An edge computing based anomaly detection method in IoT industrial sustainability

A Survey of AI-Based Anomaly Detection in IoT and Sensor Networks

“…Application Primary Focus Secondary Focus [38] malicious actor IDS - [39] malicious actor IDS - [40] malicious actor DDoS - [41] malicious actor SYN attack - [11] malicious actor botnet - [42] malicious actor -- [14] malicious actor -time series data [43] malicious actor malware detection - [46] malicious actor feature selection - [12] malicious actor -- [44] malicious actor IDS - [10] malicious actor IDS - [45] malicious actor IDS - [47] sensor performance water systems time series data [48] sensor performance charging system - [49] sensor performance nuclear power plant - [51] sensor performance edge connection fault detection - [15] sensor performance emergency detection - [54] time series data IIoT sensor drift - [7] time series data -- [13] time series data multivariate time series data - [55] time series data -- [57] general AD time series data multi-class detection [56] general AD automated vehicles - [58] general AD time series data energy efficiency [52] distributed AD -- [53] distributed AD time series data -…”

“…In step with [ 52 ], the work in [ 53 ]focused on distributed anomaly detection, citing the incredible increase in IoT devices over the last few years and subsequent increase in load on cloud computing systems. The primary motivation in [ 53 ] was to handle anomalies in real-time, rather than wait for an analysis to occur at the cloud level. The Internet of Vehicles (IoV) (a subset of IoT) producing anomalous sensor data was used as a motivating example.…”

“…In [ 53 ], a distributed approach was utilized, where the analysis using a CNN-inspired rule-based classifier was used to update an anomaly rules database (ARB). This ARB was used by the edge nodes to detect anomalies in univariate and multivariate time series data.…”

“…Of all the papers surveyed, only three were found to address this issue as a primary concern. Two of these approaches [ 52 , 53 ] were surveyed here. Another of these approaches [ 62 ], did not meet the criteria of this survey, but is worth mentioning here due to the unique nature of the research.…”

“…Lastly, work focusing on distributed AD in IoT similar to [ 52 , 53 ] and edge computing AD similar to [ 64 ] in the IoT is scarce. With the proliferation of the IoT at home, on our person, in the workplace, and in the environment, research on the efficiency/performance of distributed AD and edge-computing AD are in a prime position for expanding the state-of-the-art and improving AD overall in the area of the IoT.…”