AI-Powered Prepaid Smart Energy Meter with LSTM Load Forecasting and Anomaly Detection Government College of Engineering, Amravati
Abstract: The increasing demand for efficient energy management has led to the development of smart metering systems integrated with artificial intelligence. This paper presents an AI-powered prepaid smart energy meter that combines Long Short-Term Memory (LSTM) based load forecasting with real-time anomaly detection. The proposed system enables consumers to monitor and control electricity usage through a prepaid mechanism while providing predictive insights into future consumption patterns. LSTM models are employed to capture temporal dependencies in energy usage, improving forecasting accuracy. Additionally, anomaly detection algorithms identify irregular consumption patterns, power theft, and system faults. The integration of forecasting and anomaly detection enhances grid reliability, reduces energy wastage, and promotes efficient demand-side management.
Keywords: smart energy meter, prepaid electricity system, energy load forecasting, anomaly detection, power theft monitoring
How to Cite?: Pratigya C. Kolhatkar, Dr. Kawita D. Thakur, "AI-Powered Prepaid Smart Energy Meter with LSTM Load Forecasting and Anomaly Detection Government College of Engineering, Amravati", Volume 15 Issue 5, May 2026, International Journal of Science and Research (IJSR), Pages: 1124-1126, https://www.ijsr.net/getabstract.php?paperid=SR26515181150, DOI: https://dx.doi.org/10.21275/SR26515181150