arXiv subjects

Arumugam Nallanathan

Publications and source records attributed to Arumugam Nallanathan.

At least 127 records · Page 7Linked to original sources

arXiv2022

A Reliable Reinforcement Learning for Resource Allocation in Uplink NOMA-URLLC Networks

In this paper, we propose a deep state-action-reward-state-action (SARSA) $λ$ learning approach for optimising the uplink resource allocation in non-orthogonal multiple access (NOMA) aided ultra-reliable low-latency communication (URLLC). To reduce the mean decoding error probability in time-varying network environments, this work designs a reliable learning algorithm for providing a long-term resource allocation, where the reward feedback is based on the instantaneous network performance. With the aid of the proposed algorithm, this paper addresses three main challenges of the reliable resource sharing in NOMA-URLLC networks: 1) user clustering; 2) Instantaneous feedback system; and 3) Optimal resource allocation. All of these designs interact with the considered communication environment. Lastly, we compare the performance of the proposed algorithm with conventional Q-learning and SARSA Q-learning algorithms. The simulation outcomes show that: 1) Compared with the traditional Q learning algorithms, the proposed solution is able to converges within \myb{200} episodes for providing as low as $10^{-2}$ long-term mean error; 2) NOMA assisted URLLC outperforms traditional OMA systems in terms of decoding error probabilities; and 3) The proposed feedback system is efficient for the long-term learning process.

cs.IT↗

arXiv2022

Performance Analysis and Power Allocation of Joint Communication and Sensing Towards Future Communication Networks

To mitigate the radar and communication frequency overlapping caused by massive devices access, we propose a novel joint communication and sensing (JCS) system in this paper, where a micro base station (MiBS) can realize target sensing and cooperative communication simultaneously. Concretely, the MiBS, as the sensing equipment, can also serve as a full-duplex (FD) decode-and-forward (DF) relay to assist the end-to-end communication. To further improve the spectrum utilization, non-orthogonal multiple access (NOMA) is adopted such that the communication between the macro base station (MaBS) and the Internet-of-Things (IoT) devices. To facilitate the performance evaluation, the exact and asymptotic outage probabilities, ergodic rates, sensing probability of the system are characterized. Subsequently, two optimal power allocation (OPA) problems of maximizing the received signal-to-interference-plus-noise ratio of sensing signal and maximizing the sum rate for communication are designed that are solved by means of the Lagrangian method and function monotonicity. The simulation results demonstrate that: 1) the proposed JCS NOMA system can accomplish both communication enhancement and sensing function under the premise of the same power consumption as non-cooperative NOMA; 2) the proposed OPA schemes manifest superiorities over a random power allocation scheme.

cs.IT↗

arXiv2021

Optimization of Grant-Free NOMA with Multiple Configured-Grants for mURLLC

Massive Ultra-Reliable and Low-Latency Communications (mURLLC), which integrates URLLC with massive access, is emerging as a new and important service class in the next generation (6G) for time-sensitive traffics and has recently received tremendous research attention. However, realizing efficient, delay-bounded, and reliable communications for a massive number of user equipments (UEs) in mURLLC, is extremely challenging as it needs to simultaneously take into account the latency, reliability, and massive access requirements. To support these requirements, the third generation partnership project (3GPP) has introduced enhanced grant-free (GF) transmission in the uplink (UL), with multiple active configured-grants (CGs) for URLLC UEs. With multiple CGs (MCG) for UL, UE can choose any of these grants as soon as the data arrives. In addition, non-orthogonal multiple access (NOMA) has been proposed to synergize with GF transmission to mitigate the serious transmission delay and network congestion problems. In this paper, we develop a novel learning framework for MCG-GF-NOMA systems with bursty traffic. We first design the MCG-GF-NOMA model by characterizing each CG using the parameters: the number of contention-transmission units (CTUs), the starting slot of each CG within a subframe, and the number of repetitions of each CG. Based on the model, the latency and reliability performances are characterized. We then formulate the MCG-GF-NOMA resources configuration problem taking into account three constraints. Finally, we propose a Cooperative Multi-Agent based Double Deep Q-Network (CMA-DDQN) algorithm to allocate the channel resources among MCGs so as to maximize the number of successful transmissions under the latency constraint. Our results show that the MCG-GF-NOMA framework can simultaneously improve the low latency and high reliability performances in massive URLLC.

