
- Accepts Direction: Users are provided a mechanism to prescribe QoS Goals, and the SAN responds by trying to achieve these via dynamic routing, and reports back as to how well they have been achieved.
- Self-Observation: With the help of Smart Packets (SPs), the SAN is able to obtain an up-to-date view of the network, including the location of (possibly mobile) nodes, power levels at nodes, topology, paths and path QoS.
- Self-Improvement and Learning: Through the use of Neural Networks and Genetic Algorithms, the SAN is able to constantly learn routing schemes with better QoS as network conditions change.
This work was initially supported by the UK Engineering and Physical Sciences Research Council under Grant EPSRC GR/S52360/01, with additional funding from the European Union under EU FP6 under the Marie Curie Grant SAPAD, and from BT under the SATURN Contract. In a second phase, the work has been supported by EU FP6 Project CASCADAS, EU FP 7 Project DIESIS, and by BT and MoD with the HYPERION and SHIELD Projects. Further support is also available via the joint EPSRC, BAE Systems and Selex Project ALADDIN.