AdaGUM: An Adaptive Graph Updating Model-Based Anomaly Detection Method for Edge Computing Environment

Xiang Yu,Ying Chen,Xianfei Yang,Haifeng Song,Jilong Bian,Chun Shan,Muhammad Shafiq

doi:10.1155/2021/9954951

Abstract

With the rapid development of Internet of Things (IoT), massive sensor data are being generated by the sensors deployed everywhere at an unprecedented rate. As the number of Internet of Things devices is estimated to grow to 25 billion by 2021, when facing the explicit or implicit anomalies in the real-time sensor data collected from Internet of Things devices, it is necessary to develop an effective and efficient anomaly detection method for IoT devices. Recent advances in the edge computing have significant impacts on the solution of anomaly detection in IoT. In this study, an adaptive graph updating model is first presented, based on which a novel anomaly detection method for edge computing environment is then proposed. At the cloud center, the unknown patterns are classified by a deep leaning model, based on the classification results, the feature graphs are updated periodically, and the classification results are constantly transmitted to each edge node where a cache is employed to keep the newly emerging anomalies or normal patterns temporarily until the edge node receives a newly updated feature graph. Finally, a series of comparison experiments are conducted to demonstrate the effectiveness of the proposed anomaly detection method for edge computing. And the results show that the proposed method can detect the anomalies in the real-time sensor data efficiently and accurately. More than that, the proposed method performs well when there exist newly emerging patterns, no matter they are anomalous or normal.

Highlights

With the rapid development of Internet of ings and wireless technologies, more and more applications, which are enabled by IoT, such as smart home appliances, selfdriving, and intelligent temperature control, appear in our daily life
Each sensor data to be detected must be in accordance with a certain known pattern. en, we compare the performance of adaptive graph updating model (AdaGUM) with the performance of the other three anomaly detection methods, which are
As to AdaGUM and AdaGUM_CL, we focus on the average True-positive rate (TPR) and False-positive rate (FPR) within each updating cycle

Summary

Introduction

With the rapid development of Internet of ings and wireless technologies, more and more applications, which are enabled by IoT, such as smart home appliances, selfdriving, and intelligent temperature control, appear in our daily life. As an indispensable component of IoT, all kinds of sensors are widely used for data collection in the tasks of various fields [1,2,3]. According to the research on the anomaly detection for sensor data [4], it is hard to determine the occurrence time and frequency of the anomalies. Anomalies should be detected in real-time rather than being detected at the cloud center after a period of time. Anomalous temperature data from the sensors deployed in a forest might represent a fire warning which means that immediate action is required. The accuracy of anomaly detection should be ensured because high false-positive rate will lead to frequent false alarm and high false-negative rate will lead to anomalies undetected

Methods

Results

Conclusion