Improving the exploration efficiency of DQNs via the confidence bound methods

Wen, Yingpeng; Su, Qinliang; Shen, Minghua; Xiao, Nong

doi:10.1007/s10489-022-03363-0

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Mdrl-tp Multiagent Cross-domain Routing Algorithm Designmentioning

confidence: 99%

“…On the other hand, the use of empirical samples from different strategies reduces the correlations between data and improves the generalization ability of the algorithm. The MDRL-TP multiagent cross-domain routing algorithm also uses a decaying ε-greedy detection mechanism (Wen et al, 2022): Cross-domain routing method in SDN 5.2 Prediction algorithm performance and experimental parameter analysis By using the GRU-based network traffic state prediction algorithm developed in our previous work (Huang et al, 2022), an agent can learn to obtain a higher reward value. The reason for this is that the GRU-based prediction algorithm can monitor hidden network traffic states in a largescale SDN under multicontroller management, which are difficult to obtain based solely on the multithreaded SDN measurement mechanism and cooperative communication module.…”

Section: Dueling Dqn Drl Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

A new intelligent cross-domain routing method in SDN based on a proposed multiagent reinforcement learning algorithm

Ye,

Huang,

Wang

et al. 2024

IJICC

View full text Add to dashboard Cite

PurposeA cross-domain intelligent software-defined network (SDN) routing method based on a proposed multiagent deep reinforcement learning (MDRL) method is developed.Design/methodology/approachFirst, the network is divided into multiple subdomains managed by multiple local controllers, and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement mechanism. Then, a cooperative communication module is designed to realize message transmission and message synchronization between the root and local controllers, and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to acquire global network state information in real time. Finally, after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers, a network traffic state prediction mechanism is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real time.FindingsExperimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and open shortest path first (OSPF) routing methods.Originality/valueMessage transmission and message synchronization for multicontroller interdomain routing in SDN have long adaptation times and slow convergence speeds, coupled with the shortcomings of traditional interdomain routing methods, such as cumbersome configuration and inflexible acquisition of network state information. These drawbacks make it difficult to obtain global state information about the network, and the optimal routing decision cannot be made in real time, affecting network performance. This paper proposes a cross-domain intelligent SDN routing method based on a proposed MDRL method. First, the network is divided into multiple subdomains managed by multiple local controllers, and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement mechanism. Then, a cooperative communication module is designed to realize message transmission and message synchronization between root and local controllers, and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to realize the real-time acquisition of global network state information. Finally, after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers, a prediction mechanism for the network traffic state is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real time. Experimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and OSPF routing methods.

show abstract