Yan Kyaw Tun’s research while affiliated with Aalborg University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (92)


Optimizing Multi-User Semantic Communication via Transfer Learning and Knowledge Distillation
  • Article

January 2025

·

16 Reads

·

1 Citation

IEEE Communications Letters

·

·

·

[...]

·

Semantic Communication (SemCom), notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, eliminates redundant information, and mitigates noise effects from wireless channel. However, most studies overlook multiple user scenarios and resource availability, limiting real-world applications. This paper addresses this gap by focusing on downlink communication from a base station to multiple users with varying computing capacities. Users employ variants of Swin transformer models for source decoding and a simple architecture for channel decoding. We propose a novel training procedure FRENCA, incorporating transfer learning and knowledge distillation to improve low-computing users' performance. Extensive simulations validate the proposed methods.


Data Service Maximization in Space-Air-Ground Integrated 6G Networks

November 2024

·

6 Reads

·

1 Citation

IEEE Communications Letters

Integrating terrestrial and non-terrestrial networks has emerged as a promising paradigm to fulfill the constantly growing demand for connectivity, low transmission delay, and quality of services (QoS). This integration brings together the strengths of the reliability of terrestrial networks, broad coverage and service continuity of non-terrestrial networks like low earth orbit satellites (LEOSats), etc. In this work, we study a data service maximization problem in space-air-ground integrated network (SAGIN) where the ground base stations (GBSs) and LEOSats cooperatively serve the coexisting aerial users (AUs) and ground users (GUs). Then, by considering the spectrum scarcity, interference, and QoS requirements of the users, we jointly optimize the user association, AU’s trajectory, and power allocation. To address the formulated mixed-integer non-convex problem, we decompose it into two subproblems: 1) user association problem and 2) trajectory and power allocation problem. We formulate the user association problem as a binary integer programming problem and solve it by using the Gurobi optimizer. Meanwhile, the trajectory and power allocation problem is solved by the deep deterministic policy gradient (DDPG) method to cope with the problem’s non-convexity and dynamic network environments. Then, the two subproblems are alternately solved by the proposed block coordinate descent algorithm. By comparing with the baselines in the existing literature, extensive simulations are conducted to evaluate the performance of the proposed framework.


Towards Satellite Non-IID Imagery: A Spectral Clustering-Assisted Federated Learning Approach

October 2024

·

20 Reads

Low Earth orbit (LEO) satellites are capable of gathering abundant Earth observation data (EOD) to enable different Internet of Things (IoT) applications. However, to accomplish an effective EOD processing mechanism, it is imperative to investigate: 1) the challenge of processing the observed data without transmitting those large-size data to the ground because the connection between the satellites and the ground stations is intermittent, and 2) the challenge of processing the non-independent and identically distributed (non-IID) satellite data. In this paper, to cope with those challenges, we propose an orbit-based spectral clustering-assisted clustered federated self-knowledge distillation (OSC-FSKD) approach for each orbit of an LEO satellite constellation, which retains the advantage of FL that the observed data does not need to be sent to the ground. Specifically, we introduce normalized Laplacian-based spectral clustering (NLSC) into federated learning (FL) to create clustered FL in each round to address the challenge resulting from non-IID data. Particularly, NLSC is adopted to dynamically group clients into several clusters based on cosine similarities calculated by model updates. In addition, self-knowledge distillation is utilized to construct each local client, where the most recent updated local model is used to guide current local model training. Experiments demonstrate that the observation accuracy obtained by the proposed method is separately 1.01x, 2.15x, 1.10x, and 1.03x higher than that of pFedSD, FedProx, FedAU, and FedALA approaches using the SAT4 dataset. The proposed method also shows superiority when using other datasets.


Figure 1: Multi-satellites architecture for joint beamforming, spectrum allocation, and RUE scheduling management.
Figure 2: Flowchart illustrating the proposed algorithms for solving joint beamforming and resource management.
Figure 3: Proposed multi-agent asynchronous federated inverse reinforcement learning (MA-AFIRL) learning framework.
Training Parameters
Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning
  • Preprint
  • File available

