Resource Allocation In Wireless Networks Research Articles

Optimizing 5G network slicing with DRL: Balancing eMBB, URLLC, and mMTC with OMA, NOMA, and RSMA

The advent of 5th Generation (5G) networks has introduced the strategy of network slicing as a paradigm shift, enabling the provision of services with distinct Quality of Service (QoS) requirements. The 5th Generation New Radio (5G NR) standard complies with the use cases Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communications (URLLC), and Massive Machine Type Communications (mMTC), which demand a dynamic adaptation of network slicing to meet the diverse traffic needs. This dynamic adaptation presents both a critical challenge and a significant opportunity to improve 5G network efficiency. This paper proposes a Deep Reinforcement Learning (DRL) agent that performs dynamic resource allocation in 5G wireless network slicing according to traffic requirements of the 5G use cases within two scenarios: eMBB with URLLC and eMBB with mMTC. The DRL agent evaluates the performance of different decoding schemes such as Orthogonal Multiple Access (OMA), Non-Orthogonal Multiple Access (NOMA), and Rate Splitting Multiple Access (RSMA) and applies the best decoding scheme in these scenarios under different network conditions. The DRL agent has been tested to maximize the sum rate in scenario eMBB with URLLC and to maximize the number of successfully decoded devices in scenario eMBB with mMTC, both with different combinations of number of devices, power gains and number of allocated frequencies. The results show that the DRL agent dynamically chooses the best decoding scheme and presents an efficiency in maximizing the sum rate and the decoded devices between 84% and 100% for both scenarios evaluated.

Adaptive Beamforming, Cell-Free Resource Allocation and NOMA in Large-Scale Wireless Networks

The goal of the study presented in this work is to evaluate the performance of a proposed adaptive beamforming approach when combined with non-orthogonal multiple access (NOMA) in cell-free massive multiple input multiple output (CF m-MIMO) orientations. In this context, cooperative beamforming is employed taking into consideration the geographically adjacent access points (APs) of a virtual cell, aiming to minimize co-channel interference (CCI) among mobile stations (MSs) participating in NOMA transmission. Performance is evaluated statistically via extensive Monte Carlo (MC) simulations in a two-tier wireless orientation. As the results indicate, for high data rate services, various key performance indicators (KPIs) can be improved compared to orthogonal multiple access, such as the minimum number of users in the topology as well as the available PRBs for downlink transmission. Although in NOMA transmission more directional beamforming configurations are required to compensate for the increased CCI levels, the increase in the number of hardware elements is reduced compared to the corresponding gain in the considered KPIs.

Deep Deterministic Policy Gradient-Based Resource Allocation Considering Network Slicing and Device-to-Device Communication in Mobile Networks.

Next-generation mobile networks, such as those beyond the 5th generation (B5G) and 6th generation (6G), have diverse network resource demands. Network slicing (NS) and device-to-device (D2D) communication have emerged as promising solutions for network operators. NS is a candidate technology for this scenario, where a single network infrastructure is divided into multiple (virtual) slices to meet different service requirements. Combining D2D and NS can improve spectrum utilization, providing better performance and scalability. This paper addresses the challenging problem of dynamic resource allocation with wireless network slices and D2D communications using deep reinforcement learning (DRL) techniques. More specifically, we propose an approach named DDPG-KRP based on deep deterministic policy gradient (DDPG) with K-nearest neighbors (KNNs) and reward penalization (RP) for undesirable action elimination to determine the resource allocation policy maximizing long-term rewards. The simulation results show that the DDPG-KRP is an efficient solution for resource allocation in wireless networks with slicing, outperforming other considered DRL algorithms.

Intelligent resource allocation in wireless networks: Predictive models for efficient access point management

With the significant increase in mobile users connected to the wireless network, coupled with the escalating energy consumption and the risk of network saturation, the search for resource management has become paramount. Managing several access points throughout a whole region is hugely relevant in this context. Moreover, a wireless network must keep its Service Level Agreement, regardless of the number of connected users. With that in mind, in this work, we propose four prediction models that allow one to predict the number of connected users on a wireless network. Once the number of users has been predicted, the network resources can be properly allocated, minimizing the number of active access points. We investigate the use of Particle Swarm Optimization and Genetic Algorithms to hyper-parameterize a Multilayer Perceptron neural network and a Decision Tree. We evaluate our proposal using a campus-based wireless network dataset with more than 20,000 connected users. As a result, our model can considerably improve network performance by intelligently allocating the number of access points, thereby addressing concerns related to energy consumption and network saturation. The results have shown an average accuracy of 95.18%, managing to save network resources effectively.

