ENERGY EFFICIENT SECURE COMMUNICATION USING TRUST MODEL AND MACHINE LEARNING

Abstract

In general, a sink and various tiny sensor nodes are included in Wireless sensor networks (WSNs). Overall performance and security of WSNs are degraded due to limited resources and hostile environments, broadcasted and untrusted transmissions, unprotected and free communications and nodes misbehavior due to malicious selfishness or compromised intentions. Against various attacks, WSNs’ security is also degraded. Clustered based models are thanks of structure for saving power, least computational overhead, while has a lake of scalability. The flat models are more reliable and scalable but have a computational overhead and power consumption. Network flow information is checked for effective recognition of intruder. For every malicious and good node’s behavior, both penalty and reward policies are used in direct trust establishment scheme. In this, we have proposed an energy efficient secure trust communication model by using machine learning. The efficiency of K-Nearest Neighbor is low, and all the data should be calculated once for each classification, which takes a long time when the data is large The greatest advantage of the model is by using the Rapid Machine Learning along with K-Nearest Neighbor (RML-KNN) the system learns more quickly and by the learning it work on its own.  This is done for making more realistic trust computation and for detecting on /off attack.