FUSE-IS: multi-modal data fusion for carbon-aware security in industrial energy systems

Modern industrial energy systems are increasingly reliant on heterogeneous data streams from sensors, grid infrastructure, renewable forecasts, and cybersecurity telemetry. Effectively fusing these diverse sources is essential for achieving resilient, efficient, and sustainable operations. In this paper, we present a Fusion-based Unified Security and Energy efficiency approach for Industrial Systems (FUSE-IS), a novel multi-modal data fusion framework. FUSE-IS integrates deep learning-based threat detection, differential privacy mechanisms, and carbon-aware resource scheduling. It enhances security, privacy, and energy efficiency in industrial energy environments. Unlike traditional solutions that address these objectives in isolation, FUSE-IS employs a unified data fusion approach that combines these solutions. As a result, it enabled real-time adaptive decision-making for threat mitigation, data protection, and carbon-optimized computing. Experimental results demonstrate that FUSE-IS achieves 98.5 % detection accuracy with only 1.2 % false positives, while reducing energy consumption by 24 % and carbon emissions by 20 % compared to baseline methods. The framework maintains strong privacy guarantees (ϵ = 0.9) with minimal accuracy degradation (0.7 %). A case study on DDoS mitigation illustrates FUSE-IS's ability to dynamically adjust defense strategies based on carbon intensity fluctuations, resulting in a 27 % emission reduction during the attack window.