Multi-Agent Based Distributed Algorithms for Optimization and Machine Learning

Prof Zhengtao Ding

School of Electrical and Electronic Engineering

University of Manchester, UK

Abstract:

             

In this network-connected world, many tasks require coordination and cooperation of subsystems/agents via network connection. Multi-agent systems are good examples of interplay between network communication and decision making. Distributed algorithms have been developed based multi-agent systems for control and other applications. Algorithms based on multi-agents have also been developed for distributed optimization which aims at making decisions in local level, and achieving certain global optimization task through network communications. Algorithms and cost functions for distributed optimization would expect to be different from their centralized counterparts. Some key ideas in multi-agent systems have also been explored in machine learning. This talk will cover the exploration and some advances in applying multi-agent fundamentals to optimization and machine learning in the speaker’s team in University of Manchester. Applications in resource management for several different tasks in smart grids will be demonstrated, including optimization of charge station for electrical vehicles, cooperative optimal control of battery energy storage system etc.

   

Speaker:

 

Zhengtao Ding received B.Eng. degree from Tsinghua University, Beijing, China, and M.Sc. degree in systems and control, and the Ph.D. degree in control systems from the University of Manchester Institute of Science and Technology, Manchester, U.K. After working as a Lecturer with Ngee Ann Polytechnic, Singapore, for ten years, he joined the University of Manchester in 2003, where he is currently Professor of Control Systems with the Dept of Electrical and Electronic Engineering. He serves a member of the school/department leadership team, and Deputy Head of Control, Communication and Signal Processing Division in the university. He is the author of the book: Nonlinear and Adaptive Control Systems (IET, 2013) and has published over 260 research articles. His research interests include nonlinear and adaptive control theory and their applications, more recently network-based control, distributed optimization and distributed machine learning, with applications to power systems and robotics. Prof. Ding has served as an Associate Editor for the IEEE Transactions on Automatic Control, IEEE Control Systems Letters, and several other journals. He is a member of IEEE Technical Committee on Nonlinear Systems and Control, IEEE Technical Committee on Intelligent Control, and IFAC Technical Committee on Adaptive and Learning Systems.