PDC: Prediction-based data-aware clustering in wireless sensor networks

• Utilizing prediction along with data-aware clustering to form long lived clusters.
• Building a prediction model utilizing OWA weights.
• Extensive simulations on a real-world WSN data set.

Minimizing energy consumption is the most important concern in wireless sensor networks (WSNs). To achieve this, clustering and prediction methods can enjoy the inherent redundancy of raw data and reduce transmissions more effectively. In this paper, we focus on designing a prediction-based approach, named PDC, to mainly contribute in data-aware clustering. It exploits both spatial and temporal correlations to form highly stable clusters of nodes sensing similar values. Here, the sink node uses only the local prediction models of cluster heads to forecast all readings in the network without direct communication. To the best of our knowledge, PDC is a novel energy efficient approach which provides a high precision of the approximate results with bounded error. Our simple prediction model presents high accuracy as well as low computation and communication costs. Extensive simulations have been conducted to evaluate the prediction model as well as our clustering approach. The results verify the superiority of our simple prediction model. Moreover, PDC implies a significant improvement on existing alternatives.