Neural network based automated detection of link failures in wireless sensor networks and extension to a study on the detection of disjoint nodes

Abstract

In the broad research area of wireless sensor networks (WSN), detection of link failure is still in its infancy. In this paper, we propose to use a neural network model for detection of link failure in WSN. The neural network has been allowed to learn and adapt with the help of gradient descent based learning algorithm. We demonstrate the proposed model with regard to the preparation of training data and implementation of the model. This paper also provides a thorough theoretical and analytical investigation of link failures in WSN. The proposed neural network based model has been evaluated carefully with regard to testbed experiments. The simulation-based experiment has been conducted to justify the applicability of the proposed model for dense networks that could contain around 1000 links. We also analyze the theoretical performance of the proposed neural network based algorithm with regard to various performance evaluative measures such as failure detection accuracy, false alarm rate. The simulated experiments, as well as the testbed experiments in indoor and outdoor environments, suggest that the method is capable of link failure detection with higher detection rate and it is consistent. Furthermore, this article also reports a comprehensive case study as an extension of this present research towards automated detection of disjoint and disconnected nodes in a sensor network.

Appendix: Fundamental details of graph theory with respect to wireless sensor networks

A wireless sensor network, G defined as a graph, i.e. $G=(N, L)$, where N is set of all nodes in G, and L is set of all links in G.

Digraph

In a Digraph each links represented by order pair of nodes $(N_i,N_j)$, link from $N_i$ to $N_j$.

Degree of a node

Degree of a node in a nondirected graph defined deg(N), number of links incident with the node.

Adjacency

In a graph two nodes are said to be adjacent if there exists a link in between the two nodes.

In-degree and out-degree of a node

In-degree of node ($deg^+(N)$) is number of links incident to the node. Out-degree of node ($deg^-(N)$) is number of links incident from the node.

$$\begin{aligned} deg(N)=deg^+(N)+deg^-(N) \end{aligned}$$

(26)

Connected network

Network is said to be connected if there exists a path between every pair of the node. The network which is not connected will 2 or more connected components.

Cut node

Let G be a connected network if there exists a node $n\in G$ such that $G-n$ results on a disconnected network. Then n is called as a cut node of G.

Cut link

Let G be a connected network if there exists a link $e\in G$ such that $G-e$ results on a disconnected network. Then e is called as a cut link of G.

Cut set

Let $G=(N,L)$ be a connected network. A subset ${L}'$ of L is called a cut set of G, if removal of ${L}'$ from G makes the network disconnected and removal of no proper subset of ${L}'$ from G, makes G disconnected.

Node connectivity

Let G be a connected graph, the minimum number of nodes in G, whose removal makes G disconnected or isolated is called node connectivity of G.

Link connectivity

Let G be a connected graph, the minimum number of links in G, which removal makes G disconnected is called as link connectivity of G.