Graph attention neural network for water network partitioning

Springer Science and Business Media LLC - 2023
Kezhen Rong1, Minglei Fu1, Yunjie Huang1, Ming Zhang1, Lejin Zheng2, Jianfeng Zheng2, Miklas Scholz3, Zaher Mundher Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬4
1College of Sciences, Zhejiang University of Technology, Hangzhou, 310023, China
2Hangzhou Laison Technology Co., Ltd, Hangzhou, 310063, China
3Directorate of Engineering the Future, School of Science, Engineering and Environment, The University of Salford, Newton Building, Salford, M5 4WT, UK
4Civil and Environmental Engineering Department, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia

Tóm tắt

AbstractPartitioning a water distribution network into several district metered areas is beneficial for its management. Partitioning a network according to its node features and connections remains a challenge. A recent study has realized water network partitioning based on node features or pipe connections individually. This study proposes an unsupervised clustering method for nodes based on a graph neural network, which uses graph attention technology to update node features based on the connections and a neural network to cluster nodes. The similarity between nodes located in each area and the balance of the total water demand between areas are optimized, and the importance of the boundary pipes is calculated to determine the installation position of flowmeters and valves. Three water distribution networks with different structures and sizes are used to verify the proposed model. The results show that the average location differences (LocDiffs) within the areas of the three networks completed by partitioning are 0.12, 0.07, and 0.06, and the total demand differences (DemDiffs) between areas are 0.13, 0.27, and 0.29, respectively. The LocDiff and DemDiff of the proposed method decreased by 6% and 55%, respectively, when compared to the traditional clustering method. Additionally, the proposed method for calculating the importance of boundaries provides an objective basis for boundary closure. When the same number of boundaries are closed, the comprehensive impact of the proposed method on the pipe network decreases by 17.1%. The proposed method can be used in practical applications because it ensures a highly reliable and interpretive water distribution network partitioning method.

Từ khóa


Tài liệu tham khảo

Alvisi S (2015) A new procedure for optimal design of district metered areas based on the multilevel balancing and refinement algorithm. Water Resour Manag 29:4397–4409

Alvisi S, Franchini M (2014) A procedure for the design of district metered areas in water distribution systems. Procedia Eng 70:41–50. https://doi.org/10.1016/j.proeng.2014.02.006

Bhagat SK, Tiyasha Welde W et al (2019) Evaluating physical and fiscal water leakage in water distribution system. Water (Switzerland). https://doi.org/10.3390/w11102091

Brentan BM, Luvizotto E, Montalvo I et al (2017) Near real time pump optimization and pressure management. Procedia Eng 186:666–675. https://doi.org/10.1016/j.proeng.2017.06.248

Brentan B, Campbell E, Goulart T et al (2018) Social network community detection and hybrid optimization for dividing water supply into district metered areas. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0000924

Charalambous B (2008) Use of district metered areas coupled with pressure optimisation to reduce leakage. Water Supply 8:57–62. https://doi.org/10.2166/ws.2008.030

Choudhary M, Chouhan SS, Pilli ES, Vipparthi SK (2021) BerConvoNet: a deep learning framework for fake news classification. Appl Soft Comput 110:107614. https://doi.org/10.1016/j.asoc.2021.107614

Ciaponi C, Murari E, Todeschini S (2016) Modularity-based procedure for partitioning water distribution systems into independent districts. Water Resour Manag 30:2021–2036. https://doi.org/10.1007/s11269-016-1266-1

Di Nardo A, Di Natale M (2011) A heuristic design support methodology based on graph theory for district metering of water supply networks. Eng Optim 43:193–211. https://doi.org/10.1080/03052151003789858

Di Nardo A, Di Natale M, Di Mauro A (2013) Case study: Monterusciello network. In: Di Nardo A, Di Natale M, Di Mauro A (eds) Water supply network district metering. Springer Vienna, Vienna, pp 39–85. https://doi.org/10.1007/978-3-7091-1493-3_4