Distributed-Optimization With Centralized-Refining for Efficient Resource Allocation in Future Wireless Networks

Distributed-Optimization With Centralized-Refining for Efficient Resource Allocation in Future Wireless Networks

Optimizing resource allocation in 5G wireless networks for enhanced spectral efficiency and energy conservation using machine learning methods

Optimizing resource allocation in 5G wireless networks for enhanced spectral efficiency and energy conservation using machine learning methods

A spiral modeling based on manta ray foraging optimization for wireless networks resource allocation

SummaryThe wireless network resource allocation is a NP‐hard combinatorial optimization problem. This paper proposes a new optimization method using the manta ray foraging optimization (MRFO) based on spiral modeling to solve the wireless network resource problem. In order to reduce the computational complexity and ensure the optimal performance of the allocation scheme, a MRFO algorithm based on spiral modeling and mutation strategy is proposed. In the first stage, spiral modeling is introduced to narrow the exploration area, while the mutation strategy of the genetic algorithm enhances the ability of the algorithm to jump out of the local optimal. In the second stage, a binary MRFO algorithm for using different transfer functions is proposed to solve the mixed integer programming problem. The experimental results show that IMRFO and BIMRFO have high comprehensive performance advantages, achieve better effects than the other optimization algorithms, which lead to faster convergence, faster accuracy, and lower complexity.

Secure Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless MEC Networks

Secure Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless MEC Networks

Radial basis function neural network-based algorithm unfolding for energy-aware resource allocation in wireless networks

Radial basis function neural network-based algorithm unfolding for energy-aware resource allocation in wireless networks

FEDRESOURCE

Deep reinforcement learning can effectively deal with resource allocation (RA) in wireless networks. However, more complex networks can have slower learning speeds, and a lack of network adaptability requires new policies to be learned for newly introduced systems. To address these issues, a novel federated learning-based resource allocation (FEDRESOURCE) has been proposed in this paper which efficiently performs RA in wireless networks. The proposed FEDRESOURCE technique uses federated learning (FL) which is a ML technique that shares the DRL-based RA model between distributed systems and a cloud server to describe a policy. The regularized local loss that occurs in the network will be reduced by using a butterfly optimization technique, which increases the convergence of the FL algorithm. The suggested FL framework speeds up policy learning and allows for adoption by employing deep learning and the optimization technique. Experiments were conducted using a Python-based simulator and detailed numerical results for the wireless RA sub-problems. The theoretical results of the novel FEDRESOURCE algorithm have been validated in terms of transmission power, convergence of algorithm, throughput, and cost. The proposed FEDRESOURCE technique achieves maximum transmit power up to 27%, 55%, and 68% energy efficiency compared to Scheduling policy, Asynchronous FL framework, and Heterogeneous computation schemes respectively. The proposed FEDRESOURCE technique can increase discrimination accuracy by 1.7%, 1.2%, and 0.78% compared to the scheduling policy framework, Asynchronous FL framework, and Heterogeneous computation schemes respectively.

Energy efficient resource allocation for re-configurable intelligent surface-assisted wireless networks

This paper focuses on energy-efficient resource allocation in reconfigurable intelligent surface (RIS)-assisted multiple-input-single-output (MISO) communication systems. Specifically, it revisits the solution to the energy efficiency (EE) problem using the alternating optimization (AO) approach. In each AO iteration, the RIS phase optimization is achieved using the gradient descent method, which unfortunately does not guarantee convergence. To overcome this limitation, we propose two alternatives: the Wolfe-based gradient-descent (GAW) EE maximization Algorithm and the trust region (TR)-based EE maximization algorithm. Additionally, we use Dinkelbach’s algorithm to obtain the optimal transmit power allocation. Our results demonstrate that the proposed methods outperform the existing approach that uses sequential fractional programming (SFP) for phase optimization and the traditional relay-based method.

Enhanced Slime Mould Optimization with Deep-Learning-Based Resource Allocation in UAV-Enabled Wireless Networks.

