A deep learning framework for building energy consumption forecast

Increasing global building energy demand, with the related economic and environmental impact, upsurges the need for the design of reliable energy demand forecast models. This work presents kCNN-LSTM, a deep learning framework that operates on the energy consumption data recorded at predefined intervals to provide accurate building energy consumption forecasts. kCNN-LSTM employs (i) k−means clustering – to perform cluster analysis to understand the energy consumption pattern/trend; (ii) Convolutional Neural Networks (CNN) – to extract complex features with non-linear interactions that affect energy consumption; and (iii) Long Short Term Memory (LSTM) neural networks – to handle long-term dependencies through modeling temporal information in the time series data. The efficiency and applicability of kCNN-LSTM were demonstrated using a real time building energy consumption data acquired from a four-storeyed building in IIT-Bombay, India. The performance of kCNN-LSTM was compared with the k-means variant of the state-of-the-art energy demand forecast models in terms of well-known quality metrics. It is also observed that the accurate energy demand forecast provided by kCNN-LSTM due to its ability to learn the spatio-temporal dependencies in the energy consumption data makes it a suitable deep learning model for energy consumption forecast problems. •kCNN-LSTM, a deep learning based energy consumption forecast model, is presented.•Timestamp based features generated from the timestamp provides parameter-rich data.•k-means clustering analyzes the trend in energy consumption data.•CNN-LSTM captures spatio-temporal characteristics in energy consumption data.•A case study on KReSIT building energy consumption data is presented.