ENGLISH 中财主站 加入收藏
当前位置: 首 页 > 学术科研 > 讲座报告 > 正文

讲座 | 智能管理交叉学科系列讲座题目(第十五期)

发布时间:2022-12-05来源:管理科学系 浏览次数:

讲座题目:OnlineLearning and Optimization for Queueing Systems



讲座地点:腾讯会议: 442-543-286


We investigate an online learning and optimization problem for queueing systems in a data-driven environment, i.e., the model parameters are unknown a prior. Service provider’s objective is to seek the optimal service fee and service capacity so as to maximize the cumulative expected profit (the service revenue minus the capacity cost and delay penalty). We develop a framework to developing online learning algorithms that effectively evolve the service provider’s decisions utilizing real-time data including customers’ arrival and service times for a variety of queueing systems. Effectiveness of these online learning algorithms is substantiated by (i) theoretical results including the algorithm convergence and analysis of the regret, i.e., the cost to pay over time for the algorithm to learn the optimal policy, and (ii) engineering confirmation via simulation experiments of a variety of representative examples. The talk is based on joint works with Yunan Liu from NCSU and Guiyu Hong from CUHK-Shenzhen.


陈昕韫博士于2014年取得哥伦比亚大学运筹学博士学位。毕业后先后任教于美国纽约州立大学石溪分校和武汉大学,现在香港中文大学(深圳)数据科学学院任助理教授。陈昕韫博士的主要研究领域为随机模拟、排队模型和强化学习。她的研究工作多次发表在Annals of Applied Probability、Mathematics of Operations Research和ICLR等知名期刊和会议上。陈昕韫博士曾任美国运筹学和管理学研究协会(INFORMS)应用概率学会理事会成员,目前担任期刊《Journal of Applied Probability》,《Advances in Applied Probability》编辑。