Neural network with multiple time series and exogenous variables inputs

Dear all,

I am trying to address the following problem: I would like to apply some neural network architecture to a group of different time series (multivariate) each function of one or more exogenous variables. The purpose is the prediction of the temporal trend of the output Y(t) as a function of the variables X(t) and Z variables that do not have temporal variations but whose value determines, with X(t), the temporal trend of Y(t).

Which neural network architecture can I use?