In this paper we introduce a traffic growth model for optical networks with time-varying traffic arrivals assuming the nodes are capable of full wavelength conversion. We propose a network dimensioning method based on the traffic growth model and it eventually results in a nonlinear optimization problem with cost minimization as the objective and route absorption probabilities as the constraints. The absorption probabilities can be obtained from transient analysis of a Markov chain. Computation of exact absorption probabilities requires huge computing resources and is thus feasible only for small networks. We consider a reduced load approximation for estimating absorption probabilities of a wavelength routed network with arbitrary topology and traffic patterns. We show that the approximation method performs very well for optical networks with long-lived lightpaths.