About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Cloud Computing. 11th EAI International Conference, CloudComp 2021, Virtual Event, December 9–10, 2021, Proceedings

Research Article

Load Quality Analysis and Forecasting for Power Data Set on Cloud Platform

Download(Requires a free EAI acccount)
1 download
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-030-99191-3_1,
        author={Jixiang Gan and Qi Liu and Jing Zhang},
        title={Load Quality Analysis and Forecasting for Power Data Set on Cloud Platform},
        proceedings={Cloud Computing. 11th EAI International Conference, CloudComp 2021, Virtual Event, December 9--10, 2021, Proceedings},
        proceedings_a={CLOUDCOMP},
        year={2022},
        month={3},
        keywords={Data quality Load forecasting Data cleaning Cloud platform},
        doi={10.1007/978-3-030-99191-3_1}
    }
    
  • Jixiang Gan
    Qi Liu
    Jing Zhang
    Year: 2022
    Load Quality Analysis and Forecasting for Power Data Set on Cloud Platform
    CLOUDCOMP
    Springer
    DOI: 10.1007/978-3-030-99191-3_1
Jixiang Gan1, Qi Liu1,*, Jing Zhang1
  • 1: School of Computer and Software, Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology
*Contact email: qi.liu@nuist.edu.cn

Abstract

In the era of big data, The prediction management system combined with cloud computing platform can start from massive structured, semi-structured and unstructured data, which has a positive impact on improving the compliance quality analysis and prediction of power data sets. This paper focuses on the characteristics of all kinds of data sets needed in the research of power demand side business process of cloud platform at home and abroad, and analyzes, compares and summarizes all kinds of data sets. First, this paper analyzes the problems existing in various common data sets, and expounds the methods to improve the quality of data sets from two aspects of data cleaning and data preprocessing. Secondly, the LSTM prediction model and ARIMA prediction model are used to predict and analyze the collected power data to judge whether the data set has obvious defects in advance. Finally, through the experimental comparison of the two models, a more efficient prediction model is analyzed.

Keywords
Data quality Load forecasting Data cleaning Cloud platform
Published
2022-03-23
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-030-99191-3_1
Copyright © 2021–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL