#5386. Centrality Based Congestion Detection Using Reinforcement Learning Approach for Traffic Engineering in Hybrid SDN

August 2026publication date
Proposal available till 13-05-2025
4 total number of authors per manuscript0 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Strategy and Management;
Information Systems;
Computer Networks and Communications;
Hardware and Architecture;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
2350 $1200 $1050 $900 $
Contract №5386.1 Contract №5386.2 Contract №5386.3 Contract №5386.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
The rising number of users and the demand for more diverse and specialized applications have led to a tremendous increase in network traffic. Managing diverse traffic demands from numerous applications is a challenging task for the existing traditional networking architecture. Hybrid software defined network is widely used to simplify operations providing flexible traffic management and automation. However, managing dynamic traffic demands and routing traffic flows is a challenging task. Therefore, in this paper, a centrality based Q-learning routing traffic engineering method for congestion detection and optimized traffic routing is proposed. The proposed method uses the reinforcement Q-learning algorithm to find an optimal path for routing the traffic. The centrality measures of the nodes are computed and ranked using the simple additive weighted method to detect the top k high-risk nodes. Simulations are carried out under different network scenarios for various traffic profiles.
Keywords:
Centrality measures; Congestion aware routing; High-risk nodes; Optimal path; Q-learning; Simple additive weighted method

Contacts :
0