当前位置: 学院首页  >  科学研究  >  学术动态  >  正文

【电气讲坛】Efficient Computational Approaches and Applications to Some Optimization Problems in Smart Grid

点击: 发布人:袁波 发布时间:2021-10-18 16:23:20


报告名称

Efficient Computational Approaches   and Applications to Some Optimization Problems in Smart Grid

 

20211022 14:00-15:30

 

水电楼217/腾讯会议ID648506376

主 讲 人

黄廷文,美国德州农工大学卡塔尔分校

主办单位

官网|6165con金沙

备注

Abstract: In a smart   grid context, a demand response strategy of electric vehicle charging is   modelled by a stochastic game, where a big data analytic framework is   proposed for controlling the electric vehicle charging behaviours. We will   look at Plug-In Electric Vehicles (PEVs) Charging: Feeder Overload Control   problem. Moreover, a two-stage stochastic game theoretical model is proposed for   energy trading problem in a multi-energy microgrid system. In these two work,   the risk measurement technique, conditional value at risk (CVaR), is   harnessed to estimate the overload risk during the peak hour and the   overbidding risk while distributed alternating direction method of   multipliers (ADMM) is accelerated by Nesterov gradient method to solve two   game models. Concerning the privacy, a research branch of reinforcement   learning (RL) that dominates distributed learning for years will be presented   by making the first attempt to apply RL-based algorithms in the energy   trading game among smart microgrids where no information concerning the   distribution of payoffs is a priori available and the strategy chosen by each   microgrid is private to opponents, even trading partners. To solve this   challenge, a new energy trading framework based on the repeated game that   enables each microgrid to individually and randomly choose a strategy with   probability to trade the energy in an independent market so as to maximize   his/her average revenue.

 

 Prof.   Tingwen Huang's research focuses on dynamics of nonlinear systems including   neural networks, complex networks and multi-agent and their applications to   smart grids and cybersecurity. He has published papers in these areas. He is   a Highly Cited Researcher by Clarivate Analytics, formerly Thomson Reuters.

He   is very actively involving in professional service. He serves/served as the   Past-President (2021), President (2020), President-Elect (2019) for Asia   Pacific Neural Network Society, as an action editor or associate editor for   several international journals, as a guest editor for 10 special issues.

He   is a Member of the European Academy of Sciences and Arts, an Academician of   the International Academy for Systems and Cybernetic Sciences, a Fellow of   IEEE and AAIA (Asia-Pacific Artificial Intelligence Association), a   Changjiang Chair Professor.

 

Baidu
sogou