머신러닝 기반 멀티모달 센싱 IoT 플랫폼 리소스 관리 지원
Machine learning-based Multi-modal Sensing IoT Platform Resource Management
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we propose a machine learning-based method for supporting resource management of IoT software platforms in a multi-modal sensing scenario. We assume that an IoT device installed with a oneM2M-compatible software platform is connected with various sensors such as PIR, sound, dust, ambient light, ultrasonic, accelerometer, through different embedded system interfaces such as general purpose input output (GPIO), I2C, SPI, USB. Based on a collected dataset including CPU usage and user-defined priority, a machine learning model is trained to estimate the level of nice value required to adjust according to the resource usage patterns. The proposed method is validated by comparing with a rule-based control strategy, showing its practical capability in a multi-modal sensing scenario of IoT devices.
Abstract
In this paper, we propose a machine learning-based method for supporting resource management of IoT software platforms in a multi-modal sensing scenario. We assume that an IoT device installed with a oneM2M-compatible software platform is connected with various sensors such as PIR, sound, dust, ambient light, ultrasonic, accelerometer, through different embedded system interfaces such as general purpose input output (GPIO), I2C, SPI, USB. Based on a collected dataset including CPU usage and user-defined priority, a machine learning model is trained to estimate the level of nice value required to adjust according to the resource usage patterns. The proposed method is validated by comparing with a rule-based control strategy, showing its practical capability in a multi-modal sensing scenario of IoT devices.
참고문헌 (15)
- J. Kim, "Towards the OneM2M Standards for Building IoT Ecosystem : Analysis, Implementation and Lessons", Peer-to-Peer Networking and Applications. Appl, 11, pp.139~151 (2018)
- TTA, "TTAR-10.0137. Technical Specification", ~ (2020)
- 성낙명, "협업가능 표준기반 IoT 시스템을 위한 자가적응 IoT 소프트웨어 플랫폼 개발", 대한임베디드공학회논문지, 12(6), pp.369~375 (2017), 대한임베디드공학회[DOI]
- S. W. Cheng, "Rainbow:Architecture-Based Self-Adaptation with Reusable Infrastructure", IEEE on Computer, 37(10), pp.46~54 (2004)
- P. Bresciani, "Tropos: An Agent-Oriented Software Development Methodology. Autonomous Agents and Multi-Agent Systems", Autonomous Agents and Multi-Agent Systems, 8(3), pp.203~236 (2004)
- M. Morandini, "Towards Goal-Oriented Development of Self-Adaptive Systems", SEAMS '08 Proceedings of the 2008 International Workshop on Software Engineering for Adaptive and Self-managing Systems, pp.9~16 (2008)
- 장준혁, "애플리케이션 특징에 따른 CFS 태스크 우선순위 제어 기법", 한국콘텐츠학회 논문지, 21(6), pp.12~18 (2021), 한국콘텐츠학회[DOI]
- N. N. Jain, "Improvising Process Scheduling Using Machine Learning", 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology, pp.1379~1382 (2018)
- C. S. Wong, "Fairness and Interactive Performance of O(1)and CFS Linux Kernel Schedulers", 2008 International Symposium on Information Technology, 4, pp.1~8 (2008)
- IITP, "Weekly ICT Trends, No. 2024", 6~ (2021)
- S. M. Mostafa, "Achieving Better Fairness for Multithreaded Programs in Linux using Group Threads Scheduler", 2013 International Workshop on ICT at Beppu (2013)
- 정한수, "K10026 기반 스마트 플러그 시스템 개발 및 성능 분석", 대한임베디드공학회논문지, 11(5), pp.287~298 (2016), 대한임베디드공학회[DOI]