Data science and machine learning in the IIoT concepts of power plants

被引:17
作者
Milic, Sasa D. [1 ]
Durovic, Zeljko [2 ]
Stojanovic, Mirjana D. [3 ]
机构
[1] Univ Union Nikola Tesla, Fac Diplomacy & Secur, Belgrade, Serbia
[2] Univ Belgrade, Sch Elect Engn, Belgrade, Serbia
[3] Univ Belgrade, Fac Transport & Traff Engn, Belgrade, Serbia
关键词
Machine learning; Data Science (DS); Data processing; Algorithm selection; Industrial internet of things (IIoT); Smart power plant; INDUSTRIAL INTERNET; THINGS; SYSTEMS; CLOUD;
D O I
10.1016/j.ijepes.2022.108711
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Smart power plants are no longer just futuristic ideas but are rapidly becoming a reality, and for this to be achievable, an application of artificial intelligence in Industrial Internet of Things (IIoT) concepts is necessary. This paper presents the place and role of Data Science (DS) and Machine Learning (ML) on edge, fog, and cloud levels of vertical IIoT concepts of power plants. A comprehensive functional analysis of edge, fog, and cloud levels has been done. Data analyzing, preprocessing, and processing are described on all levels separately. Limitations in signal conversion and data preprocessing at the edge level (edge computing), data processing and analysis at the fog level (fog computing), and information processing at the application and cloud levels (highend and cloud computing) are described in detail. ML algorithms have been selected based on the particular management and control level. The proposed concepts represent management and maintenance improvements with minimal investment and avoidance of production downtime.
引用
收藏
页数:8
相关论文
共 36 条
  • [1] Deploying Fog Computing in Industrial Internet of Things and Industry 4.0
    Aazam, Mohammad
    Zeadally, Sherali
    Harras, Khaled A.
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2018, 14 (10) : 4674 - 4682
  • [2] Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
    Alzubaidi, Laith
    Zhang, Jinglan
    Humaidi, Amjad J.
    Al-Dujaili, Ayad
    Duan, Ye
    Al-Shamma, Omran
    Santamaria, J.
    Fadhel, Mohammed A.
    Al-Amidie, Muthana
    Farhan, Laith
    [J]. JOURNAL OF BIG DATA, 2021, 8 (01)
  • [3] [Anonymous], CISKOS IOT REF MOD
  • [4] Bangert P, 2021, MACHINE LEARNING DAT, P237
  • [5] The industrial internet of things (IIoT): An analysis framework
    Boyes, Hugh
    Hallaq, Bit
    Cunningham, Joe
    Watson, Tim
    [J]. COMPUTERS IN INDUSTRY, 2018, 101 : 1 - 12
  • [6] Geron A., 2019, HANDS ON MACHINE LEA
  • [7] An IoT-Based Ship Berthing Method Using a Set of Ultrasonic Sensors
    Kamolov, Ahmadhon
    Park, Suhyun
    [J]. SENSORS, 2019, 19 (23)
  • [8] Kang Z, 2020, COMPUT IND ENG, V149, P1
  • [9] Edge Computing in the Industrial Internet of Things Environment: Software-Defined-Networks-Based Edge-Cloud Interplay
    Kaur, Kuljeet
    Garg, Sahil
    Aujla, Gagangeet Singh
    Kumar, Neeraj
    Rodrigues, Joel J. P. C.
    Guizani, Mohsen
    [J]. IEEE COMMUNICATIONS MAGAZINE, 2018, 56 (02) : 44 - 51
  • [10] Deep learning in power systems research: A review
    Khodayar, Mandi
    Liu, Guangyi
    Wang, Jianhui
    Khodayar, Mohammad E.
    [J]. CSEE JOURNAL OF POWER AND ENERGY SYSTEMS, 2021, 7 (02): : 209 - 220