Error Scene Restoration with Runtime Logs of Wireless Sensor Networks

The application of Wireless Sensor Networks (WSNs) often falls into unexpected poor performance conditions due to many factors such as complex network interactions, software bugs and incorrect configurations. Diagnosing such a network is challenging since it is difficult to obtain information from the network due to factors including (1) non-deterministic network interactions among motes, (2) difficulties in reconstructing the status of each individual mote, and (3) unavailability of the real environment information. To address these problems, we propose a diagnosis tool called ALog which analyzes the local logs and the source code to infer what happens in network. Based on the analysis, we further derive the states and possible problems accordingly. We implement ALog and evaluate its efficiency with two real case studies. The results demonstrate that ALog is accurate and applicable for diagnosing real sensor networks.