Section: New Results
Data Agregation, and address allocation in Wireless Networks
Participants : Alia Ghaddar, Tahiry Razafindralambo, Isabelle Simplot-Ryl, David Simplot-Ryl.
A primary purpose of sensing in a sensor network is to collect and aggregate information about a phenomenon of interest. The batteries on today's wireless sensor barely last a few days, and nodes typically expend a lot of energy in computation and wireless communication. Hence, the energy efficiency of the system is a major issue. Aggregation techniques were used to reduce the amount of data communication generated by sensors. Depending on the data type, ARMA series and forecasting are possible ways to reduce data transmission. In [20] , we propose different data aggregation algorithms based on the AutoRegressive model built at each sensor to predict local readings. The experiments show that it is possible not only to reduce the frequency of the AR re-parametrization but also to decrease the number of computational operations and hence increasing the node's lifetime which of course affects on the longevity of the network.
In [5] , we present for mobile ad hoc networks an efficient distributed address allocation protocol which is immune to topology changes caused by node's mobility. Contrary to the common belief that mobility makes protocol design more difficult, we show that node's mobility can, in fact, be useful to provide efficient address allocation in ad hoc networks. In our protocol, each node that has been assigned an address manages a disjoint subset of free addresses independently. By taking advantage of node mobility, we can achieve roughly even distribution of free addresses amongst nodes in the system, which enables a new joining node to be configured by its neighbors via only local communication. Theoretical analysis and extensive simulation results are presented. We show that most of the address allocation requests can be processed in a timely fashion via local communication in the requester's neighborhood with time and message complexity in the order of node's degree, regardless of the network size.
