Yuanyuan Wang

Yuanyuan Wang

Auto-generated profile, based on publicly available information

Yuanyuan Wang

School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2024 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
YWYuanyuan Wang
Yuanyuan Wang
CZChi Zhang
Chi Zhang
TGTaiheng Ge
Taiheng Ge
Miao PanMiao Pan
Miao Pan
The exponential growth of Internet of Things (IoT) devices and emerging applications have significantly increased the requirements for ubiquitous connectivity and efficient computing paradigms. Traditional terrestrial edge computing architectures cannot provide massive IoT connectivity worldwide. In this paper, we propose an aerial hierarchical mobile edge computing system composed of high-altitude platforms (HAPs) and unmanned aerial vehicles (UAVs). In particular, we consider non-divisible tasks and formulate a task offloading problem to minimize the long-term processing cost of tasks while satisfying the queueing mechanism in the offloading procedure and processing procedure of tasks. We propose a multi-agent deep reinforcement learning (DRL) based computation offloading algorithm in which each device can make its offloading decision according to local observations. Due to the limited computing resources of UAVs, high task loads of UAVs will increase the ratio of abandoning offloaded tasks. To increase the success ratio of completing tasks, the convolutional LSTM (ConvLSTM) network is utilized to estimate the future task loads of UAVs. In addition, a prioritized experience replay (PER) method is proposed to increase the convergence speed and improve the training stability. The experimental results demonstrate that the proposed computation offloading algorithm outperforms other benchmark methods.

18 January 2024 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
YWYuanyuan Wang
Yuanyuan Wang
CZChi Zhang
Chi Zhang
TGTaiheng Ge
Taiheng Ge
Miao PanMiao Pan
Miao Pan
Due to the wide coverage and station-keeping feature of high altitude platforms (HAPs), a large-area sensor network above remote regions can be achieved by the use of a mobile HAP ad hoc network. To realize efficient data transmission in the HAP network, we propose two schemes at the network layer and MAC layer, respectively. At the network layer, we propose a break and reconstitution (B&R) algorithm to construct an aggregation tree with minimum convergecast delay (MCD) for collecting data generated by each HAP. This scheme is beneficial in many monitoring systems, especially for time-critical and safety-critical tasks. In addition, a rapid parent selection (RPS) algorithm is presented to deal with the dynamic changes in the HAP network. At the MAC layer, we utilize a particle swarm optimization algorithm to optimize transmission and reception beamwidths to maximize the minimum transmission data rate. This scheme is beneficial for supporting tremendous data in the HAP network. Finally, we evaluate the performance of our proposed schemes through extensive experiments with real wind data and results show that they outperform some baseline approaches.


14 November 2025 in IEEE Access
Verified
Journal Article
Open access
YWYuanyuan Wang
Yuanyuan Wang
JLJing Liu
Jing Liu
KLKun Liu
Kun Liu
The sixth generation (6G) of wireless communication system aims to provide global coverage for remote user equipments in the depopulated areas, especially those have marine activities. High altitude platforms are expected to improve the communication connectivity for maritime network. In this paper, we propose a novel high altitude balloon-enabled maritime network (HABMN) architecture, in which controllers can configure the network according to specific transmission requests. Then, we present a space-time graph to illustrate the predictable dynamics of the HABMN and formulate a multi-commodity flow problem to maximize the total amount of received data. Considering unpredictable network changes, the controller should recompute the optimal routing policy. However, frequent network reconfiguration will lower the system stability. Hence we propose a greedy update policy which minimizes the time-average optimality gap while respecting a network reconfiguration budget. Finally, extensive simulation experiments evaluate our proposed update policy.