A Cost-Effective CNN-LSTM-Based Solution for Predicting Faulty Remote Water Meter Reading Devices in AMI Systems

Abstract

Automatic meter infrastructure (AMI) systems using remote metering are being widely used to utilize water resources efficiently and minimize non-revenue water. We propose a convolutional neural network-long short-term memory network (CNN-LSTM)-based solution that can predict faulty remote water meter reading (RWMR) devices by analyzing approximately 2,850,000 AMI data collected from 2762 customers over 360 days in a small-sized city in South Korea. The AMI data used in this study is a challenging, highly unbalanced real-world dataset with limited features. First, we perform extensive preprocessing steps and extract meaningful features for handling this challenging dataset with limited features. Next, we select important features that have a higher influence on the classifier using a recursive feature elimination method. Finally, we apply the CNN-LSTM model for predicting faulty RWMR devices. We also propose an efficient training method for ML models to learn the unbalanced real-world AMI dataset. A cost-effective threshold for evaluating the performance of ML models is proposed by considering the mispredictions of ML models as well as the cost. Our experimental results show that an F-measure of 0.82 and MCC of 0.83 are obtained when the CNN-LSTM model is used for prediction.

Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson’s Disease Affected by COVID-19: A Narrative Review

“…The authors designed the Markov cohort model, by taking into consideration the parameters based on previous studies databases. Lee et al [ 283 ] proposed an AI-based solution to faulty remote water-meter-reading (RWMR) devices. The authors adapted a convolutional neural network–long short-term memory network (CNN-LSTM) by considering 2762 customers over 360 days and collecting 2,850,000 AMI datasets in semi-rural areas of South Korea.…”

A Hierarchical Network with Fault Tolerance by a Multi-Factor Method for Neighborhood Area Network in Smart Grid

“…Recently, some papers and reports have investigated the monitoring and management functions of AMI, such as voltage monitoring, grid edge situational awareness, real-time demand response, and so on. In order to support the monitoring and management function of AMI, smart meters in AMI are required to report meter readings (not only the measurements for kW or kWh, but also reactive power and voltage readings) in 15 min, 30 min, or 1 h time intervals [12,13]. A large amount of metering data depends on NAN transmission.…”