A mobile edge–cloud collaboration outlier detection framework in wireless sensor networks

Abstract

Wireless sensor networks (WSNs) are extensively deployed to collect various data. Due to harsh environments and limitation of computing and communication capabilities of sensor nodes, the quality and reliability of sensor data are compromised by outliers. With the advent of 5G, sensors tend to generate increasingly more complex data. When faced with big data, traditional outlier detection methods relied on sensor nodes and remote cloud are unable to accord satisfactory performance in terms of delay and energy consumption. To address this problem, we propose a mobile edge-cloud collaboration outlier detection framework. Outlier detection is performed by edge nodes between the remote cloud and the underlying WSNs, while the training and updating of detection model are conducted on the cloud. A fast angle-based outlier detection method is developed to obtain training data. The detection model is constructed based on support vector data description. An online learning-based iterative optimization scheme is devised to update the detection model. Besides, a fuzzy concept is incorporated into the detection model to alleviate the problem of loose decision boundary. Extensive experiments are conducted on real-world data set. Simulation results show that our model is superior to three popular methods in terms of delay and energy consumption. In addition, when the percentage of operational nodes is 60%, our proposal prolongs the network lifetime by 14.2% to 69.8% compared to the three methods. 1 How to cite this article: Gao C, et al.: A mobile edge-cloud collaboration outlier detection framework in wireless sensor networks. IET Commun. 1-14 (2021).

A Literature Review on Outlier Detection in Wireless Sensor Networks

“…Hypergrid based Adaptive Detection of Faults (HADF) [48], a distributed method that uses hypergrid and statistical analysis to identify sensor data faults. The approach in [49] uses an outlier detection framework based on collaboration between mobile edge and cloud, including Fast angle-based outlier detection algorithm (FastABOD) and f-SVDD (SVDD + fuzzy theory). In Ref.…”

“…The ERF algorithm [7] relies on an ensemble learning approach that combines multiple base classifiers, which may increase computational complexity and execution time compared with a simpler approach. Some potential limitations or challenges that might arise in the outlier detection framework based on collaboration between the mobile edge and the cloud [49] include the demand for periodic updates and optimizations of the detection model to preserve its accuracy and reliability, as well as the need to maintain a balance between performance and energy consumption at the edge nodes. The technique proposed in [50] is based on the analysis of historical data gathered from multiple medical sensors to identify anomalies and dynamically adjust the threshold value.…”