Abstract
District heating systems that distribute heat through pipelines to residential and commercial buildings have been widely used in Northern Europe and according to the latest study (Werner, 2017) [1], district heating has the largest share of the heat supply market in Sweden. Therefore, energy efficiency of district heating systems is of great interest to energy stakeholders. However, it is common that district heating systems fail to achieve the expected performance due to various faults or inappropriate operations. Night setback is one control strategy that has been proved to be not a suitable setting for well insulated modern buildings in terms of both economic factor and energy efficiency. Especially, night setback leads to sudden morning peak that can be problematic to utility companies. In this study, a bidirectional long short term memory neural network based approach with attention mechanism is proposed for classifying substations that use night setback regularly. To evaluate the effectiveness of the proposed approach, data of 10 anonymous substations in Sweden are used in the case study. Precision, recall, and f1 score are used as the performance measures. Results of out of sample testing show that the proposed approach outperform the baseline models in this study.
Highlights
With the development of smart thermal grids framework [2], district heating systems play an important role in sustainable thermal energy production [3,4]
Six commonly used baseline classifiers, namely, Support Vector Classifier (SVC), Multi-layer perceptron neural network (MLP), Logistic Regression (LR), K-Nearest Neighbor (KNN), Decision Trees (DT), Random Forest (RF) and a Bidirectional Long Short Memory (BDLSTM) without attention mechanism are used in the experiment to compare the performance of the proposed method
Results show that BDLSTM classifier with attention mechanism outperforms the other models in terms of average f1 score, while DT has the lowest f1 scores among all eight classifiers
Summary
With the development of smart thermal grids framework [2], district heating systems play an important role in sustainable thermal energy production [3,4]. A supervised learning approach for night setback classification is proposed using BDLSTM [12] and attention mechanism as the main building blocks for night setback identification of district heating substations, which is the first attempt in this problem domain. A machine learning approach is proposed for night setback identification of district heating substations, which is barely found in the literature Both deep neural network and attention mechanism are explored for the first time in this problem domain. Attention distributions of different cases are plotted and analyzed, the result shows that the distribution of attention probabilities is reasonably aligned with domain expert knowledge that is not all time steps of a daily energy usage series contribute when identifying night setback. Conclusions and future works are presented in the last section
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
