Das, Sherin S and Majumdar, Rudrodip and Krishnan, AV and Srikanth, R (2025) Assessing water consumption in Indian thermal power plants and parametric strategy for optimal usage: An explanatory approach using machine learning algorithms. In: Water use efficiency, sustainability and the circular economy edited by Suhaib A. Bandh, Fayaz A. Malla and Anthony Halog. Elsevier, pp. 301-324. ISBN 978-0-443-26749-9
![[img]](http://eprints.nias.res.in/style/images/fileicons/text.png) |
Text
CH21_Assessing water consumption in Indian TPPs and parametric strategy for optimal use.pdf - Published Version Restricted to Repository staff only Download (11MB) |
| Contribution | Name |
|---|
| Abstract: | The reliability of water supply resources is of utmost importance for the electricity sector, particularly for the cooling requirements in Steam Rankine Cycle (SRC)-based thermo-electric power plants. The study investigates the influence of specific power plant parameters, such as Cycles of Concentration (CoC) and Plant Load Factor (PLF), and meteorological conditions (such as temperature, humidity, and wind speed) on the specific water consumption (SWC) of Indian thermal power stations using Machine Learning (ML) based Decision Tree Algorithms. While regulations exist to reduce water consumption, the study highlights the underexplored potential of improving these power plant parameters, which are crucial for water use curtailment. By leveraging data-driven decision-making, the study identifies the order of importance for the significant variables that influence SWC in thermal power plants and highlights the necessity of optimizing these variables. The study concludes that an optimal operational range can be established by effectively controlling CoC and PLF, considering the local meteorological parameters, that yields minimal water consumption for power plant operations. The results derived from the Machine Learning algorithms possess intuitive validity, as confirmed by descriptive analysis and insights from domain experts, as well as previously published scholarly articles. This study is a testament to the practical effectiveness of machine learning tools in addressing socially important sustainability issues. |
|---|---|
| Item Type: | Book Chapter |
| Subjects: | School of Natural and Engineering Sciences > Energy and Environment |
| Divisions: | Schools > Natural Sciences and Engineering |
| Date Deposited: | 22 Jul 2025 04:32 |
| Last Modified: | 22 Jul 2025 04:33 |
| Official URL: | https://www.sciencedirect.com/science/article/abs/... |
| Related URLs: | |
| Funders: | * |
| Projects: | * |
| DOI: | https://doi.org/10.1016/B978-0-443-26749-9.00018-1 |
| URI: | http://eprints.nias.res.in/id/eprint/2966 |
Actions (login required)
 |
View Item |
