An ANFIS estimator based data aggregation scheme for fault tolerant Wireless Sensor Networks

Wireless Sensor Networks (WSNs) are used widely in many mission critical applications like battlefield surveillance, environmental monitoring, forest fire monitoring etc. A lot of research is being done to reduce the energy consumption, enhance the network lifetime and fault tolerance capability of WSNs. This paper proposes an ANFIS estimator based data aggregation scheme called Neuro-Fuzzy Optimization Model (NFOM) for the design of fault-tolerant WSNs. The proposed scheme employs an Adaptive Neuro-Fuzzy Inference System (ANFIS) estimator for intracluster and inter-cluster fault detection in WSNs. The Cluster Head (CH) acts as the intra-cluster fault detection and data aggregation manager. It identifies the faulty Non-Cluster Head (NCH) nodes in a cluster by the application of the proposed ANFIS estimator. The CH then aggregates data from only the normal NCHs in that cluster and forwards it to the high-energy gateway nodes. The gateway nodes act as the inter-cluster fault detection and data aggregation manager. They pro-actively identify the faulty CHs by the application of the proposed ANFIS estimator and perform inter-cluster fault tolerant data aggregation. The simulation results confirm that the proposed NFOM data aggregation scheme can significantly improve the network performance as compared to other existing schemes with respect to different performance metrics. (C) 2016 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University.