eess.SY↗

arXiv2021

Computational Intelligence and Deep Learning for Next-Generation Edge-Enabled Industrial IoT

In this paper, we investigate how to deploy computational intelligence and deep learning (DL) in edge-enabled industrial IoT networks. In this system, the IoT devices can collaboratively train a shared model without compromising data privacy. However, due to limited resources in the industrial IoT networks, including computational power, bandwidth, and channel state, it is challenging for many devices to accomplish local training and upload weights to the edge server in time. To address this issue, we propose a novel multi-exit-based federated edge learning (ME-FEEL) framework, where the deep model can be divided into several sub-models with different depths and output prediction from the exit in the corresponding sub-model. In this way, the devices with insufficient computational power can choose the earlier exits and avoid training the complete model, which can help reduce computational latency and enable devices to participate into aggregation as much as possible within a latency threshold. Moreover, we propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round. Simulation experiments are conducted on the classical Fashion-MNIST dataset under a non-independent and identically distributed (non-IID) setting, and it shows that the proposed strategy outperforms the conventional FL. In particular, the proposed ME-FEEL can achieve an accuracy gain up to 32.7% in the industrial IoT networks with the severely limited resources.

cs.LG↗

arXiv2021

A Framework of Robust Transmission Design for IRS-aided MISO Communications with Imperfect Cascaded Channels

Intelligent reflection surface (IRS) has recently been recognized as a promising technique to enhance the performance of wireless systems due to its ability of reconfiguring the signal propagation environment. However, the perfect channel state information (CSI) is challenging to obtain at the base station (BS) due to the lack of radio frequency (RF) chains at the IRS. Since most of the existing channel estimation methods were developed to acquire the cascaded BS-IRS-user channels, this paper is the first work to study the robust beamforming based on the imperfect cascaded BS-IRS-user channels at the transmitter (CBIUT). Specifically, the transmit power minimization problems are formulated subject to the worst-case rate constraints under the bounded CSI error model and the rate outage probability constraints under the statistical CSI error model, respectively. After approximating the worst-case rate constraints by using the S-procedure and the rate outage probability constraints by using the Bernstein-type inequality, the reformulated problems can be efficiently solved. Numerical results show that the negative impact of the CBIUT error on the system performance is greater than that of the direct CSI error.

eess.SP↗

arXiv2021

Dilated Convolution based CSI Feedback Compression for Massive MIMO Systems

Although the frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) system can offer high spectral and energy efficiency, it requires to feedback the downlink channel state information (CSI) from users to the base station (BS), in order to fulfill the precoding design at the BS. However, the large dimension of CSI matrices in the massive MIMO system makes the CSI feedback very challenging, and it is urgent to compress the feedback CSI. To this end, this paper proposes a novel dilated convolution based CSI feedback network, namely DCRNet. Specifically, the dilated convolutions are used to enhance the receptive field (RF) of the proposed DCRNet without increasing the convolution size. Moreover, advanced encoder and decoder blocks are designed to improve the reconstruction performance and reduce computational complexity as well. Numerical results are presented to show the superiority of the proposed DCRNet over the conventional networks. In particular, the proposed DCRNet can achieve almost the state-of-the-arts (SOTA) performance with much lower floating point operations (FLOPs). The open source code and checkpoint of this work are available at https://github.com/recusant7/DCRNet.

cs.IT↗

arXiv2021

Transmit Power Pool Design for Grant-Free NOMA-IoT Networks via Deep Reinforcement Learning

