Title :
Multicore thermal management with model predictive control
Author :
Zanini, Francesco ; Atienza, David ; Benini, Luca ; De Micheli, Giovanni
Author_Institution :
Lab. of Integrated Syst., EPFL, Lausanne, Switzerland
Abstract :
The goal of thermal management is to meet maximum operating temperature constraints, while at the same time tracking time-varying performance requirements. Current approaches avoid thermal violations by forcing abrupt operating points changes (e.g. processor shutdown), which cause sharp performance degradation. In this paper we aim at achieving a smooth thermal control action, that minimizes the variance of performance tracking error. We formulate this problem as a discrete-time optimal control problem, which can be solved using the theory and computational tools developed in the field of model-predictive control. Our optimization process considers the thermal profile of the system, its evolution over time, and time-varying workload requirements. Experimental results show that the proposed approach offers significant thermal balancing improvements over previous methods.
Keywords :
discrete time systems; multiprocessing systems; optimal control; predictive control; system-on-chip; temperature control; thermal management (packaging); discrete-time optimal control problem; model predictive control; multicore thermal management; optimization process; smooth thermal control action; thermal balancing; Control systems; Energy management; Frequency; Laboratories; Multicore processing; Power system management; Predictive control; Predictive models; Temperature; Thermal management;
Conference_Titel :
Circuit Theory and Design, 2009. ECCTD 2009. European Conference on
Conference_Location :
Antalya
Print_ISBN :
978-1-4244-3896-9
Electronic_ISBN :
978-1-4244-3896-9
DOI :
10.1109/ECCTD.2009.5275073