Wei Huangfu

Dr. Wei Huangfu

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
28 March 2023 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
YQYunhui Qin
Yunhui Qin
ZZZhongshan Zhang
Zhongshan Zhang
XLXulong Li
Xulong Li
WHWei Huangfu
Wei Huangfu
HZHaijun Zhang
Haijun Zhang
In this paper, multi-UAVs serve as mobile aerial ISAC platforms to sense and communicate with on-ground target users. To optimize the communication and sensing performance, we formulate a joint user association, UAV trajectory planning and power allocation problem to maximize the minimum weighted spectral efficiency among UAVs. This paper exploits the centralized and the decentralized deep reinforcement learning (DRL) solutions to solve the sequential decision-making problem. On one hand, we first introduce the centralized soft actor-critic (SAC) algorithm. Then, we explore the equivalent transformation of the optimization objective based on symmetric group, propose the random and the adaptive data augmentation schemes to design the replay memory buffer of SAC, and accordingly propose SAC algorithms assisted by data augmentation to tackle the transformed problem. On the other hand, the multi-agent soft actor-critic (MASAC), a decentralized solution, is also introduced to solve this sequential decision-making problem. The experiment results reveal the effectiveness of the centralized and the decentralized solutions in considered scenarios. Specifically, the SAC assisted by the adaptive scheme significantly outperforms other centralized solutions in the training speed and the weighted spectral efficiency. Meanwhile, the decentralized MASAC algorithm behaves best in the early training speed.

24 March 2020 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
HZHaijun Zhang
Haijun Zhang
NYNing Yang
Ning Yang
WHWei Huangfu
Wei Huangfu
KLKeping Long
Keping Long
Victor C. M. LeungVictor C. M. Leung
Victor C. M. Leung
In the current researches, artificial intelligence (AI) plays a crucial role in resource management for the next generation wireless communication network. However, traditional RL cannot solve the continuous and high dimensional problems. To handle this problems, the concept of deep neural network (DNN) is introduced into RL to solve high dimensional problems. In this paper, we first construct an information interaction model among primary user (PU), secondary user (SU) and wireless sensors in a cognitive radio system. In the model, the SU is unable to get the power allocation information of the PU, and needs to use the received signal strengths (RSSs) of the wireless sensors to adjust its own power. The PU allocates transmit power relying on its power control scheme. We propose an asynchronous advantage actor critic (A3C)-based power control of SU that is a parallel actor-learners framework with root mean square prop (RMSProp) optimization. Multiple SUs learn power control scheme simultaneously on different CPU threads, reducing neural network gradient update interdependence. To further improve the efficiency of spectrum sharing, the distributed proximal policy optimization (DPPO)-based power control is proposed which is an asynchronous variant of actor-critic with adaptive moment (Adam) optimization. It enables the network to converge quickly. After several power adjustments, the PU and the SU meet quality of service (QoS) requirements and achieve spectrum sharing.

7 May 2019 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
YLYaxi Liu
Yaxi Liu
WHWei Huangfu
Wei Huangfu
HZHaijun Zhang
Haijun Zhang
KLKeping Long
Keping Long
Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and tilts of antennas is focused and the existing approaches are mainly gradient-free methods. A standard gradient descent algorithm and its improved version, namely a Stochastic Gradient Descent (SGD) algorithm are proposed on the basis of a novel coverage indicator, named as the soft coverage indicator, to approximate the hard version of the original coverage indicator. We prove that the gradient vector is sparse, which accelerates gradient calculation, due to the number limitation of base stations within a specific distance from a given sampling point even if there are many decision variables of azimuths and tilts. Also, the SGD algorithm only requires a small amount of computation based on cheap estimates of the gradients, and thus is applicable to large-scale networks in an efficient manner. Experiments show that the proposed approaches perform well both in their near-optimal solutions and in their computation efficiency compared with the meta-heuristic algorithms. The extensibility and practicality of the proposed algorithms are also discussed.

