Affiliation:
1. College of Electrical Engineering, Zhejiang University, 866 Yuhangtang Rd., Hangzhou 310058, China
2. School of Spatial Planning and Design, Hangzhou City University, 51 Huzhou Street, Hangzhou 310015, China
Abstract
Improving the accuracy of the forecasting of building power consumption is helpful in reducing commercial expenses and carbon emissions. However, challenges such as the shortage of training data and the absence of efficient models are the main obstacles in this field. To address these issues, this work introduces a model named MTLTFT, combining multi-task learning (MTL) with the temporal fusion transformer (TFT). The MTL approach is utilized to maximize the effectiveness of the limited data by introducing multiple related forecasting tasks. This method enhances the learning process by enabling the model to learn shared representations across different tasks, although the physical number of data remains unchanged. The TFT component, which is optimized for feature learning, is integrated to further improve the model’s performance. Based on a dataset from a large exposition building in Hangzhou, we conducted several forecasting experiments. The results demonstrate that MTLTFT outperforms most baseline methods (such as LSTM, GRU, N-HiTS) in terms of Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE), suggesting that MTLTFT is a promising approach for the forecasting of building power consumption and other similar tasks.
Funder
Zhejiang Provincial Natural Science Foundation of China
Key Research and Development Projects of ‘Vanguard’ and ‘Leading Goose’ in Zhejiang Province
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference43 articles.
1. Heating and cooling energy trends and drivers in buildings;Cabeza;Renew. Sustain. Energy Rev.,2015
2. Electricity demand response in China: Status, feasible market schemes and pilots;Li;Energy,2016
3. Box, G.E., Jenkins, G.M., Reinsel, G.C., and Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control, John Wiley & Sons.
4. A comparative analysis of artificial neural network architectures for building energy consumption forecasting;Moon;Int. J. Distrib. Sens. Netw.,2019
5. An expression-driven approach for long-term electric power consumption forecasting;Kaboli;Am. J. Data Min. Knowl. Discov.,2016