IEEE802.1 Time-Sensitive Networking (TSN) makes it conceivable to convey the data traffic of time as well as critical applications using Ethernet shared by different applications having diversified Quality of Service (QoS) requirements for both TSN and non-TSN. TSN assures a guaranteed data delivery with limited latency, low jitter, and amazingly low loss of data for time-critical traffic. By holding networking resources for basic traffic, and applying different queuing and traffic shaping strategies, TSN accomplishes zero congestion loss for basic time-critical traffic. In proposed system, backpropagation algorithm is used to train the training set and fuzzy inference system methodologies such as Mamdani fuzzy inference system which has fuzzy inputs and fuzzy outputs, Sugeno FIS which has fuzzy inputs and a crisp output and adaptive-network-based fuzzy inference system has obtained from the neural network and fuzzy logic. The proposed system uses neuro-fuzzy techniques to handle frame pre-emption and reduces the time taken for decision making. It presents a decision making process using the traffic class.

No abstract

IEEE 802.1 Time-Sensitive Networking (TSN) assures a guaranteed data delivery with limited latency, low jitter, and amazingly low loss of data in handling time-critical traffic. TSN handles different quality of service (QoS) requirements and frame preemption is one of the key features of TSN. In the healthcare sector networking technology preferred by large organizations uses an enormous number of nodes, and thereby, the complexity of the network increases. Since the priority of the medical data varies at times based on the patient's health, dynamic traffic scheduling mechanisms are preferred. To improve the efficiency of the network, the software-defined access mechanism is used to control the network switches and bridges in the time-sensitive network. This work uses reinforcement learning to identify and eliminate the bridges dropping packets, and the alternative path is used to schedule the real-time data traffic. It is perceived that it performs well for the time-critical data in congestion network, increases the throughput, and reduces latency.