User Interaction Aware Reinforcement Learning for Power and Thermal Efficiency of CPU-GPU Mobile MPSoCs

2020/03/01 by Somdip Dey, Amit Kumar Singh, Xiaohang Wang +1 · 1 citation
Engineering · Computer Science · #Green IT and Sustainability #Caching and Content Delivery #Energy Harvesting in Wireless Networks #MPSoC #Computer science #Reinforcement learning #Android (operating system) #Quality of service #Frame rate #Embedded system #Power management #Real-time computing #Operating system #System on a chip #Power (physics) #Computer network #Artificial intelligence

paper · doi:10.23919/date48585.2020.9116294

openalex publication_date 2020/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

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.

Citations

• Federated Learning: Strategies for Improving Communication Efficiency
• SoCodeCNN: Program Source Code for Visual CNN Classification Using Computer Vision Methodology

Cited by

• Reinforcement learning [wikipedia]

Related

• Deep Reinforcement Learning for Energy-Efficient on the Heterogeneous Computing Architecture
• Adaptive Processor Frequency Adjustment for Mobile Edge Computing with Intermittent Energy Supply
• Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach
• QECO: A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning for Mobile Edge Computing
• An Energy-Aware Online Learning Framework for Resource Management in Heterogeneous Platforms