Sequential Quadratic Programming and Simulating Annealing techniques to calculate optimized Air Quality control policies

In this work the air quality control problem is formalized through a two-objective approach. The objectives considered are (a) the emission reduction cost and (b) the Air Quality Index. The control variables are the precursor emission reductions due to application of available technologies. The nonlinear relationship linking air quality objective and precursor emissions is described by artificial neural networks, identified by processing deterministic Chemical Transport Modeling system simulations. This paper presents the comparison of the optimization problem results computed by means of different procedures: the Sequential Quadratic Programming and the Simulating Annealing. The test case of a polluted domain in Northern Italy is shown.