Effective Deep Learning Techniques for Prediction of Energy Consumption in Smart Buildings

Energy consumption is an important aspect of the energy management system. Over the past few decades, it has been recorded that there has been a drastic increase in global energy use. As a result, every country develops different approaches to reducing energy consumption in different sectors. Recently deep learning models are the most effective in the field of prediction. For estimating power consumption, this work employs the LSTM model to identify an accurate pattern of time series data. After the model has been trained, it is finally put to examine the future trend. Applying a standard hourly energy consumption data set, we conducted the analysis and used the R2_Score and Mean Square Logarithmic error (MSLE) metric to find the error.