Phoenix: Thermal-Aware On-Device Inference of Multi-Instance DNNs for Mobile Video Applications
Open Access
- 6 March 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 25 (2) , 1-23
Abstract
Running multiple deep neural networks (DNNs) simultaneously on mobile devices introduces challenges due to constrained computing resources. Previous research has explored the use of heterogeneous processors for accelerating DNN inference but often overlooks thermal issues, which can degrade computing power. In this article, we propose Phoenix, a system specifically designed to enhance the performance of multi-instance DNNs in video applications by maximizing accuracy and ensuring the achievement of a required frame rate. Phoenix allocates DNN tasks to the most suitable hardware processors, understanding complex thermal dynamics through reinforcement learning, and postpones the onset of thermal throttling. Despite optimized task allocation, continuous inference of multiple DNNs can still lead to thermal throttling. To manage performance degradation, Phoenix employs a multi-exit network, adaptively executing inference tasks to ensure consistent frame rates. Phoenix minimizes accuracy loss from early exits by optimally generating and operating multi-exit networks. We evaluated Phoenix using two different benchmarks and Virtual Youtuber streaming application. The results demonstrated that Phoenix effectively enhances device performance by delaying thermal throttling and achieving optimal accuracy while maintaining a consistent frame rate.Keywords
Funding Information
- Institute for Information and Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (RS-2018-II180532, 50%)
- National Research Foundation of Korea (NRF) grant funded by the Korea government (RS-2024-00344323, 50%)
This publication has 34 references indexed in Scilit:
- OmniLive: Super-Resolution Enhanced 360° Video Live Streaming for Mobile Devices2023
- NN-Stretch: Automatic Neural Network Branching for Parallel Inference on Heterogeneous Multi-Processors2023
- Dělen: Enabling Flexible and Adaptive Model-serving for Multi-tenant Edge AI2023
- Adaptable mobile vision systems through multi-exit neural networks2022
- Adaptive Inference through Early-Exit Networks2021
- An Energy-aware Online Learning Framework for Resource Management in Heterogeneous PlatformsACM Transactions on Design Automation of Electronic Systems, 2020
- Q-Learning: Theory and ApplicationsAnnual Review of Statistics and Its Application, 2020
- Deep Reinforcement Learning: A Brief SurveyIEEE Signal Processing Magazine, 2017
- BranchyNet: Fast inference via early exiting from deep neural networks2016
- Power and thermal challenges in mobile devices2013