Publication

Abstract : The development of Wireless Sensor Networks (WSN) is broad research in recent communication approaches. Due to the increasing demand for service, the quality is insufficient to meet the requirements to take energy efficient network. This leads to high energy losses, traffic, improper scheduling, and poor network performance. Selecting a higher traffic route introduces higher packet drop and reduces the throughput performance. Analyzing the traffic in the existing process is complex and doesn't provide Quality of Service (QoS). So data analysis is essential based on reinforcement learning with an intelligent machine learning approach. To resolve this problem, we propose a Cooperative self-scheduling routing approach (CS2RA) based on energy Efficient Optimal Link stability routing allocation (EOLSRA) designed to improve the quality of service in Wireless sensor networks. The dynamic network topology medium is constructed with Neighbor Stable Link Connectivity Based Routing. With the Probability support, the traffic density approximation rate (PTDAR) is estimated by improving energy stabilization. By intending an optimistic Q-learning network model based on the energy-consuming parameters using an adaptive Petal spider ant colony cluster (PSACC) is constructed for link stability for route optimization. Then Cooperative stabilized proactive Energy-aware cluster routing protocol (CSPECR) was intended to make self-balanced congestion routing with the support of the Lookup energy constraint duty cycle (LECDC) to improve the lifetime of the network.