Huy Cuong Truong

1. Graph Neural Networks for Pressure Estimation in Water Distribution Systems (H. Truong, A. Tello, L. Alexander and V. Degeler), In Water Resources Research, 2024.

   Abstract

   Abstract Pressure and flow estimation in water distribution networks (WDNs) allows water management companies to optimize their control operations. For many years, mathematical simulation tools have been the most common approach to reconstructing an estimate of the WDNs hydraulics. However, pure physics-based simulations involve several challenges, for example, partially observable data, high uncertainty, and extensive manual calibration. Thus, data-driven approaches have gained traction to overcome such limitations. In this work, we combine physics-based modeling and graph neural networks (GNN), a data-driven approach, to address the pressure estimation problem. Our work has two main contributions. First, a training strategy that relies on random sensor placement making our GNN-based estimation model robust to unexpected sensor location changes. Second, a realistic evaluation protocol that considers real temporal patterns and noise injection to mimic the uncertainties intrinsic to real-world scenarios. As a result, a new state-of-the-art model, GAT with Residual Connections, for pressure estimation is available. Our model surpasses the performance of previous studies on several WDNs benchmarks, showing a reduction of absolute error of ≈40% on average.

   ---

   BibTeX

   
   @article{huy2024gatres, title = "Graph Neural Networks for Pressure Estimation in Water Distribution Systems", abstract = "Abstract Pressure and flow estimation in water distribution networks (WDNs) allows water management companies to optimize their control operations. For many years, mathematical simulation tools have been the most common approach to reconstructing an estimate of the WDNs hydraulics. However, pure physics-based simulations involve several challenges, for example, partially observable data, high uncertainty, and extensive manual calibration. Thus, data-driven approaches have gained traction to overcome such limitations. In this work, we combine physics-based modeling and graph neural networks (GNN), a data-driven approach, to address the pressure estimation problem. Our work has two main contributions. First, a training strategy that relies on random sensor placement making our GNN-based estimation model robust to unexpected sensor location changes. Second, a realistic evaluation protocol that considers real temporal patterns and noise injection to mimic the uncertainties intrinsic to real-world scenarios. As a result, a new state-of-the-art model, GAT with Residual Connections, for pressure estimation is available. Our model surpasses the performance of previous studies on several WDNs benchmarks, showing a reduction of absolute error of ≈40\% on average.", author = "H. Truong and A. Tello and L. Alexander and V. Degeler", year = "2024", month = jun, language = "English", doi = "https://doi.org/10.1029/2023WR036741", url = "https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2023WR036741", journal = "Water Resources Research", }

   ---

   urldoi
2. Large-scale multipurpose benchmark datasets for assessing data-driven deep learning approaches for water distribution networks (A. Tello, H. Truong, A. Lazovik and V. Degeler), In Engineering Proceedings, MDPI, volume 69, 2024.

   BibTeX

   
   @article{tello2024:wdsa-ccwi, title={Large-scale multipurpose benchmark datasets for assessing data-driven deep learning approaches for water distribution networks}, author={A. Tello and H. Truong and A. Lazovik and V. Degeler}, journal={Engineering Proceedings}, volume={69}, number={1}, pages={50}, year={2024}, publisher={MDPI} }

   ---

3. Graph neural networks for pressure estimation in water distribution systems (H. Truong, A. Tello, A. Lazovik and V. Degeler), In Water Resources Research, Wiley Online Library, volume 60, 2024.

   BibTeX

   
   @article{truong2024:wrr, title={Graph neural networks for pressure estimation in water distribution systems}, author={H. Truong and A. Tello and A. Lazovik and V. Degeler}, journal={Water Resources Research}, volume={60}, number={7}, pages={e2023WR036741}, year={2024}, publisher={Wiley Online Library} }

   ---

4. Large-Scale Multipurpose Benchmark Datasets for Assessing Data-Driven Deep Learning Approaches for Water Distribution Networks (A. Tello, H. Truong, L. Alexander and V. Degeler), In 3rd International Joint Conference on Water Distribution Systems Analysis & Computing and Control for the Water Industry (WDSA/CCWI), 2024.

   Abstract

   Currently, the number of common benchmark datasets that researchers can use straight away for assessing data-driven deep learning approaches is very limited. Most studies provide data as configuration files. It is still up to each practitioner to follow a particular data generation method and run computationally intensive simulations to obtain usable data for model training and evaluation. In this work, we provide a collection of datasets that includes several small- and medium-sized publicly available Water Distribution Networks (WDNs), including Anytown, Modena, Balerma, C-Town, D-Town, L-Town, Ky1, Ky6, Ky8, and Ky10. In total, 1,394,400 h of WDN data operating under normal conditions are made available to the community.

   ---

   BibTeX

   
   @inproceedings{tello2024:wdsa, title = "Large-Scale Multipurpose Benchmark Datasets for Assessing Data-Driven Deep Learning Approaches for Water Distribution Networks", abstract = "Currently, the number of common benchmark datasets that researchers can use straight away for assessing data-driven deep learning approaches is very limited. Most studies provide data as configuration files. It is still up to each practitioner to follow a particular data generation method and run computationally intensive simulations to obtain usable data for model training and evaluation. In this work, we provide a collection of datasets that includes several small- and medium-sized publicly available Water Distribution Networks (WDNs), including Anytown, Modena, Balerma, C-Town, D-Town, L-Town, Ky1, Ky6, Ky8, and Ky10. In total, 1,394,400 h of WDN data operating under normal conditions are made available to the community.", author = "A. Tello and H. Truong and L. Alexander and V. Degeler", year = "2024", month = sep, language = "English", doi = "10.3390/engproc2024069050", url = "https://www.mdpi.com/2673-4591/69/1/50", booktitle = "3rd International Joint Conference on Water Distribution Systems Analysis & Computing and Control for the Water Industry (WDSA/CCWI)", }

   ---

   urldoi