Improving TCP performance over networks with wireless components using "probing devices"

TCP error control mechanism lacks the ability to detect with precision the nature of potential errors during communication. It is only capable of detecting the results of the errors, namely, that segments are dropped. As a result, the protocol lacks the ability to implement an appropriate error recovery strategy cognizant of current network conditions and responsive to the distinctive error characteristics of the communication channel. TCP sender always calls for the sending window to shrink. We show that probing mechanisms could enhance the error detection capabilities of the protocol. TCP could then flexibly adjust its window in a manner that permits the available bandwidth to be exploited without violating the requirements of stability, efficiency and fairness that need to be guaranteed during congestion. Our experiments have three distinct goals: First, to demonstrate the potential contribution of probing mechanisms. A simple probing mechanism and an Immediate Recovery strategy are grafted into TCP-Tahoe and TCP-Reno. We show that, this way, standard TCP can improve its performance without requiring any further change. Second, to study the performance of adaptive strategies. An adaptive TCP with probing is used, that is responsive to the detected error conditions by alternating Slow Start, Fast Recovery and Immediate Recovery. An adaptive error recovery strategy can yield better performance. Third, to study the design limitations of the probing device itself. The aggressive or conservative nature of the probing mechanisms themselves can determine the aggressive or conservative behavior of the protocol and exploit accordingly the energy/throughput tradeoff.