arXiv subjects

Nader Mokari

Publications and source records attributed to Nader Mokari.

At least 37 records · Page 2Linked to original sources

arXiv2021

Online Service Provisioning in NFV-enabled Networks Using Deep Reinforcement Learning

In this paper, we study a Deep Reinforcement Learning (DRL) based framework for an online end-user service provisioning in a Network Function Virtualization (NFV)-enabled network. We formulate an optimization problem aiming to minimize the cost of network resource utilization. The main challenge is provisioning the online service requests by fulfilling their Quality of Service (QoS) under limited resource availability. Moreover, fulfilling the stochastic service requests in a large network is another challenge that is evaluated in this paper. To solve the formulated optimization problem in an efficient and intelligent manner, we propose a Deep Q-Network for Adaptive Resource allocation (DQN-AR) in NFV-enable network for function placement and dynamic routing which considers the available network resources as DQN states. Moreover, the service's characteristics, including the service life time and number of the arrival requests, are modeled by the Uniform and Exponential distribution, respectively. In addition, we evaluate the computational complexity of the proposed method. Numerical results carried out for different ranges of parameters reveal the effectiveness of our framework. In specific, the obtained results show that the average number of admitted requests of the network increases by 7 up to 14% and the network utilization cost decreases by 5 and 20 %.

eess.SY↗

arXiv2021

Optimal SIC Ordering and Power Allocation in Downlink Multi-Cell NOMA Systems

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.

cs.IT↗

arXiv2021

Proactive and AoI-aware Failure Recovery for Stateful NFV-enabled Zero-Touch 6G Networks: Model-Free DRL Approach

In this paper, we propose a Zero-Touch, deep reinforcement learning (DRL)-based Proactive Failure Recovery framework called ZT-PFR for stateful network function virtualization (NFV)-enabled networks. To this end, we formulate a resource-efficient optimization problem minimizing the network cost function including resource cost and wrong decision penalty. As a solution, we propose state-of-the-art DRL-based methods such as soft-actor-critic (SAC) and proximal-policy-optimization (PPO). In addition, to train and test our DRL agents, we propose a novel impending-failure model. Moreover, to keep network status information at an acceptable freshness level for appropriate decision-making, we apply the concept of age of information to strike a balance between the event and scheduling based monitoring. Several key systems and DRL algorithm design insights for ZT-PFR are drawn from our analysis and simulation results. For example, we use a hybrid neural network, consisting long short-term memory layers in the DRL agents structure, to capture impending-failures time dependency.

eess.SP↗

arXiv2021

Learning based E2E Energy Efficient in Joint Radio and NFV Resource Allocation for 5G and Beyond Networks

In this paper, we propose a joint radio and core resource allocation framework for NFV-enabled networks. In the proposed system model, the goal is to maximize energy efficiency (EE), by guaranteeing end-to-end (E2E) quality of service (QoS) for different service types. To this end, we formulate an optimization problem in which power and spectrum resources are allocated in the radio part. In the core part, the chaining, placement, and scheduling of functions are performed to ensure the QoS of all users. This joint optimization problem is modeled as a Markov decision process (MDP), considering time-varying characteristics of the available resources and wireless channels. A soft actor-critic deep reinforcement learning (SAC-DRL) algorithm based on the maximum entropy framework is subsequently utilized to solve the above MDP. Numerical results reveal that the proposed joint approach based on the SAC-DRL algorithm could significantly reduce energy consumption compared to the case in which R-RA and NFV-RA problems are optimized separately.

eess.SP↗

arXiv2021

AoI Minimization in Energy Harvesting and Spectrum Sharing Enabled 6G Networks

Spectrum sharing is a method to solve the problem of frequency spectrum deficiency. This paper studies a novel AI based spectrum sharing and energy harvesting system in which the freshness of information (AoI) is guaranteed. The system includes a primary user with access rights to the spectrum and a secondary user. The secondary user is an energy harvesting sensor that intends to use the primary user spectrum opportunistically. The problem is formulated as partially observable Markov decision processes (POMDPs) and solved using two methods: a deep Q-network (DQN) and dueling double deep Q-Network (D3QN) to achieve the optimal policy. The purpose is to choose the best action adaptively in every time slot based on its situation in both overlay and underlay modes to minimize the average AoI of the secondary user. Finally, simulation experiments are performed to evaluate the effectiveness of the proposed scheme compared to the overlay mode. According to the results, the average AoI in the proposed system is less than that of the existing models, including only overlay mode. The average user access improved from 30% in the overlay mode to 45% in the DQN and 48% in the D3QN.

eess.SY↗

arXiv2021

AI-Based Secure NOMA and Cognitive Radio enabled Green Communications: Channel State Information and Battery Value Uncertainties

