Learning automaton‐based self‐protection algorithm for wireless sensor networks

Abstract

Wireless sensor networks (WSNs) have been widely used for many applications such as surveillance and security applications. Every simple sensor in a WSN plays a critical role and it has to be protected from any attack and failure. The self‐protection of WSNs focuses on using sensors to protect themselves to resist against attacks targeting them. Therefore, it is necessary to provide a certain level of protection to each sensor. The authors propose an irregular cellular learning automaton (ICLA)‐based algorithm, which is called SPLA, to preserve sensors protection. Learning automaton at each cell of ICLA with proper rules aims at investigating the minimum possible number of nodes in order to guarantee the self‐protection requirements of the network. To evaluate the performance of SPLA, several simulation experiments were carried out and the obtained results show that SPLA performs on average of 50% better than maximum independent set and minimum connected dominating set algorithms in terms of active node ratio and can provide two times reduction in energy consumption.