Di Nardo A, Di Natale M, Santonastaso GF et al (2014) Divide and conquer partitioning techniques for smart water networks. Procedia Eng 89:1176–1183. https://doi.org/10.1016/j.proeng.2014.11.247

Di Nardo A, Di Natale M, Giudicianni C et al (2015) Water distribution system clustering and partitioning based on social network algorithms. Procedia Eng 119:196–205. https://doi.org/10.1016/j.proeng.2015.08.876

Di Nardo A, Di Natale M, Gargano R et al (2018) Performance of partitioned water distribution networks under spatial-temporal variability of water demand. Environ Model Softw 101:128–136. https://doi.org/10.1016/j.envsoft.2017.12.020

Diao K, Zhou Y, Rauch W (2013) Automated creation of district metered area boundaries in water distribution systems. J Water Resour Plan Manag 139:184–190. https://doi.org/10.1061/(asce)wr.1943-5452.0000247

Farmani R, Walters G, Savic D (2006) Evolutionary multi-objective optimization of the design and operation of water distribution network: total cost vs. reliability vs. water quality. J Hydroinformatics 8:165–179. https://doi.org/10.2166/hydro.2006.019b

Ferrari G, Savic D, Becciu G (2014) Graph-theoretic approach and sound engineering principles for design of district metered areas. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0000424

Gajghate PW, Mirajkar A, Shaikh U et al (2021) Optimization of layout and pipe sizes for irrigation pipe distribution network using Steiner point concept. Math Probl Eng. https://doi.org/10.1155/2021/6657459

Giudicianni C, Di Nardo A, Di Natale M et al (2018) Topological taxonomy of water distribution networks. Water 10:444. https://doi.org/10.3390/w10040444

Giudicianni C, Herrera M, di Nardo A, Adeyeye K (2020) Automatic multiscale approach for water networks partitioning into dynamic district metered areas. Water Resour Manag 34:835–848. https://doi.org/10.1007/s11269-019-02471-w

Giustolisi O, Ridolfi L (2014) A novel infrastructure modularity index for the segmentation of water distribution networks. Water Resour Res 50:7648–7661. https://doi.org/10.1002/2014wr016067

Gomes R, Sá Marques A, Sousa J (2011) Estimation of the benefits yielded by pressure management in water distribution systems. Urban Water J 8:65–77. https://doi.org/10.1080/1573062x.2010.542820

Grayman WM, Murray R, Savic DA (2009) Effects of redesign of water systems for security and water quality factors. In: World environmental and water resources congress 2009. Great Rivers, pp 1–11

Gupta A, Bokde N, Kulat K, Yaseen ZM (2020) Nodal matrix analysis for optimal pressure-reducing valve localization in a water distribution system. Energies 13:1878

Hajebi S, Temate S, Barrett S et al (2014) Water distribution network sectorisation using structural graph partitioning and multi-objective optimization. Procedia Eng 89:1144–1151. https://doi.org/10.1016/j.proeng.2014.11.238

Herrera M, Izquierdo J, Pérez-García R, Montalvo I (2012) Multi-agent adaptive boosting on semi-supervised water supply clusters. Adv Eng Softw 50:131–136. https://doi.org/10.1016/j.advengsoft.2012.02.005

Herrera M, Abraham E, Stoianov I (2016) A graph-theoretic framework for assessing the resilience of sectorised water distribution networks. Water Resour Manag 30:1685–1699. https://doi.org/10.1007/s11269-016-1245-6

Herrera M, Canu S, Karatzoglou A, et al (2010) An approach to water supply clusters by semi-supervised learning

Izquierdo J, Herrera M, Montalvo I, Pérez-García R (2009) Division of water supply systems into district metered areas using a multi-agent based approach. In: International conference on software and data technologies. Springer, pp 167–180

