Optimal Operation Of Multi-reservoir System Using Dynamic Programming And Neural Network
Free (open access)
H. Raman & V.Chandramouli
A combined approach of a Dynamic Programming algorithm and Artificial Neural Network model is used for multi reservoir operation. The Dynamic programming algorithm is used for deriving optimum results for a four reservoir system and from the results, neural network is trained using back propagation algorithm to derive general operating policy for multi-reservoir operation. The performance is analyzed using a simulation model for the considered case study. 1 Introduction In monsoon countries like India the availability of water with respect to time and space varies considerably. Rainfall, the major source of water in India, varies from 11000 mm at Cherrapunji in Assam State to 150 mm in the extreme west of Rajasthan State, due to orographic influence.