- 2022.10: 🎉🎉 一篇论文被 JSA 期刊接收！
- 2022.10: 🎉🎉 谷歌学术引用量达 100+!
- 2022.09: 一个发明专利已授权！
- 2022.06: 一篇论文被 IEEE ITSC 2022 会议接收！
Enabling Digital Twin in Vehicular Edge Computing: A Multi-Agent Multi-Objective Deep Reinforcement Learning Solution
Xincao Xu, Kai Liu, Penglin Dai, and Biwen Chen*
- We present a DT-VEC architecture, where the heterogeneous information can be sensed by vehicles and uploaded to the edge node via V2I communications. The DT-VEC are modeled at the edge node, forming a logical view to reflect the physical vehicular environment.
- We model the DT-VEC by deriving an ISAC-assisted sensing model and a reliability-guaranteed uploading model.
- We formulate the bi-objective problem to maximize the system quality and minimize the system cost, simultaneously. In particular, we define the quality of DT-VEC by considering the timeliness and consistency, and define the cost of DT-VEC by considering the redundancy, sensing cost, and transmission cost.
- We propose a multi-agent multi-objective (MAMO) deep reinforcement learning solution implemented distributedly in the vehicles and the edge nodes. Specifically, a dueling critic network is proposed to evaluate the advantage of action over the average of random actions.
- Submitted to IEEE Transactions on Consumer Electronics (under review)
Cooperative Sensing and Heterogeneous Information Fusion in VCPS: A Multi-agent Deep Reinforcement Learning Approach
Xincao Xu, Kai Liu*, Penglin Dai, Ruitao Xie, and Jiangtao Luo
- We present a cooperative sensing and heterogeneous information fusion architecture in VCPS via vehicular edge computing. The heterogeneous information can be sensed via either onboard sensors such as LIDAR, GPS, and cameras, or roadside infrastructures such as traffic lights. The sensed information is queued in vehicles for uploading via the V2I bandwidth, which is allocated by the corresponding edge node. Logical views can be constructed via the information fusion at edge nodes, and different views may be required to enable upper-layer applications.
- We formulate the problem to maximize the quality of VCPS. Specifically, we derive a cooperative sensing model, in which the information queuing and data uploading are modeled based on the multi-class M/G/1 priority queue and the Shannon theory, respectively. Then, we derive a heterogeneous information fusion model by modeling the timeliness, completeness, and consistency of views. On this basis, a new metric called Age of View (AoV) is defined to quantitatively measure the quality of information fusion. Finally, we model the quality of VCPS and present the optimization objective, which is to maximize the VCPS quality.
- We propose a multi-agent deep reinforcement learning solution. Specifically, the solution model is presented, in which vehicles act as independent agents with action space of determining the sensing frequencies and uploading priorities, and the edge action space is the V2I bandwidth allocation. The system state consists of vehicle sensed information, edge cached information, and view requirements. The system reward is defined as the achieved VCPS quality. In particular, the system reward is divided into the Difference Reward (DR) to capture vehicle individual contributions on view constructions by the DR-based credit assignment.
- Submitted to IEEE Transactions on Intelligent Transportation Systems (under review)
Joint Task Offloading and Resource Optimization in NOMA-based Vehicular Edge Computing: A Game-Theoretic DRL Approach
Xincao Xu, Kai Liu*, Penglin Dai, Feiyu Jin, Hualing Ren, Choujun Zhan, and Songtao Guo
- We present a NOMA-based VEC architecture, where the vehicles share the same frequency of bandwidth resources and communicate with the edge node with the allocated transmission power. The tasks arrive stochastically at vehicles and are heterogeneous regarding computation resource requirements and deadlines, which are uploaded by vehicles via V2I communications. Then, the edge nodes with heterogeneous computation capabilities, i.e., CPU clock speed, can either execute the tasks locally with allocated computation resources or offload the tasks to neighboring edge nodes through a wired network.
- We propose a cooperative resources optimization (CRO) problem by jointly offloading tasks and allocating communication and computation resources to maximize the service ratio, which is the number of tasks serviced before the deadlines divided by the number of requested tasks. Specifically, a V2I transmission model considering both intra-edge and inter-edge interference and a task offloading model considering the heterogeneous resources and cooperation of edge nodes are theoretically modeled, respectively.
