Smart Microgrid Architecture For Home Energy Management System

被引:2
作者
Shakir, Majed [1 ]
Biletskiy, Yevgen [1 ]
机构
[1] Univ New Brunswick, Dept Elect & Comp Engn, Fredericton, NB, Canada
来源
2021 IEEE ENERGY CONVERSION CONGRESS AND EXPOSITION (ECCE) | 2021年
关键词
Smar Grid; Microgrid; HEMS; AI; Machine learning;
D O I
10.1109/ECCE47101.2021.9595165
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The present paper is devoted to adaptation of the achievements in the general research field of smart grid to the small power utilization systems, or microgrids. In particular, the focus of the present research is the architectural solution for a smart microgrid for automated home energy management systems. The proposed system architecture includes three main subsystems: load identification, forecasting and optimization. An automated home energy management system design requires general understanding of regulations and the ethics in collecting the building appliances data. The system design requires power data from the appliances be handled carefully when the data is stored. This is implemented to track the algorithm accuracy and data integrity. The software developed based on the present smart microgrid architecture delivers the lowest energy consumption price without sacrificing users comfort. One of the important features of the present architecture is adjustability because any of the three subsystems can be easily replaced by another subsystem with a more effective method in background.
引用
收藏
页码:808 / 813
页数:6
相关论文
共 16 条
  • [1] Energy Management Systems: State of the Art and Emerging Trends
    Aman, Saima
    Simmhan, Yogesh
    Prasanna, Viktor K.
    [J]. IEEE COMMUNICATIONS MAGAZINE, 2013, 51 (01) : 114 - 119
  • [2] [Anonymous], THESIS MIT
  • [3] LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT
    BENGIO, Y
    SIMARD, P
    FRASCONI, P
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02): : 157 - 166
  • [4] Intelligent Home Energy Management System based on Bi-directional Long-short Term Memory and Reinforcement Learning
    Diyan, Muhammd
    Khan, Murad
    Cao Zhenbo
    Silva, Bhagya Nathali
    Han, Jihun
    Han, Ki Jun
    [J]. 35TH INTERNATIONAL CONFERENCE ON INFORMATION NETWORKING (ICOIN 2021), 2021, : 782 - 787
  • [5] Framewise phoneme classification with bidirectional LSTM and other neural network architectures
    Graves, A
    Schmidhuber, J
    [J]. NEURAL NETWORKS, 2005, 18 (5-6) : 602 - 610
  • [6] Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
  • [7] McLorn Gareth, 2017, CIRED - Open Access Proceedings Journal, V2017, P1094, DOI 10.1049/oap-cired.2017.0190
  • [8] Medsker L., 1999, Recurrent neural networks: design and applications
  • [9] More J. J., 1978, Proceedings of the Biennial Conference on numerical analysis, P105
  • [10] Paszke S. A., 2017, PYTORCH PYTORCH