High performance TCP in ANSNET
ACM SIGCOMM Computer Communication Review
Fixed point approximations for TCP behavior in an AQM network
Proceedings of the 2001 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications
Part I: buffer sizes for core routers
ACM SIGCOMM Computer Communication Review
Part II: control theory for buffer sizing
ACM SIGCOMM Computer Communication Review
A DRAM/SRAM Memory Scheme for Fast Packet Buffers
IEEE Transactions on Computers
A critique of recently proposed buffer-sizing strategies
ACM SIGCOMM Computer Communication Review
Designing packet buffers with statistical guarantees
HOTI '04 Proceedings of the High Performance Interconnects, 2004. on Proceedings. 12th Annual IEEE Symposium
Router buffer sizing revisited: the role of the output/input capacity ratio
CoNEXT '07 Proceedings of the 2007 ACM CoNEXT conference
Beyond the Model of Persistent TCP Flows: Open-Loop vs Closed-Loop Arrivals of Non-persistent Flows
ANSS-41 '08 Proceedings of the 41st Annual Simulation Symposium (anss-41 2008)
Designing packet buffers for router linecards
IEEE/ACM Transactions on Networking (TON)
| Hi-index | 0.02 |
Today, because of TCP dynamics, Internet backbone routers hold large packet buffers, which significantly increase their power consumption and design time. Recent models of large-buffer networks have suggested that these large buffers could be replaced with much smaller ones. Unfortunately, it turns out that these large-buffer network models are not valid anymore in small-buffer networks, and therefore cannot predict how these small-buffer networks will behave. In this paper, we introduce a new model that provides a complete statistical description of small-buffer Internet networks. We present novel models of the distributions of several network components, such as the line occupancies of each flow, the instantaneous arrival rates to the bottleneck queues, and the bottleneck queue sizes. Later, we combine all these models in a single fixed-point algorithm that forms the key to a global statistical small-buffer network model. In particular, given some QoS requirements, we show how this new model can be used to precisely size small buffers in backbone router designs.