Data aggregation for wireless sensor networks using self-organizing map

Abstract

Sensor Networks have recently emerged as a ubiquitous computing platform. However, the energy constrained and limited computing resources of the sensor nodes present major challenges in gathering data. In this work, we propose a self-organizing method for aggregating data in ad-hoc wireless sensor networks. We present new network architecture, CODA (Cluster-based self-Organizing Data Aggregation), based on the Kohonen Self-Organizing Map to aggregate sensor data in cluster. Before deploying the network, we train the nodes to have the ability to classify the sensor data. Thus, it increases the quality of data and reduces data traffic as well as energy-conserving. Our simulation results show that CODA increases the accuracy of data than traditional aggregation of database system. Finally, we show a real-world platform, TIP, on that we will implement the idea. © Springer-Verlag Berlin Heidelberg 2005.