Optimization Of The Water Use In The River Damodar In West Bengal In India : An Integrated Multi - Reservoir System With The Help Of Artificial Neural Network

The present study attempts to optimize the outflow and the water distribution of entire Damodar catchment with the help of Artificial Neural Network(ANN). It is worth to mention that the large river valley project like Damodar Valley Corporation (DVC) with four dams and one barrage makes the simulation of Damodar more challenging, as it becomes a controlled flow system. Event of heavy floods are common which necessitates the development of a proper optimization of the water distribution. 8 inputs and 24 output parameters are configured and with the help of NeuroDimension 5, a commercial software. 4 ANN Models are prepared. The data from 1996 to 2000 was used to create and test the models. The model with minimum average mean square error (MSE) (2.55%) was selected and used for the optimization. The distribution of water by the model shows a priority wise selection giving the highest priority to the most important use of the local area of the adjacent reservoir.