Thermal-aware Real-time Scheduling Using Timed Continuous Petri Nets

Abstract

We present a thermal-aware, hard real-time (HRT) global scheduler for a multiprocessor system designed upon three novel techinques. First, we present a modeling methodology based on Timed Continuous Petri nets (TCPN) that yields a complete state variable model, including job arrivals, CPU usage, power, and thermal behavior. The model is accurate and avoids the calibration stage of RC thermal models. Second, based on this model, a linear programming problem (LPP) determines the existence of a feasible HRT thermal-aware schedule. Last, a sliding-mode controller and an online discretization algorithm implement the global HRT scheduler, which is capable of managing thermal constraints, context switching, migrations, and disturbances.

Maximizing Utilization and Minimizing Migration in Thermal-Aware Energy-Efficient Real-Time Multiprocessor Scheduling

“…The downside of the heuristic approach in [12] is that it cannot ensure schedulability, and only explores a very small portion of the solution space, yielding sub-optimal results. Also, authors in [12] apply an abstraction of an RC thermal and power model at the chip level, whereas we can fine-tune thermal properties and dynamics by discretizing the MPSoC or the relevant part of it with prisms as small as desired [13], [14]. We provide a holistic formal model of the system, whereas RC power and thermal models do not provide a true integrated state model.…”

“…This makes possible to generate a pre-schedule which is tracked by a controller which modifies the frequency. We introduced a similar approach in [13]. Although it was capable of managing thermal and temporal constraints of HRT tasks, it did not accounted for energy minimization and incurred in a great number of context switches.…”

“…Additionally, we now provide full proofs and development of the LPP solution presented in [36], which is a conference paper with limited extension. The TCPN model of the system we use in this research is based on [13], [14] and [36] with changes on the flow of the execution transitions. The thermal module within this model was validated with Ansys® in [37].…”

A Flexible Framework for Real-Time Thermal-Aware Schedulers using Timed Continuous Petri Nets

“…The TCPN model representing the Task arrival and CPU's Module ( Fig. 4) was first introduced in [17] and evaluated in [16]. Here we present a brief explanation of the TCPN model and the differential equations that represent the behaviour.…”

“…We have included three schedulers: a global EDF scheduler from [1], and other two from our own authorship a RT fluid scheduler ( [15]) and a thermal aware RT scheduler ( [16]), however the user can define his own scheduler. Sec.…”