Data aggregation in wireless sensor networks using computational intelligence technologies

Abstract

. The article considers the problem of effective data aggregation in wireless sensor networks (WSNs), which is important procedure for reducing energy consumption, minimizing excess transmission, and extending the network lifetime. Given the limited resources of WSN nodes, traditional data aggregation methods are not always able to function effectively in a heterogeneous environment. In this context, special attention is paid to the application of computational intelligence technologies, such as neural networks, genetic algorithms, fuzzy logic, which allow for adaptive aggregation depending on the characteristics of the environment and network. At the same time, the combination of fuzzy logic, evolutionary algorithms, and artificial neural networks in a single hybrid system makes it possible to use the strengths of each technology, ensuring high adaptability and accuracy of data aggregation. As part of the research, a model of a fuzzy inference system for data aggregation was developed, which takes into account such node parameters as residual energy, load, and distance to the base station. The model was implemented in the MATLAB environment using the Fuzzy Logic Designer tool. To increase the efficiency of the system, it was optimized using a genetic algorithm, which made it possible to adjust the membership functions. At the final stage, the model was transformed into an adaptive neuro-fuzzy inference system ANFIS, which was trained on the basis of simulated data in MATLAB. The simulation results confirm that the proposed approach provides flexible and energy-efficient control of the aggregation process in the dynamic environment of the WSN