Abstract: Wireless Sensor Network (WSN) is a network that is formed using many sensor nodes which are positioned inside an application based environment for monitoring the physical entities within a target area. A primary challenge in the organizing of such networks is its efficacy of energy. Clustering is found to be an efficient technique that can prolong the WSN lifetime. It includes the grouping of the sensor nodes into various clusters and also the electing of the Cluster Heads (CH) for the clusters. The CHs will collect data from their respective clusters and their nodes to forward all aggregated data to the Base Station (BS). The CH selection is a Non-deterministic Polynomial (NP)-hard problem. This study proposes a very energy efficient CH algorithm for selection that has been based on the Genetic Algorithm (GA) and the Invasive Weed Optimization (IWO) algorithm. The sensor network and its lifetime will be extended using the power based clustering protocols. The operations in clustering will be optimized using the optimizations of swarm and their Evolutionary Algorithms (EA). Here, there is an improved IWO based upon the hybrid genetic (GA-IWO) has been presented. In this new algorithm, the inertial weight is adaptively adjusted for improving the speed of convergence and the weeds are multipled by means of selection and hybridization of the GA. This import of such hybrid genes will improve the t performance of weeds and will further reduce the likelihood of getting into the local optima. The results of the experiment prove that the method proposed can achieve better performance compared to the other methods.
Satyanarayana Mummana and Kuda Nageswara Rao, 2019. Hybrid Optimized Multi Sink Network for Optimal Data Aggregation in Wireless Sensor Network Using Genetic Algorithm and Invasive Weed Optimization. Asian Journal of Information Technology, 18: 193-202.