On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models
A Predictor-Corrector (PC) approach for on-line forecasting of water usage in an urban water system is presented and demonstrated. The M5 Model-Trees algorithm is used to predict water demands and Genetic Algorithms (GAs) are used to correct (i.e., calibrate according to on-line pressure and flow ra...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
CRC Press
2012
|
| Online Access: | http://hdl.handle.net/1721.1/73921 https://orcid.org/0000-0001-5358-4140 |
| _version_ | 1826189858834481152 |
|---|---|
| author | Preis, Ami Whittle, Andrew Ostfeld, A. Perelman, L. |
| author2 | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Preis, Ami Whittle, Andrew Ostfeld, A. Perelman, L. |
| author_sort | Preis, Ami |
| collection | MIT |
| description | A Predictor-Corrector (PC) approach for on-line forecasting of water usage in an urban water system is presented and demonstrated. The M5 Model-Trees algorithm is used to predict water demands and Genetic Algorithms (GAs) are used to correct (i.e., calibrate according to on-line pressure and flow rate measurements) these predicted values in real-time. The PC loop repeats itself at each subsequent time-step with the forecasting model inputs being the corrected outputs of previous iterations, thus improving the model performances
over time. To meet the computational efficiency requirements of real-time hydraulic state estimation, the urban network model which is comprised of over ten thousand pipelines and nodes is reduced using a water system aggregation technique. The reduced model, which resembles the original system's hydraulic performances with high accuracy, simplifies the computation of the PC loop and facilitates the implementation of the on-line model. The developed methodology is tested against the real input data of an urban water distribution
system comprised of approximately 12500 nodes and 15000 pipes. |
| first_indexed | 2024-09-23T08:25:23Z |
| format | Article |
| id | mit-1721.1/73921 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:25:23Z |
| publishDate | 2012 |
| publisher | CRC Press |
| record_format | dspace |
| spelling | mit-1721.1/739212022-09-23T12:38:20Z On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models Preis, Ami Whittle, Andrew Ostfeld, A. Perelman, L. Massachusetts Institute of Technology. Department of Civil and Environmental Engineering Whittle, Andrew Whittle, Andrew Preis, Ami A Predictor-Corrector (PC) approach for on-line forecasting of water usage in an urban water system is presented and demonstrated. The M5 Model-Trees algorithm is used to predict water demands and Genetic Algorithms (GAs) are used to correct (i.e., calibrate according to on-line pressure and flow rate measurements) these predicted values in real-time. The PC loop repeats itself at each subsequent time-step with the forecasting model inputs being the corrected outputs of previous iterations, thus improving the model performances over time. To meet the computational efficiency requirements of real-time hydraulic state estimation, the urban network model which is comprised of over ten thousand pipelines and nodes is reduced using a water system aggregation technique. The reduced model, which resembles the original system's hydraulic performances with high accuracy, simplifies the computation of the PC loop and facilitates the implementation of the on-line model. The developed methodology is tested against the real input data of an urban water distribution system comprised of approximately 12500 nodes and 15000 pipes. Singapore-MIT Alliance for Research and Technology Singapore. National Research Foundation 2012-10-12T14:54:24Z 2012-10-12T14:54:24Z 2009-09 2009-05 Article http://purl.org/eprint/type/ConferencePaper 9780415548519 0415548519 9780203864289 020386428X http://hdl.handle.net/1721.1/73921 Preis, A. et al. "On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models." in Integrating water systems: proceedings of the tenth International Conference on Computing and Control for the Water Industry, CCWI 2009, Sheffield, UK, 1-3 September 2009, editors: Joby Boxall, Cedo Maksimovicc. CRC Press. https://orcid.org/0000-0001-5358-4140 en_US http://www.crcpress.com/product/isbn/9780415548519 Integrating Water Systems: Proceedings of the Tenth International Conference on Computing and Control in the Water Industry 2009 Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf CRC Press Whittle via Anne Graham |
| spellingShingle | Preis, Ami Whittle, Andrew Ostfeld, A. Perelman, L. On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models |
| title | On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models |
| title_full | On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models |
| title_fullStr | On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models |
| title_full_unstemmed | On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models |
| title_short | On-line Hydraulic State Estimation in Urban Water Networks Using Reduced Models |
| title_sort | on line hydraulic state estimation in urban water networks using reduced models |
| url | http://hdl.handle.net/1721.1/73921 https://orcid.org/0000-0001-5358-4140 |
| work_keys_str_mv | AT preisami onlinehydraulicstateestimationinurbanwaternetworksusingreducedmodels AT whittleandrew onlinehydraulicstateestimationinurbanwaternetworksusingreducedmodels AT ostfelda onlinehydraulicstateestimationinurbanwaternetworksusingreducedmodels AT perelmanl onlinehydraulicstateestimationinurbanwaternetworksusingreducedmodels |