DOI QR코드

DOI QR Code

컴퓨팅 부하 예측 DNN 모델 기반 디지털 트윈 소프트웨어 개발 프레임워크

A Digital Twin Software Development Framework based on Computing Load Estimation DNN Model

  • 김동연 (한국기술교육대학교 컴퓨터공학과) ;
  • 윤성진 (한국기술교육대학교 컴퓨터공학과) ;
  • 김원태 (한국기술교육대학교 컴퓨터공학과)
  • Kim, Dongyeon (The Department of Computer Science and Engineering, Korea University of Technology and Education) ;
  • Yun, Seongjin (The Department of Computer Science and Engineering, Korea University of Technology and Education) ;
  • Kim, Won-Tae (The Department of Computer Science and Engineering, Korea University of Technology and Education)
  • 투고 : 2021.05.18
  • 심사 : 2021.07.19
  • 발행 : 2021.07.30

초록

인공지능 클라우드는 학습된 모델 공유 및 실행 환경을 제공하여 인공지능 기술과 제어 기술을 융합하는 자율 사물 개발을 지원한다. 기존 자율 사물 개발 기술은 인공지능 모델의 정확도만을 고려하여 은닉 계층 수 및 커널 수 증가 등 모델의 복잡성을 증가시켜 결과적으로 많은 연산량을 요구하게 한다. 자원 제약적 컴퓨팅 환경은 해당 모델이 필요로 하는 충분한 자원을 제공할 수 없어 자율 사물의 실시간성 장애를 발생시킬 수 있다. 본 논문은 컴퓨팅 환경에 최적화된 인공지능 모델을 선택하는 디지털 트윈 소프트웨어 개발 프레임워크를 제안한다. 제안 프레임워크는 DNN 기반 부하 예측 모델을 활용하여 제어 소프트웨어를 개발한다. 부하 예측 모델은 디지털 트윈을 활용하여 인공지능 모델의 부하를 예측하여 특정 컴퓨팅 환경에 최적의 모델 선택을 지원한다. 대표적인 CNN 모델을 활용한 부하 예측 실험으로 제안 부하 예측 DNN 모델이 수식 기반 부하 예측 대비 최대 20%의 오류를 보임을 확인했다.

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

키워드

과제정보

본 논문은 2020년도 한국기술교육대학교 교수 교육연구진흥과제의 지원과 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원(No. 2018-0-01456) 지원을 통하여 연구되었음.

참고문헌

  1. Software Policy & Research Institute, Report on the AI Talents in New Southern and Northern Countries, 2020.
  2. R. Kanan, O. Elhassan, R. Bensalem, "An IoT-based autonomous system for workers' safety in construction sites with real-time alarming, monitoring, and positioning strategies," Automation in Construction, Vol.88, pp.73-86, Apr 2018. https://doi.org/10.1016/j.autcon.2017.12.033
  3. C.J. Marshalla, B. Roberts, M. Grenn, "Adaptive and automated reasoning for autonomous system resilience in uncertain worlds," Disciplinary Convergence in Systems Engineering Research, pp.799-812, 2018, doi:10.1007/978-3-319-62217-0_56.
  4. N. Tijtgat, W. Van Ranst, T. Goedeme, B. Volckaert, F. De Turck, "Embedded real-time object detection for a UAV warning system," Proceedings of the IEEE International Conference on Computer Vision Workshops, pp.2110-2118, 2017.
  5. F. Luo, C. Jiang, S. Yu, J. Wang, Y. Li, Y. Ren, "Stability of cloud-based UAV systems supporting big data acquisition and processing," IEEE Transactions on Cloud Computing, Vol.7, No.3, pp.866-877, Apr 2017. https://doi.org/10.1109/tcc.2017.2696529
  6. D. Kim, S. Yun, W.T. Kim, "Intelligent solution software development framework for easy Autonomous thing development," Proceedings of Symposium of the Korean Institute of communications and Information Sciences, Jeju, Korea, pp 770-771, 2021 June.
  7. R. Huang, J. Pedoeem, C. Chen, "YOLO-LITE: a real-time object detection algorithm optimized for non-GPU computers," In 2018 IEEE International Conference on Big Data (Big Data), pp.2503-2510, Dec 2018.
  8. V.S. Marco, B. Talyor, Z. Wang, Y. Elkhatib, "Optimizing deep learning inference on embedded systems through adaptive model selection," ACM Transactions on Embedded Computing Systems (TECS), Vol.19, No.1, pp.1-28, Feb 2020.
  9. A. llic, F. Pratas, L. Sousa, "Cache-aware roofline model: Upgrading the loft," IEEE Computer Architecture Letters, Vol.13, No.1, pp.21-24, Apr 2013. https://doi.org/10.1109/L-CA.2013.6
  10. K. He, J. Sun, "Convolutional neural networks at constrained time cost", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.5353-5360, 2015.
  11. N. Ma, X. Zhang, H.T. Zheng, J. Sun, "Shufflenet v2: Practical guidelines for efficient cnn architecture design," Proceedings of the European conference on computer vision (ECCV), pp.116-131, 2018.