张金泉，工学博士，广东工业大学讲师。主要研究方向为云计算资源管理、无服务器计算、调度优化、大模型推理优化。在IEEE Transactions on Parallel and Distributed Systems (TPDS)、IEEE Transactions on Services Computing (TSC)、Future Generation Computer Systems (FGCS)、IEEE Transactions on Cloud Computing (TCC)、MLSys、SIGKDD等国际知名学术期刊和会议上发表学术论文十余篇。参与国家重点研发计划项目、国家自然科学基金项目、企业合作项目等多项课题研究。获得华为火花奖，指导学生获全国研究生数学建模竞赛国家一等奖，专利和软件著作权各一项。

研究方向：云计算与智能调度，无服务器计算、大模型推理优化。

联系方式：zjq8860@gdut.edu.cn。

欢迎大家加入课题组！

主要成果：

[1] J. Zhang, H. Cao, L. Chen, S. Li, X. Li*, B. Ai. "Container-State-Aware Energy Consumption Minimization for Serverless Functions," in IEEE Transactions on Services Computing, 2026. (CCF A)

[2] J. Zhang, X. Li*, L. Chen, R. Ruiz. "Scheduling Workflows With Limited Budget to Cloud Server and Serverless Resources," in IEEE Transactions on Services Computing, 2024. (CCF A)

[3] Zhang, Jinquan, Li Xiaoping*, Ding Zhicheng, Li Yibo, Bao Guoqiang, Chen Long*. Dynamic Function Deployment and Task Offloading in Serverless Multi-Edge Systems. ICWS2026 (CCF B)

[4] Zhang, Jinquan, Li, Xiaoping*, Rajput, Kamran Yaseen, Chen, Long. Reinforcement Learning Based Memory Configuration for Linear Dynamic Function Chains. 2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD), IEEE, 2024 (CCF C)

[5] 考虑价值因素的服务调用网资源配置与在离线业务混部调度. 华为火花奖. 第一完成人．（授权机构：华为技术有限公司）. 2024.09

社会服务：

担任相关领域众多期刊和会议的审稿人：IEEE Transactions on Systems, Man and Cybernetics，IEEE Transactions on Sustainable Computing, Journal of the Franklin Institute, Cluster Computing, Future Generation Computer Systems, Journal of Supercomputing , Computing, Journal of Scheduling, IC3APP, ICPADS, ICWS等。

学生成果：

[1] 第二十二届中国研究生数学建模竞赛. 国家一等奖. 指导老师.（授权机构：中国学位与研究生教育学会）. 2025.12

[2] 植株叶片植食率智能检测系统. 本科生毕业设计创新奖. 指导老师.（授权机构：广东工业大学）. 2026.06

[3] Jiang Fengkai, Kou Fulu, Zhang Jinquan*, Yang Rui, Pang Shujie. EcoFlow: Cost-Aware LLM Serving on Heterogeneous GPUs via Min-Cost Max-Flow. ICWS2026 (CCF B)

[4] Tan Yinming, Zhang, Jinquan*, Chen Long, Di Kai, Li Pan. CompQ: QoE-Aware Compensation for Resumed Requests in Interactive LLM Inference Services. ICWS 2026 (CCF B)

[5] Ling Jianfeng, Feng Feilong, Zhang, Jinquan*, Chen Long, Wan Jihong. FedAlloy: Dual-Channel Federated Learning across Quantized and Heterogeneous Language Models. ICWS2026 (CCF B)

[6] Guo, Kejia, Zhang, Jinquan*, Li, Xiaoping*. DSPJ: Deep Reinforcement Learning-based Scheduling Algorithm for Parallel Multi-stage Cloud Fuzzy Jobs. 2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS), 2025: 1-4 (CCF C)

[7] Fengkai Jiang, Jinquan Zhang*, Xiaoping Li. Chorus: Mitigating GPU Fragmentation in LLM Serving by Unifying Prefill-Decode Disaggregation and Aggregation. ChineseCSCW 2025.（EI检索）

[8] Jie Qiu, Jinquan Zhang, Xiaoping Li*. Deadline- and Reliability-Constrained Workflow Scheduling in GDCs. 20th CCF Conference on Computer Supported Cooperative Work and Social Computing, 2025.（EI检索）

[9] 郭可珈, 张金泉, 李小平. 一种异构集群并行多阶段模糊作业调度方法. 发明专利申请号: 202511293756.4

[10] 邱杰, 李小平, 张金泉. 一种动态截止期与可靠性约束的云工作流调度方法. 发明专利申请号: 202511557707.7