Jinrong Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jinrong Li has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Biao Han
National university of defense technology, Changsha, China
2 shared publications - Congxi Song
National university of defense technology, Changsha, China
1 shared publication - Xiangyu Ju
National University of Defense Technology, Changsha, Hunan, China
1 shared publication - Xueqiang Han
Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
1 shared publication - Yitang Chen
National University of Defense Technology, Changsha, Hunan, China
1 shared publication
Latest Publications
- Open Access
- 16 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (7) , 1-23
Multi-agent DRL-based Multipath Scheduling for Video Streaming with QUIC
The popularization of video streaming brings challenges in satisfying diverse Quality of Service (QoS) requirements. The multipath extension of the Quick UDP Internet Connection (QUIC) protocol, also called MPQUIC, has the potential to improve video streaming performance with multiple simultaneously transmitting paths. The multipath scheduler of MPQUIC determines how to distribute the packets onto different paths. However, while applying current multipath schedulers into MPQUIC, our experimental results show that they fail to adapt to various receive buffer sizes of different devices and comprehensive QoS requirements of video streaming. These problems are especially severe under heterogeneous and dynamic network environments. To tackle these problems, we propose MARS, a Multi-agent deep Reinforcement learning (MADRL)-based Multipath QUIC Scheduler, which is able to promptly adapt to dynamic network environments. It exploits the MADRL method to learn a neural network for each path and generate scheduling policy. Besides, it introduces a novel multi-objective reward function that takes out-of-order queue size and different QoS metrics into consideration to realize adaptive scheduling optimization. We implement MARS in an MPQUIC prototype and deploy in Dynamic Adaptive Streaming over HTTP system. Then, we compare it with the state-of-the-art multipath schedulers in both emulated and real-world networks. Experimental results show that MARS outperforms the other schedulers with better adaptive capability regarding the receive buffer sizes and QoS.
- 16 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (7) , 1-23
Open AccessMulti-agent DRL-based Multipath Scheduling for Video Streaming with QUIC
The popularization of video streaming brings challenges in satisfying diverse Quality of Service (QoS) requirements. The multipath extension of the Quick UDP Internet Connection (QUIC) protocol, also called MPQUIC, has the potential to improve video streaming performance with multiple simultaneously transmitting paths. The multipath scheduler of MPQUIC determines how to distribute the packets onto different paths. However, while applying current multipath schedulers into MPQUIC, our experimental results show that they fail to adapt to various receive buffer sizes of different devices and comprehensive QoS requirements of video streaming. These problems are especially severe under heterogeneous and dynamic network environments. To tackle these problems, we propose MARS, a Multi-agent deep Reinforcement learning (MADRL)-based Multipath QUIC Scheduler, which is able to promptly adapt to dynamic network environments. It exploits the MADRL method to learn a neural network for each path and generate scheduling policy. Besides, it introduces a novel multi-objective reward function that takes out-of-order queue size and different QoS metrics into consideration to realize adaptive scheduling optimization. We implement MARS in an MPQUIC prototype and deploy in Dynamic Adaptive Streaming over HTTP system. Then, we compare it with the state-of-the-art multipath schedulers in both emulated and real-world networks. Experimental results show that MARS outperforms the other schedulers with better adaptive capability regarding the receive buffer sizes and QoS.
- Open Access
- 16 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 314-315
Demo: A Prototype for Detecting and Localizing Hidden Devices in Unfamiliar Environments
We have designed PanguVision: an Android software system that can be deployed on personal handheld devices (cell phones, PCs, etc.). The prototype described enables the detection of hidden devices and recognition of their types. It utilizes augmented reality to visualize the location of these hidden devices, facilitating swift identification. The demo showcases a prototype mounted on a user's handheld device, enabling users to detect and recognize hidden devices in unfamiliar environments. Test results show that the prototype achieves 98% accuracy in recognizing IoT device types, and the average error is controlled at 0.8m when locating the device.
- 16 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 314-315
Open AccessDemo: A Prototype for Detecting and Localizing Hidden Devices in Unfamiliar Environments
We have designed PanguVision: an Android software system that can be deployed on personal handheld devices (cell phones, PCs, etc.). The prototype described enables the detection of hidden devices and recognition of their types. It utilizes augmented reality to visualize the location of these hidden devices, facilitating swift identification. The demo showcases a prototype mounted on a user's handheld device, enabling users to detect and recognize hidden devices in unfamiliar environments. Test results show that the prototype achieves 98% accuracy in recognizing IoT device types, and the average error is controlled at 0.8m when locating the device.