ANNs and inflow forecast to aid stochastic optimization of reservoir operation
Implicit stochastic reservoir optimization (ISO) typically utilizes nonlinear regression to correlate release as a function of initial storage plus inflow forecasted for the month. This study shows that improved ISO-based policies can be derived by replacing current-month forecast and regression for...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Taylor & Francis
2019
|
| Subjects: |
| _version_ | 1825722058618699776 |
|---|---|
| author | Silva Santos, Kelly Marina Celeste, Alcigeimes B. El-Shafie, Ahmed |
| author_facet | Silva Santos, Kelly Marina Celeste, Alcigeimes B. El-Shafie, Ahmed |
| author_sort | Silva Santos, Kelly Marina |
| collection | UM |
| description | Implicit stochastic reservoir optimization (ISO) typically utilizes nonlinear regression to correlate release as a function of initial storage plus inflow forecasted for the month. This study shows that improved ISO-based policies can be derived by replacing current-month forecast and regression for long-term mean inflow forecast (LTF) and artificial neural networks (ANN), respectively. The ISO-LTF-ANN approach is applied to the Aswan High Dam reservoir, Egypt. First, perfect-forecast deterministic optimization (PFDO) defines operation strategies for 100 scenarios of 100-year inflows. Then, optimal release and storage data are grouped into databases corresponding to different forecast horizons. Next, ANNs are trained for each database to serve as release policies. Later, the policies are used to operate the system under other scenarios. Operations by the standard operation policy (SOP), stochastic dynamic programming (SDP) and PFDO are employed for comparison. ISO-LTFANN performs near PFDO and better than SOP, SDP and a regression-based ISO-LTF approach. © 2019, © 2019 IAHR and WCCE. |
| first_indexed | 2024-03-06T05:59:51Z |
| format | Article |
| id | um.eprints-23431 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:59:51Z |
| publishDate | 2019 |
| publisher | Taylor & Francis |
| record_format | dspace |
| spelling | um.eprints-234312020-01-14T04:59:18Z http://eprints.um.edu.my/23431/ ANNs and inflow forecast to aid stochastic optimization of reservoir operation Silva Santos, Kelly Marina Celeste, Alcigeimes B. El-Shafie, Ahmed TA Engineering (General). Civil engineering (General) Implicit stochastic reservoir optimization (ISO) typically utilizes nonlinear regression to correlate release as a function of initial storage plus inflow forecasted for the month. This study shows that improved ISO-based policies can be derived by replacing current-month forecast and regression for long-term mean inflow forecast (LTF) and artificial neural networks (ANN), respectively. The ISO-LTF-ANN approach is applied to the Aswan High Dam reservoir, Egypt. First, perfect-forecast deterministic optimization (PFDO) defines operation strategies for 100 scenarios of 100-year inflows. Then, optimal release and storage data are grouped into databases corresponding to different forecast horizons. Next, ANNs are trained for each database to serve as release policies. Later, the policies are used to operate the system under other scenarios. Operations by the standard operation policy (SOP), stochastic dynamic programming (SDP) and PFDO are employed for comparison. ISO-LTFANN performs near PFDO and better than SOP, SDP and a regression-based ISO-LTF approach. © 2019, © 2019 IAHR and WCCE. Taylor & Francis 2019 Article PeerReviewed Silva Santos, Kelly Marina and Celeste, Alcigeimes B. and El-Shafie, Ahmed (2019) ANNs and inflow forecast to aid stochastic optimization of reservoir operation. Journal of Applied Water Engineering and Research, 7 (4). pp. 314-323. ISSN 2324-9676, DOI https://doi.org/10.1080/23249676.2019.1687017 <https://doi.org/10.1080/23249676.2019.1687017>. https://doi.org/10.1080/23249676.2019.1687017 doi:10.1080/23249676.2019.1687017 |
| spellingShingle | TA Engineering (General). Civil engineering (General) Silva Santos, Kelly Marina Celeste, Alcigeimes B. El-Shafie, Ahmed ANNs and inflow forecast to aid stochastic optimization of reservoir operation |
| title | ANNs and inflow forecast to aid stochastic optimization of reservoir operation |
| title_full | ANNs and inflow forecast to aid stochastic optimization of reservoir operation |
| title_fullStr | ANNs and inflow forecast to aid stochastic optimization of reservoir operation |
| title_full_unstemmed | ANNs and inflow forecast to aid stochastic optimization of reservoir operation |
| title_short | ANNs and inflow forecast to aid stochastic optimization of reservoir operation |
| title_sort | anns and inflow forecast to aid stochastic optimization of reservoir operation |
| topic | TA Engineering (General). Civil engineering (General) |
| work_keys_str_mv | AT silvasantoskellymarina annsandinflowforecasttoaidstochasticoptimizationofreservoiroperation AT celestealcigeimesb annsandinflowforecasttoaidstochasticoptimizationofreservoiroperation AT elshafieahmed annsandinflowforecasttoaidstochasticoptimizationofreservoiroperation |