ReLeTA: Reinforcement Learning for Thermal-Aware Task Allocation on Multicore

2019/11/30 by Shi-Gui Yang, Yang, Shi-Gui, Yuan-Yuan Wang +13
Computer Science · Engineering · #Cloud Computing and Resource Management #Ferroelectric and Negative Capacitance Devices #Parallel Computing and Optimization Techniques #cs.SY #eess.SY

paper · pdf · doi:10.48550/arxiv.1912.00189

arxiv created 2019/11/30 · arxiv updated 2019/12/03

Abstract

In this paper, we propose ReLeTA: Reinforcement Learning based Task Allocation for temperature minimization. We design a new reward function and use a new state model to facilitate optimization of reinforcement learning algorithm. By means of the new reward function and state model, \releta is able to effectively reduce the system peak temperature without compromising the application performance. We implement and evaluate \releta on a real platform in comparison with the state-of-the-art approaches. Experimental results show \releta can reduce the average peak temperature by 4 ^∘C and the maximum difference is up to 13 ^∘C.

Related

• RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems
• Reinforcement Learning Testbed for Power-Consumption Optimization
• An SMDP-Based Approach to Thermal-Aware Task Scheduling in NoC-based MPSoC platforms
• Reinforcement Learning for Adaptive Resource Scheduling in Complex System Environments
• SLA-MORL: SLA-Aware Multi-Objective Reinforcement Learning for HPC Resource Optimization