2019 VOL.2 Aug No.4

• Title: Real-time monitoring algorithm for task scheduling abnormal data of IoT equipment
• Name: Eltahir Akram
• Company: University of Wollongong
• Abstract:

  The real-time monitoring algorithm of conventional IoT task scheduling anomaly data can detect real-time detection of abnormal data of IoT task scheduling. However, when real-time monitoring of the underlying IoT device is performed, there is a shortage of real-time monitoring coverage. Device task scheduling abnormal data real-time monitoring algorithm. Using the real-time monitoring data frame construction of abnormal data, KPCA dimensionality reduction processing is performed on the task scheduling abnormal data, realizing the real-time monitoring data preprocessing of the underlying equipment task scheduling abnormal data of the Internet of Things; Based on the real-time monitoring algorithm SVM-weights program and the weighted SVDD-Negative program design, the real-time monitoring algorithm for the task scheduling abnormal data of the IoT underlying device is designed. The experimental data shows that the proposed real-time monitoring algorithm is 35.89% higher than the conventional real-time monitoring algorithm, which is suitable for real-time monitoring of the abnormal data of task scheduling of the underlying equipment of the Internet of Things.

  
  

• Keyword: underlying equipment; task scheduling; abnormal data; real-time monitoring algorithm;
• DOI: 10.12250/jpciams2019040118
• Citation form: Eltahir Akram.Real-time monitoring algorithm for task scheduling abnormal data of IoT equipment[J]. Computer Informatization and Mechanical System, 2019, vol. 2, pp. 74-78.

[1] Qian Xiaojun, Fan Dongping, Ji Genlin. Fast Mining Simulation of Fault Data in IoT Difference Database[J]. Computer Simulation, 2016, 33(1):301-304.

[2] HAN Kui-kui, XIE Zai-peng, Lü Xin. A Scheduling Strategy for Fog Calculation Based on Improved Genetic Algorithm[J]. Computer Science, 2018, 45(4):137-142.

[3] Guo Huiyun, Fang Jun, Li Dong. Multi-source data real-time storage system based on load balancing[J]. Computer Engineering and Science, 2017, 39(4):641-647.

[4] Yang Fei, Ma Weichun, Hou Jin, et al. Matrix Multiplication Acceleration Algorithm Based on MPSoC Parallel Scheduling[J]. Computer Science, 2017, 44(8):36-41.

[5] Zhang Qi, Hu Yupeng, Zang Cun, et al. Edge Computing Application: Abnormal Real-time Detection Algorithm for Sensing Data[J]. Computer Research and Development, 2018, 55(3):524-536.

[6] Qian Xiaojun, Fan Dongping, Ji Genlin. Clustering Scheduling Algorithm for Real-Time Task Transmission in Internet of Things Environment[J]. Computer Science, 2016, 43(11):176-179.

[7] Deng Xiaoheng, Guan Peiyuan, Wan Zhiwen, et al. Collaborative Research of Edge Computing Resources Based on Comprehensive Trust[J]. Computer Research and Development, 2018, 55(3):449-477.

[8] Ding Nan, Nie Zhenghang, Xu Li, et al. Data association task scheduling algorithm for vehicle networking applications [J]. Journal of Computer, 2017, 40(7):1614-1625.

[9] Wang Xianghua, Chen Tefang, Zhang Biming, et al. Web data clustering algorithm based on time series and task scheduling[J] . Computer Engineering and Applications, 2016, 52(9):159-163.

[10] Chen Wei, Ke Wende, Xu Bo. A Web Data Clustering Algorithm Based on Incremental Time Series and Optimal Task Scheduling[J] . Modern Electronic Technology, 2016, v.39;No.469(14):4-8.