Unmanned aerial vehicle (UAV) networks offer a wide range of applications in an overload situation, broadcasting and advertising, public safety, disaster management, etc. Providing robust communication services to mobile users (MUs) is a challenging task because of the dynamic characteristics of MUs. Resource allocation, including subchannels, transmit power, and serving users, is a critical transmission problem; further, it is also crucial to improve the coverage and energy efficacy of UAV-assisted transmission networks. This paper presents an Enhanced Slime Mould Optimization with Deep-Learning-based Resource Allocation Approach (ESMOML-RAA) in UAV-enabled wireless networks. The presented ESMOML-RAA technique aims to efficiently accomplish computationally and energy-effective decisions. In addition, the ESMOML-RAA technique considers a UAV as a learning agent with the formation of a resource assignment decision as an action and designs a reward function with the intention of the minimization of the weighted resource consumption. For resource allocation, the presented ESMOML-RAA technique employs a highly parallelized long short-term memory (HP-LSTM) model with an ESMO algorithm as a hyperparameter optimizer. Using the ESMO algorithm helps properly tune the hyperparameters related to the HP-LSTM model. The performance validation of the ESMOML-RAA technique is tested using a series of simulations. This comparison study reports the enhanced performance of the ESMOML-RAA technique over other ML models.

NOMA-based energy efficient resource allocation in wireless energy harvesting sensor networks

Non Orthogonal Multiple Access (NOMA) and energy harvesting are two widely used concepts to improve the performance of Wireless Sensor Networks. In this paper, we consider a NOMA-based Wireless Energy Harvesting Sensor Network (WEHSN), in which all sensors harvest their energy from a Hybrid Access Point (HAP), and then, simultaneously transmit their information in NOMA-based protocol to the HAP, if their harvested energy are sufficient and they have data for transmission. We formulate the resource allocation as an optimization problem to maximize the energy efficiency, defined as system throughput per total energy consumption in the network, in which the total energy consumption is summation of energy consumption in downlink and uplink phases. The optimization problem constraints are the time scheduling parameters and the sensors’ transmission powers. To solve this maximization problem, we use the Dinkelbach method to convert it to the parametric form and then, we apply the Karush–Kuhn–Tucker (KKT) conditions in the parametric optimization problem to derive the closed form expression for optimization problem. We evaluate the performance of proposed scheme in relation to energy efficiency, throughput and total energy consumption, and we compare them with OFDMA and TDMA-based WEHSN method. The numerical results show that, NOMA-based WEHSN has better performance in compared with OFDMA and TDMA-based WEHSN. Also, the effect of different amount of data at the sensors has been considered in numerical result which shows that when the sensors always have data for transmission, the system has better performance in terms of energy efficiency and throughput but it has more total energy consumption in comparison to the situation that the sensors occasionally have data for transmission.

An Efficient Hybrid Ensemble SVM for Optimal Channel and Power Allocation Using Chaotic Quantum Bat Optimization

This paper addresses the challenge of resource allocation in wireless networks, given the increasing usage of mobile devices and sensors. To achieve energy efficiency, we propose a novel method called Hybrid Random Forest Ensemble Support Vector Machine (RFESVM) with Chaotic Cloud Quantum Bat Algorithm (CCQBA). The proposed method identifies the best power allocation for each user in Device-to-Device (D2D) communication, which can significantly improve coverage and lower data rates and latency. To overcome the shortcomings of existing methods, we use the chaotic cloud quantum bat algorithm that combines randomness, ergodicity of chaotic mapping, and stability inclination to enhance the convergence speed. To address the issue of class imbalance in the dataset, we combine SVM with RF and establish an ensemble technique called RFESVM. Our proposed method achieves higher energy efficiency compared to other techniques, demonstrating the effectiveness of optimal power allocation in D2D communication. Overall, the proposed method can significantly improve the systems' energy efficiency while ensuring high network performance in wireless networks.

Deep neural network based resource allocation in D2D wireless networks

The increased complexity of future 5G wireless communication networks presents a fundamental issue for optimal resource allocation. This continuous, constrained optimal control problem must be solved in real-time since the power allocation should be consistent with the instantly evolving channel state. This paper emphasizes the application of deep learning to develop solutions for radio resource allocation problems in multiple-input multiple-output systems. We introduce a supervised deep neural network model combined with particle swarm optimization to address the issue using heuristic-generated data. We train the model and evaluate its ability to anticipate resource allocation solutions accurately. The simulation result indicates that the trained DNN-based model can deliver the nearoptimal solution.

