The 9th International Conference on Next Generation Computing 2023 (2023.12)바로가기
페이지
pp.187-189
저자
Changhun Han, Seokho Yoon, Sangeun Oh
언어
영어(ENG)
URL
https://www.earticle.net/Article/A448147
원문정보
초록
영어
Artificial Intelligence (AI) has demonstrated unprecedented performance across a multitude of sectors, including disaster response. However, deploying AI in safetycritical environments poses unique challenges, especially regarding thermal management and real-time decision-making. Utilizing Edge TPU, one of the Neural Processing Units (NPUs), has shown promise in overcoming some of these challenges. Despite its advantages, Edge TPU still has limitations in thermal management and real-time task scheduling. This study introduces an approach employing Dynamic Frequency Scaling (DFS) and SRAM allocation techniques to address these challenges. By dynamically adjusting operating frequencies and resource allocations, the proposed approach aims to optimize both thermal management and real-time performance, thereby enhancing the reliability and efficiency of AI technologies in critical applications like disaster response.
목차
Abstract I. INTRODUCTION II. PRELIMINARY OBSERVATIONS III. OPTIMIZING DFS AND SRAM ALLOCATION IV. CONCLUSION AND FUTURE WORKS ACKNOWLEDGMENT REFERENCES