CSP plants cooling technology: Techno-economic analysis, parametric study, and stacking ensemble learning forecasting
The growing solar industry and technological developments that increase the efficiency and affordability of solar plants are driven by the growing need for sustainable energy sources. The selection of the type of cooling tower technology significantly impacts the overall performance of concentrating...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Elsevier Ltd
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The growing solar industry and technological developments that increase the efficiency and affordability of solar plants are driven by the growing need for sustainable energy sources. The selection of the type of cooling tower technology significantly impacts the overall performance of concentrating solar power (CSP) plants because the cooling towers are essential elements for heat expulsion. The primary objective is to assess the influence of cooling tower technology on CSP plants from the perspective of techno-economic performance by implementing wet, dry, and hybrid cooling systems and optimizing the variables affecting solar tower power plants by conducting a parametric analysis. Moreover, a unique stacking ensemble model comprising a dual-layer structure is developed for solar tower power plant performance prediction. Following the findings, dry and wet cooling technologies came in second and third, respectively, with the hybrid cooling technique achieving the best performance outcomes. By incorporating wet-dry as well as hybrid cooling towers at the Benban location, the levelized cost of electricity for the solar tower was determined to be 13.99, 13.62, and 13.37 �/kWh. The results show that based on the parametric assessment; the capacity factor rose from 11.73 to 73.13% when the mirror reflectance changed from 0.6 to 0.95% and the reflective area to profile ratio from 0.5 to 0.9%. The proposed stacking ensemble demonstrated superior performance compared to standalone base models and existing techniques. ? 2024 Elsevier Ltd |
|---|