Guaranteeing real-time traffic through an ATM network

Presents a method for providing hard real-time guarantees for traffic through an asynchronous transfer mode (ATM) network. Guaranteed delivery also implies that we have to guarantee that no cells are lost due to over-full buffers in the network. By using priority queues in the output buffers, we allow urgent messages short end-to-end delays, while still guaranteeing end-to-end delays for low-priority messages. We can determine a priori if message deadlines will be met by calculating maximum end-to-end delays and buffer needs. The analysis is based on CPU schedulability analysis, which means that it provides a framework for analysing an entire system, including both CPU and network scheduling