arXiv subjects

Yu Min Park

Publications and source records attributed to Yu Min Park.

16 recordsLinked to original sources

arXiv2025

Resource-Efficient Beam Prediction in mmWave Communications with Multimodal Realistic Simulation Framework

Beamforming is a key technology in millimeter-wave (mmWave) communications that improves signal transmission by optimizing directionality and intensity. However, conventional channel estimation methods, such as pilot signals or beam sweeping, often fail to adapt to rapidly changing communication environments. To address this limitation, multimodal sensing-aided beam prediction has gained significant attention, using various sensing data from devices such as LiDAR, radar, GPS, and RGB images to predict user locations or network conditions. Despite its promising potential, the adoption of multimodal sensing-aided beam prediction is hindered by high computational complexity, high costs, and limited datasets. Thus, in this paper, a novel resource-efficient learning framework is introduced for beam prediction, which leverages a custom-designed cross-modal relational knowledge distillation (CRKD) algorithm specifically tailored for beam prediction tasks, to transfer knowledge from a multimodal network to a radar-only student model, achieving high accuracy with reduced computational cost. To enable multimodal learning with realistic data, a novel multimodal simulation framework is developed while integrating sensor data generated from the autonomous driving simulator CARLA with MATLAB-based mmWave channel modeling, and reflecting real-world conditions. The proposed CRKD achieves its objective by distilling relational information across different feature spaces, which enhances beam prediction performance without relying on expensive sensor data. Simulation results demonstrate that CRKD efficiently distills multimodal knowledge, allowing a radar-only model to achieve $94.62%$ of the teacher performance. In particular, this is achieved with just $10%$ of the teacher network's parameters, thereby significantly reducing computational complexity and dependence on multimodal sensor data.

cs.NI↗

arXiv2025

SemSpaceFL: A Collaborative Hierarchical Federated Learning Framework for Semantic Communication in 6G LEO Satellites

The advent of the sixth-generation (6G) wireless networks, enhanced by artificial intelligence, promises ubiquitous connectivity through Low Earth Orbit (LEO) satellites. These satellites are capable of collecting vast amounts of geographically diverse and real-time data, which can be immensely valuable for training intelligent models. However, limited inter-satellite communication and data privacy constraints hinder data collection on a single server for training. Therefore, we propose SemSpaceFL, a novel hierarchical federated learning (HFL) framework for LEO satellite networks, with integrated semantic communication capabilities. Our framework introduces a two-tier aggregation architecture where satellite models are first aggregated at regional gateways before final consolidation at a cloud server, which explicitly accounts for satellite mobility patterns and energy constraints. The key innovation lies in our novel aggregation approach, which dynamically adjusts the contribution of each satellite based on its trajectory and association with different gateways, which ensures stable model convergence despite the highly dynamic nature of LEO constellations. To further enhance communication efficiency, we incorporate semantic encoding-decoding techniques trained through the proposed HFL framework, which enables intelligent data compression while maintaining signal integrity. Our experimental results demonstrate that the proposed aggregation strategy achieves superior performance and faster convergence compared to existing benchmarks, while effectively managing the challenges of satellite mobility and energy limitations in dynamic LEO networks.

cs.IT↗

arXiv2024

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

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.

cs.NI↗

arXiv2024

Enhancing Spectrum Efficiency in 6G Satellite Networks: A GAIL-Powered Policy Learning via Asynchronous Federated Inverse Reinforcement Learning

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 $14.6\%$ improvement in convergence and reward value. The novel GAIL-driven policy learning establishes a novel benchmark for 6G NTN optimization.

cs.NI↗

arXiv2024

Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach

Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) provides 360-degree full-space coverage, optimizing both transmission and reflection for improved network performance and dynamic control of the indoor environment. However, deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication. To address these, we formulate an optimization problem involving user assignment, access point (AP) beamforming, and STAR-RIS phase control. A decomposition approach is used to solve the complex problem efficiently, employing a many-to-one matching algorithm for user-AP assignment and K-means clustering for resource management. Additionally, 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 in which each decision variable acts as an independent agent, enabling collaborative learning and decision making. The MADRL framework is enhanced by incorporating convex approximation (CA), which accelerates policy learning through suboptimal solutions from successive convex approximation (SCA), leading to faster adaptation and convergence. Simulations demonstrate significant improvements in network utility compared to baseline approaches.

cs.NI↗

arXiv2024

Joint UAV Deployment and Resource Allocation in THz-Assisted MEC-Enabled Integrated Space-Air-Ground Networks

Multi-access edge computing (MEC)-enabled integrated space-air-ground (SAG) networks have drawn much attention recently, as they can provide communication and computing services to wireless devices in areas that lack terrestrial base stations (TBSs). Leveraging the ample bandwidth in the terahertz (THz) spectrum, in this paper, we propose MEC-enabled integrated SAG networks with collaboration among unmanned aerial vehicles (UAVs). We then formulate the problem of minimizing the energy consumption of devices and UAVs in the proposed MEC-enabled integrated SAG networks by optimizing tasks offloading decisions, THz sub-bands assignment, transmit power control, and UAVs deployment. The formulated problem is a mixed-integer nonlinear programming (MILP) problem with a non-convex structure, which is challenging to solve. We thus propose a block coordinate descent (BCD) approach to decompose the problem into four sub-problems: 1) device task offloading decision problem, 2) THz sub-band assignment and power control problem, 3) UAV deployment problem, and 4) UAV task offloading decision problem. We then propose to use a matching game, concave-convex procedure (CCP) method, successive convex approximation (SCA), and block successive upper-bound minimization (BSUM) approaches for solving the individual subproblems. Finally, extensive simulations are performed to demonstrate the effectiveness of our proposed algorithm.

cs.NI↗

arXiv2023

Joint User Pairing and Beamforming Design of Multi-STAR-RISs-Aided NOMA in the Indoor Environment via Multi-Agent Reinforcement Learning

The development of 6G/B5G wireless networks, which have requirements that go beyond current 5G networks, is gaining interest from academia and industry. However, to increase 6G/B5G network quality, conventional cellular networks that rely on terrestrial base stations are constrained geographically and economically. Meanwhile, NOMA allows multiple users to share the same resources, which improves the spectral efficiency of the system and has the advantage of supporting a larger number of users. Additionally, by intelligently manipulating the phase and amplitude of both the reflected and transmitted signals, STAR-RISs can achieve improved coverage, increased spectral efficiency, and enhanced communication reliability. However, STAR-RISs must simultaneously optimize the amplitude and phase shift corresponding to reflection and transmission, which makes the existing terrestrial networks more complicated and is considered a major challenging issue. Motivated by the above, we study the joint user pairing for NOMA and beamforming design of Multi-STAR-RISs in an indoor environment. Then, we formulate the optimization problem with the objective of maximizing the total throughput of MUs by jointly optimizing the decoding order, user pairing, active beamforming, and passive beamforming. However, the formulated problem is a MINLP. To address this challenge, we first introduce the decoding order for NOMA networks. Next, we decompose the original problem into two subproblems, namely: 1) MU pairing and 2) Beamforming optimization under the optimal decoding order. For the first subproblem, we employ correlation-based K-means clustering to solve the user pairing problem. Then, to jointly deal with beamforming vector optimizations, we propose MAPPO, which can make quick decisions in the given environment owing to its low complexity.

cs.IT↗

arXiv2023

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

Satellite systems face a significant challenge in effectively utilizing limited communication resources to meet the demands of ground network traffic, characterized by asymmetrical spatial distribution and time-varying characteristics. Moreover, the coverage range and signal transmission distance of low Earth orbit (LEO) satellites are restricted by notable propagation attenuation, molecular absorption, and space losses in sub-terahertz (THz) frequencies. This paper introduces a novel approach to maximize LEO satellite coverage by leveraging reconfigurable intelligent surfaces (RISs) within 6G sub-THz networks. The optimization objectives encompass enhancing the end-to-end data rate, optimizing satellite-remote user equipment (RUE) associations, data packet routing within satellite constellations, RIS phase shift, and ground base station (GBS) transmit power (i.e., active beamforming). The formulated joint optimization problem poses significant challenges owing to its time-varying environment, non-convex characteristics, and NP-hard complexity. To address these challenges, we propose a block coordinate descent (BCD) algorithm that integrates balanced K-means clustering, multi-agent proximal policy optimization (MAPPO) deep reinforcement learning (DRL), and whale optimization (WOA) techniques. The performance of the proposed approach is demonstrated through comprehensive simulation results, exhibiting its superiority over existing baseline methods in the literature.

cs.NI↗

arXiv2023

Satellite-based ITS Data Offloading & Computation in 6G Networks: A Cooperative Multi-Agent Proximal Policy Optimization DRL with Attention Approach

The proliferation of intelligent transportation systems (ITS) has led to increasing demand for diverse network applications. However, conventional terrestrial access networks (TANs) are inadequate in accommodating various applications for remote ITS nodes, i.e., airplanes and ships. In contrast, satellite access networks (SANs) offer supplementary support for TANs, in terms of coverage flexibility and availability. In this study, we propose a novel approach to ITS data offloading and computation services based on SANs. We use low-Earth orbit (LEO) and cube satellites (CubeSats) as independent mobile edge computing (MEC) servers that schedule the processing of data generated by ITS nodes. To optimize offloading task selection, computing, and bandwidth resource allocation for different satellite servers, we formulate a joint delay and rental price minimization problem that is mixed-integer non-linear programming (MINLP) and NP-hard. We propose a cooperative multi-agent proximal policy optimization (Co-MAPPO) deep reinforcement learning (DRL) approach with an attention mechanism to deal with intelligent offloading decisions. We also decompose the remaining subproblem into three independent subproblems for resource allocation and use convex optimization techniques to obtain their optimal closed-form analytical solutions. We conduct extensive simulations and compare our proposed approach to baselines, resulting in performance improvements of 9.9%, 5.2%, and 4.2%, respectively.