Grant-free non-orthogonal multiple access (GF-NOMA) is a potential multiple access framework for short-packet internet-of-things (IoT) networks to enhance connectivity. However, the resource allocation problem in GF-NOMA is challenging due to the absence of closed-loop power control. We design a prototype of transmit power pool (PP) to provide open-loop power control. IoT users acquire their transmit power in advance from this prototype PP solely according to their communication distances. Firstly, a multi-agent deep Q-network (DQN) aided GF-NOMA algorithm is proposed to determine the optimal transmit power levels for the prototype PP. More specifically, each IoT user acts as an agent and learns a policy by interacting with the wireless environment that guides them to select optimal actions. Secondly, to prevent the Q-learning model overestimation problem, double DQN based GF-NOMA algorithm is proposed. Numerical results confirm that the double DQN based algorithm finds out the optimal transmit power levels that form the PP. Comparing with the conventional online learning approach, the proposed algorithm with the prototype PP converges faster under changing environments due to limiting the action space based on previous learning. The considered GF-NOMA system outperforms the networks with fixed transmission power, namely all the users have the same transmit power and the traditional GF with orthogonal multiple access techniques, in terms of throughput.

cs.IT↗

arXiv2021

Modeling and Coverage Analysis for RIS-aided NOMA Transmissions in Heterogeneous Networks

Reconfigurable intelligent surface (RIS) has been regarded as a promising tool to strengthen the quality of signal transmissions in non-orthogonal multiple access (NOMA) networks. This article introduces a heterogeneous network (HetNet) structure into RIS-aided NOMA multi-cell networks. A practical user equipment (UE) association scheme for maximizing the average received power is adopted. To evaluate system performance, we provide a stochastic geometry based analytical framework, where the locations of RISs, base stations (BSs), and UEs are modeled as homogeneous Poisson point processes (PPPs). Based on this framework, we first derive the closed-form probability density function (PDF) to characterize the distribution of the reflective links created by RISs. Then, both the exact expressions and upper/lower bounds of UE association probability are calculated. Lastly, the analytical expressions of the signal-to-interference-plus-noise-ratio (SINR) and rate coverage probability are deduced. Additionally, to investigate the impact of RISs on system coverage, the asymptotic expressions of two coverage probabilities are derived. The theoretical results show that RIS length is not the decisive factor for coverage improvement. Numerical results demonstrate that the proposed RIS HetNet structure brings significant enhancement in rate coverage. Moreover, there exists an optimal combination of RISs and BSs deployment densities to maximize coverage probability.

cs.IT↗

arXiv2021

A General Deep Reinforcement Learning Framework for Grant-Free NOMA Optimization in mURLLC

Grant-free non-orthogonal multiple access (GF-NOMA) is a potential technique to support massive Ultra-Reliable and Low-Latency Communication (mURLLC) service. However, the dynamic resource configuration in GF-NOMA systems is challenging due to random traffics and collisions, that are unknown at the base station (BS). Meanwhile, joint consideration of the latency and reliability requirements makes the resource configuration of GF-NOMA for mURLLC more complex. To address this problem, we develop a general learning framework for signature-based GF-NOMA in mURLLC service taking into account the multiple access signature collision, the UE detection, as well as the data decoding procedures for the K-repetition GF and the Proactive GF schemes. The goal of our learning framework is to maximize the long-term average number of successfully served users (UEs) under the latency constraint. We first perform a real-time repetition value configuration based on a double deep Q-Network (DDQN) and then propose a Cooperative Multi-Agent learning technique based on the DQN (CMA-DQN) to optimize the configuration of both the repetition values and the contention-transmission unit (CTU) numbers. Our results show that the number of successfully served UEs under the same latency constraint in our proposed learning framework is up to ten times for the K-repetition scheme, and two times for the Proactive scheme, more than that with fixed repetition values and CTU numbers. In addition, the superior performance of CMA-DQN over the conventional load estimation-based approach (LE-URC) demonstrates its capability in dynamically configuring in long term. Importantly, our general learning framework can be used to optimize the resource configuration problems in all the signature-based GF-NOMA schemes.

cs.IT↗

arXiv2021

AoA-Based Pilot Assignment in Massive MIMO Systems Using Deep Reinforcement Learning

In this paper, the problem of pilot contamination in a multi-cell massive multiple input multiple output (M-MIMO) system is addressed using deep reinforcement learning (DRL). To this end, a pilot assignment strategy is designed that adapts to the channel variations while maintaining a tolerable pilot contamination effect. Using the angle of arrival (AoA) information of the users, a cost function, portraying the reward, is presented, defining the pilot contamination effects in the system. Numerical results illustrate that the DRL-based scheme is able to track the changes in the environment, learn the near-optimal pilot assignment, and achieve a close performance to that of the optimum pilot assignment performed by exhaustive search, while maintaining a low computational complexity.

