An Efficient Anomaly Detection Framework for Wireless Sensor Networks Using Markov Process

TL;DR

This paper tackles anomaly detection in resource-constrained Wireless Sensor Networks by proposing a lightweight unsupervised framework based on a first-order Markov chain. Continuous sensor readings are discretized into finite states and a transition probability matrix $P$ captures normal dynamics, with anomalies identified when observed transitions satisfy $P_{ij} < \theta$. Validation on the Intel Berkeley Lab indoor dataset yields robust detection with an F1-score around $0.86$, balancing accuracy, interpretability, and computational efficiency for potential on-node deployment. The approach offers scalable, real-time anomaly detection suitable for smart building, industrial, and agriculture contexts, while remaining explainable and hardware-friendly. Potential extensions include adaptive thresholds, multivariate and higher-order Markov models, and online/edge-focused implementations to broaden applicability and generalization.

Abstract

Wireless Sensor Networks forms the backbone of modern cyber physical systems used in various applications such as environmental monitoring, healthcare monitoring, industrial automation, and smart infrastructure. Ensuring the reliability of data collected through these networks is essential as these data may contain anomalies due to many reasons such as sensor faults, environmental disturbances, or malicious intrusions. In this paper a lightweight and interpretable anomaly detection framework based on a first order Markov chain model has been proposed. The method discretizes continuous sensor readings into finite states and models the temporal dynamics of sensor transitions through a transition probability matrix. Anomalies are detected when observed transitions occur with probabilities below a computed threshold, allowing for real time detection without labeled data or intensive computation. The proposed framework was validated using the Intel Berkeley Research Lab dataset, as a case study on indoor environmental monitoring demonstrates its capability to identify thermal spikes, voltage related faults, and irregular temperature fluctuations with high precision. Comparative analysis with Z score, Hidden Markov Model, and Auto encoder based methods shows that the proposed Markov based framework achieves a balanced trade-off between accuracy, F1 score is 0.86, interoperability, and computational efficiency. The systems scalability and low resource footprint highlight its suitability for large-scale and real time anomaly detection in WSN deployments.

Figures (5)

• Figure 1: Hierarchical Wireless Sensor Network
• Figure 2: Flow of control in the proposed framework
• Figure 3: Confusion matrix
• Figure 4: Node-wise anomaly rate (%)
• Figure 5: High and Low anomaly node comparison