Packet-Level Throughput Analysis and Energy Efficiency Optimization for UAV-Assisted IAB Heterogeneous Cellular Networks

Zhang, Yue; Shan, Hangguan; Song, Meiyan; Yang, Howard H.; Zhang, Qi; He, Xiang

doi:10.1109/tvt.2023.3252093

Cited by 11 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the authors in [24] proposed an outer approximation novel algorithm, with the aim of maximizing the users sum data rate by optimizing the power allocation and users' association, considering a UAV-assisted HetNet. In [25], the authors developed a theoretical framework for analyzing the energy efficiency and the mean packet throughput of a millimeter-wave (mmWave) UAV-assisted integrated access and backhaul HetNet, based on stochastic geometry and queueing theory. A coalition formation game combined with deep reinforcement learning approach was proposed in [26].…”

Section: ) Sum Rate Maximizationmentioning

confidence: 99%

“…In this model, the average path loss between the UAV Base stations (UBSs) m and wireless devices i in downlink communication can be represented by considering the Line of Sight (LoS) and Non-Line of Sight (NLoS) probabilities as follows [25]:…”

Section: B Path Loss Modelsmentioning

confidence: 99%

“…Where P LoS im , and P NLoS im are the probabilities of LoS and NLoS between WD i and UBS m, respectively, such that P LoS im + P NLoS im = 1; η LoS , and η NLoS are the excessive path loss coefficients in LoS and NLoS, respectively; K 0 = 4πfc c such that f c is the carrier frequency and c is the speed of light; α is the path loss exponent; and d im is the distance between WD i and UBS m. The probability of LoS between WD i and UBS m as recommended by the International Telecommunication Union (ITU) can be calculated as follows [25]:…”

Section: B Path Loss Modelsmentioning

confidence: 99%

“…Then, an action is selected and executed based on the ε-greedy policy at each state [49], which represents the exploration (i.e., random action selection) and the exploitation (i.e., action with the maximum Q-value) tradeoff (line 4,5). After that, r t is calculated according to (25) based on the resulted state s t+1 , and the state-action table is updated (lines 6-8). An episode is terminated after Q-table is converged (i.e., if r t is equal to the maximum reward achieved from the past steps r max prev , and is repeated N conv times, while the number of steps is more than or equal to T min ), or a predefined number of iteration T is reached (lines 10-15).…”

Section: B Reinforcement Learningmentioning

confidence: 99%

See 3 more Smart Citations

Location and User Association Optimization in Multiple Radio Access UAV-Assisted Heterogeneous IoT Networks

Anany,

Elmesalawy,

Ibrahim

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Recently, the huge growth in multimedia demand derived from smart devices and Internet of Things (IoT) development requires efficient heterogeneous networks with high data rates. To fulfill these requirements, the exploitation of Unmanned Aerial Vehicles (UAVs) enabled with multiple radio access for providing efficient connectivity should be considered, since it offers flexibility, ease of deployment, and ondemand service for wireless devices. In this paper, the idea of deploying Multiple Radio Access Technologies (Multi-RAT) base stations on a UAV is proposed, in order to utilize the unlicensed spectrum. The problem of optimizing the Multi-RAT UAV's location along with the wireless devices' association to maximize the total system throughput considering a heterogeneous LTE and WLAN ground network is investigated. To solve this problem, we propose a novel framework based on reinforcement learning and regret matching algorithms, such that the Q-learning algorithm is used to find the Multi-RAT UAV's optimum location, while regret matching is used to solve the optimum users' association. Moreover, a K-means clustering algorithm is adopted as an initialization phase to speed up the convergence of the proposed solution. Simulation results show the significance of the proposed idea of deploying Multi-RAT base stations on a UAV. Further, the performance analysis shows the effectiveness of the proposed framework by applying K-means as an initialization phase.

show abstract

Section: ) Sum Rate Maximizationmentioning

confidence: 99%

Section: B Path Loss Modelsmentioning

confidence: 99%

Section: B Path Loss Modelsmentioning

confidence: 99%

Section: B Reinforcement Learningmentioning

confidence: 99%

See 2 more Smart Citations

Location and User Association Optimization in Multiple Radio Access UAV-Assisted Heterogeneous IoT Networks