Deep Reinforcement Learning for Resource Allocation in Multi-Band and Hybrid OMA-NOMA Wireless Networks

Exploiting the advantages of both non-orthogonal multiple access technique and millimeter-wave communications requires joint efficient resource allocation techniques toward satisfying the stringent requirements of future mobile communication systems. This paper focuses on a multi-band (i.e., millimeter-wave band and sub-6 GHz band) wireless network where both orthogonal and non-orthogonal multiple access techniques coexist. A joint optimization of user association, transmit power allocation, sub-channel assignment, and multiple access technique selection is investigated to maximize the down-link sum-rate under a minimum rate requirement per user and power constraints. The problem is formulated as a non-convex mixed-integer optimization problem; then, it is proved to be <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {NP}$ </tex-math></inline-formula> -hard. First, simple greedy and meta-heuristic solutions are proposed. Then, since model-based approaches have generally a high computational complexity, model-free centralized and distributed approaches based on deep reinforcement learning technique are proposed. The latter are based on multiple parallel deep neural networks to generate resource allocation solutions. The proposed approaches are evaluated and compared. Simulation results corroborate the high performance offered by the proposed solutions for stationary and mobile users. They also highlight the benefits of employing hybrid orthogonal and non-orthogonal multiple access scheme in multi-band systems in terms of down-link sum-rate and user fairness.

Lyapunov Drift-Plus-Penalty Based Resource Allocation in IRS-Assisted Wireless Networks with RF Energy Harvesting

Lyapunov Drift-Plus-Penalty Based Resource Allocation in IRS-Assisted Wireless Networks with RF Energy Harvesting

Power and delay optimization based uplink resource allocation for wireless networks with device-to-device communications

In this paper, the resource allocation problem for all devices is investigated in a multi-sharing uplink scenario of mmWave cyclic prefix-orthogonal frequency division multiplexing (CP-OFDM) based wireless networks with device-to-device (D2D) communications. More specifically, a power and delay optimization based uplink resource allocation (PDO-URA) algorithm is proposed divided into two steps. At first, network resources are allocated to cellular user equipments (CUEs) in terms of power and transmission rate through a proposed approach that intends to maximize throughput. Next, idle resources are allocated by considering delay minimization. To this end, we propose to apply an algorithm based on delay optimization where idle resources are shared with D2D user equipments (DUEs) in the network considering the formed conflicts graphs and the delay information estimated through Network Calculus concepts such as envelope process and service curve. Computational simulations are carried out considering a communication scenario with 5G characteristics such as millimeter waves at frequencies above 6 GHz, comparing also the performance of other algorithms from the literature in terms of quality of service (QoS) parameters such as throughput and delay. The results confirm that the proposed algorithm presents superior performance in terms of throughput and delay for the mmWave CP-OFDM wireless networks with D2D communications than the other considered algorithms.

Integrated UAV Trajectory Control and Resource Allocation for UAV-Based Wireless Networks With Co-Channel Interference Management

In this article, we study the trajectory control, subchannel assignment, and user association design for unmanned aerial vehicles (UAVs)-based wireless networks. We propose a method to optimize the max-min average rate subject to data demand constraints of ground users (GUs) where spectrum reuse and co-channel interference management are considered. The mathematical model is a mixed-integer nonlinear optimization problem which we solve by using the alternating optimization approach where we iteratively optimize the user association, subchannel assignment, and UAV trajectory control until convergence. For the subchannel assignment subproblem, we propose an iterative subchannel assignment (ISA) algorithm to obtain an efficient solution. Moreover, the successive convex approximation (SCA) is used to convexify and solve the nonconvex UAV trajectory control subproblem. Via extensive numerical studies, we illustrate the effectiveness of our proposed design considering different UAV flight periods and number of subchannels and GUs as compared with a simple heuristic.

Wireless Network Virtualization Resource Sharing Based on Dynamic Resource Allocation Algorithm

In recent years, with the continuous development of IT industry, network virtualization technology has gradually developed into a hotspot of research and application in the field of communication because IT allows the construction of customized virtual network (VN) on shared physical infrastructure. In particular, the proposal of wireless network virtualization for the development of the enhanced Internet. Because these technologies require effective algorithms named virtual network mapping (VNE) to instantiate virtual networks on the SN, on the basis of satisfying the isolation between wireless network slices, a resource allocation mechanism based on bilateral auction is proposed. At present, many researchers have proposed that network virtualization technology is a feasible way to solve the rigid Internet architecture. In the field of existing research focuses on the cable network virtualization, mainly related to the data center network and backbone, then, the side of the wireless access network virtualization the key technology research is still in its infancy, in order to accelerate the process of wireless skill for innovation and meet the demand of the difference of the emerging business, wireless network virtualization becomes the research hotspot and focus of academia and industry. However, no one has applied the dynamic resource allocation algorithm to wireless network virtualization resource sharing field. Here, this paper analyzes and summarizes the existing virtual network resource allocation schemes at home and abroad. The wireless virtual network resource allocation model and cross-domain virtual network resource allocation model are established, and the network centrality theory in social network and complex network is introduced to analyze the topology properties of virtual network and physical network, and two efficient virtual network resource allocation methods are proposed.