Yu Wang

Yu Wang

Auto-generated profile, based on publicly available information

Yu Wang

8th Geological Brigade of Hebei Bureau of Geology and Mineral Resources Exploration and Hebei Provincial Innovation Center for Marine Intelligent Perception and Big Data Application Technology, Qinhuangdao, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 July 2023 in Transactions on Emerging Telecommunications Technologies
Verified
Journal Article
Closed access
XSXin Song
Xin Song
YWYu Wang
Yu Wang
ZXZhigang Xie
Zhigang Xie
RZRunfeng Zhang
Runfeng Zhang
SXSiyang Xu
Siyang Xu

16 February 2026 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
SXSiyang Xu
Siyang Xu
ZFZe Fan
Ze Fan
ZZZijian Zhou
Zijian Zhou
QLQiuyu Lu
Qiuyu Lu
BZBiao Zhang
Biao Zhang
XSXin Song
Xin Song
To enable compute-intensive and delay-sensitive maritime services, unmanned surface vessels (USVs) can offload tasks to mobile edge computing (MEC) servers mounted on unmanned aerial vehicles (UAVs). However, jointly minimizing energy consumption and latency is challenging due to the strong coupling between communication, computation, and mobility under stringent quality-of-service (QoS) requirements. To capture this trade-off, we formulate a weighted energy–delay minimization problem that jointly optimizes one-to-one UAV–USV scheduling, task partitioning, and UAV trajectory. The resulting problem is particularly difficult due to a hybrid discrete–continuous decision space and strong temporal coupling under stringent feasibility constraints. To address this mixed-integer nonconvex optimization problem, we reformulate it as a Markov decision process (MDP) and develop a constraint-aware OU–TD3 algorithm that integrates differentiable scheduling relaxation, feasibility-aware action mapping, and adaptive OU–Gaussian mixed exploration for stable learning in high-dimensional continuous control. We further extend the formulation and solution to a cooperative multi-UAV MEC setting with signal-to-interference-plus-noise ratio (SINR)-coupled interference and coordination constraints. Extensive simulations with statistical evaluation demonstrate stable convergence and up to 54.2% cost reduction over baseline schemes, while maintaining robustness under realistic maritime disturbances.

12 June 2024 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
XSXin Song
Xin Song
YWYu Wang
Yu Wang
SXSiyang Xu
Siyang Xu
RZRunfeng Zhang
Runfeng Zhang
YZYuqi Zhang
Yuqi Zhang
ZXZhigang Xie
Zhigang Xie
The integration of electric vehicles (EVs) into the power grid has led to a significant increase in load demand. However, the absence of efficient edge computing services for charging EVs poses challenges to the grid's safe and stable operation. Our study proposes an intelligent reflective surface (IRS)-assisted air-to-ground task offloading network for charging EVs that utilizes tethered unmanned aerial vehicles (tUAVs) equipped with IRS for task transmission to provide efficient edge computing services. The network architecture includes single-IRS and double-IRS links to enhance communication efficiency, while EVs are equipped with Network in Box (NIB) units to provide flexible computing power. We formulate a multi-objective optimization problem aimed at minimizing transmission obstacle, power purchase cost, transmission delay, and failure rate in the network. Since the optimization problem is NP-hard, we propose an improved Self-Learning Discrete Jaya (SD-Jaya) algorithm which finds the offloading strategy using historical knowledge and the selection of strategy-related operators. Moreover, we develop a novel tournament-based algorithm to select the Pareto layer in the multi-objective problem. Simulation results show that the proposed algorithm is able to find better non-dominated solutions. The power purchase cost of the proposed scheme is 43% and 54% lower than that of the single-IRS scheme and the local scheme, respectively.

7 July 2023
Verified
Conference Paper
Closed access
XSXin Song
Xin Song
YWYu Wang
Yu Wang
RZRunfeng Zhang
Runfeng Zhang
SXSiyang Xu
Siyang Xu
YZYuqi Zhang
Yuqi Zhang
ZXZhigang Xie
Zhigang Xie
Nowadays, the connection of electric vehicles (EVs) to the grid leads to significant load growth, which is a challenge for the safe and stable operation of the grid. In vehicle edge computing networks, as grid-charged EVs offloading tasks, offloading strategy optimization is a crucial method of reducing power purchase from the grid by EVs. Therefore, we first construct an intelligent reflecting surface (IRS)-aided task offloading networks for charging EVs, innovatively employing tethered UAVs (tUAVs) equipped with IRS to transmit the task. Communication efficiency can be improved by choosing single-IRS or double-IRS links. In addition, EV is equipped with the network in box (NIB) to provide flexible computing power. Subsequently, the multi-objective problem of minimizing transmission obstacle, power purchase cost, and transmission delay is formulated. However, finding the Pareto front for such a multi-objective optimization problem in this paper is challenging. An improved SD-Jaya algorithm is proposed to obtain the selection of policy operators through historical knowledge. The simulation results illustrate that the proposed algorithm can get better non-dominated solutions.