This paper presets a fast computation algorithm for connection admission control for heterogeneous delay sensitive traffic in ATM networks. Cell loss probability is adopted as the measure of quality of service. In our study, cells of each connection are allowed to have two different loss priorities and the aggregate traffic can have more than two. To cope with multiple quality of service requirements, the link capacity is divided into several bands. For simplicity, each traffic source is assumed to alternate between active and idle periods. However, the results can be extended to traffic sources having more than two states. Upper bounds of actual cell loss probabilities are derived based on the bufferless fluidflow model. Numerical results show that the upper bounds are close to the actual cell loss probabilities.

To provide convenient wireless access, wireless mesh networks (WMNs) can be rapidly deployed and connected for mobile clients. Although route redirection traffic control schemes and dynamic routing metrics can be used to improve the performance of WMNs, more of the available network bandwidth will be consumed by control message exchange. This paper proposes a capacity-aware and multipath supported traffic control framework in WMNs. The proposed framework can be used to dispatch data traffic in a multipath manner to improve the utilization of wireless links and forwarding latency. A hierarchical queue architecture is proposed to monitor and classify network traffic without the effort of control message exchange. Our traffic control strategy, which is based on local minimization of the forwarding latency, consists of two phases to automatically adapt to the utilization rate of the network links. In the first phase, the incoming packets are dispatched to the lower level queues according to the Internet gateway capacity. In the second phase, the packets are dispatched to the related network links according to the link load. The current study implements the proposed traffic control system on NS2 for simulation and on Linux 2.6 for real traffic analysis. Experimental results show that the proposed framework improves the throughput and reduces forwarding delay with an approximate minimum delay time. The results also show that the behavior of the long-term delay model can be applied to short-term traffic control methods in WMNs.