Anany,

Elmesalawy,

Ibrahim

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The IAB technology is getting a lot of attention as a promising solution to increase spectrum utilization efficiency with limited frequency resources. However, since the frequency bandwidth for user access links is shared by wireless backhaul links in the IAB architecture, this makes the resource allocation algorithm more complicated, resulting in increased network energy consumption [13], [14]. Thus, developing an advanced resource allocation algorithm with low complexity is of utmost importance to achieve an optimal solution in IAB.…”

mentioning

confidence: 99%

Low-Complexity Q-Learning for Energy-Aware Small-Cell Networks With Integrated Access and Backhaul

Lee,

Choi,

Lim

et al. 2023

IEEE Access

View full text Add to dashboard Cite

An integrated access and backhaul (IAB)-enabled small-cell network commonly utilizes frequency channels for access and backhaul links, and thus this network has a chance to utilize the frequency channels efficiently and optimally. However, there are still several problems with applying the IAB technology to practical small-cell networks, such as extremely high computational complexity caused by shared resource utilization and additional co-tier and cross-tier interference management. Therefore, we herein propose a multi-agent distributed Q-learning with pre-resource partitioning (MADQ-PRP) algorithm to solve the problem of frequency channel allocation and energy consumption. In MADQ-PRP, to reduce the computational complexity, each RL agent only considers its local state information to determine its following action. Nevertheless, by sharing and redistributing the rewards among agents, the overall reward can be maximized. Furthermore, we devise a pre-resource partitioning method depending on the variations in the number of SBSs per MBS and the numbers of MBS and SBS channels to reduce the computational complexity of the proposed MADQ-PRP algorithm. Through intensive simulations, we show the convergence of the proposed MADQ-PRP algorithm to the optimal solution obtained by the exhaustive search algorithm. Also, we demonstrate that the proposed MADQ-PRP algorithm outperforms several benchmark algorithms such as 'Random action,' 'SBS on-off,' 'SBS-only,' and 'MADQ-only' in IAB-enabled small-cell networks with non-uniform traffic distribution. Furthermore, it is confirmed that the proposed MADQ-PRP algorithm can reduce the CPU execution time by 9.1% and 97.9% compared to the distributed and centralized RL algorithms, respectively. The proposed algorithm based on the lowcomplexity RL and PRP could be one of the solutions to optimize the heterogeneous network performance from the perspective of the network operators when considering the coverage-capacity tradeoff.INDEX TERMS Low complexity multi-agent Q-learning, pre-resource partitioning, network-wide energy efficiency, user outage, integrated access and backhaul, IAB-enabled small-cell network. I. INTRODUCTION A. BACKGROUND AND MOTIVATIONM OBILE data traffic is expected to exponentially increase in the forthcoming sixth generation (6G) cellular networks [1]-[5]. However, the limited frequency resources are insufficient to support this traffic demand. Fur-thermore, access and backhaul networks require a large amount of spectrum bandwidth as well as consume a vast amount of energy to support many kinds of real-time mobile application services. In particular, access technology accounts for a large portion of the total network energy consumption [6]- [8]. Also, to meet the technical requirements of

show abstract

Alignment of Heterogeneous Packet Lengths for Random Access in 5G Massive Machine Type Communication

Woo,

2024

Wireless Pers Commun

View full text Add to dashboard Cite

Packet-Level Throughput Analysis and Energy Efficiency Optimization for UAV-Assisted IAB Heterogeneous Cellular Networks

Cited by 11 publications

References 39 publications

Location and User Association Optimization in Multiple Radio Access UAV-Assisted Heterogeneous IoT Networks

Location and User Association Optimization in Multiple Radio Access UAV-Assisted Heterogeneous IoT Networks

Low-Complexity Q-Learning for Energy-Aware Small-Cell Networks With Integrated Access and Backhaul

Alignment of Heterogeneous Packet Lengths for Random Access in 5G Massive Machine Type Communication

Contact Info

Product

Resources

About