Jinglin Shi

Jinglin Shi

Auto-generated profile, based on publicly available information

Jinglin Shi

State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
15 July 2024 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
QCQing Cai
Qing Cai
YZYiqing Zhou
Yiqing Zhou
LLLing Liu
Ling Liu
YQYanli Qi
Yanli Qi
JSJinglin Shi
Jinglin Shi
Collaborative mobile edge computing enables resource-constrained edge facilities to work cooperatively for computation-intensive tasks. However, as the number of tasks demanded by various applications increases, resource competition is inevitable in edge facilities. Existing works tackle the resource competition problem with a first come first served (FCFS) scheme, which is blind to different delay requirements among tasks. This may result in tasks with higher delay requirements waiting a long time for service, thereby reducing overall service quality. This paper proposes a prioritized queuing scheme with task dependency (PQTD), which allows high-prioritized sub-tasks with higher delay requirements to jump into the queue ahead of low-prioritized sub-tasks with lower delay requirements. To describe the complicated delay change caused by queue-jumping, a joint DAG-queue delay (JDQD) model is proposed, which analyzes the chain reaction of delay changes caused by the processing queue on the server and the task dependency. With JDQD, a multi-task assignment optimization problem is formulated to maximize the average satisfaction degree (AvgSatD), which is defined according to the priorities of the tasks and their delay requirements. Then, a tree-based algorithm is proposed to solve the NP-hard optimization problem, i.e., Monte Carlo Tree Search (MCTS). Simulation results demonstrate the effectiveness of the PQTD queuing scheme and tree search mechanism of MCTS. Overall, PQTD + MCTS can increase AvgSatD by at least 45.8% with an acceptable complexity.

18 February 2025 in Sensors
Verified
Journal Article
Open access
PDF file
YCYan Chen
Yan Chen
HCHuan Cao
Huan Cao
LWLonghe Wang
Longhe Wang
DCDaojin Chen
Daojin Chen
ZLZifan Liu
Zifan Liu
JSJinglin Shi
Jinglin Shi
Low-orbit satellite communication networks have gradually become the research focus of fifth-generation (5G) beyond and sixth generation (6G) networks due to their advantages of wide coverage, large communication capacity, and low terrain influence. However, the low earth orbit mega satellite network (LEO-MSN) also has difficulty in constructing stable traffic transmission paths, network load imbalance and congestion due to the large scale of network nodes, a highly complex topology, and uneven distribution of traffic flow in time and space. In the service-based architecture proposed by 3GPP, the introduction of service function chain (SFC) constraints exacerbates these challenges. Therefore, in this paper, we propose GDRL-SFCR, an end-to-end routing decision method based on graph neural network (GNN) and deep reinforcement learning (DRL) which jointly optimize the end-to-end transmission delay and network load balancing under SFC constraints. Specifically, this method constructs the system model based on the latest NTN low-orbit satellite network end-to-end transmission architecture, taking into account the SFC constraints, transmission delays, and network node loads in the end-to-end traffic transmission, uses a GNN to extract node attributes and dynamic topology features, and uses the DRL method to design specific reward functions to train the model to learn routing policies that satisfy the SFC constraints. The simulation results demonstrate that, compared with graph theory-based methods and reinforcement learning-based methods, GDRL-SFCR can reduce the end-to-end traffic transmission delay by more than 11.3%, reduce the average network load by more than 14.1%, and increase the traffic access success rate and network capacity by more than 19.1% and two times, respectively.

18 June 2018 in IEEE Communications Magazine
Verified
Journal Article
Closed access
MGMingjin Gao
Mingjin Gao
JLJun Li
Jun Li
Dushantha Nalin K. JAYAKODYDushantha Nalin K. JAYAKODY
Dushantha Nalin K. JAYAKODY
HCHe CHEN
He CHEN
YLYonghui Lee
Yonghui Lee
JSJinglin Shi
Jinglin Shi
To meet the explosive growth of mobile data traffic, ultra-dense networks have emerged to enhance spatial and spectral efficiency. Densely deployed small cell architecture faces several major challenges, including low infrastructure utilization ratio, severe inter-cell interference, and so on. In this article, we aim to develop a novel super base station (SupBS) network architecture to tackle these issues. The proposed SupBS architecture consists of two layers, namely, an infrastructure layer and a virtualized network layer. In the infrastructure layer, there are three key physical components: the hybrid heterogeneous radio unit pool, line interface switch unit, and computing resources pool. In the virtualized network layer, there are two logical modules designed on top of the three physical components, namely, the virtualized base station and virtualized software defined core network. The two logical modules are designed to facilitate the use of the underlying three physical components by reducing the energy consumption and processing delay. We present the functionalities of the two virtualized modules and explain how they are utilized to create virtual networks. Moreover, we demonstrate a recently developed SupBS prototype, and provide an application scenario for this prototype in an Internet information broadcast-storage system to show the advantages of our architecture.

