A Scalable Ensemble Approach to Forecast the Electricity Consumption of Households

• Published in: IEEE transactions on smart grid Vol. 14; no. 1; pp. 757 - 768
• Main Authors: Botman, Lola, Soenen, Jonas, Theodorakos, Konstantinos, Yurtman, Aras, Bekker, Jessa, Vanthournout, Koen, Blockeel, Hendrik, De Moor, Bart, Lago, Jesus
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Buildings; Clustering; Customers; Data models; Electricity consumption; Forecasting; household consumption; Households; Long-term load forecasting; Measurement; Meteorological data; Predictive models; Residential energy; smart meter; Smart meters; Urban areas
• ISSN: 1949-3053; 1949-3061
• DOI: 10.1109/TSG.2022.3191399

Long-term individual household forecasting is useful in various applications, e.g., to determine customers' advance payments. However, the literature on this type of forecasting is limited; existing methods either focus on short-term predictions for individual households, or long-term prediction at an aggregated level (e.g., neighborhood). To fill this gap, we present a method that predicts the monthly consumption of individual households over the next year, given only a few months of consumption data during the current year. Utility companies can exploit this method to predict the consumption of any customer for the next year even with incomplete data. The method consists of three steps: clustering the data using <inline-formula> <tex-math notation="LaTeX">{k} </tex-math></inline-formula>-means, prediction using an ensemble of forecasts based on the historical median distribution among similar households, and smoothing the predictions to remove weather-dependent patterns. The method is highly accurate as it finished third in the IEEE-CIS competition (and ranks first when leveraging insights from another team), focused on forecasting long-term household consumption with incomplete data. It is also very scalable thanks to its low computational complexity and weak data requirements: the method only requires a few months of historical data and no household-specific or weather information.