Reservoir operation frequently follows a conventional policy based on Guide curves that prescribes reservoir releases. Operating policies can be derived using system techniques such as simulation, optimisation and combination of these two. In recent years, artificial intelligence techniques like Artificial Neural Network (ANN) arisen as an alternative to overcome some of the limitations of conventional methods. In most of the studies, feed forward structure and the back propagation algorithm have been used to design and train the ANN model respectively.


A case study of Wadgaon reservoir is considered. On the basis of data available and observations simulation based Multiple regression (MLR) modelling and Artificial Neural Network (ANN) modelling is carried out . Forty seven years of 10 daily Inflow data and other relevant data is used for the analysis.


The main finding of the research is that the ANN procedure to derive the general operating policy for reservoir operation gives better and robust performance, indicating that ANN has a great potential for deriving optimal operating policy for reservoir.