Paper Title: Predicting Anomalous Energy Consumption for Manufacturing Systems Using LSTM
Conference Name: Korean Institute of Communications and Information Sciences (KICS Summer 2024) Conference
Abstract: Anomalous energy consumption is a critical issue in the industrial sector that can signal operational inefficiencies, equipment malfunctions, or cyber-attacks. This work presents a method for predicting anomalous energy consumption using Long Short-Term Memory (LSTM) networks, a recurrent neural network well-known for its efficiency in time-series forecasting. The study compares LSTM with Autoregressive integrated moving average (ARIMA) and interquartile range (IQR)-based anomaly detection methods by analysing industry class codes, seasons, and hourly energy usage. The results show that LSTM outperforms ARIMA and IQR in accuracy and precision, reducing errors with each training epoch. The results demonstrate the value of multidimensional analysis in raising the industrial sector's energy systems' dependability and efficiency.