Critical infrastructures such as wireless network systems demand dependability. Dependability attributes addressed in this thesis include availability, reliability, maintainability and survivability (ARMS). This research uses computer simulation and artificial intelligence to introduce a new approach to measure dependability of wireless networks. The new approach is based on the development of a neural network, which is trained to investigate ARMS attributes of a wireless network capable of serving 100,000 subscribers. Given the reliability and maintainability of wireless infrastructure components, the resulting impact on network availability and survivability are determined. Component mean time to failure (MTTF) is used to model reliability, while mean time to restore (MTR) is used for maintainability. Here, unavailability, the complement of availability, is defined as the fraction of time the entire network system is down, while survivability is the fraction of network users who have service. Both availability and survivability can be instantaneous or averaged over some period. The simulation output is used to train the neural network, which is obtained from simulation experiments for a range of component’s MTTF and MTTR values. In turn, the NN is used to gain insights not easily apparent from simulation results. The NN also assists in estimating the number of FCC-Reportable outages of a wireless network. Lastly, a variety of reliability/maintainability growth and deterioration scenarios is analyzed with the NN. Besides focusing on questions regarding availability and survivability under reliability and maintainability growth/deterioration scenarios, this research also focuses on the relative performance of neural network modeling compared to analytical and simulation techniques.