Neural network-based transmission scheduling in a sensor network with mobile sink

Using the YAES simulator, you need to implement a strategy for transmission scheduling towards a mobile sync based on sensor networks. The strategy needs to optimize the energy consumption while reducing lost data.

The paper you want to read on this topic is L. Bölöni and D. Turgut. Should I send now or send later? A decision-theoretic approach to transmission scheduling in sensor networks with mobile sinks. The code used to generate the results in that paper will be made available for you. What you need to implement is:

• A neural network based model which learn the optimal transmission time from its own history of interacting with the mobile sink. Feel free to experiment with several NN models and use external Java-based neural network libraries, such as Joone
.
• You will need to develop several realistic scenarios. Realistic means that the performance of the elements in the scenario needs to be tied to the performance of some well known devices. For instance, you might want to assume that the mobile sink is mounted on an iRobot Packbot 510. Then, the speed, maneuverability and so on should be appropriate to that device. Or you can consider a nano-UAV, and then you need to consider its capabilities and limitations.

MORE INFO TO COME