The objective of resource allocation systems is to assign valuable corporat
e resources to meet business demands. However, in applications involving st
ochastic events, demands cannot be determined explicitly beforehand. For th
ose applications, computer simulation is often used to predict resource dem
ands. This paper describes research in developing a knowledge-based simulat
ion system to predict resource requirements at an international airport. Ou
r intelligent resource simulation system (IRSS) determines how many check-i
n counters should be allocated to each departure flight while providing pas
sengers with sufficient quality of service. This predicted resource require
ment is then used by a constraint-based resource allocation system to alloc
ate the actual check-in counters. Because IRSS considers many more factors
than a human can, the resulting allocation schedule is more efficient. Thes
e factors include: 1) different service rates for different destinations, a
irlines, or handling agents; 2) different passenger arrival rates for diffe
rent times of the day or days of the week; and 3) different requirements fo
r different service levels, etc. Our experiments show that there are substa
ntial resource savings by combining a resource allocation system with an in
telligent resource simulation system.