Neural Networks for Dynamic Shortest Path Routing Problems - A Survey

TL;DR

This survey reviews how neural networks are effectively used to solve dynamic shortest path routing problems in networks, highlighting their computational advantages over other soft computing methods.

Contribution

It provides a comprehensive overview of neural network approaches for dynamic shortest path routing, emphasizing their efficiency and suitability for real-time network optimization.

Findings

Neural networks are effective for dynamic shortest path routing.

They outperform other soft computing methods in computation speed.

Neural networks are the best candidates for real-time network optimization.

Abstract

This paper reviews the overview of the dynamic shortest path routing problem and the various neural networks to solve it. Different shortest path optimization problems can be solved by using various neural networks algorithms. The routing in packet switched multi-hop networks can be described as a classical combinatorial optimization problem i.e. a shortest path routing problem in graphs. The survey shows that the neural networks are the best candidates for the optimization of dynamic shortest path routing problems due to their fastness in computation comparing to other softcomputing and metaheuristics algorithms