- We decompose the CRO problem into two subproblems: 1) task offloading game model and 2) resource allocation convex problem. Specifically, we model the first subproblem as a non-cooperative game among edge nodes, which is further proved as an EPG with the existence and convergence of NE. Then, we design a MAD4PG algorithm, a multi-agent version of D4PG, to achieve the NE, where edge nodes act as independent agents to determine the task offloading decisions and receive the achieved potential as rewards. Further, we model the second subproblem as two independent convex problems and derive an optimal mathematical solution based on the gradient-based iterative method and KKT condition.
- Accepted by Journal of Systems Architecture [JCR Q1|SCI Q2|CCF B]
- Xincao Xu, Kai Liu*, Penglin Dai, Feiyu Jin, Hualing Ren, Choujun Zhan, and Songtao Guo, Joint Task Offloading and Resource Optimization in NOMA-Based Vehicular Edge Computing: A Game-Theoretic DRL Approach, Journal of Systems Architecture, volume 134, pp. 102780, January 2023. IF: 5.836 (2021), 4.497 (5-year) [JCR Q1|SCI Q2|CCF B]
- Chunhui Liu, Kai Liu*, Hualing Ren, Xincao Xu, Ruitao Xie and Jingjing Cao, RtDS: Real-time Distributed Strategy for Multi-period Task Offloading in Vehicular Edge Computing Environment, Neural Computing and Applications, to appear. IF: 5.606 (2020), 5.573 (5-year) [JCR Q1|SCI Q2]
- Ke Xiao, Kai Liu*, Xincao Xu, Liang Feng, Zhou Wu and Qiangwei Zhao, Cooperative Coding and Caching Scheduling via Binary Particle Swarm Optimization in Software Defined Vehicular Networks, Neural Computing and Applications, volume 33, issue 5, pp. 1467-1478, May 2021. IF: 5.606 (2020), 5.573 (5-year) [JCR Q1|SCI Q2]
- Ke Xiao, Kai Liu*, Xincao Xu, Yi Zhou and Liang Feng, Efficient Fog-assisted Heterogeneous Data Services in Software Defined VANETs, Journal of Ambient Intelligence and Humanized Computing, volume 12, issue 1, pp.261-273, January 2021. IF: 7.104 (2020), 6.163 (5-year) [JCR Q2|SCI Q3]
- Xincao Xu, Kai Liu*, Ke Xiao, Liang Feng, Zhou Wu and Songtao Guo, Vehicular Fog Computing Enabled Real-time Collision Warning via Trajectory Calibration, Mobile Networks and Applications, volume 25, issue 6, pp. 2482-2494, December 2020. IF: 2.602 (2019), 2.76 (5-year) [JCR Q2|CCF C]
- Kai Liu*, Xincao Xu, Mengliang Chen, Bingyi Liu*, Libing Wu and Victor Lee, A Hierarchical Architecture for the Future Internet of Vehicles, IEEE Communications Magazine, volume 57, issue 7, pp. 41-47, July 2019. IF: 10.356 (2018), 12.091 (5-year) [JCR Q1|SCI Q1]
- Xincao Xu, Kai Liu, Qisen Zhang, Hao Jiang, Ke Xiao and Jiangtao Luo, Age of View: A New Metric for Evaluating Heterogeneous Information Fusion in Vehicular Cyber-Physical Systems, IEEE 25th International Conference on Intelligent Transportation Systems (IEEE ITSC’22), Macau, China, October 8-12, 2022.
- Chunhui Liu, Kai Liu, Xincao Xu, Hualing Ren, Feiyu Jin and Songtao Guo, Real-time Task Offloading for Data and Computation Intensive Services in Vehicular Fog Computing Environments, IEEE International Conference on Mobility, Sensing and Networking (IEEE MSN’20), Tokyo, Japan, December 17-19, 2020.
