Mohammad Reza Javan

Mohammad Reza Javan

Auto-generated profile, based on publicly available information

Mohammad Reza Javan

Faculty of Electrical Engineering, Shahrood University of Technology, Shahrood, Iran

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 March 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
MPMohammad Parvini
Mohammad Parvini
MJMohammad Reza Javan
Mohammad Reza Javan
NMNader Mokari
Nader Mokari
BABijan Abbasi Arand
Bijan Abbasi Arand
EJEduard A. Jorswieck
Eduard A. Jorswieck
This paper investigates the problem of age of information (AoI) aware radio resource management for a platooning system. Multiple autonomous platoons exploit the cellular wireless vehicle-to-everything (C-V2X) communication technology to disseminate the cooperative awareness messages (CAMs) to their followers while ensuring timely delivery of safety-critical messages to the Road-Side Unit (RSU). To lower the computational load at the RSU and cope with the challenges of dynamic channel conditions, we exploit a distributed resource allocation framework based on multi-agent reinforcement learning (MARL), where each platoon leader (PL) acts as an agent and interacts with the environment to learn its optimal policy. Motivated by the existing literature in RL, we propose two novel MARL frameworks based on the multi-agent deep deterministic policy gradient (MADDPG), named Modified MADDPG, and Modified MADDPG with task decomposition. Both algorithms train two critics with the following goals: A global critic which estimates the global expected reward and motivates the agents toward a cooperating behavior and an exclusive local critic for each agent that estimates the local individual reward. Furthermore, based on the tasks each agent has to accomplish, in the second algorithm, the holistic individual reward of each agent is decomposed into multiple sub-reward functions where task-wise value functions are learned separately. Numerical results indicate our proposed algorithms' effectiveness compared with other contemporary RL frameworks, e.g., federated reinforcement learning (FRL) in terms of AoI performance and CAM message transmission probability.

31 August 2021 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
AKAta Khalili
Ata Khalili
EMEhsan Mohammadi Monfared
Ehsan Mohammadi Monfared
SZShayan Zargari
Shayan Zargari
MJMohammad Reza Javan
Mohammad Reza Javan
NMNader Mokari
Nader Mokari
EJEduard Axel Jorswieck
Eduard Axel Jorswieck
This paper proposes a novel approach to improve the performance of a heterogeneous network (HetNet) supported by dual connectivity (DC) by adopting multiple unmanned aerial vehicles (UAVs) as passive relays that carry reconfigurable intelligent surfaces (RISs). More specifically, RISs are deployed under the UAVs termed as UAVs-RISs that operate over the micro-wave ( $\mu \text{W}$ ) channel in the sky to sustain a strong line-of-sight (LoS) connection with the ground users. The macro-cell operates over the $\mu \text{W}$ channel based on orthogonal multiple access (OMA), while small base stations (SBSs) operate over the millimeter-wave (mmW) channel based on non-orthogonal multiple access (NOMA). We study the problem of total transmit power minimization by jointly optimizing the trajectory/velocity of each UAV, RISs’ phase shifts, subcarrier allocations, and active beamformers at each BS. The underlying problem is highly non-convex and the global optimal solution is intractable. To handle it, we decompose the original problem into two subproblems, i.e., a subproblem which deals with the UAVs’ trajectories/velocities, RISs’ phase shifts, and subcarrier allocations for $\mu \text{W}$ ; and a subproblem for active beamforming design and subcarrier allocation for mmW. In particular, we solve the first subproblem via the dueling deep Q-Network (DQN) learning approach by developing a distributed algorithm which leads to a better policy evaluation. Then, we solve the active beamforming design and subcarrier allocation for the mmW via the successive convex approximation (SCA) method. Simulation results exhibit the effectiveness of the proposed resource allocation scheme compared to other baseline schemes. In particular, it is revealed that by deploying UAVs-RISs, the transmit power can be reduced by 6 dBm while maintaining similar guaranteed QoS.

5 January 2018 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
MMMohammad Moltafet
Mohammad Moltafet
PAPaeiz Azmi
Paeiz Azmi
NMNader Mokari
Nader Mokari
MJMohammad Reza Javan
Mohammad Reza Javan
AMAli Mokdad
Ali Mokdad
In this paper, the trade-off among the energy efficiency, fairness, harvested energy, and system sum rate is studied. In this regard, various fairness methods namely: max-min fairness, proportional fairness, and minimum delay potential fairness in power domain non-orthogonal multiple access (PDNOMA)- based heterogeneous cellular networks (HetNet) are investigated. In order to perform successive interference cancellation (SIC), we use two ordering approaches and compare their performance. To this end, we propose joint subcarrier and power allocation algorithms to achieve fair energy efficient resource allocation for each fairness method and SIC ordering. Since the proposed optimization problems are non-convex and intractable, the existing methods to solve the convex problems could not be directly used. To overcome this difficulty, an iterative algorithm based on successive convex approximation is used. Moreover, to show the optimality gap of the proposed solution method, an optimal approach based on the monotonic optimization is applied in which we first transform each of the proposed optimization problems into a monotonic optimization problem of canonical form, and then, we obtain the optimal solution of each problem which coincides with the optimal solution of the original non-convex problem. We finally study the performance of the proposed schemes using simulations for different values of the system parameters.