In this paper, the security-aware robust resource allocation in energy harvesting cognitive radio networks is considered with cooperation between two transmitters while there are uncertainties in channel gains and battery energy value. To be specific, the primary access point harvests energy from the green resource and uses time switching protocol to send the energy and data towards the secondary access point (SAP). Using power-domain non-orthogonal multiple access technique, the SAP helps the primary network to improve the security of data transmission by using the frequency band of the primary network. In this regard, we introduce the problem of maximizing the proportional-fair energy efficiency (PFEE) considering uncertainty in the channel gains and battery energy value subject to the practical constraints. Moreover, the channel gain of the eavesdropper is assumed to be unknown. Employing the decentralized partially observable Markov decision process, we investigate the solution of the corresponding resource allocation problem. We exploit multi-agent with single reward deep deterministic policy gradient (MASRDDPG) and recurrent deterministic policy gradient (RDPG) methods. These methods are compared with the state-of-the-art ones like multi-agent and single-agent DDPG. Simulation results show that both MASRDDPG and RDPG methods, outperform the state-of-the-art methods by providing more PFEE to the network.

eess.SP↗

arXiv2021

Fairness-Aware Caching and Radio Resource Allocation for the Downlink of Multi-Cell OFDMA Systems

The unprecedented growth of internet contents, specially social media, invoking a challenge to the load of cellular networks. In addition, nowadays, the demands of quality of experience (QoE) became a more practical norm in contrast of quality of service (QoS), in which downloading delay is an important factor of it. To satisfy this demand, we propose two resource allocation (RA) algorithms to optimize the place of social media in the cache of the Base stations (BSs) and radio resources (i.e., transmit powers and subcarriers), jointly in a multi-cell Orthogonal Frequency Division Multiple Access (OFDMA) based system. In the first scheme, the total downloading delay of the network is minimized, while in the second scheme, a fairness-aware scheme is proposed in which the maximum downloading delays is minimized. We propose iterative algorithms to solve each problem, where the content placement problem and the joint subcarrier and transmit power allocation problem will be iteratively optimized. We also prove that the proposed approaches converges to a near-optimal solution, as well as the number of iterations increases.

cs.IT↗

arXiv2021

Smart Soft-RAN for 5G: Dynamic Resource Management in CoMP-NOMA Based Systems

In this paper, we design a new smart software-defined radio access network architecture which is flexible and traffic and density aware for the fifth generation (5G) of cellular wireless networks and beyond. The proposed architecture, based on network parameters such as density of users and system traffic, performs five important tasks namely, dynamic radio resource management (RRM), dynamic BS type selection, dynamic functionality splitting, dynamic transmission technology selection, and dynamic framing. In this regard, we first elaborate the structure of the proposed smart soft-RAN model and explain the details of the proposed architecture and RRM algorithms. Next, as a case study, based on the proposed architecture, we design a novel coordinated multi point beamforming technique to enhance the throughput of a virtualized software defined-based 5G network utilizing the combination of power domain non-orthogonal multiple access and multiple-input single-output downlink communication. In doing so, we formulate an optimization problem with the aim of maximizing the total throughput subject to minimum required data rate of each user and maximum transmit power constraint of each mobile virtual network operator and each BS, and find jointly the non-orthogonal set, beamforming, and subcarrier allocation. To solve the proposed optimization problem, based on the network density, we design two centralized and semi-centralized algorithms. Specifically, for the ultra-dense scenario, we use the centralized algorithm while the semi-centralized one is used for the high and moderate density scenarios. Numerical results illustrate the performance and signaling overhead of the proposed algorithms, e.g., taking computational limitations into account the number of supported users is increased by more than 60%.

cs.IT↗

arXiv2021

Resource Management for Transmit Power Minimization in UAV-Assisted RIS HetNets Supported by Dual Connectivity

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 ($μ$W) channel in the sky to sustain a strong line-of-sight (LoS) connection with the ground users. The macro-cell operates over the $μ$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 $μ$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.

cs.IT↗

arXiv2021

Energy-Efficient Task Offloading Under E2E Latency Constraints

In this paper, we propose a novel resource management scheme that jointly allocates the transmit power and computational resources in a centralized radio access network architecture. The network comprises a set of computing nodes to which the requested tasks of different users are offloaded. The optimization problem minimizes the energy consumption of task offloading while takes the end-to-end latency, i.e., the transmission, execution, and propagation latencies of each task, into account. We aim to allocate the transmit power and computational resources such that the maximum acceptable latency of each task is satisfied. Since the optimization problem is non-convex, we divide it into two sub-problems, one for transmit power allocation and another for task placement and computational resource allocation. Transmit power is allocated via the convex-concave procedure. In addition, a heuristic algorithm is proposed to jointly manage computational resources and task placement. We also propose a feasibility analysis that finds a feasible subset of tasks. Furthermore, a disjoint method that separately allocates the transmit power and the computational resources is proposed as the baseline of comparison. A lower bound on the optimal solution of the optimization problem is also derived based on exhaustive search over task placement decisions and utilizing Karush-Kuhn-Tucker conditions. Simulation results show that the joint method outperforms the disjoint method in terms of acceptance ratio. Simulations also show that the optimality gap of the joint method is less than 5%.