- Yi Zhou, Kai Liu, Xincao Xu, Chunhui Liu, Liang Feng and Chao Chen, Multi-period Distributed Delay-sensitive Tasks Offloading in a Two-layer Vehicular Fog Computing Architecture, International Conference on Neural Computing and Applications (NCAA’20), Shenzhen, China, July 3-6, 2020.
- Yi Zhou, Kai Liu, Xincao Xu, Songtao Guo, Zhou Wu, Victor Lee and Sang Son, Distributed Scheduling for Time-Critical Tasks in a Two-layer Vehicular Fog Computing Architecture, IEEE Consumer Communications and Networking Conference (IEEE CCNC’20), Las Vegas, USA, January 11-14, 2020.
- Xincao Xu, Kai Liu, Ke Xiao, Hualing Ren, Liang Feng and Chao Chen, Design and Implementation of a Fog Computing Based Collision Warning System in VANETs, IEEE International Symposium on Product Compliance Engineering-Asia (IEEE ISPCE-CN’18), Hong Kong/Shengzhen, December 5-7, 2018. (Best Paper Award)
- 许新操, 刘凯*, 刘春晖, 蒋豪, 郭松涛, 吴巍炜, 基于势博弈的车载边缘计算信道分配方法, 电子学报, 2021, 49(5), 851-860. [CCF T1]
- 许新操, 周易, 刘凯, 向朝参, 李艳涛, 郭松涛, 车载雾计算环境中基于势博弈的分布式信道分配, 第十四届中国物联网学术会议(CWSN’20), 中国敦煌, 2020/9/18-9/21. (最佳论文候选)
- 许新操, 刘凯, 李东, 一种针对软件定义车联网的控制平面视图构建方法, 发明专利 (ZL202110591822.1), 2022.10.11.
- 刘凯, 张浪, 许新操, 任华玲, 周易, 一种基于边缘计算的盲区车辆碰撞预警方法, 发明专利 (ZL201910418745.2), 2021.08.03.
- 任华玲, 刘凯, 陈梦良, 周易, 许新操, 一种基于雾计算的信息采集、计算、传输架构, 发明专利 (ZL201910146357.3), 2021.06.18.
- 国家自然科学基金面上项目，面向车联网边缘智能的计算模型部署与协同跨域优化，62172064，2022/01–2025/12 (参与)
- 国家自然科学基金面上项目，基于相继干扰消除的无线携能通信网络高效能数据收发机制研究, 62072064，2021/01-2024/12 (参与)
- 国家自然科学基金面上项目，面向大规模数据服务的异构融合车联网架构与协议研究，61872049，2019/01–2022/12 (参与)
- 国家自然科学基金面上项目，面向车联网多信道I2V/V2V混合通信与时态信息服务研究，61572088，2016/01–2019/12 (参与)
- 2017.09 - 2023.06 (今), 攻读博士学位, 计算机科学与技术, 计算机学院, 重庆大学, 重庆. (硕博连读)
- 2013.09 - 2017.06, 本科, 网络工程, 计算机与控制工程学院, 中北大学, 太原.
- 算法导论 by 麻省理工学院 [Link]
- 机器学习 by 李宏毅教授 [Link]
- 机器学习 by 徐亦达教授 [Link]
- 深度学习 by 吴恩达教授 [Link]
- 深度强化学习 by 王树森博士 [Link]
- 机器学习（🍉书） by 周志华教授 [Chinese]
- 深度学习 by Dr. Ian Goodfellow, Prof. Yoshua Bengio, and Prof. Aaron Courville [English] [Chinese]
- 机器学习训练秘籍 by 吴恩达教授 [Chinese]
- 动手学深度学习 by Dr. Aston Zhang, Dr. Zachary C. Lipton, Dr. Mu Li, and Dr. Alexander I. Smola [English] [Chinese]
- 谷歌学术: 最大的学术文献搜索引擎 [Link]
- dblp: 计算机领域文献数据库 [Link]
- 会伴: 学术会议信息查询 [Link]
- LetPub: SCI 期刊信息查询 [Link]
- Academic Accelerator: 各种学术相关工具集合 [Link]
- WikiCFP: 征稿信息的维基百科 [Link]
- Zotero: 个人文献管理工具 [Link]