Distributed Learning for Decentralized Dynamic Output Feedback Controller Design

Abstract

This paper proposes a distributed learning algorithm for designing decentralized dynamic output feedback controllers for partially observable networked systems affected by process and observation noise. This algorithm is scalable for the number of subsystems, making it applicable to large-scale networked systems. The effectiveness of the proposed algorithm is shown through a numerical simulation of Heating Ventilation and Air Conditioning (HVAC) systems.