10 January 2024 in IEEE Network
Verified
Journal Article
Closed access
YQYanli Qi
Yanli Qi
YZYiqing Zhou
Yiqing Zhou
QCQing Cai
Qing Cai
HZHaoyue Zhang
Haoyue Zhang
YXYaxing Xu
Yaxing Xu
SLShaoyang Li
Shaoyang Li
With the spread of emerging services, multi-dimensional extreme performance requirements have been put forward for the sixth generation (6G) networks. The integration of sensing, communications, and computing (ISCAC) is expected to transform the 6G networks from simple transmission pipelines to smart infrastructures with enhanced capabilities. To help the 6G networks live up to their potential, we firstly design a three-dimensional ISCAC network architecture from the perspectives of network space, horizontal functionality, and vertical functionality. Next, we propose two performance indicators for the ISCAC network to map the multi-dimensional resources into the same evaluation system. Based on the proposed indicator, an AoI-enabled resource management mechanism is developed. Finally, performance evaluations are carried out and the time average expectation of AoI can be reduced by up to 36.39% compared with the existing mechanism.

29 September 2022 in Sensors
Verified
Journal Article
Open access
PDF file
ZZZixu Zhao
Zixu Zhao
YZYucheng Zhang
Yucheng Zhang
JSJinglin Shi
Jinglin Shi
LLLong Long
Long Long
ZLZaiwang Lu
Zaiwang Lu
Unmanned ground vehicles (UGVs) are making more and more progress in many application scenarios in recent years, such as exploring unknown wild terrain, working in precision agriculture and serving in emergency rescue. Due to the complex ground conditions and changeable surroundings of these unstructured environments, it is challenging for these UGVs to obtain robust and accurate state estimations by using sensor fusion odometry without prior perception and optimization for specific scenarios. In this paper, based on an error-state Kalman filter (ESKF) fusion model, we propose a robust lidar-inertial odometry with a novel ground condition perception and optimization algorithm specifically designed for UGVs. The probability distribution gained from the raw inertial measurement unit (IMU) measurements during a certain time period and the state estimation of ESKF were both utilized to evaluate the flatness of ground conditions in real-time; then, by analyzing the relationship between the current ground condition and the accuracy of the state estimation, the tightly coupled lidar-inertial odometry was dynamically optimized further by adjusting the related parameters of the processing algorithm of the lidar points to obtain robust and accurate ego-motion state estimations of UGVs. The method was validated in various types of environments with changeable ground conditions, and the robustness and accuracy are shown through the consistent accurate state estimation in different ground conditions compared with the state-of-art lidar-inertial odometry systems.

8 September 2020 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
QSQian Sun
Qian Sun
LTLin Tian
Lin Tian
YZYiqing Zhou
Yiqing Zhou
JSJinglin Shi
Jinglin Shi
YWYuanyuan Wang
Yuanyuan Wang
ZZZongshuai Zhang
Zongshuai Zhang
In the fifth generation (5G) networks, isolated logical slices are formed by the same infrastructure and spectrum resource. In the coverage regions of the sharing access points (APs), device to device (D2D) communication can occur among different slices, i.e., one mobile terminal (MT) acts as a D2D relay for another MT serving by a different slice. Since the slices and the MTs are selfish who will not help others voluntarily, this paper proposes a two-layered incentive scheme to stimulate cooperation. To achieve this, two resource allocating problems of the proposed incentive scheme are formulated which introducing the slices' and the MTs' cooperative activities, thus more resources will be allocated to the cooperative slices and MTs as reward. Since the slices' and the MTs' instantaneous resource allocations can not be obtained by the two optimal problems, the incentive scheduling algorithms of the slices and the MTs are designed. Finally, we define the isolation indexes to evaluate the slice isolation when carrying out cooperation. By simulating, it is proved that the proposed incentive scheme can stimulate cooperation efficiently, since the throughputs of the cooperative slices and MTs are both improved. And the proposed incentive scheme is helpful for the slices and the MTs to meet the statistical service quality requirements and brings the bad effect to the instantaneous service quality requirements.