eess.SP↗

arXiv2021

Low-Complexity Robust Beamforming Design for IRS-Aided MISO Systems with Imperfect Channels

In this paper, large-scale intelligent reflecting sur-face (IRS)-assisted multiple-input single-output (MISO) system is considered in the presence of channel uncertainty. To maximize the average sum rate of the system by jointly optimizing the active beamforming at the BS and the passive phase shifts at the IRS, while satisfying the power constraints, a novel robust beamforming design is proposed by using the penalty dual decomposition (PDD) algorithm. By applying the upper bound maximization/minimization (BSUM) method, in each iteration of the algorithm, the optimal solution for each variable can be obtained with closed-form expression. Simulation results show that the proposed scheme achieves high performance with very low computational complexity.

eess.SP↗

arXiv2021

Machine Learning for Massive Industrial Internet of Things

Industrial Internet of Things (IIoT) revolutionizes the future manufacturing facilities by integrating the Internet of Things technologies into industrial settings. With the deployment of massive IIoT devices, it is difficult for the wireless network to support the ubiquitous connections with diverse quality-of-service (QoS) requirements. Although machine learning is regarded as a powerful data-driven tool to optimize wireless network, how to apply machine learning to deal with the massive IIoT problems with unique characteristics remains unsolved. In this paper, we first summarize the QoS requirements of the typical massive non-critical and critical IIoT use cases. We then identify unique characteristics in the massive IIoT scenario, and the corresponding machine learning solutions with its limitations and potential research directions. We further present the existing machine learning solutions for individual layer and cross-layer problems in massive IIoT. Last but not the least, we present a case study of massive access problem based on deep neural network and deep reinforcement learning techniques, respectively, to validate the effectiveness of machine learning in massive IIoT scenario.

cs.LG↗

arXiv2021

Resource Allocation in Uplink NOMA-IoT Networks: A Reinforcement-Learning Approach

Non-orthogonal multiple access (NOMA) exploits the potential of the power domain to enhance the connectivity for the Internet of Things (IoT). Due to time-varying communication channels, dynamic user clustering is a promising method to increase the throughput of NOMA-IoT networks. This paper develops an intelligent resource allocation scheme for uplink NOMA-IoT communications. To maximise the average performance of sum rates, this work designs an efficient optimization approach based on two reinforcement learning algorithms, namely deep reinforcement learning (DRL) and SARSA-learning. For light traffic, SARSA-learning is used to explore the safest resource allocation policy with low cost. For heavy traffic, DRL is used to handle traffic-introduced huge variables. With the aid of the considered approach, this work addresses two main problems of fair resource allocation in NOMA techniques: 1) allocating users dynamically and 2) balancing resource blocks and network traffic. We analytically demonstrate that the rate of convergence is inversely proportional to network sizes. Numerical results show that: 1) Compared with the optimal benchmark scheme, the proposed DRL and SARSA-learning algorithms have lower complexity with acceptable accuracy and 2) NOMA-enabled IoT networks outperform the conventional orthogonal multiple access based IoT networks in terms of system throughput.

cs.IT↗

arXiv2021

Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing

In this paper, we consider a platform of flying mobile edge computing (F-MEC), where unmanned aerial vehicles (UAVs) serve as equipment providing computation resource, and they enable task offloading from user equipment (UE). We aim to minimize energy consumption of all the UEs via optimizing the user association, resource allocation and the trajectory of UAVs. To this end, we first propose a Convex optimizAtion based Trajectory control algorithm (CAT), which solves the problem in an iterative way by using block coordinate descent (BCD) method. Then, to make the real-time decision while taking into account the dynamics of the environment (i.e., UAV may take off from different locations), we propose a deep Reinforcement leArning based Trajectory control algorithm (RAT). In RAT, we apply the Prioritized Experience Replay (PER) to improve the convergence of the training procedure. Different from the convex optimization based algorithm which may be susceptible to the initial points and requires iterations, RAT can be adapted to any taking off points of the UAVs and can obtain the solution more rapidly than CAT once training process has been completed. Simulation results show that the proposed CAT and RAT achieve the similar performance and both outperform traditional algorithms.

