Technology

A Sequential Modelling Approach for Indoor Temperature Prediction and Heating Control in Smart Buildings

Smart building solutions can help to save a lot for operations and maintenance and to maintain a high level of comfort. One of the examples is meeting a target temperature at a pre-set time. A recent paper on arXiv.org suggests how to decide the best time to switch on the radiator, for instance, when a person asks the building management system to heat up a room before arriving home.

Smart home - artistic interpretation. Image credit: geralt via Pixabay (Pixabay licence)

Smart home – artistic interpretation. Image credit: geralt via Pixabay (Pixabay licence)

The intelligent building system is connected to lighting, occupancy, temperature, air quality, and other sensors. The collected data are analyzed in a two-stage algorithm. The first part predicts ambient conditions using time series. The second uses machine learning to predict future indoor temperature. The mixed temporal-spatial approach is more flexible compared to traditional rule-based control systems and enables real-time control of the temperature. It contributes to efficient energy utilization and sustainability in smart buildings.

The rising availability of large volume data has enabled a wide application of statistical Machine Learning (ML) algorithms in the domains of Cyber-Physical Systems (CPS), Internet of Things (IoT) and Smart Building Networks (SBN). This paper proposes a learning-based framework for sequentially applying the data-driven statistical methods to predict indoor temperature and yields an algorithm for controlling building heating system accordingly. This framework consists of a two-stage modelling effort: in the first stage, an univariate time series model (AR) was employed to predict ambient conditions; together with other control variables, they served as the input features for a second stage modelling where an multivariate ML model (XGBoost) was deployed. The models were trained with real world data from building sensor network measurements, and used to predict future temperature trajectories. Experimental results demonstrate the effectiveness of the modelling approach and control algorithm, and reveal the promising potential of the data-driven approach in smart building applications over traditional dynamics-based modelling methods. By making wise use of IoT sensory data and ML algorithms, this work contributes to efficient energy management and sustainability in smart buildings.

Link: https://arxiv.org/abs/2009.09847