In the present paper, we propose to solve the global
optimization problem by using a recurrent neural network
(RNN), to determine the optimal amounts of power supplied
for each energy source. Many real-time systems, such as
massively interconnected electric power grids, require solving
large-scale linear programming problems in real time [28]. In
such applications, existing sequential algorithms such as the
classical simplex or the interior point methods are usually not
efficient due to the limitation of sequential processing. In
general, traditional algorithms may not be efficient since the
computing time required for a solution is greatly dependent on
the dimension and structure of the problems [29]. One possible
and very promising approach to real-time optimization is to
apply artificial neural networks. Because of the inherent
massive parallelism, the neural network approach can solve
optimization problems in running time at the orders of
magnitude much faster than those of the most popular
optimization algorithms executed on general-purpose digital
computers [30].