**Acknowledgements**

*Xmin* Minimum value of variable *Xi*

*NMAE* Normalized Mean Absolute Error *NRMSE* Normalized Root Mean Square Error

*NMBE* Normalized Mean Bias Error

*Sub-section 4.2*

*<sup>N</sup> (*<sup>μ</sup> *\_ ;* σ

*qi '*

> *pi '*

*AFlSlb*

*AFlSF2*

*FreTF2*

*Sub-section 5.1*

*AFlCNl, AFlCNop, AFlCNq,*

*AFlT31, AFlT32, AFlSF1,*

*FreSF1, FreSF2, FreTF1,*

*CVRMSE* Coefficient of Variation of the Root Mean Square Error

*N (*μ*;* σ*)* Normal distribution with mean μand standard deviation σ

*f (x)* Probability density function (pdf) of a random variable *X* Φ*(x)* Cumulative distribution function (cdf) of a random variable *X*

<sup>σ</sup>*min* Standard deviation equals to half the interval in which a desired <sup>μ</sup>

*x0, x1, …, xL L* + 1bounds of the *L* intervals of a Interval Discrete Chance node of a BN

*, qi* Probability of interval *i*of a non-periodic discrete node (not normalized and normalized

*, pi* Probability of interval *i*of a periodic discrete node (not normalized and normalized,

Air flows in station's rooms named as CNl, CNop, CNq, Slb

Air flows in tunnels TF1 and TF2 and in station fan ducts SF1 and SF2

Frequencies that drive the two fans in the station and the two fans in the tunnels,

\_

and standard deviation σ

\_

\_ falls

*\_)* Desired distribution with mean value <sup>μ</sup>

respectively)

respectively)

respectively

*ACOPL3* Air changes per hour

*WiSMet* Outdoor wind speed *WiDMet* Outdoor wind direction

*Ei* Prediction error at time *i AEi* Absolute error at time *i S Ei* Squared error at time *i PEi* Percentage error at time *i MAE* Mean Absolute Error *RMSE* Root Mean Square Error

*K* Number of samples in a validation data set

34 Dynamic Programming and Bayesian Inference, Concepts and Applications

This work is part of the EU-funded research SEAM4US. Also, we are very grateful to our colleagues Engs. Roberta Ansuini and Sara Ruffini, who helped us develop the models.
