Fast Wireless Sensor Anomaly Detection based on Data Stream in Edge Computing Enabled Smart Greenhouse

TL;DR

This paper introduces DLSHiForest, a novel anomaly detection method for wireless sensor data streams in smart greenhouses, addressing challenges of data volume, correlation, and concept drift to improve accuracy and efficiency.

Contribution

The paper presents DLSHiForest, combining Locality-Sensitive Hashing and time window techniques for real-time anomaly detection in data streams, overcoming limitations of traditional algorithms.

Findings

Effective detection of anomalies in greenhouse sensor data

High detection accuracy with low memory usage

Demonstrated scalability and robustness in real-world data

Abstract

Edge computing enabled smart greenhouse is a representative application of Internet of Things technology, which can monitor the environmental information in real time and employ the information to contribute to intelligent decision-making. In the process, anomaly detection for wireless sensor data plays an important role. However, traditional anomaly detection algorithms originally designed for anomaly detection in static data have not properly considered the inherent characteristics of data stream produced by wireless sensor such as infiniteness, correlations and concept drift, which may pose a considerable challenge on anomaly detection based on data stream, and lead to low detection accuracy and efficiency. First, data stream usually generates quickly which means that it is infinite and enormous, so any traditional off-line anomaly detection algorithm that attempts to store the whole dataset or to scan the dataset multiple times for anomaly detection will run out of memory space. Second, there exist correlations among different data streams, which traditional algorithms hardly consider. Third, the underlying data generation process or data distribution may change over time. Thus, traditional anomaly detection algorithms with no model update will lose their effects. Considering these issues, a novel method (called DLSHiForest) on basis of Locality-Sensitive Hashing and time window technique in this paper is proposed to solve these problems while achieving accurate and efficient detection. Comprehensive experiments are executed using real-world agricultural greenhouse dataset to demonstrate the feasibility of our approach. Experimental results show that our proposal is practicable in addressing challenges of traditional anomaly detection while ensuring accuracy and efficiency.