10 February 2023 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
AGAmir Gharehgoli
Amir Gharehgoli
Ali NouruziAli Nouruzi
Ali Nouruzi
NMNader Mokari
Nader Mokari
PAPaeiz Azmi
Paeiz Azmi
MJMohammad Reza Javan
Mohammad Reza Javan
EJEduard A. Jorswieck
Eduard A. Jorswieck
Network slicing (NwS) is one of the main technologies in the fifth-generation of mobile communication and beyond (5G+). One of the important challenges in the NwS is information uncertainty which mainly involves demand and channel state information (CSI). Demand uncertainty is divided into three types: number of users requests, amount of bandwidth, and requested virtual network functions workloads. Moreover, the CSI uncertainty is modeled by three methods: worst-case, probabilistic, and hybrid. In this paper, our goal is to maximize the utility of the infrastructure provider by exploiting deep reinforcement learning (DRL) algorithms in end-to-end NwS resource allocation under demand and CSI uncertainties. Enhanced mobile broadband (eMBB) requires high data rates. The uncertainties we argued above have a direct negative impact on the data rate and our objective function. Therefore, we focus primarily on eMBB. Additionally, we also consider ultra-reliable low latency communications (uRLLC) and massive machine-type communication (mMTC). The proposed formulation is a non-convex mixed-integer non-linear programming problem. To perform resource allocation in problems that involve uncertainty, we need a history of previous information. To this end, we use a recurrent deterministic policy gradient (RDPG) algorithm, a recurrent and memory-based approach in DRL. Then, we compare the RDPG method in different scenarios with soft actor-critic (SAC), deep deterministic policy gradient (DDPG), distributed, and greedy algorithms. The simulation results show that the SAC method is better than the DDPG, distributed, and greedy methods, respectively. Moreover, the RDPG method out performs the SAC approach on average by 70%.

25 January 2023 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
MPMohammad Parvini
Mohammad Parvini
AZAmir Hossein Zarif
Amir Hossein Zarif
Ali NouruziAli Nouruzi
Ali Nouruzi
NMNader Mokari
Nader Mokari
MJMohammad Reza Javan
Mohammad Reza Javan
HYHalim Yanikomeroglu
Halim Yanikomeroglu
As the services and requirements of next-generation wireless networks become increasingly diversified, it is estimated that the current frequency bands of mobile network operators (MNOs) will be unable to cope with the immensity of anticipated demands. Due to spectrum scarcity, there has been a growing trend among stakeholders toward identifying practical solutions to make the most productive use of the exclusively allocated bands on a shared basis through spectrum sharing mechanisms. However, due to the technical complexities of these mechanisms, their design presents challenges, as it requires coordination among multiple entities. To address this challenge, in this paper, we begin with a detailed review of the recent literature on spectrum sharing methods, classifying them on the basis of their operational frequency regime—that is, whether they are implemented to operate in licensed bands (e.g., licensed shared access (LSA), spectrum access system (SAS), and dynamic spectrum sharing (DSS)) or unlicensed bands (e.g., LTE-unlicensed (LTE-U), licensed assisted access (LAA), MulteFire, and new radio-unlicensed (NR-U)). Then, in order to narrow the gap between the standardization and vendor-specific implementations, we provide a detailed review of the potential implementation scenarios and necessary amendments to legacy cellular networks from the perspective of telecommunication vendors and regulatory bodies. Next, we analyze applications of artificial intelligence (AI) and machine learning (ML) techniques for facilitating spectrum sharing mechanisms and leveraging the full potential of autonomous sharing scenarios. Finally, we conclude the paper by presenting open research challenges, which aim to provide insights into prospective research endeavors.

21 October 2021 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
SRSepehr Rezvani
Sepehr Rezvani
EJEduard Axel Jorswieck
Eduard Axel Jorswieck
NYNader Mokari Yamchi
Nader Mokari Yamchi
MJMohammad Reza Javan
Mohammad Reza Javan
In this work, we propose a globally optimal joint successive interference cancellation (SIC) ordering and power allocation (JSPA) algorithm for the sum-rate maximization problem in downlink multi-cell non-orthogonal multiple access (NOMA) systems. The proposed algorithm is based on the exploration of base stations (BSs) power consumption, and closed-form of optimal powers obtained for each cell. Although the optimal JSPA algorithm scales well with larger number of users, it is still exponential in the number of cells. For any suboptimal decoding order, we propose a low-complexity near-optimal joint rate and power allocation (JRPA) strategy in which the complete rate region of users is exploited. Furthermore, we design a near-optimal semi-centralized JSPA framework for a two-tier heterogeneous network such that it scales well with larger number of small-BSs and users. Numerical results show that JRPA highly outperforms the case that the users are enforced to achieve their channel capacity by imposing the well-known SIC necessary condition on power allocation. Moreover, the proposed semi-centralized JSPA framework significantly outperforms the fully distributed framework, where all the BSs operate in their maximum power budget. Therefore, the centralized JRPA and semi-centralized JSPA algorithms with near-optimal performances are good choices for larger number of cells and users.