报告题目：Microgrid Energy Dispatching for Industrial Zones with Renewable Generations and Electric Vehicles via Stochastic Optimization and Learning
报告人：   李景治 博士  南方科技大学
主持人：   周爱民
报告时间：2019年5月20日  周一10:00-11:00 
报告地点：理科大楼B816

报告摘要：
In this talk, a stochastic optimization framework is proposed to address the microgrid energy dispatching problem with random renewable generation and vehicle activity pattern, which is more close to the practical applications. The patterns of energy generation, consumption and storage availability are all random and unknown at the beginning, and the microgrid controller design (MCD) is formulated as a Markov decision process (MDP). Hence, an online learning-based control algorithm is proposed for the microgrid, which could adapt the control policy with increasing knowledge of the system dynamics and finally converges to the optimal algorithm. We adopt linear approximation idea to decompose the original value functions to the summation of each per-battery value function. As a consequence, the computational complexity is significantly reduced from exponential growth to linear growth with respect to the size of battery states. Monte Carlo simulation of different scenarios demonstrates the effectiveness and efficiency of our algorithm.

报告人简介：
李景治，博士，南方科技大学数学系tenured副教授、系副主任。2013年入选深圳市海外高层次人才——孔雀人才（B类）。2009年获香港中文大学数学系应用数学哲学博士学位，获香港数学会最佳博士论文奖；2009年至2011年，在苏黎世联邦理工大学数学系做博士后。主要从事计算数学及相关领域，研究领域涉及到反问题理论与计算方法，形状优化与微分形式统一理论，科学计算，有限元方法。