Files
Abstract
Low-power wireless networks constructed of thousands of nodes forming a mesh topology are becoming increasingly common. Various standards notably Wi-SUN tried to provide a solid frame for the networking part of these networks. However, as the network size grows, congested nodes become a bottleneck and make the network unreliable. Many routing algorithms, including RPL used by most mesh network standards, are based on the local decision of each node without having a global prevision of the ongoing traffic in other links. Additionally, the propagation of traffic information from each link creates an extra load in the network and increases management complexity. To tackle this problem, one solution is to optimize the network for high Quality of Service (QoS) by adding multiple border routers. It allows splitting a large network into manageable sub networks. This remains a cheaper and simpler solution because instead of creating many control packets, we only redirect traffic to a new sink which has high bandwidth and reliable connection towards the cloud/destination. Still, adding border routers needs an arrangement of the whole network so that only the minimum number of border routers for the level of QoS requested by the service user is used. This arrangement consists of finding the best location for the new border routers. This is done in two essential steps: i) Clustering the current big network into small sub-networks ii) Finding the nodes in the cluster that are optimal to be a new border router.