Lessons learned during the implementation of the BVR Wireless Sensor Network protocol on SunSPOTs

The Beacon Vector Routing (BVR) protocol is a well known routing protocol for Wireless Sensor Networks (WSNs). Simulations have shown that the protocol scales well in an environment with perfect links and an ideal circular radio coverage. However, when it comes to an implementation on an embedded hardware that uses IEEE 802.15.4 2.4 GHz wireless transceivers, some problems turn out that have significant impact on the overall performance of the protocol. The design of BVR (and most other WSN protocols) is based on certain assumptions about the underlying physics of the wireless communication links. We will show in this paper that some of these assumptions are insufficient or sometimes even unrealistic. The most important observation is that BVR is based on fairly stable, bidirectional communication links. However, our experiments with IEEE 802.15.4-based 2.4 GHz network, typical technology for WSNs, have shown, that this assumption is not always true. Here the signal strength is highly variable, even if the environment is stable. Even more severe, in many cases a link between two nodes only works reliably in one direction, i.e., it is not bidirectional. We have implemented and evaluated the BVR protocol on SunSPOTs (experimental sensor nodes from Sun). We will give an overview and a description of all of the problems we realized during implementation (including the problems described in the BVR paper). Then we discuss the approaches and adaptations of the algorithms we used to work around these problems. Some of these ideas might be relevant for other WSN protocols as well.