Skip to content. Skip to navigation
CIM Menus
 

Informal Systems Seminar (ISS), Centre for Intelligent Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Decisions (GERAD)

Distributed Coordination for Network Optimization


Jorge Cortes
Department of Mechanical and Aerospace Engineering University of California, San Diego

March 24, 2017 at  11:00 AM
Room 4488, Andre-Aisenstadt Building, Universite de Montreal Campus, 2920 chemin de la Tour, H3T 1J4

The need for network optimization is pervasive, from the coordination of distributed energy resources in power networks to multi-sensor fusion and motion coordination in robotic networks, passing through traffic coordination at intersections of networked vehicles. From a systems and control perspective, such optimization problems pose formidable research challenges in order to guarantee the reliable, efficient, and safe operation of networked systems in real-world applications. This talk describes our progress on engineering networks with predictable behavior through the design of distributed coordination strategies. We deal with network optimization problems defined by separable convex objective functions encoding goals and performance metrics, and constraints that couple the state of individual agents encoding physical, communication, or operational specifications. In our discussion, we pay particular attention to establishing guarantees on algorithm correctness, characterizing the algorithm robustness against disturbances and communication link failures, and synthesizing opportunistic state-triggered coordination strategies for the efficient use of the available resources.