A graph neural network based fault diagnosis strategy for power communication networks

ABSTRACT

The power communication network (PCN) is the backbone network of the power system. However, faulty nodes in the network may cause communication interruptions, seriously affecting the reliable operation of the power system. Therefore, accurate diagnosis of faulty nodes is crucial for timely detection, localization, and troubleshooting. Based on graph neural networks, we propose a Neighbour Selection and Merge Fault Diagnosis (NSMFD) strategy, which aims to identify faulty nodes capturing graph structure information and node feature information. First, we construct a graph representation of PCN, where nodes represent devices in the network and edges represent the connections between devices. Then, we use sampling and aggregation in node embedding to capture adjacent feature information of nodes, gradually fuse and update node representations through graph convolutional layers, which could be applied as the input layer of diagnostic process. Finally, we use softmax and cross entropy loss function to get a probabilistic representation and optimize it by backpropagation for prediction. We conduct experiments using real PCN datasets and compare it with other advanced diagnostic methods in terms of accuracy, false positive rate, and false negative rate. Compared with diagnostic methods, our method can accurately identify faulty nodes and achieve timely fault detection and recovery.

CO EDITOR-IN-CHIEF:

• Hsieh, Sun-Yuan

ASSOCIATE EDITOR:

• Hsieh, Sun-Yuan

KEYWORDS:

• Graph neural networks
• fault diagnosis
• power communication network

Nomenclature

$\mathit{A}:[\mathit{B},\mathit{C},\mathit{D}]$	=	First-order neighbours of $\mathit{A}$
$\mathit{AG}{G}_M$	=	Aggregator function
$\mathit{d}$	=	Feature dimension
$\mathit{E}$	=	Edge set
$F_{\mathit{faulty}}$	=	Faulty set
$F_{\mathit{fault}-\mathit{free}}$	=	Fault-free set
$\mathit{G}\left(\mathit{V},\mathit{E}\right)$	=	Graph containing V and E
$j_{N\left(v\right)}^m$	=	Aggregation information
k	=	Average degree of neighbours
m	=	Sampling size
M	=	Sampling
n	=	Number of nodes
Ov	=	Node embedding
p	=	Output dimension
pt	=	Probability threshold
V	=	Node set
Wm	=	Weight matrices
yv	=	Node features
$\mathit{\sigma }$	=	Non-linear activation function

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The data are available from http://www.52phm.cn/datasets/

Additional information

Funding

This work was supported by the National Natural Science Foundation of China under Grant [62171132, 62102088, U1905211]; Fok Ying Tung Education Foundation under Grant [171061]; and Natural Science Foundation of Fujian Province [2021J05228, 2020J01167].