[This article belongs to Volume - 56, Issue - 03]
Gongcheng Kexue Yu Jishu/Advanced Engineering Science
Journal ID : AES-19-04-2024-695

Title : Hybrid BSO+BMO: An Optimal Routing with Adaptive Deep Learning and Attention Mechanism for Link Failure Detection in Elastic Optical Network
Sahana Sharma M, Dr. K.V.S.S.S.S Sairam,

Abstract : Elastic Optical Network (EON) is a popular framework for interconnecting data centers, providing a spectrum tailored to bandwidth requirements. Verifying the high stage "Quality of Service (QoS)" for candidate requests following the fault is the main focus in the connection failure scenario. The resilience of a high-speed network is crucial because, as network sizes increase, so does the probability of node and link degradation. Thus, an adaptive method is required to forecast the link deterioration in EON. A unique approach employing hybrid heuristic implementation is suggested to achieve this goal. The required data is obtained and entered into the first stage of the connection failure detection model. The novel method is named as Atrous Spatial Pyramid Pooling – 1 Dimensional Convolution Neural Network with Attention mechanism (ASPP-1DCNN-AM), in which some of the hyper-parameters are tuned by proposing the hybrid algorithm as Iteration-aided Position of Beetle and Barnacles Mating (IPBBM). The model must choose the optimal routing in order to improve communication. Here, the optimal path is identified by using the IPBBM algorithm. Finally, the validation is done using divergent measurements and in contrast with traditional models. Hence, the designed system demonstrates that it achieves the higher detection results to make the data transmission effectively.