A Novel Traffic Management Protocol Design for Avoiding Data Loss through Artificial Intelligence
Abstract
Multiple sensors are installed and wirelessly networked in Wireless Sensor Networks, which are occurrence communication information available instantly and securely of many sensors nodes. This enables data retrieval from surveillance devices. Whenever an event occurs in a wireless sensor network, the information related with that event must be transmitted to the data collection node and due to high data traffic, the sink node serves as the network's barrier. Loss of data occurs as a consequence of congestion, and it might be vital data. Artificial Intelligence enabled Neural Networks Design (NN) based Congestion Controller method is presented to attain this goal. The Wireless Sensor Network communication is controlled by the waveform convolution operation, which activates the proposed model. Using this present methodology of AINNCCM method, the up-stream traffic ratio is measured to prevent overcrowding in the future and the downstream traffic figure is projected, with all three aspects working together to improve Quality of Service (QoS) by enhancing the ratio of Packet-Loss, throughput ratio and Overall Network . This AINNCCM method avoids congestion issues and network traffic by using AI logic and also improving the overall network Quality-of-Service.