Adaptive run-time performance optimization through scalable client request rate control
Proceedings of the 2nd ACM/SPEC International Conference on Performance engineering
| Hi-index | 0.00 |
From operating systems to cell phones and web servers to PDAs, more products and systems depend on TCP for network interconnection everywhere and anytime. Congestion control is a key feature of TCP. TCP performance could have significant impact on the network life for wireless ad-hoc/sensor networks, as higher TCP throughput and lower retransmissions could reduce resource consumption. This paper evaluates the feasibility of an adaptive Proportional and Integral (PI) rate control algorithm in wireless ad-hoc/sensor networks. Performance evaluation and comparison of this adaptive rate controller with TCP New Reno have been conducted by means of simulation. The results obtained from the simulations show that the adaptive PI rate control algorithm can improve the overall average throughput for static scenarios and the collision level at the MAC layer is also reduced, which could have a considerable impact on energy consumption.