Genetic Algorithm Optimized Support Vector Machine in NOMA-based Satellite Networks with Imperfect CSI

Yan, Xiaojuan; An, Kang; Wang, Cheng-Xiang; Zhu, Wei-Ping; Li, Yusheng; Feng, Zhiqiang

doi:10.1109/icassp40776.2020.9053003

Cited by 4 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The channel vectors of these 2 M users were thereafter, fed to our proposed UGA; to generate the desired pairs. To calculate the respective channel vectors of the 2 M users, the Frii's equation was used for the path loss, the log-normal model was used for the shadowing; and the Rician model was used for the multipath fading, which best describes the multipath fading of a satellite-to-earth link [28][29][30].…”

Section: Test Setupmentioning

confidence: 99%

Users' grouping algorithm for fairness improvement of NOMA‐based multi‐beams satellite networks intended for 5G

Biyoghe

Balyan

2023

IET Communications

View full text Add to dashboard Cite

Non‐Orthogonal Multiple‐Access (NOMA)‐based Multibeam Satellite Networks (MBSNs) are intended for 5G implementation, and 5G networks set the requirement for both high system capacity as well as high system reliability to all users, which is achieved via high system's fairness. The NOMA network requires a user grouping algorithm (UGA), and most existing UGAs for 2‐users NOMA‐MBSNs, favor the system's capacity maximization with little regard to the system's fairness. Thus, this paper proposes a UGA that maximizes the fairness of 2‐users NOMA‐MBSNs. The algorithm seeks to group 2M users into M‐pairs satisfying three requirements, (i) a minimum channel‐gain margin; (ii) high channel‐correlation coefficients; and (iii) there is high fairness amongst the resulting pairs, in term of their respective channel‐correlation coefficients, to increase the users' fairness of the system. To achieve this, the 2M users are split into two sets of M‐far and M‐near users based on users' channel gains for pairing far and near users with high channel‐correlation coefficients. It will turn it into a maximization Bipartite Matching problem (BPMP) of channel‐correlation coefficients. The BPMP is addressed by means of the Hungarian Method (HM) to ensure high fairness amongst resulting pairs regarding their channel‐correlation coefficients. The proposed UGA demonstrates superior fairness compared to existing UGAs.

show abstract

Section: Test Setupmentioning

confidence: 99%

Users' grouping algorithm for fairness improvement of NOMA‐based multi‐beams satellite networks intended for 5G

Biyoghe

Balyan

2023

IET Communications

View full text Add to dashboard Cite

show abstract

“…is the PDF of User j's location [4] if it distributes in an annular area with inner radius R jn and outer radius R j f . To evaluate (15), we first express 1 F 1 m j ; 1; δ j x in ( 4) and (1 + x) a in terms of the Meijer G-functions from Equation (9.34.8) in [32] and binominals represented by Equation (1.11) in [32], as…”

Section: Power Allocation Strategymentioning

confidence: 99%

“…It is worth noting that, in addition to free space loss (FSL), antenna gain, fading severity, and location information in a beam spot can also influence the link budget of a satellite user, all of which, combined with users’ various delay QoS requirements, make the user grouping in a NOMA-based system nontrivial, especially in satellite networks, which are highly applied in military and civilian fields. To solve this challenge, a supervised learning algorithm, with which solutions can be obtained without model-oriented analysis and design, as an effective solution for resource management has been widely used in several prior works, such as work [ 15 ], which proposed a genetic algorithm (GA)-improved support vector machine scheme to effectively pair users for NOMA-based satellite networks. A fully connected deep neural network-assisted approach was studied in [ 16 , 17 ] to facilitate efficient beam hopping and design beam illumination pattern in multibeam satellite systems, respectively.…”

Section: Introductionmentioning

confidence: 99%

User Pairing for Delay-Limited NOMA-Based Satellite Networks with Deep Reinforcement Learning