cs.NI↗

arXiv2021

AI-Based and Mobility-Aware Energy Efficient Resource Allocation and Trajectory Design for NFV Enabled Aerial Networks

In this paper, we propose a novel joint intelligent trajectory design and resource allocation algorithm based on user's mobility and their requested services for unmanned aerial vehicles (UAVs) assisted networks, where UAVs act as nodes of a network function virtualization (NFV) enabled network. Our objective is to maximize energy efficiency and minimize the average delay on all services by allocating the limited radio and NFV resources. In addition, due to the traffic conditions and mobility of users, we let some Virtual Network Functions (VNFs) to migrate from their current locations to other locations to satisfy the Quality of Service requirements. We formulate our problem to find near-optimal locations of UAVs, transmit power, subcarrier assignment, placement, and scheduling the requested service's functions over the UAVs and perform suitable VNF migration. Then we propose a novel Hierarchical Hybrid Continuous and Discrete Action (HHCDA) deep reinforcement learning method to solve our problem. Finally, the convergence and computational complexity of the proposed algorithm and its performance analyzed for different parameters. Simulation results show that our proposed HHCDA method decreases the request reject rate and average delay by 31.5% and 20% and increases the energy efficiency by 40% compared to DDPG method.

cs.NI↗

arXiv2021

AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning

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). Due to the challenges of dynamic channel conditions, centralized resource management schemes that require global information are inefficient and lead to large signaling overheads. Hence, 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. Existing MARL algorithms consider a holistic reward function for the group's collective success, which often ends up with unsatisfactory results and cannot guarantee an optimal policy for each agent. Consequently, motivated by the existing literature in RL, we propose a novel MARL framework that trains 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, the 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 algorithm's effectiveness compared with the conventional RL methods applied in this area.

eess.SP↗

arXiv2021

Age of Information Aware VNF Scheduling in Industrial IoT Using Deep Reinforcement Learning

In delay-sensitive industrial internet of things (IIoT) applications, the age of information (AoI) is employed to characterize the freshness of information. Meanwhile, the emerging network function virtualization provides flexibility and agility for service providers to deliver a given network service using a sequence of virtual network functions (VNFs). However, suitable VNF placement and scheduling in these schemes is NP-hard and finding a globally optimal solution by traditional approaches is complex. Recently, deep reinforcement learning (DRL) has appeared as a viable way to solve such problems. In this paper, we first utilize single agent low-complex compound action actor-critic RL to cover both discrete and continuous actions and jointly minimize VNF cost and AoI in terms of network resources under end-to end Quality of Service constraints. To surmount the single-agent capacity limitation for learning, we then extend our solution to a multi-agent DRL scheme in which agents collaborate with each other. Simulation results demonstrate that single-agent schemes significantly outperform the greedy algorithm in terms of average network cost and AoI. Moreover, multi-agent solution decreases the average cost by dividing the tasks between the agents. However, it needs more iterations to be learned due to the requirement on the agents collaboration.

eess.SP↗

arXiv2021

Resource Allocation in Virtualized CoMP-NOMA HetNets: Multi-Connectivity for Joint Transmission

In this work, we design a generalized joint transmission coordinated multi-point (JT-CoMP)-non-orthogonal multiple access (NOMA) model for a virtualized multi-infrastructure network. In this model, all users benefit from multiple joint transmissions of CoMP thanks to the multi-connectivity opportunity provided by wireless network virtualization (WNV) in multi-infrastructure networks. The NOMA protocol in CoMP results in an unlimited NOMA clustering (UNC) scheme, where the order of each NOMA cluster is the maximum possible value. We show that UNC results in maximum successful interference cancellation (SIC) complexity at users. In this regard, we propose a limited NOMA clustering (LNC) scheme, where the SIC is performed to only a subset of users. We formulate the problem of joint power allocation and user association for the UNC and LNC schemes. Then, one globally and one locally optimal solution are proposed for each problem based on mixed-integer monotonic optimization and sequential programming, respectively. Numerical assessments reveal that WNV and LNC improves users sum-rate and reduces users SIC complexity by up to $35\%$ and $46\%$ compared to the non-virtualized CoMP-NOMA system and UNC model, respectively. Therefore, the proposed algorithms are suitable candidates for the implementation on open and intelligent radio access networks.

cs.IT↗

arXiv2021

Robust Energy-Efficient Resource Management, SIC Ordering, and Beamforming Design for MC MISO-NOMA Enabled 6G

