Open AccessDevelopment of an ANN Model to Simulate the Auxiliary Power Generation from an Irrigation Barrage
Author(s) -
P. S. Koshy,
Prince Arulraj G,
J. Brema
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a9469.109119
Subject(s) - irrigation , electricity generation , environmental science , hydrology (agriculture) , upstream (networking) , inflow , electric power , hydroelectricity , water resource management , agricultural engineering , engineering , power (physics) , meteorology , electrical engineering , geography , telecommunications , geotechnical engineering , agronomy , physics , quantum mechanics , biology
The aim of this paper is to correlate the auxiliary power generation from an irrigation reservoir with the power generation of its upstream hydro power project in a cascade reservoir system. System considered for the study is the Pamba Basin- Kakkad Hydro Power Project and Maniyar Reservoir of Pamba Irrigation Project of Kerala State. In a water year from the 1st June to 31st May, irrigation period spans for seven months from November to May in the Irrigation Project. As the water release of the upstream Hydro Electric Plant exceeds the irrigation demand, even during the peak irrigating months of January and February, there is surplus inflow for power generation. A water year is divided to two seasons namely, Irrigation and Non-Irrigation. An Artificial Neural Network (ANN) based model is developed to optimize the power generation using the surplus water and the outputs are compared with the real time data. In the ANN model, the inputs considered are the Generation in units of the upstream Kakkad Hydro Electric Project (Kakkad-HEP), the Rainfall in the catchment and the Irrigation Supply. Spillage from the barrage and the Power Generation in the adjoining Carborandum Universal Madras India Ltd. company’s Small Hydro Electric Project (CUMI-SHEP) is considered as the output. The results obtained shows that the power generation from the ANN model closely matches with the real time data. Analysis is done with the aid of MATLAB ANN tool box.