eess.SP↗

arXiv2021

Learning based signal detection for MIMO systems with unknown noise statistics

This paper aims to devise a generalized maximum likelihood (ML) estimator to robustly detect signals with unknown noise statistics in multiple-input multiple-output (MIMO) systems. In practice, there is little or even no statistical knowledge on the system noise, which in many cases is non-Gaussian, impulsive and not analyzable. Existing detection methods have mainly focused on specific noise models, which are not robust enough with unknown noise statistics. To tackle this issue, we propose a novel ML detection framework to effectively recover the desired signal. Our framework is a fully probabilistic one that can efficiently approximate the unknown noise distribution through a normalizing flow. Importantly, this framework is driven by an unsupervised learning approach, where only the noise samples are required. To reduce the computational complexity, we further present a low-complexity version of the framework, by utilizing an initial estimation to reduce the search space. Simulation results show that our framework outperforms other existing algorithms in terms of bit error rate (BER) in non-analytical noise environments, while it can reach the ML performance bound in analytical noise environments. The code of this paper is available at https://github.com/skypitcher/manfe.

cs.LG↗

arXiv2020

Robust Transmission Design for Intelligent Reflecting Surface Aided Secure Communication Systems with Imperfect Cascaded CSI

In this paper, we investigate the design of robust and secure transmission in intelligent reflecting surface (IRS) aided wireless communication systems. In particular, a multi-antenna access point (AP) communicates with a single-antenna legitimate receiver in the presence of multiple single-antenna eavesdroppers, where the artificial noise (AN) is transmitted to enhance the security performance. Besides, we assume that the cascaded AP-IRS-user channels are imperfect due to the channel estimation error. To minimize the transmit power, the beamforming vector at the transmitter, the AN covariance matrix, and the IRS phase shifts are jointly optimized subject to the outage rate probability constraints under the statistical cascaded channel state information (CSI) error model that usually models the channel estimation error. To handle the resulting non-convex optimization problem, we first approximate the outage rate probability constraints by using the Bernstein-type inequality. Then, we develop a suboptimal algorithm based on alternating optimization, the penalty-based and semidefinite relaxation methods. Simulation results reveal that the proposed scheme significantly reduces the transmit power compared to other benchmark schemes.

eess.SP↗

arXiv2020

Signal Fractions Analysis and Safety-Distance Modeling in V2V Inter-lane Communications

For vehicular networks, safety distances are important, but existing spatial models fail to characterize this parameter, especially for inter-lane communications. This work proposes a Matern hard-core processes based framework to appraise the performance of signal fractions (SF), where the hard-core distance is used to depict safety distances. By considering both semicircle and omnidirectional antennas, we derive high-accurate closed-form probability density functions of communication distances to acquire the complementary cumulative distribution function of SF. The derived expressions theoretically demonstrate that the nearest vehicle within the safety distance follows a uniform distribution and there is an upper limit for SF in terms of the transmit power.

cs.IT↗

arXiv2020

Multiple Transmit Power Levels based NOMA for Massive Machine-type Communications

This paper proposes a tractable solution for integrating non-orthogonal multiple access (NOMA) into massive machine-type communications (mMTC) to increase the uplink connectivity. Multiple transmit power levels are provided at the user end to enable open-loop power control, which is absent from the traditional uplink NOMA with the fixed transmit power. The basics of this solution are firstly presented to analytically show the inherent performance gain in terms of the average arrival rate (AAR). Then, a practical framework based on a novel power map is proposed to associate a set of well-designed transmit power levels with each geographical region for handling the no instantaneous channel state information problem. Based on this framework, the semi-grant-free (semi-GF) transmission with two practical protocols is introduced to enhance the connectivity, which has higher AAR than both the conventional grand-based and GF transmissions. When the number of active GF devices in mMTC far exceeds the available resource blocks, the corresponding AAR tends to zero. To solve this problem, user barring techniques are employed into the semi-GF transmission to stable the traffic flow and thus increase the AAR. Lastly, promising research directions are discussed for improving the proposed networks.

cs.IT↗