Particle Swarm Optimization-Intruder Detection for Traffic Prediction over Wireless Sensor Networks
Wireless Sensor Network (WSN) remains a system which is based on a framework with lots of sensor node. The Sensor Node has a reliable data transfer in the sink, which is dependent on aggregate data which are given by sensor nodes. However, due to untrustworthy wireless communication nature and traffic issue, it is difficult to ensure the end to end delay reliable quality as well its timeliness. The proposed work is used to forecast the forthcoming traffic in Wireless Sensor Network. In this work, Particle Swarm Optimization-Intruder Detection (PSOID) is proposed to improve the overall network performance. The abnormal movement is anticipated and it shows the likelihood for violence as well as it starts a hopping occurrence to maintain a strategic distance from this. Increment in the hopping frequency time is distinguished by PSOID model, which give a alert signal to the network which intends will keep away from the anomaly channel. Efficiency of this model is been demonstrated to be productive in recognizing the abnormality station from the imitation outcomes ever since the data about the assailants in the station can be realized utilizing swarm intelligence (particles).Thus the simulation results conclude, proposed PSOID algorithm is enhanced compared to the existing methods in terms of lower energy consumption, advanced amount, lower end to end delay and advanced net lifetime.