This paper studies a novel approach for successive interference cancellation (SIC) ordering and beamforming in a multiple antennas non-orthogonal multiple access (NOMA) network with multi-carrier multi-user setup. To this end, we formulate a joint beamforming design, subcarrier allocation, user association, and SIC ordering algorithm to maximize the worst-case energy efficiency (EE). The formulated problem is a non-convex mixed integer non-linear programming (MINLP) which is generally difficult to solve. To handle it, we first adopt the linearizion technique as well as relaxing the integer variables, and then we employ the Dinkelbach algorithm to convert it into a more mathematically tractable form. The adopted non-convex optimization problem is transformed into an equivalent rank-constrained semidefinite programming (SDP) and is solved by SDP relaxation and exploiting sequential fractional programming. Furthermore, to strike a balance between complexity and performance, a low complex approach based on alternative optimization is adopted. Numerical results unveil that the proposed SIC ordering method outperforms the conventional existing works addressed in the literature.

eess.SP↗

arXiv2020

CECT: Computationally Efficient Congestion-avoidance and Traffic Engineering in Software-defined Cloud Data Centers

The proliferation of cloud data center applications and network function virtualization (NFV) boosts dynamic and QoS dependent traffic into the data centers network. Currently, lots of network routing protocols are requirement agnostic, while other QoS-aware protocols are computationally complex and inefficient for small flows. In this paper, a computationally efficient congestion avoidance scheme, called CECT, for software-defined cloud data centers is proposed. The proposed algorithm, CECT, not only minimizes network congestion but also reallocates the resources based on the flow requirements. To this end, we use a routing architecture to reconfigure the network resources triggered by two events: 1) the elapsing of a predefined time interval, or, 2) the occurrence of congestion. Moreover, a forwarding table entries compression technique is used to reduce the computational complexity of CECT. In this way, we mathematically formulate an optimization problem and define a genetic algorithm to solve the proposed optimization problem. We test the proposed algorithm on real-world network traffic. Our results show that CECT is computationally fast and the solution is feasible in all cases. In order to evaluate our algorithm in term of throughput, CECT is compared with ECMP (where the shortest path algorithm is used as the cost function). Simulation results confirm that the throughput obtained by running CECT is improved up to 3x compared to ECMP while packet loss is decreased up to 2x.

cs.NI↗

arXiv2020

A Unified Framework for Joint Energy and AoI Optimization via Deep Reinforcement Learning for NOMA MEC-based Networks

In this paper, we design a novel scheduling and resource allocation algorithm for a smart mobile edge computing (MEC) assisted radio access network. Different from previous energy efficiency (EE) based or the average age of information (AAoI)-based network designs, we propose a unified metric for simultaneously optimizing ESE and AAoI of the network. To further improve the system capacity, non-orthogonal multiple access (NOMA) is proposed as a candidate for multiple access schemes for future cellular networks. Our main aim is to maximize the long-term objective function under AoI, NOMA, and resource capacity constraints using stochastic optimization. To overcome the complexities and unknown dynamics of the network parameters (e.g., wireless channel and interference), we apply the concept of reinforcement learning and implement a deep Q-network (DQN). Simulation results illustrate the effectiveness of the proposed framework and analyze different parameters impact on network performance. Based on the results, our proposed reward function converges fast with negligible loss value. Also, they illustrate our work outperforms the existing state of the art baselines up to 64% in the objective function and 51% in AAoI, which are stated as examples.

eess.SP↗

arXiv2020

Cost-Effective Radio and NFV Resource Allocation: E2E QoS Provision

To fend off network ossification and support high degrees of flexibility and various services, network virtualization and slicing are introduced for the next-generation wireless cellular networks. These two technologies allow diversifying attributes of the future inter-networking and time-varying workloads based resource management paradigms. In this paper, we propose an end-to-end (E2E) resource allocation framework for future networks considering radio and core network by leveraging network function virtualization (NFV). We aim to minimize the network cost defined based on the utilized energy and spectrum while providing E2E quality of service (QoS) for diverse services with stringent QoS requirements. This goal is realized by formulating a novel optimization problem which performs the power and spectrum allocation in radio, and service function chaining and scheduling in the NFV environment while guaranteeing the distinct QoS constraints of the requested services. The proposed optimization problem is mixed-integer non-linear programming, which is a non-convex and NP-hard problem. To solve it, we adopt an iterative algorithm with novel admission control and a greedy-based heuristic algorithm, which is shown to have a polynomial order of complexity with 13:66% global optimality gap on average for a small scaled network. To validate the proposed framework, simulation results are carried out by considering different values of the network parameters and topologies. Moreover, our proposed framework and solution algorithm are assessed and compared with the existing works. Simulation results demonstrate that the proposed heuristic algorithm and framework outperforms the existing ones by 34% on average in cost reduction.

eess.SP↗