cs.NI↗

arXiv2023

Federated Learning with Intermediate Representation Regularization

In contrast to centralized model training that involves data collection, federated learning (FL) enables remote clients to collaboratively train a model without exposing their private data. However, model performance usually degrades in FL due to the heterogeneous data generated by clients of diverse characteristics. One promising strategy to maintain good performance is by limiting the local training from drifting far away from the global model. Previous studies accomplish this by regularizing the distance between the representations learned by the local and global models. However, they only consider representations from the early layers of a model or the layer preceding the output layer. In this study, we introduce FedIntR, which provides a more fine-grained regularization by integrating the representations of intermediate layers into the local training process. Specifically, FedIntR computes a regularization term that encourages the closeness between the intermediate layer representations of the local and global models. Additionally, FedIntR automatically determines the contribution of each layer's representation to the regularization term based on the similarity between local and global representations. We conduct extensive experiments on various datasets to show that FedIntR can achieve equivalent or higher performance compared to the state-of-the-art approaches. Our code is available at https://github.com/YLTun/FedIntR.

cs.LG↗

arXiv2022

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

In the realm of wireless communications in 5G, 6G and beyond, deploying unmanned aerial vehicle (UAV) has been an innovative approach to extend the coverage area due to its easy deployment. Moreover, reconfigurable intelligent surface (RIS) has also emerged as a new paradigm with the goals of enhancing the average sum-rate as well as energy efficiency. By combining these attractive features, an energy-efficient RIS-mounted multiple UAVs (aerial RISs: ARISs) assisted downlink communication system is studied. Due to the obstruction, user equipments (UEs) can have a poor line of sight to communicate with the base station (BS). To solve this, multiple ARISs are implemented to assist the communication between the BS and UEs. Then, the joint optimization problem of deployment of ARIS, ARIS reflective elements on/off states, phase shift, and power control of the multiple ARISs-assisted communication system is formulated. The problem is challenging to solve since it is mixed-integer, non-convex, and NP-hard. To overcome this, it is decomposed into three sub-problems. Afterwards, successive convex approximation (SCA), actor-critic proximal policy optimization (AC-PPO), and whale optimization algorithm (WOA) are employed to solve these sub-problems alternatively. Finally, extensive simulation results have been generated to illustrate the efficacy of our proposed algorithms.

cs.NI↗

arXiv2022

Joint Trajectory and Resource Optimization of MEC-Assisted UAVs in Sub-THz Networks: A Resources-based Multi-Agent Proximal Policy Optimization DRL with Attention Mechanism

THz band communication technology will be used in the 6G networks to enable high-speed and high-capacity data service demands. However, THz-communication losses arise owing to limitations, i.e., molecular absorption, rain attenuation, and coverage range. Furthermore, to maintain steady THz-communications and overcome coverage distances in rural and suburban regions, the required number of BSs is very high. Consequently, a new communication platform that enables aerial communication services is required. Furthermore, the airborne platform supports LoS communications rather than NLoS communications, which helps overcome these losses. Therefore, in this work, we investigate the deployment and resource optimization for MEC-enabled UAVs, which can provide THz-based communications in remote regions. To this end, we formulate an optimization problem to minimize the sum of the energy consumption of both MEC-UAV and MUs and the delay incurred by MUs under the given task information. The formulated problem is a MINLP problem, which is NP-hard. We decompose the main problem into two subproblems to address the formulated problem. We solve the first subproblem with a standard optimization solver, i.e., CVXPY, due to its convex nature. To solve the second subproblem, we design a RMAPPO DRL algorithm with an attention mechanism. The considered attention mechanism is utilized for encoding a diverse number of observations. This is designed by the network coordinator to provide a differentiated fit reward to each agent in the network. The simulation results show that the proposed algorithm outperforms the benchmark and yields a network utility which is $2.22\%$, $15.55\%$, and $17.77\%$ more than the benchmarks.

cs.NI↗

arXiv2022

Dependency Tasks Offloading and Communication Resource Allocation in Collaborative UAVs Networks: A Meta-Heuristic Approach

In recent years, unmanned aerial vehicles (UAVs) assisted mobile edge computing systems have been exploited by researchers as a promising solution for providing computation services to mobile users outside of terrestrial infrastructure coverage. However, it remains challenging for the standalone MEC-enabled UAVs in order to meet the computation requirement of numerous mobile users due to the limited computation capacity of their onboard servers and battery lives. Therefore, we propose a collaborative scheme among UAVs so that UAVs can share the workload with idle UAVs. Moreover, current task offloading strategies frequently overlook task topology, which may result in poor performance or even system failure. To address the problem, we consider offloading tasks consisting of a set of sub-tasks, and each sub-task has dependencies on other sub-tasks, which is practical in the real world. Sub-tasks with dependencies need to wait for the resulting signal from preceding sub-tasks before being executed. This mechanism has serious effects on the offloading strategy. Then, we formulate an optimization problem to minimize the average latency experienced by users by jointly controlling the offloading decision for dependent tasks and allocating the communication resources of UAVs. The formulated problem appears to be NP-hard and cannot be solved in polynomial time. Therefore, we divide the problem into two sub-problems: the offloading decision problem and the communication resource allocation problem. Then a meta-heuristic method is proposed to find the sub-optimal solution of the task offloading problem, while the communication resource allocation problem is solved by using convex optimization. Finally, we perform substantial simulation experiments, and the result shows that the proposed offloading technique effectively minimizes the average latency of users, compared with other benchmark schemes.

cs.NI↗

arXiv2022

3TO: THz-Enabled Throughput and Trajectory Optimization of UAVs in 6G Networks by Proximal Policy Optimization Deep Reinforcement Learning

Next-generation networks need to meet ubiquitous and high data-rate demand. Therefore, this paper considers the throughput and trajectory optimization of terahertz (THz)-enabled unmanned aerial vehicles (UAVs) in the sixth-generation (6G) communication networks. In the considered scenario, multiple UAVs must provide on-demand terabits per second (TB/s) services to an urban area along with existing terrestrial networks. However, THz-empowered UAVs pose some new constraints, e.g., dynamic THz-channel conditions for ground users (GUs) association and UAV trajectory optimization to fulfill GU's throughput demands. Thus, a framework is proposed to address these challenges, where a joint UAVs-GUs association, transmit power, and the trajectory optimization problem is studied. The formulated problem is mixed-integer non-linear programming (MINLP), which is NP-hard to solve. Consequently, an iterative algorithm is proposed to solve three sub-problems iteratively, i.e., UAVs-GUs association, transmit power, and trajectory optimization. Simulation results demonstrate that the proposed algorithm increased the throughput by up to 10%, 68.9%, and 69.1% respectively compared to baseline algorithms.

cs.NI↗

arXiv2021

A Business Model for Resource Sharing in Cell-Free UAVs-Assisted Wireless Networks

Unmanned aerial vehicles (UAVs) are widely deployed to enhance the wireless network capacity and to provide communication services to mobile users beyond the infrastructure coverage. Recently, with the help of a promising technology called network virtualization, multiple service providers (SPs) can share the infrastructures and wireless resources owned by the mobile network operators (MNOs). Then, they provide specific services to their mobile users using the resources obtained from MNOs. However, wireless resource sharing among SPs is challenging as each SP wants to maximize their utility/profit selfishly while satisfying the QoS requirement of their mobile users. Therefore, in this paper, we propose joint user association and wireless resource sharing problem in the cell-free UAVs-assisted wireless networks with the objective of maximizing the total network utility of the SPs while ensuring QoS constraints of their mobile users and the resource constraints of the UAVs deployed by MNOs. To solve the proposed mixed-integer non-convex problem, we decompose the proposed problem into two subproblems: users association, and resource sharing problems. Then, a two-sided matching algorithm is deployed in order to solve users association problem. We further deploy the whale optimization and Lagrangian relaxation algorithms to solve the resource sharing problem. Finally, extensive numerical results are provided in order to show the effectiveness of our proposed algorithm.

cs.NI↗

arXiv2021

Trajectory Optimization and Phase-Shift Design in IRS Assisted UAV Network for High Speed Trains

The recent trend towards the high-speed transportation system has spurred the development of high-speed trains (HSTs). However, enabling HST users with seamless wireless connectivity using the roadside units (RSUs) is extremely challenging, mostly due to the lack of line of sight link. To address this issue, we propose a novel framework that uses intelligent reflecting surfaces (IRS)-enabled unmanned aerial vehicles (UAVs) to provide line of sight communication to HST users. First, we formulate the optimization problem where the objective is to maximize the minimum achievable rate of HSTs by jointly optimizing the trajectory of UAV and the phase-shift of IRS. Due to the non-convex nature of the formulated problem, it is decomposed into two subproblems: IRS phase-shift problem and UAV trajectory optimization problem. Next, a Binary Integer Linear Programming (BILP) and a Soft Actor-Critic (SAC) are constructed in order to solve our decomposed problems. Finally, comprehensive numerical results are provided in order to show the effectiveness of our proposed framework.

cs.NI↗