A Combined Deep Learning Approach for Time Series Prediction in Energy Environments

In smart grids and microgrids, time series prediction is a fundamental tool for enabling intelligent energy resource management and advanced interactions between heterogeneous agents. In this work, we propose a solution to the energy forecasting problem based on two machine learning techniques: Convolutional Neural Network and Long Short-Term Memory Network. These techniques are combined with a new embedding format to appropriately feed the time series to the stacked network architecture. The resulting novel deep learning scheme is able to retrieve information from the data by inferring time dependent correlation structures. The model is validated using real-world examples, showing good performances with a 3-days forecasting horizon.