Distributed Model-Free Adaptive Predictive Control for Urban Traffic Networks

Data-driven control without using mathematical models is a promising research direction for urban traffic control due to the massive amounts of traffic data generated every day. This article proposes a novel distributed model-free adaptive predictive control (D-MFAPC) approach for multiregion urban traffic networks. More specifically, the...

Gas Turbines Power Regulation Subject to Actuator Constraints, Disturbances and Measurement Noises

An accurate understanding of the output power functionality in gas turbines concerning the fuel, inlet valve status and other parameters can provide a general overview of the turbine's performance. In this study, the problem of practical power regulation in gas turbines is investigated in the simultaneous presence of actuator constraints,...

Selecting Informative Data Samples for Model Learning Through Symbolic Regression

Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accuracy is impaired when data from repetitive motions prevail in the training set and outweigh...