September 2024

·

66 Reads

In this paper, a novel generative adversarial imitation learning (GAIL)-powered policy learning approach is proposed for optimizing beamforming, spectrum allocation, and remote user equipment (RUE) association in NTNs. Traditional reinforcement learning (RL) methods for wireless network optimization often rely on manually designed reward functions, which can require extensive parameter tuning. To overcome these limitations, we employ inverse RL (IRL), specifically leveraging the GAIL framework, to automatically learn reward functions without manual design. We augment this framework with an asynchronous federated learning approach, enabling decentralized multi-satellite systems to collaboratively derive optimal policies. The proposed method aims to maximize spectrum efficiency (SE) while meeting minimum information rate requirements for RUEs. To address the non-convex, NP-hard nature of this problem, we combine the many-to-one matching theory with a multi-agent asynchronous federated IRL (MA-AFIRL) framework. This allows agents to learn through asynchronous environmental interactions, improving training efficiency and scalability. The expert policy is generated using the Whale optimization algorithm (WOA), providing data to train the automatic reward function within GAIL. Simulation results show that the proposed MA-AFIRL method outperforms traditional RL approaches, achieving a 14.6%14.6\% improvement in convergence and reward value. The novel GAIL-driven policy learning establishes a novel benchmark for 6G NTN optimization.

Download

Semantic Communication Enabled 6G-NTN Framework: A Novel Denoising and Gateway Hop Integration Mechanism

September 2024

·

37 Reads

The sixth-generation (6G) non-terrestrial networks (NTNs) are crucial for real-time monitoring in critical applications like disaster relief. However, limited bandwidth, latency, rain attenuation, long propagation delays, and co-channel interference pose challenges to efficient satellite communication. Therefore, semantic communication (SC) has emerged as a promising solution to improve transmission efficiency and address these issues. In this paper, we explore the potential of SC as a bandwidth-efficient, latency-minimizing strategy specifically suited to 6G satellite communications. While existing SC methods have demonstrated efficacy in direct satellite-terrestrial transmissions, they encounter limitations in satellite networks due to distortion accumulation across gateway hop-relays. Additionally, certain ground users (GUs) experience poor signal-to-noise ratios (SNR), making direct satellite communication challenging. To address these issues, we propose a novel framework that optimizes gateway hop-relay selection for GUs with low SNR and integrates gateway-based denoising mechanisms to ensure high-quality-of-service (QoS) in satellite-based SC networks. This approach directly mitigates distortion, leading to significant improvements in satellite service performance by delivering customized services tailored to the unique signal conditions of each GU. Our findings represent a critical advancement in reliable and efficient data transmission from the Earth observation satellites, thereby enabling fast and effective responses to urgent events. Simulation results demonstrate that our proposed strategy significantly enhances overall network performance, outperforming conventional methods by offering tailored communication services based on specific GU conditions.



Active STAR-RIS Empowered Edge System for Enhanced Energy Efficiency and Task Management

August 2024

·

26 Reads

The proliferation of data-intensive and low-latency applications has driven the development of multi-access edge computing (MEC) as a viable solution to meet the increasing demands for high-performance computing and storage capabilities at the network edge. Despite the benefits of MEC, challenges such as obstructions cause non-line-of-sight (NLoS) communication to persist. Reconfigurable intelligent surfaces (RISs) and the more advanced simultaneously transmitting and reflecting (STAR)-RISs have emerged to address these challenges; however, practical limitations and multiplicative fading effects hinder their efficacy. We propose an active STAR-RIS-assisted MEC system to overcome these obstacles, leveraging the advantages of active STAR-RIS. The main contributions consist of formulating an optimization problem to minimize energy consumption with task queue stability by jointly optimizing the partial task offloading, amplitude, phase shift coefficients, amplification coefficients, transmit power of the base station (BS), and admitted tasks. Furthermore, we decompose the non-convex problem into manageable sub-problems, employing sequential fractional programming for transmit power control, convex optimization technique for task offloading, and Lyapunov optimization with double deep Q-network (DDQN) for joint amplitude, phase shift, amplification, and task admission. Extensive performance evaluations demonstrate the superiority of the proposed system over benchmark schemes, highlighting its potential for enhancing MEC system performance. Numerical results indicate that our proposed system outperforms the conventional STAR-RIS-assisted by 18.64\% and the conventional RIS-assisted system by 30.43\%, respectively.


Fig. 1: The architectural framework for facilitating multi-satellite semantic communication in Earth observation for disaster relief systems.
Semantic Enabled 6G LEO Satellite Communication for Earth Observation: A Resource-Constrained Network Optimization

July 2024

·

48 Reads

·

1 Citation

Earth observation satellites generate large amounts of real-time data for monitoring and managing time-critical events such as disaster relief missions. This presents a major challenge for satellite-to-ground communications operating under limited bandwidth capacities. This paper explores semantic communication (SC) as a potential alternative to traditional communication methods. The rationality for adopting SC is its inherent ability to reduce communication costs and make spectrum efficient for 6G non-terrestrial networks (6G-NTNs). We focus on the critical satellite imagery downlink communications latency optimization for Earth observation through SC techniques. We formulate the latency minimization problem with SC quality-of-service (SC-QoS) constraints and address this problem with a meta-heuristic discrete whale optimization algorithm (DWOA) and a one-to-one matching game. The proposed approach for captured image processing and transmission includes the integration of joint semantic and channel encoding to ensure downlink sum-rate optimization and latency minimization. Empirical results from experiments demonstrate the efficiency of the proposed framework for latency optimization while preserving high-quality data transmission when compared to baselines.


Fig. 1: The architectural framework for facilitating multi-satellite semantic communication in Earth observation for disaster relief systems.
Semantic Enabled 6G LEO Satellite Communication for Earth Observation: A Resource-Constrained Network Optimization

July 2024

·

30 Reads

·

2 Citations

Earth observation satellites generate large amounts of real-time data for monitoring and managing time-critical events such as disaster relief missions. This presents a major challenge for satellite-to-ground communications operating under limited bandwidth capacities. This paper explores semantic communication (SC) as a potential alternative to traditional communication methods. The rationality for adopting SC is its inherent ability to reduce communication costs and make spectrum efficient for 6G non-terrestrial networks (6G-NTNs). We focus on the critical satellite imagery downlink communications latency optimization for Earth observation through SC techniques. We formulate the latency minimization problem with SC quality-of-service (SC-QoS) constraints and address this problem with a meta-heuristic discrete whale optimization algorithm (DWOA) and a one-to-one matching game. The proposed approach for captured image processing and transmission includes the integration of joint semantic and channel encoding to ensure downlink sum-rate optimization and latency minimization. Empirical results from experiments demonstrate the efficiency of the proposed framework for latency optimization while preserving high-quality data transmission when compared to baselines.


Fig. 1: STAR-RISs architecture.
Fig. 2: NOMA aided multi-STAR-RISs indoor networks.
Fig. 4: Proposed Convex Approximation-imitated PPO.
Fig. 5: Learning convergence results.
Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach

June 2024

·

102 Reads

Sixth-generation (6G) networks leverage simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) to overcome the limitations of traditional RISs. STAR-RISs offer 360-degree full-space coverage and optimized transmission and reflection for enhanced network performance and dynamic control of the indoor propagation environment. However, deploying STAR-RISs indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs) and STAR-RISs is proposed for indoor communication. An optimization problem encompassing user assignment, access point beamforming, and STAR-RIS phase control for reflection and transmission is formulated. The inherent complexity of the formulated problem necessitates a decomposition approach for an efficient solution. This involves tackling different sub-problems with specialized techniques: a many-to-one matching algorithm is employed to assign users to appropriate access points, optimizing resource allocation. To facilitate efficient resource management, access points are grouped using a correlation-based K-means clustering algorithm. Multi-agent deep reinforcement learning (MADRL) is leveraged to optimize the control of the STAR-RIS. Within the proposed MADRL framework, a novel approach is introduced where each decision variable acts as an independent agent, enabling collaborative learning and decision-making. Additionally, the proposed MADRL approach incorporates convex approximation (CA). This technique utilizes suboptimal solutions from successive convex approximation (SCA) to accelerate policy learning for the agents, thereby leading to faster environment adaptation and convergence. Simulations demonstrate significant network utility improvements compared to baseline approaches.


Citations (57)


... Transfer learning particularly enhances the effectiveness of transferring knowledge from one task to related tasks, proving invaluable in contexts where devices handle multiple tasks or face limited training data. For instance, Nguyen et al. [196] demonstrate optimizing multiuser SC through transfer learning and knowledge distillation, significantly boosting performance for users with varying computing capabilities by facilitating knowledge transfer from high-capacity to low-capacity user models. Similarly, Wu et al. [197] introduce a novel transfer learning strategy to guide the training process in object detection with limited labels by leveraging semantic information across tasks, enhancing fewshot detection performance and reducing IoT devices' storage pressures. ...

Reference:

Resource Management, Security, and Privacy Issues in Semantic Communications: A Survey
Optimizing Multi-User Semantic Communication via Transfer Learning and Knowledge Distillation
  • Citing Article
  • January 2025

IEEE Communications Letters

... [21] proposes a neural network-based algorithm to effectively decompose the complex mixed integer quadratic constrained quadratic programming problem into more manageable sub problems for joint user association and resource allocation in millimeter wave communication systems with multi connectivity and integrated access feedback. Ei et al. [22] formulates the user association problem as a binary integer programming problem and applies the Gurobi optimiser to solve it, with the aim of maximising the performance of the entire network. Furthermore, [23] developed an iterative optimization algorithm for a multi intelligent reflecting surface (IRS) assisted ultra-reliable and low-latency communication (URLLC) system, which jointly optimizes user association and resource allocation. ...

