DOI QR코드

DOI QR Code

IoT 정보 수집을 위한 확률 기반의 딥러닝 클러스터링 모델

Probability-based Deep Learning Clustering Model for the Collection of IoT Information

  • 정윤수 (목원대학교 정보통신융합공학부)
  • Jeong, Yoon-Su (Dept. of Information Communication & Engineeringe, Mokwon University)
  • 투고 : 2020.01.29
  • 심사 : 2020.03.20
  • 발행 : 2020.03.28

초록

최근 IoT 네트워크는 이기종의 IoT 장치에서 발생하는 데이터를 효율적으로 처리하기 위해서 다양한 클러스터링 기법들이 연구되고 있다. 그러나, 기존 클러스터링 기법들은 정적으로 네트워크를 분할하는데 초점을 맞추고 있어서 이동이 가능한 IoT 장치에는 기존 클러스터링 기법들이 적합하지 않다. 본 논문에서는 에지 네트워크를 이용하여 IoT 장치의 정보를 수집·분석하기 위한 확률적 딥러닝 기반의 동적 클러스터링 모델을 제안한다. 제안 모델은 수집된 정보의 속성값의 빈도수를 확률적으로 딥러닝에 적용하여 서브넷을 구축한다. 구축된 서브넷은 시드로 추출된 연계 정보를 계층적 구조로 그룹핑할 때 사용하며, IoT 장치에 대한 동적 클러스터링의 속도 및 정확도를 향상시킨다. 성능평가 결과, 제안모델은 기존 모델에 비해 데이터 처리 시간이 평균 13.8% 향상되었고, 서버의 오버헤드는 기존 모델보다 평균 10.5% 낮게 나타났다. 서버에서 IoT 정보를 추출할 때의 정확도는 기존모델보다 평균 8.7% 향상되었다.

Recently, various clustering techniques have been studied to efficiently handle data generated by heterogeneous IoT devices. However, existing clustering techniques are not suitable for mobile IoT devices because they focus on statically dividing networks. This paper proposes a probabilistic deep learning-based dynamic clustering model for collecting and analyzing information on IoT devices using edge networks. The proposed model establishes a subnet by applying the frequency of the attribute values collected probabilistically to deep learning. The established subnets are used to group information extracted from seeds into hierarchical structures and improve the speed and accuracy of dynamic clustering for IoT devices. The performance evaluation results showed that the proposed model had an average 13.8 percent improvement in data processing time compared to the existing model, and the server's overhead was 10.5 percent lower on average than the existing model. The accuracy of extracting IoT information from servers has improved by 8.7% on average from previous models.

키워드

참고문헌

  1. L. Cheng, S. Kotoulas, T. E. Ward & G. Theodoropoulos. (2017). Improving the robustness and performance of parallel joins over distributed systems, Journal of Parallel and Distributed Computing, 109, 310-323. https://doi.org/10.1016/j.jpdc.2017.06.016
  2. M. Zaharia, M. Chowdhury, M. J. Franklin, S. Shenker & I. Stoica. (2010). Spark: cluster computing with working sets, Proceedings of the 2nd USENIX conference on Hot topics in cloud computing(HotCloud'10), 10-10.
  3. W. R. Heinzelman, A. Chandrakasan HAND & alakrishnan. (2000). Energyefficient communication protocol for wireless microsensor networks, Proceedings of the 33rd annual Hawaii international conference on System sciences, IEEE, 10
  4. G. Chen, C. Li, M. Ye & J. Wu. (2009). An unequal cluster-based routing protocol in wireless sensor networks, Wireless Networks, 15(2), 193-207. https://doi.org/10.1007/s11276-007-0035-8
  5. H. Mao, M. Alizadeh, I. Menache & S. Kandula,. (2016). Resource management with deep reinforcement learning, in Proceedings of the 15th ACM Workshop on Hot Topics in Networks. ACM, 50-56.
  6. X. Cui, J. S. Charles & T. Potok. (2013). GPU enhanced parallel computing for large scale data clustering, Journal of Future Generation Computer Systems, 29(7), 1736-1741. https://doi.org/10.1016/j.future.2012.07.009
  7. G. Andrade, G. Ramos, D. Madeira, R. Sachetto, R. Ferreira & L. Rocha. (2013). G-dbscan: A gpu accelerated algorithm for density based clustering, Journal of Procedia Computer Science, 18, 369-378. https://doi.org/10.1016/j.procs.2013.05.200
  8. H. Karau, A. Konwinski, P. Wendell & M. Zaharia. (2015). Learning Spark: Lightning-Fast Big Data Analysis, O'Reilly Media, Inc. 1-276.
  9. A. Katal, M. Wazid & R. H. Goudar. (2013). Big data: Issues, challenges, tools and Good practices, 2013 Sixth International Conference on Contemporary Computing(IC3), 404-409.
  10. X. Cui, P. Zhu, X. Yang, K. Li & C. Ji. (2014) Optimized big data K-means clustering using MapReduce, Journal of Supercomputing, 70(3), 1249-1259. https://doi.org/10.1007/s11227-014-1225-7
  11. Y. H. Kim, K S. Shim, M. S. Kim & J. S. Lee. (2014). DBCURE-MR: an efficient density-based clustering algorithm for large data using MapReduce, Journal of Information Systems, 42, 15-35.
  12. H. Hu, Y. Wen, T. S. Chua & X. Li. (2014). Toward Scalable Systems for Big Data Anaqlytics: A Technology Tutorial, IEEE Access, 2, 652-687. https://doi.org/10.1109/ACCESS.2014.2332453
  13. Q. Liu, A. Pruteanu, and S. Dulman. (2013). Gradient-based distance estimation for spatial computers, The Computer Journal, 56(12), 1469-1499. https://doi.org/10.1093/comjnl/bxt124
  14. Q. Liu, S. Dulman & M. Warnier. (2013). Area: an automatic runtime evolutionary adaptation mechanism for creating self-adaptation algorithms in wireless networks, Proceedings of the Spatial Computing Workshop in AAMAS, 23-28.
  15. H. Ye & G. Y. Li. (2018). Deep reinforcement learning for resource allocation in v2v communications, in 2018 IEEE International Conference on Communications (ICC). IEEE, 1-6.