@inproceedings{85e64caa363d445886f4425dea7eca6e,
title = "Cross-Domain Data Fusion on Distribution Network Voltage Estimation with D-S Evidence Theory",
abstract = "The Cyber-Physical system (CPS) is an emerging concept for realizing the system wholeness and the interplay of different network components in the electricity system with various embedded devices. However, the increasing penetration of embedded devices also brings severe data explosion and uncertainties to the voltage estimation process in practical power grid operations. Data fusion method has significant performance on improving the accuracy of state estimation on the deficient cross-domain dataset. This paper applies the data fusion method and D-S evidence theory to aggerate the information from various monitored devices in the distribution network and resolve the voltage estimation problem of the distribution network. Apart from conventional data fusion model, a two-stage D-S evidence data fusion framework is also proposed to improve the estimation accuracy and also quantify correlation factors between recorded parameters of monitored network devices and the overall network status of the whole distribution systems. This paper illustrates the feasibility and reliability of the proposed data fusion frameworks by a case study on an actual MV distribution system with deficient datasets and operation information of the main 33/11 kV transformer.",
keywords = "Cyber-physical systems, Data fusion, Decision making, Dempster-Shafer (D-S) evidence theory",
author = "Yuanbin Zhu and Chenghong Gu and Furong Li",
year = "2020",
month = jul,
doi = "10.1109/IJCNN48605.2020.9207414",
language = "English",
series = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "IEEE",
booktitle = "2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings",
address = "USA United States",
note = "2020 International Joint Conference on Neural Networks, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",
}