For single reservoir forecasting, models
A and B showed better performance (R2) than
models C and D. The monthly model showed the
better result than the weekly and daily models. For
multi-reservoir forecasting, the performance of the
four models was not different. Model C was
recommended since it required less data. The
training and testing performance of daily, weekly
and monthly models were not much different in
case of multi-reservoir. However, the multireservoir
problem required a lot longer training
time than the single reservoir problem, particularly
the case of daily model. This could be the
disadvantage of the ANNs multi-reservoir inflow
forecasting. In general, the single reservoir inflow
forecasting showed the better result.