An efficient routing protocol to reduce traffic and congestion control in cloud edge networks of wireless sensor networks

• Published in: International journal of communication systems 2024-07, Vol.37 (10), p.n/a
• Main Authors: Alwarsamy, Vijayaraj, Rethnaraj, Jebakumar, Gurumuni Nathan, Uma Devi, Pandiarajan, Gururama Senthilvel
• Format: Article
• Language: English
• Subjects: cloud edge network; congestion control; Data integrity; Data loss; Data transmission; Delay; delay‐aware routing protocol; distributed communication model; Edge computing; Energy efficiency; Protocol (computers); Queueing; Routing (telecommunications); Traffic congestion; Traffic control; traffic reduction; Wireless sensor networks
• ISSN: 1074-5351; 1099-1131
• DOI: 10.1002/dac.5779

Summary Recently, wireless sensor networks (WSNs) have been used for monitoring, sensing, processing, and communication purposes in real‐time applications. It is employed with a routing protocol that performs an effective data transmission process. However, while transmitting large data, there occurs an over fitting issue, which leads to determining a huge data leakage. Also, the delay is increased with heavy congestion in the network. Hence, a novel method is proposed to diminish the network congestion regarding distributed networks as well as cloud edge computing. Moreover, it diminished the data loss from an overloaded condition. However, the proposed technique controls congestion that resists the traffic in the network through lightweight, ultra‐dense label‐less federation and incorporates adaptive multi‐agent Markov reinforcement learning. Furthermore, a distributed energy‐efficient delay‐aware routing protocol is employed to analyze and regulate congestion control in the network. Also, it varies the network dynamically by adjusting the routing protocol that optimizes the congestion and implements the traffic mechanism. Moreover, the congestion in WSNs overwhelms the nodes and channels distributed in the packets. The evaluation of the proposed method is determined by various metrics such as queuing delay, network lifetime, energy efficiency, throughput, and packet delivery ratio. The experimental results revealed that the proposed method attained an enhanced performance by maximizing energy efficiency and packet delivery ratio by 94% as well as 89% and reducing the delay by 55%, respectively. This research proposes a novel approach to mitigate congestion in wireless sensor networks (WSNs) by integrating distributed networks with cloud edge computing. The method utilizes lightweight, label‐less federation and adaptive multi‐agent Markov reinforcement learning for efficient traffic management. A distributed energy‐efficient delay‐aware routing protocol dynamically regulates congestion, optimizing network performance. Evaluation metrics include queuing delay, network lifetime, energy efficiency, throughput, and packet delivery ratio. Experimental results demonstrate significant improvements: up to 94% in energy efficiency, 89% in packet delivery ratio, and a 55% reduction in delay. This approach addresses critical challenges in WSNs, enhancing their effectiveness in real‐time applications.