The Forecastability of Underlying Building Electricity Demand from Time Series Data

Forecasting building energy consumption has become a promising solution in Building Energy Management Systems for energy saving and optimization. Furthermore, it can play an important role in the efficient management of the operation of a smart grid. Different data-driven approaches to forecast the future energy demand of buildings at different scale, and over various time horizons, can be found in the scientific literature, including extensive Machine Learning and Deep Learning approaches. However, the identification of the most accurate forecaster model which can be utilized to predict the energy demand of such a building is still challenging. In this paper, the design and implementation of a data-driven approach to predict how forecastable the future energy demand of a building is, without first utilizing a data-driven forecasting model, is presented. The investigation utilizes a historical electricity consumption time series data set with a half-hour interval that has been collected from a group of residential buildings located in the City of London, United Kingdom. The proposed methodology mainly consists of four steps: firstly, we utilized four data-driven approaches (daily and weekly naive, Light Gradient Boosting Machine, and Linear Regression) to predict the day-ahead of building energy demand, and generate target labels of interest. The four forecasting approaches have been evaluated by using the Root Mean Squared Error, and Mean Absolute Error. Secondly, two feature extraction packages have been utilized to convert each of the building electricity demand time series into a feature matrix. Thirdly, we added the label of interest (i.e. best forecaster model) to each element of the extracted feature matrix. Finally, we utilized a classification data-driven approach (i.e. Random Forest) on the extracted feature datasets to predict how forecastable the future energy demand of such a building is. The experimental results demonstrate that it is possible to make a prior estimates about the forecastability of certain electricity demand time series of such a building.