文献类型：期刊文献

英文题名：Data consistency method of heterogeneous power IOT based on hybrid model

作者：Jiang Haoyu[1];Chen Kai[2];Ge Quanbo[3];Xu Jinqiang[1];Fu Yingying[2];Li Chunxi[2]

机构：[1]Guangdong Ocean Univ, Sch Elect & Informat Engn, 1 Haida Rd, Zhanjiang City, Guangdong, Peoples R China;[2]Shanghai Maritime Univ, Coll Logist Engn, 1550 Haigang Ave, Shanghai, Peoples R China;[3]Tongji Univ, Sch Elect & Informat Engn, 1239 Siping Rd, Shanghai, Peoples R China

年份：2021

卷号：117

起止页码：172

外文期刊名：ISA TRANSACTIONS

收录：SCI-EXPANDED(收录号：WOS:000708020200013)、、EI(收录号：20210609902153)、Scopus(收录号：2-s2.0-85100558505)、WOS

基金：The authors gratefully acknowledge financial support from the National Natural Science Foundation of China (NSFC) projects (grants 61803136) , and the assistance of Huayun Information Technology Co. Ltd and Hangzhou Zhongheng Provincial Key En-terprise Research Institute of PowerCloud.

语种：英文

外文关键词：Power IOT system; Hybrid model; Heterogeneous data consistency; Machine learning combination method

外文摘要：The data of the power Internet of Things (IOT) system is transferred from the IaaS layer to the SaaS layer. The general data preprocessing method mainly solves the problem of big data anomalies and missing at the PaaS layer, but it still lacks the ability to judge the high error data that meets the timing characteristics, making it difficult to deal with heterogeneous power inconsistent issues. This paper shows this phenomenon and its physical mechanism, showing the difficulty of building a quantitative model forward. A data-driven method is needed to form a hybrid model to correct the data. The research object is the electricity meter data on both sides of a commercial building transformer, which comes from different power IOT systems. The low-voltage side was revised based on the high-voltage side. Compared with the correction method based on purely using neural networks, the combined method, Linear Regression (LS) + Differential Evolution (DE) + Extreme Learning Machine (ELM), further reduces the deviation from approximately 4% to 1%. (C) 2021 Published by Elsevier Ltd on behalf of ISA.