Due to network users' different time-preference, network traffic load differs significantly at different time. In traffic-peak time, the quality of service provided to network users may deteriorate due to congestion. There are two ways to improve the quality of services: (1) Network service providers (NSPs) over-provision network capacity by investment; (2) NSPs use pricing to reduce the traffic at traffic-peak time by exploiting the elasticity of demand with respect to price. However, over-provisioning network capacity can be costly. Therefore, some researchers have proposed time-dependent pricing to control congestion as well as improve the revenue of NSP. To the best of our knowledge, all of the literature related to time-dependent pricing scheme only considers the monopoly NSP case. In this paper, a duopoly NSP case is studied. The NSPs try to maximize their overall revenue by setting time-dependent price, while users choose NSP by considering their own preference, congestion status in the networks, the price set by the NSPs and the switching cost set by NSPs. Analytical and experimental results show that the time-dependent pricing (TDP) benefits the NSPs, but the revenue improvement is limited due to the competition effect.