RESET: A real-time scheduler for energy and temperature aware heterogeneous multi-core systems

Moulik, Sanjay

doi:10.1016/j.vlsi.2020.11.012

Cited by 16 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen, the temperature of all processors in Q‐scheduler is less than previous state‐of‐the‐art techniques. Q‐Scheduler reduces the temperature of processors on average by 12%, 7% and 4%, in comparison with Moulik's work [5], Hung's work [14] and fuzzy's work [15], respectively. Moulik's method keeps six processors ON and the two OFF, as shown in the figure for the experimental task sets.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…It also reduces the system's energy consumption on average by 24%, 16%, and 11% compared to the above state-of-the-art techniques, respectively. In comparison with previous state-of-the-art techniques [5,14,15], Q-scheduler needs more clock cycles to make its decision in order to dispatch tasks between processors. However, the resolution of decision time is in the range of real-time systems, and it is not the challenge.…”

Section: Discussionmentioning

confidence: 99%

“…In the following experiments, Q-scheduler is evaluated with Ref. [5,14,15] via two main metrics: Temperature and energy consumption. The processor, task, and simulation parameters for all techniques are considered the same.…”

Section: � Parameters Of the Experimentsmentioning

confidence: 99%

“…RESET [5] proposes a three-phase hierarchical mechanism. The first phase computes a set of windows based on tasks' deadline partitioning.…”

Section: Related Workmentioning

confidence: 99%

“…Designers look for various ways of task mapping and task scheduling to reduce energy consumption under the thermal profile of processors in these portable devices [4][5][6][7]. In the heterogeneous MPSoCs, Dynamic Voltage and Frequency Scaling (DVFS) is an attractive option available to designers to change the device's voltage or frequency dynamically based on the amount of energy consumption; subsequently, dispatch and schedule tasks proportional to voltage and speed of processors [6,8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Q‐scheduler: A temperature and energy‐aware deep Q‐learning technique to schedule tasks in real‐time multiprocessor embedded systems

Mohammadi

Beitollahi

2022

IET Computers & Digital Tech

View full text Add to dashboard Cite

Reducing energy consumption under processors' temperature constraints has recently become a pressing issue in real‐time multiprocessor systems on chips (MPSoCs). The high temperature of processors affects the power and reliability of the MPSoC. Low energy consumption is necessary for real‐time embedded systems, as most of them are portable devices. Efficient task mapping on processors has a significant impact on reducing energy consumption and the thermal profile of processors. Several state‐of‐the‐art techniques have recently been proposed for this issue. This paper proposes Q‐scheduler, a novel technique based on the deep Q‐learning technology, to dispatch tasks between processors in a real‐time MPSoC. Thousands of simulated tasks train Q‐scheduler offline to reduce the system's power consumption under temperature constraints of processors. The trained Q‐scheduler dispatches real tasks in a real‐time MPSoC online while also being trained regularly online. Q‐scheduler dispatches multiple tasks in the system simultaneously with a single process; the effectiveness of this ability is significant, especially in a harmonic real‐time system. Experimental results illustrate that Q‐scheduler reduces energy consumption and temperature of processors on average by 15% and 10%, respectively, compared to previous state‐of‐the‐art techniques.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%