Data Service Maximization in Space-Air-Ground Integrated 6G Networks
  • Citing Article
  • November 2024

IEEE Communications Letters

... The perception-communication-computing-actuation-integrated paradigm (PCCAIP), as proposed in [26], optimizes communication process through the integration of sensing, computing, and actuation technologies. In terms of delay optimization, papers [24,25,27] have improved transmission efficiency by integrating SemCom with different modulation methods. ...

Semantic Enabled 6G LEO Satellite Communication for Earth Observation: A Resource-Constrained Network Optimization

... Second, the reliability is resource allocation design aiming to achieve high rate and low error for rate-target and error-target IoT devices, respectively. In [20], the authors proposed a joint optimization design, where power allocation, transmission blocklength, receiving beamforming, IRS reflection, and user pairing optimization are jointly optimized to minimize the maximum decoding error probability. In [21], the authors investigated an IRSasisted NOMA-based mobile edge computing (MEC) network in the FBL regime. ...

Min-max Decoding Error Probability Optimization in RIS-Aided Hybrid TDMA-NOMA Networks

IEEE Access

... Previous related works [29]- [34] investigating resource allocation in SemCom networks mainly focused on the inference period rather than model training period in our study. There are also a few studies [35]- [37] discussing the training framework of SemCom networks, but they did not design the corresponding resource allocation strategy to optimize the system holistically. In synthesizing the above discussion, we highlight the unique contribution of our work: jointly optimizing latency, energy consumption and model performance while training an image SemCom network. ...

An Efficient Federated Learning Framework for Training Semantic Communication Systems
  • Citing Article
  • May 2024

IEEE Transactions on Vehicular Technology

... This functionality enables STAR-RIS to achieve a 360 • coverage area, which is twice compared to the traditional RIS. Hence, STAR-RIS possesses enormous application potentials and has been incorporated into various wireless systems, e.g., secure communications systems [24]- [26], integrated sensing and communications (ISAC) systems [27]- [29], and MEC networks [30]- [32]. Specifically, in [32], a novel MEC scheme is suggested, utilizing a STAR-RIS vertically attached to the UAV to manipulate and adjust the tasks offloading signals from users to the MEC server at the ground BS. ...

Aerial STAR-RIS Empowered MEC: A DRL Approach for Energy Minimization

IEEE Wireless Communications Letters

... The implementation of machine learning for managing the radio resources and edge computing resources of satellite networks has been studied in the literature [4,5]. The data packet routing problem in satellite constellations is investigated in [4], which is solved by employing the deep reinforcement learning (DRL). ...

SpaceRIS: LEO Satellite Coverage Maximization in 6G Sub-THz Networks by MAPPO DRL and Whale Optimization

IEEE Journal on Selected Areas in Communications

... Only a few examined multiple users scenario in the context of SemCom [10], [11], while none of the aforementioned works considered the difference in users' resources, such as storage and computing capacity. In [12], the authors considered the difference in the computing capacity of users. Nevertheless, the proposed iterative training requires a substantial number of training epochs to achieve convergence, making it time-consuming, energy-intensive, and challenging to scale effectively. ...

Swin Transformer-Based Dynamic Semantic Communication for Multi-User With Different Computing Capacity
  • Citing Article
  • June 2024

IEEE Transactions on Vehicular Technology

... Another article [142] explored a STAR-RIS-assisted Vehicle-to-Everything (V2X) communication system to enhance coverage in urban environments. The study optimized data rates for V2I users and ensured latency and reliability for V2V communications by adjusting spectrum allocation, STAR-RIS element settings, and power levels. ...

Deep Reinforcement Learning-Based Joint Spectrum Allocation and Configuration Design for STAR-RIS-Assisted V2X Communications

IEEE Internet of Things Journal

... The authors propose a joint optimization of positioning and RIS phase shifts to improve system energy efficiency. Additionally, the case of multiple ARIS is explored in [12], where deep reinforcement learning is applied to jointly optimize ARIS placement, phase shifts, and power control. However, only a limited number of research papers have explored the impact of RIS orientation. ...

Energy-Efficient Communication Networks via Multiple Aerial Reconfigurable Intelligent Surfaces: DRL and Optimization Approach

IEEE Transactions on Vehicular Technology