ABSTRACT
We present a heat load forecasting method for district heating systems that aims to facilitate its regulation. Unlike traditional time-series prediction-based approaches, we address the problem with the Transformer, a recent breakthrough in deep learning that leverages an attention mechanism to identify recurring patterns in the input sequence regardless of their distance. Because the heat load state at a time point is highly dependent on its preceding states, we adopt a simple but effective locality enhancement method to boost the local context information. Using a simulated heating system modeled by MATLAB/Simulink software, we demonstrate that the Transformer-based heat load forecasting approach can achieve higher accuracy than classic RNN models such as LSTM. Once equipped with a locality enhancement mechanism, it can adapt to short-term heat load fluctuations swiftly and precisely.
- Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, and Xifeng Yan. 2019. Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting. In Advances in Neural Information Processing Systems 32, NeurIPS 2019. 5244--5254.Google Scholar
- Henrik Lund, Sven Werner, Robin Wiltshire, Svend Svendsen, Jan Eric Thorsen, Frede Hvelplund, and Brian Vad Mathiesen. 2014. 4th Generation District Heating (4GDH): Integrating smart thermal grids into future sustainable energy systems. Energy 68 (2014), 1--11.Google ScholarCross Ref
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30, NeurIPS 2017. 5998--6008.Google Scholar
- Zhe Wang, Tianzhen Hong, and Mary Ann Piette. 2020. Building thermal load prediction through shallow machine learning and deep learning. Applied Energy 263 (2020), 1140--683.Google ScholarCross Ref
Index Terms
- Heat load forecasting for district water-heating system using locality-enhanced transformer encoder
Recommendations
Energy-Saving Potential of Seawater-Source Heat Pump District Heating System over Boiler-House District Heating System
ICEET '09: Proceedings of the 2009 International Conference on Energy and Environment Technology - Volume 01The seawater-source heat pump district heating system (SSHPDHS) is a renewable energy utilization system. However, under what conditions can the system achieve its energy-saving effect and how to evaluate its energy-saving potential are not very clear ...
Load Forecasting in District Heating Networks: Model Comparison on a Real-World Case Study
Machine Learning, Optimization, and Data ScienceAbstractDistrict Heating networks (DHNs) are promising technologies for heat distribution in residential and commercial buildings since they enable high efficiency and low emissions. Within the recently proposed paradigm of smart grids, DHNs have acquired ...
Heat Pumps Integration Trends in District Heating Networks of the Baltic States
AbstractClimate change considerations stimulate to switch to wider use of renewable energy sources for electricity generation. However in case of solar and wind energy, the use is burdened with non-regular generation trends. Electricity storage ...
Comments