IMPROVING AUTOMATED ENERGY MONITORING SYSTEMS

Automated Energy Monitoring Systems (AEMS) are essential for efficient energy management but face challenges in data accuracy and processing speed. This study proposes a hybrid approach combining Kalman filtering for noise reduction and Long Short-Term Memory (LSTM) neural networks for predictive analytics to enhance AEMS performance. The methodology was tested on a 30-day dataset from a commercial building, achieving a 15% improvement in prediction accuracy and a 20% reduction in processing latency compared to baseline systems. These advancements enable more reliable and scalable energy monitoring, supporting sustainable energy management practices.