Neural network based multiobjective hydro scheduling assessment

This paper presents a new approach based on the multi-layer perceptron in cascade with the two-phase optimization neural network for objective satisfaction assessment in the multi-objective hydroscheduling problem. Here, the objectives are to maximize the annual hydropower generation and to satisfy the irrigation requirements as far as possible. Scheduling indicators are introduced to help the reservoir operators in making a judicious compromise between the conflicting objectives. In the proposed method the multi-layer perception is adopted for identifying the input parameters of the two-phase optimization neural network, which in turn provides the desired scheduling result. Results so obtained demonstrate the promise of this approach for providing the flexible assessment of the multi-objective operation schedule for the multi-reservoir systems.