routing

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.

Запропоновано метод підвищення ефективності алгоритму DyXY шляхом сегментації мережі на основі статистичних даних та відносної пропускної характеристики елементів. За цим методом, за наявності кількох вільних альтернативних маршрутів пакет відправляється до сегмента, в якого вища пропускна характеристика. Так зменшується ризик простою пакета через зайнятість транзитного отримувача.

The article is devoted to the problem of effective use of cross-docking as a technology of cargo delivery with increased time requirements, which allows to resolve the contradictions of guaranteed delivery time ensuring and the efficiency of the existing fleet of trucks. The process of delivery organization is considered as the ordering on the transport network of many discrete freight flows in the form of their phases. If qualitative and / or quantitative changes do not occur from phase to phase with the flow, then the tact of such flow is constant.

In this paper, the hierarchical architecture of the sensor network (MESH-network) with a high degree of scalability is proposed. The possibilities of its realization in the mode of self- configuration using the special routing protocol at the query (AODV — Ad-hoc On-Demand Distance Vectorisation) and fixed-line routing protocol (OLSR — Optimised Link-State Routing) are investigated.

This paper considers the options for combining routing algorithms in a single method for multiservice communication networks.