User Interaction Aware Reinforcement Learning for Power and Thermal Efficiency of CPU-GPU Mobile MPSoCs
Somdip Dey1,a, Amit Kumar Singh1,b, Xiaohang Wang2,d and Klaus McDonald-Maier1,c
1Embedded and Intelligent Systems Laboratory, University of Essex
asomdip.dey@essex.ac.uk
ba.k.singh@essex.ac.uk
ckdm@essex.ac.uk
2School of Software Engineering, South China University of Technology
dbaikeina@163.com
ABSTRACT
Mobile user’s usage behaviour changes throughout the day and the desirable Quality of Service (QoS) could thus change for each session. In this paper, we propose a QoS aware agent to monitor mobile user’s usage behaviour to find the target frame rate, which satisfies the desired user’s QoS, and applies reinforcement learning based DVFS on a CPU-GPU MPSoC to satisfy the frame rate requirement. Experimental study on a real Exynos hardware platform shows that our proposed agent is able to achieve a maximum of 50% power saving and 29% reduction in peak temperature compared to stock Android’s power saving scheme. It also outperforms the existing state-of-the-art power and thermal management scheme by 41% and 19%, respectively.
Keywords: Agent system, Reinforcement Learning, Machine learning, CPU, GPU, Power Optimization, Thermal optimization, MPSoCs, User behaviour, User Interaction, Smartphone, Mobile.
