Journal cover Journal topic
Proceedings of the International Association of Hydrological Sciences An open-access publication for refereed proceedings in hydrology

Journal metrics

  • SNIP value: 0.058 SNIP 0.058
  • SJR value: 0.135 SJR 0.135
  • IPP value: 0.096 IPP 0.096
Proc. IAHS, 373, 209-214, 2016
http://www.proc-iahs.net/373/209/2016/
doi:10.5194/piahs-373-209-2016
© Author(s) 2016. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
12 May 2016
Inflow forecasting using Artificial Neural Networks for reservoir operation
Chuthamat Chiamsathit, Adebayo J. Adeloye, and Soundharajan Bankaru-Swamy Institute for Infrastructure and Environment, Heriot-Watt University, Edinburgh, EH14 4AS, UK
Abstract. In this study, multi-layer perceptron (MLP) artificial neural networks have been applied to forecast one-month-ahead inflow for the Ubonratana reservoir, Thailand. To assess how well the forecast inflows have performed in the operation of the reservoir, simulations were carried out guided by the systems rule curves. As basis of comparison, four inflow situations were considered: (1) inflow known and assumed to be the historic (Type A); (2) inflow known and assumed to be the forecast (Type F); (3) inflow known and assumed to be the historic mean for month (Type M); and (4) inflow is unknown with release decision only conditioned on the starting reservoir storage (Type N). Reservoir performance was summarised in terms of reliability, resilience, vulnerability and sustainability. It was found that Type F inflow situation produced the best performance while Type N was the worst performing. This clearly demonstrates the importance of good inflow information for effective reservoir operation.

Citation: Chiamsathit, C., Adeloye, A. J., and Bankaru-Swamy, S.: Inflow forecasting using Artificial Neural Networks for reservoir operation, Proc. IAHS, 373, 209-214, doi:10.5194/piahs-373-209-2016, 2016.
Publications Copernicus
Download
Short summary
In this study, multi-layer perceptron (MLP) artificial neural networks have been applied to forecast one-month-ahead inflow for the Ubonratana reservoir, Thailand. This is necessary because without knowing the expected inflow, one would not know the amount of water to allocate at the start of each month. As expected, knowing the inflow through our forecasts significantly improved the performance of the Ubonratana reservoir, the test case. We expect the study to have utility for other systems.
In this study, multi-layer perceptron (MLP) artificial neural networks have been applied to...
Share