A Supervised Learning Framework for Physics-based Controllers Using Stochastic Model Predictive Control

Stochastic Model Predictive Control

Model Predictive Control (MPC) is a control strategy that has been used successfully in numerous and diverse application areas. The aim of the present article is to discuss how the basic ideas of MPC can be extended to problems involving random model uncertainty with known probability distribution. We discuss cost indices, constraints, closed loop properties and implementation issues.

In-silico predictive mutagenicity model generation using supervised learning approaches

UNLABELLED BACKGROUND Experimental screening of chemical compounds for biological activity is a time consuming and expensive practice. In silico predictive models permit inexpensive, rapid "virtual screening" to prioritize selection of compounds for experimental testing. Both experimental and in silico screening can be used to test compounds for desirable or undesirable properties. Prior wor...

Experience-based model predictive control using reinforcement learning

A Model Predictive Control Approach for Stochastic Networked Control Systems

In this paper we present a stochastic model predictive control (SMPC) approach for networked control systems (NCSs) that are subject to time-varying sampling intervals and timevarying transmission delays. These network-induced uncertain parameters are assumed to be described by random processes, having a bounded support and an arbitrary continuous probability density function. Assuming that the...

Stochastic Model Predictive Control for Data Centers

Datacenters operations are notoriously energy-hungry with the computing and cooling infrastructures drawing comparable amount of power. A direction to improve their efficiency is to jointly control the Information Technology (IT) and Cooling Techniques (CT) components so that less cooling power has to be spent for the same Quality of Service (QoS) level. This work investigates minimum cost cont...