Laucelli DB, Simone A, Berardi L, Giustolisi O (2016) Optimal design of district metering areas. Procedia Eng 162:403–410. https://doi.org/10.1016/j.proeng.2016.11.081

Lifshitz R, Ostfeld A (2018) District metering areas and pressure reducing valves trade-off in water distribution system leakage management. In: WDSA/CCWI joint conference proceedings

Liu J, Han R (2018) Spectral clustering and multicriteria decision for design of district metered areas. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0000916

Morrison J, Tooms S, Rogers D (2007) DMA management guidance notes version 1. In: Brothers KJ, Eng P (eds) Water loss task force, vol 1. IWA, London, pp 25–36

Nicolini M, Zovatto L (2009) Optimal location and control of pressure reducing valves in water networks. J Water Resour Plan Manag 135:178–187. https://doi.org/10.1061/(asce)0733-9496(2009)135:3(178)

Oyedele A, Ajayi A, Oyedele LO et al (2021) Deep learning and boosted trees for injuries prediction in power infrastructure projects. Appl Soft Comput 110:107587. https://doi.org/10.1016/j.asoc.2021.107587

Pesantez JE, Berglund EZ, Mahinthakumar G (2019) Multiphase procedure to design district metered areas for water distribution networks. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0001095

Puust R, Kapelan Z, Savic DA, Koppel T (2010) A review of methods for leakage management in pipe networks. Urban Water J 7:25–45

Rakhshani H, Idoumghar L, Ghambari S et al (2021) On the performance of deep learning for numerical optimization: An application to protein structure prediction. Appl Soft Comput 110:107596. https://doi.org/10.1016/j.asoc.2021.107596

Saldarriaga J, Bohorquez J, Celeita D et al (2019) Battle of the water networks district metered areas. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0001035

Sela Perelman L, Allen M, Preis A et al (2015) Automated sub-zoning of water distribution systems. Environ Model Softw 65:1–14. https://doi.org/10.1016/j.envsoft.2014.11.025

Sharma AN, Dongre SR, Gupta R, Ormsbee L (2022) Multiphase procedure for identifying district metered areas in water distribution networks using community detection, NSGA-III optimization, and multiple attribute decision making. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0001586

Taha AF, Wang S, Guo Y et al (2021) Revisiting the water quality sensor placement problem: optimizing network observability and state estimation metrics. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0001374

Tiernan ED, Hodges BR (2022) A topological approach to partitioning flow networks for parallel simulation. J Comput Civ Eng. https://doi.org/10.1061/(asce)cp.1943-5487.0001020

Todini E (2000) Looped water distribution networks design using a resilience index based heuristic approach. Urban Water 2:115–122. https://doi.org/10.1016/s1462-0758(00)00049-2

Twort AC, Ratnayaka DD, Brandt MJ (2000) Water supply. Elsevier, Amsterdam

Tzatchkov VG, Alcocer-Yamanaka VH, Bourguett Ortíz V (2008) Graph theory based algorithms for water distribution network sectorization projects. In: Water distribution systems analysis symposium 2006

Wu Y, Liu S, Wu X et al (2016) Burst detection in district metering areas using a data driven clustering algorithm. Water Res 100:28–37. https://doi.org/10.1016/j.watres.2016.05.016

Yang T, Yu X, Ma N et al (2022) An autonomous channel deep learning framework for blood glucose prediction. Appl Soft Comput 120:108636. https://doi.org/10.1016/j.asoc.2022.108636

Zhang Q, Wu ZY, Zhao M et al (2017) Automatic partitioning of water distribution networks using multiscale community detection and multiobjective optimization. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0000819

Zhang T, Yao H, Chu S et al (2021) Optimized DMA partition to reduce background leakage rate in water distribution networks. J Water Resour Plan Manag. https://doi.org/10.1061/(asce)wr.1943-5452.0001465

Thông tin
Thông tin xuất bản

Springer Science and Business Media LLC

Thông tin tác giả