Application of computational intelligence technologies in clusterization problems of wireless sensor networks

Abstract

The subject matter of the study is the process of selecting the head node of a cluster in wireless sensor networks (WSNs) using intelligent approaches that can adapt to changing environmental conditions. WSNs consist of a large number of sensor nodes with that collect, process and transmit data. Effective clustering is one of the main mechanisms for optimizing the operation of WSNs, as it allows reducing energy consumption, increasing network reliability and scalability. The goal of the study is to analyze the features of using modern computational intelligence tools and methods to increase the efficiency of the sensor node clustering process, which allow taking into account a variety of factors when making decisions about cluster formation and selecting head nodes. Traditional clustering algorithms are not always able to adapt to changes in network parameters, especially in the presence of heterogeneous nodes or changes in topology. In this regard, methods based on computational intelligence, in particular genetic algorithms, neural networks, fuzzy logic, as well as hybrid approaches, are becoming increasingly relevant. These methods allow taking into account a number of parameters when forming clusters and selecting cluster heads. Tasks of the study are analysis of existing approaches to clustering in BSM; development of a clustering fuzzy inference system; construction of a rule base for making optimal decisions; experimental verification of the proposed system. Methods of the study are tools of computational intelligence, in particular neural network learning, genetic optimization and fuzzy control, as well as computer modeling. The article analyzes the advantages of using each of the existing approaches. Results are: a structure of the fuzzy inference system was developed, input and output variables were determined, a database of fuzzy rules and membership functions was formed. The operation of the fuzzy system was simulated in the MATLAB environment. The developed system was also optimized and its operation validated. Conclusions: the use of hybrid intelligent approaches has significant advantages for solving clustering problems in BSM, which may indicate the prospects for further development of systems capable of functioning effectively in conditions of limited resources and high environmental complexity.