Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
This addresses a resource-saving issue for utility companies by targeting meter replacements more efficiently, though it appears incremental as it applies existing deep learning techniques to a specific domain.
The paper tackled the problem of detecting inaccurate smart electricity meters by developing a deep-learning method using LSTM and a modified CNN to predict usage trajectories and identify discrepancies, demonstrating high accuracy in a case study to prevent unnecessary replacements.
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.