Energy efficiency of link layer error control using TCP-Eifel on wireless networks

Background

In the Moby Dick project we develop and define the architecture of a new generation of mobile handheld computers. An important issue in this project is the energy efficiency of wireless communication for multimedia traffic with Quality of Service constraints. Wireless communication is much more difficult to achieve than wired communication because the surrounding environment interacts with the signal, blocking signal paths and introducing noise and echoes. As a result wireless connections have a lower quality than wired connections: lower bandwidth, less connection stability, higher error rates, and, moreover, with a highly varying quality. They need to be able to operate in environments that may change drastically - in short term as well as in long term - in available resources and available services. These factors can in turn increase communication latency due to retransmissions, can give largely varying throughput, and incur a high energy consumption.

Adaptive error control allows the error-control strategy to vary as the channel conditions change. The error control can be FEC, ARQ, or a hybrid. The wireless channel quality is a function of the distance of user from base station, local and average fading conditions, interference variations, and other factors. In such a dynamic environment it is likely that any of the previous schemes is not optimal in terms of energy efficiency all the time. Adaptive error control seems likely a source of efficiency gain.

Since different connections do not have the same requirements concerning e.g. cell loss rate and cell transfer delay, different error-control schemes must be applied for different connection types. The error control mechanisms can be adapted to the current error condition in such a way that it minimises the energy consumption needed and still provides (just) enough fault tolerance for a certain connection. This avoids applying error control overhead to connections that do not need it, and allows the possibility to apply it selectively to match the required QoS and the conditions of the radio link.

Assignment

In this assignment, the energy-efficiency and performance problems are studied that exist when loss responsive flows traverse wireless links, where losses are often unrelated to congestion. We concentrate on the concept of flow-adaptive wireless links, which provides service differentiation by tailoring link layer error control to the QoS requirements of each flow sharing the link. Flow-adaptive links emphasize local error control as a necessary complement to end-to-end error control, and are independent of transport (or higher) layer protocol semantics. The key idea is that applications use the IP layer as a level of indirection through which QoS requirements are communicated to each link along the path, on a per flow basis.

In particular, we will study the energy-efficiency of a new error recovery algorithm (TCP-Eifel). The algorithm eliminates the retransmission ambiguity, thereby solving the problems caused by spurious timeouts and spurious fast retransmits. It can be incrementally deployed as it is backwards compatible and does not change TCP's congestion control semantics. In environments where spurious retransmissions occur frequently, the algorithm can improve the end-to-end throughput by several tens of percent. An exact quantification is, however, highly dependent on the path characteristics over time. The Eifel algorithm finally makes TCP truly wireless-capable without the need for proxies between the end points. Another key novelty is that the Eifel algorithm provides for the implementation of a more optimistic retransmission timer because it reduces the penalty of a spurious timeout to a single (in the common case) spurious retransmission.

The assignment will contain both theoretical aspects as practical aspects (implementation and measurements on a WaveLAN network).

References

More information: