Improving K-Means Algorithm by Grid-Density Clustering for Distributed WSN Data Stream

At recent years, Wireless Sensor Networks (WSNs) had a widespread range of applications in many fields related to military surveillance, monitoring health, observing habitat and so on. WSNs contain individual nodes that interact with the environment by sensing and processing physical parameters. Sometimes, sensor nodes generate a big amount of sequential tuple-oriented and small data that is called Data Streams. Data streams usually are huge data that arrive online, flowing rapidly in a very high speed, unlimited and can't be controlled orderly during arrival. Due to WSN limitations, some challenges are faced and need to be solved. Extending network lifetime and reducing energy consumption are main challenges that could be solved by Data Mining techniques. Clustering is a common data mining technique that effectively organizes WSNs structure. It has proven its efficiency on network performance by extending network lifetime and saving energy of sensor nodes. This paper develops a grid-density clustering algorithm that enhances clustering in WSNs by combining grid and density techniques. The algorithm helps to face limitations found in WSNs that carry data streams. Grid-density algorithm is proposed based on the well-Known K-Means clustering algorithm to enhance it. By using Matlab, the grid-density clustering algorithm is compared with K-Means algorithm. The simulation results prove that the grid-density algorithm outperforms K-Means by 15% in network lifetime and by 13% in energy consumption.