Energy-Efficient Cascaded Machine Learning Framework for Network Anomaly Detection

The escalating complexity and scale of modern network infrastructures have amplified the need for intelligent intrusion detection systems (IDS) capable of identifying malicious traffic in real time, within sustainable energy budgets. This paper presents GreenShield, a two-stage cascaded machine learning framework designed to achieve high detection accuracy while minimizing computational energy consumption. The framework employs a lightweight Decision Tree classifier as a first-stage filter, resolving high-confidence samples directly and escalating only uncertain samples to a more resource-intensive Random Forest classifier in the second stage. Experiments are conducted on a network traffic dataset based on the NSL-KDD benchmark, evaluating six classifiers: Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors, assessed across accuracy, precision, recall, F1-score, training time, inference latency, memory consumption, and estimated energy usage (mWh). GreenShield achieves an F1-score of 0.9687, comparable to standalone Random Forest (0.9704), while reducing inference-time energy consumption by approximately 60% by resolving 98.5% of samples at the lightweight first stage. A sustainability efficiency metric, the ratio of F1-score to energy consumed per inference, is introduced to quantify this performance-energy trade-off. Results demonstrate that GreenShield offers a favorable balance between accuracy and sustainability, making it suitable for deployment in energy-constrained network environments. This work contributes to the growing body of research on Green AI by showing that cascaded classification architectures can reduce the environmental impact of network security operations without sacrificing protective capability. As a limitation, results are based on a single benchmark dataset derived from NSL-KDD; validation on additional public IDS datasets is identified as a direction for future work.