which has multiple reflecting elements and is equipped with a smart controller, all the controllers can communicate with each other in a point-to-point fashion via fiber links. Consequently, an optimization problem is formulated to maximize the minimum SINR at DTs, subject to the module size constraint and both individual source terminal (ST) transmit power and the reflecting coefficients constraints. Whereas this problem is NP-hard due to the module size constraint, we develop an approximate solution by introducing the mixed row block $ell_{1,F}$-norm to transform it into a suitable semidefinite relaxation. Finally, numerical results demonstrate the meaningfulness of the introduced modular IRS architecture.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
