Haojie Lin

Haojie Lin

Auto-generated profile, based on publicly available information

Haojie Lin

School of Aeronautics and Astronautics, University of Electronic Science and Technology of China, Chengdu, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
27 June 2023 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
WHWenjing Hou
Wenjing Hou
HWHong Wen
Hong Wen
NZNing Zhang
Ning Zhang
WLWenxin Lei
Wenxin Lei
HLHaojie Lin
Haojie Lin
QLQiang Liu
Qiang Liu
Multi-tier computing (MC) utilizes computing resources from the cloud, fog, edge, and end layers to promote intelligent Internet of Things (IoT) applications. Federated learning (FL) in MC offers a prospective distributed and privacy-preserving framework to deploy deep learning applications in different layers. Due to time-varying network topologies, wireless channel states, and computational workloads, MC faces a dynamic and uncertain environment, which poses additional challenges to FL task processing. In this paper, we propose a novel adaptive training and aggregation federated learning (ATAFL) framework. Specifically, local model training can be performed at end devices, edge nodes, and fog nodes. The global aggregator can choose from the edge, fog, and cloud layers. A joint optimization problem of training, aggregation node selection, and resource allocation is further formulated to minimize system latency and energy consumption. Moreover, digital twin and deep reinforcement learning (DRL) techniques are integrated into the MC network to design optimal node selection and resource allocation strategies based on captured state information of the MC system. We implement a prototype, and experimental results show that our proposed DRL-based algorithm reduces system latency and energy consumption compared with the benchmark algorithms.

1 April 2019 in Journal of Microbiological Methods
Verified
Journal Article
Closed access
BZBo Zhang
Bo Zhang
YMYibeibaihan Maimaiti
Yibeibaihan Maimaiti
CLChunyan Liu
Chunyan Liu
JLJing Li
Jing Li
HWHaiye Wang
Haiye Wang
XZXin Zhang
Xin Zhang

28 January 2021
Verified
Conference Paper
Open access
HLHaojie Lin
Haojie Lin
WHWenjing Hou
Wenjing Hou
HWHong Wen
Hong Wen
WLWenxin Lei
Wenxin Lei
SWSihui Wu
Sihui Wu
ZCZhiwei Chen
Zhiwei Chen
With the development of the Internet of Things, the number of smart devices connected to the 6th generation wireless mobile network (6G) has increased dramatically, which will produce a variety of real-time application scenarios. Edge computing is close to terminal equipment, which can improve user experience and reduce network costs. However, due to the coexistence of multi-dimensional network resources, heterogeneous network devices, and complex and time-varying network structures, this brings unprecedented challenges to wireless networks, and it is difficult to meet the needs of terminal devices for ultra-low latency, high reliability, and low power consumption services. The next generation edge computing architecture is considered to be an effective solution to the time sensitive network and communication congestion. This paper integrates artificial intelligence into the edge computing architecture, and proposes a multi-agent deep deterministic strategy gradient (MADDPG), which maximizes processing efficiency by jointly optimizing task hierarchical offloading and resource allocation.