Zhang

Yan

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate a user pairing problem in power domain non-orthogonal multiple access (NOMA) scheme-aided satellite networks. In the considered scenario, different satellite applications are assumed with various delay quality-of-service (QoS) requirements, and the concept of effective capacity is employed to characterize the effect of delay QoS limitations on achieved performance. Based on this, our objective was to select users to form a NOMA user pair and utilize resource efficiently. To this end, a power allocation coefficient was firstly obtained by ensuring that the achieved capacity of users with sensitive delay QoS requirements was not less than that achieved with an orthogonal multiple access (OMA) scheme. Then, considering that user selection in a delay-limited NOMA-based satellite network is intractable and non-convex, a deep reinforcement learning (DRL) algorithm was employed for dynamic user selection. Specifically, channel conditions and delay QoS requirements of users were carefully selected as state, and a DRL algorithm was used to search for the optimal user who could achieve the maximum performance with the power allocation factor, to pair with the delay QoS-sensitive user to form a NOMA user pair for each state. Simulation results are provided to demonstrate that the proposed DRL-based user selection scheme can output the optimal action in each time slot and, thus, provide superior performance than that achieved with a random selection strategy and OMA scheme.

show abstract

“…Finally, the validity of the theoretical results were verified by Monte-Carlo simulation. In [20], a genetic optimization algorithm based on NOMA downlink satellite networks was designed, in which NOMA users were selected according to the results of support vector machine classifier.…”

Section: Introductionmentioning

confidence: 99%

“…Although the aforementioned works such as [19], [20] have greatly improved our understanding on the NOMA based terrestrial-satellite networks under imperfect CSI condition, it should be noted that they did not take into account the effect of non-ideal SIC on system performance, and the channels considered were unordered. Additionally, unlike in [24], where the authors assumed perfect channel estimation, we consider the practical scenario where channel estimation is imperfect.…”

Section: Introductionmentioning

confidence: 99%

Joint Effects of Imperfect CSI and SIC on NOMA Based Satellite-Terrestrial Systems

et al. 2021

View full text Add to dashboard Cite

This paper investigates a satellite-terrestrial system employing the non-orthogonal multiple access (NOMA) scheme over Shadowed-Rician fading channels. The effects of both imperfect channel state information (CSI) and imperfect successive interference cancellation (SIC) on the NOMA based satellite-terrestrial system are taken into account. First, the outage performance of the proposed system is evaluated, and the closed-form expressions for the exact and asymptotic outage probabilities are obtained. Next, the expressions of the ergodic sum rate and system throughput are derived in the presence of channel estimation errors and residual interference. Moreover, we analyze the impacts of different residual interference levels on the energy efficiency. Finally, the numerical simulation results are conducted to verify the correctness of theoretical analysis and the advantages of the proposed NOMA scheme. At medium-high SNR region, the NOMA users are capable of outperforming orthogonal multiple access (OMA) users in terms of outage behaviors and system throughput with imperfect CSI and imperfect SIC. The ergodic sum rate decreases as the level of residual interference increases, and is even lower than that of OMA once goes beyond a certain value. Additionally, the energy efficiency of NOMA scheme is sensitive to the imperfect SIC.INDEX TERMS Satellite-terrestrial system, non-orthogonal multiple access (NOMA), imperfect CSI, imperfect SIC.

show abstract

Genetic Algorithm Optimized Support Vector Machine in NOMA-based Satellite Networks with Imperfect CSI

Cited by 4 publications

References 24 publications

Users' grouping algorithm for fairness improvement of NOMA‐based multi‐beams satellite networks intended for 5G

Users' grouping algorithm for fairness improvement of NOMA‐based multi‐beams satellite networks intended for 5G

User Pairing for Delay-Limited NOMA-Based Satellite Networks with Deep Reinforcement Learning

Joint Effects of Imperfect CSI and SIC on NOMA Based Satellite-Terrestrial Systems

Contact Info

Product

Resources

About