OPTIMIZATION OF THE ROUTING PROCESS IN DISTRIBUTED NETWORKS USING MACHINE LEARNING

The article proposes an innovative approach to optimize the routing process in distributed networks using machine learning techniques, specifically reinforcement learning. This method enables the adaptive determination of optimal data transmission paths based on current network conditions, enhancing overall performance and resilience to dynamic traffic fluctuations. The proposed approach dynamically adjusts to variations in network topology, traffic load, and node availability, ensuring efficient data flow management even in highly dynamic environments. Experimental results demonstrate substantial benefits of the proposed algorithm over conventional routing methods. Compared to Dijkstra’s algorithm, the new approach achieves a 15% reduction in average delay time, and improved utilization of network bandwidth. The practical significance of the obtained results lies in the potential deployment of the developed approach across various fields, including the Internet of Things, wireless sensor networks. This method can significantly enhance the performance of autonomous systems, intelligent transportation networks, and other critical infrastructures where reliability and speed are essential. Future research will focus on further refining the proposed approach, scaling it to support large-scale networks with thousands of nodes, integrating it with state-of-the-art cybersecurity measures, and developing energy-efficient learning models tailored for nodes with constrained computational resources. The proposed solution holds significant potential for improving the efficiency of modern network systems, paving the way for more intelligent and adaptive distributed network management.