Cognitive agent based fault tolerance in ubiquitous networks: a machine learning approach

Ubiquitous Networks play an essential role in accessing ubiquitous computing services at anytime, anywhere, and anyplace through computing nodes of heterogeneous networks. Nowadays, ubiquitous network faces various issues related to fault management or tolerance in a real world environment. In this type of network, fault tolerance is one of the vital issues due to dynamic and uncertain character of ubiquitous networks with various constraints of nodes and networks to maximize network lifetime, availability, and reliability of the networks. In this paper, it is proposed that a cognitive agent based fault tolerance system using reinforcement learning algorithm to provide efficient ubiquitous services to the users over the networks. The main objective of the proposed work is to emphasize the analysis, identification, and recovery of various faults under resource constraints of ubiquitous networks in terms of node, memory, load, and network level faults (link level fault and packet error) using a cognitive agent based machine learning algorithm. Also, the proposed work performs better fault tolerance than conventional methods (without using cognitive agents) by considering fault detection rate, fault recovery rate, fault recovery time, packet delivery ratio, agent computation overhead, and energy consumption for performing the desired set of tasks and services ubiquitously in the ubiquitous computing environment.