Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
Signal Processing
2020-08-11 v3 Artificial Intelligence
Machine Learning
Machine Learning
Abstract
Detecting inaccurate smart meters and targeting them for replacement can save significant resources. For this purpose, a novel deep-learning method was developed based on long short-term memory (LSTM) and a modified convolutional neural network (CNN) to predict electricity usage trajectories based on historical data. From the significant difference between the predicted trajectory and the observed one, the meters that cannot measure electricity accurately are located. In a case study, a proof of principle was demonstrated in detecting inaccurate meters with high accuracy for practical usage to prevent unnecessary replacement and increase the service life span of smart meters.
Keywords
Cite
@article{arxiv.1907.11377,
title = {Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study},
author = {Ming Liu and Dongpeng Liu and Guangyu Sun and Yi Zhao and Duolin Wang and Fangxing Liu and Xiang Fang and Qing He and Dong Xu},
journal= {arXiv preprint arXiv:1907.11377},
year = {2020}
}