26 April 2022 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
YLYaxi Liu
Yaxi Liu
WHWei Huangfu
Wei Huangfu
Huan ZhouHuan Zhou
Huan Zhou
HZHaijun Zhang
Haijun Zhang
JLJiangchuan Liu
Jiangchuan Liu
KLKeping Long
Keping Long
Unmanned Aerial Vehicle (UAV) Base Station (BS) placement optimization is an essential operational task to improve the Quality of Service (QoS) in UAV-aided wireless cellular networks. The existing approaches are almost zeroth order methods, and the few first order methods mainly ignore the allocation fairness, computational efficiency, and backhaul constraints. In this paper, we formulate the UAV placement problem as a constrained optimization problem, with the objective of maximizing the fair coverage versus energy consumption while satisfying the backhaul constraints at different time nodes. To guarantee fair QoS allocation, we introduce a novel fairness index to ensure fair communication opportunity and the novel region coverage ratio to avoid excess QoS on covered spots. An accurate and efficient proximal stochastic gradient descent based alternating algorithm that iteratively executes two optimization steps is proposed to optimize the UAV locations, which enables the fast single point-based first order methods to solve the complex problems with constraints. Experiment results manifest that the proposed algorithm performs well both in synthetic data scenario and in real city scenario. Furthermore, the proposed first order algorithm is more efficient than the existing zeroth order algorithm, typically referring to the meta-heuristic method.

4 September 2024 in Proceedings of the IEEE
Verified
Journal Article
Closed access
YLYaxi Liu
Yaxi Liu
THTianyao Huang
Tianyao Huang
FLFan Liu
Fan Liu
DMDingyou Ma
Dingyou Ma
WHWei Huangfu
Wei Huangfu
YEYonina C. Eldar
Yonina C. Eldar
Integrated sensing and communications (ISAC) has received considerable attention from both industry and academia. By sharing the spectrum and hardware platform, ISAC significantly reduces costs and improves spectral, energy, and hardware efficiencies. To support the large number of communication users (CUs) and sensing targets (STs), the design of multiple access (MA) is a fundamental issue in ISAC. MA techniques in ISAC are expected to avoid mutual interference between sensing and communicating functions under the critical constraints of both functions. In this article, we present an overview on approaches of MA for ISAC, from orthogonal transmission strategies to nonorthogonal ones, realized in time, frequency, code, spatial, delay–Doppler, power, and/or multiple domains. We discuss their individual implementation schemes and corresponding resource allocation strategies, as well as highlight future research opportunities.

4 December 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
XLXulong Li
Xulong Li
YQYunhui Qin
Yunhui Qin
JHJiahao Huo
Jiahao Huo
WHWei Huangfu
Wei Huangfu
Compared with centralized cloud computing, mobile edge computing (MEC) enables Internet of Things (IoT) devices to offload computation-intensive tasks to the edge of the network closer to them for processing, which can effectively save energy consumption of IoT devices and alleviate network congestion and high latency problems. However, the traditional terrestrial MEC system cannot adapt to scenarios such as rapid network recovery after disasters and emergency rescue due to its poor flexibility and high deployment cost, and assembling edge servers to unmanned aerial vehicles (UAVs) to assist in rapidly building mobile edge networks is a feasible solution. Therefore, this paper considers a multi-UAV-enabled MEC network with the optimization objectives of maximizing the processing success rate of computational tasks and fairness of system, while minimizing the processing delay of computational tasks. We investigate the computation offloading problem and the trajectory planning problem from the perspectives of IoT devices and UAVs, respectively. Then model them as Markov decision processes (MDPs) and propose a joint optimization scheme based on expert knowledge-assisted multi-agent reinforcement learning algorithms. Simulation results show that the proposed algorithm has significant advantages over baseline algorithms in terms of processing success rate and delay of computational tasks as well as fairness of the system.