Carbon-Aware Intrusion Detection: A Comparative Study of Supervised and Unsupervised DRL for Sustainable IoT Edge Gateways

TL;DR

This paper introduces two novel DRL-based intrusion detection systems for IoT edge gateways that enhance detection accuracy, operate sustainably with energy considerations, and adapt to evolving threats.

Contribution

It proposes a carbon-aware, multi-objective reward framework for DRL-based IDS, enabling sustainable, adaptive, and effective intrusion detection in resource-constrained IoT environments.

Findings

AutoDRL-IDS achieves 94% detection accuracy with labeled data.

DeepEdgeIDS attains 98% accuracy in label-free offline evaluation.

The proposed reward formulation supports sustainable, real-time IDS operation.

Abstract

The rapid expansion of the Internet of Things (IoT) has intensified cybersecurity challenges, particularly in mitigating Distributed Denial-of-Service (DDoS) attacks at the network edge. Traditional Intrusion Detection Systems (IDSs) face significant limitations, including poor adaptability to evolving and zero-day attacks, reliance on static signatures and labeled datasets, and inefficiency on resource-constrained edge gateways. Moreover, most existing DRL-based IDS studies overlook sustainability factors such as energy efficiency and carbon impact. To address these challenges, this paper proposes two novel Deep Reinforcement Learning (DRL)-based IDS: DeepEdgeIDS, a label-free Autoencoder-DRL hybrid, and AutoDRL-IDS, a supervised LSTM--DRL model. Both DRL-based IDS are validated through theoretical analysis and experimental evaluation on edge gateways. Results demonstrate that AutoDRL-IDS achieves 94% detection accuracy using labeled data, while DeepEdgeIDS attains 98% offline evaluation accuracy through label-free anomaly detection and online mitigation feedback. This study introduces a carbon-aware, multi-objective reward formulation that supports supervised reward optimization for AutoDRL-IDS and label-free online reward learning for DeepEdgeIDS, enabling sustainable real-time IDS operation in dynamic IoT networks.