Abstract
Industrial cyber–physical systems increasingly have relied on secure
circuits that also have aligned with carbon neutral goals. Prior studies
have emphasized detection accuracy, yet the energy footprint of
security algorithms has remained marginally addressed. The need for
energy-aware cybersecurity circuits has therefore emerged as a critical
research direction. Conventional intrusion detection circuits have
consumed excessive power due to continuous monitoring that has
depended on computationally intensive learning models. These
approaches have limited suitability for green industrial infrastructure,
where both security assurance and energy efficiency have been
demanded simultaneously. A lack of unified frameworks that have
integrated low-power algorithms with sustainable circuit deployment
has persisted. A novel energy-efficient framework that has been termed
OSV-BiSGA has been proposed for industrial cybersecurity circuits.
The framework has combined a one-class support vector model with a
bidirectional snow geese optimization algorithm that has minimized
redundant computations. Continuous monitoring that has been
designed at the circuit level has adapted sampling rates dynamically,
which has reduced idle power consumption. Green infrastructure
principles that have included low-leakage components and adaptive
voltage scaling have been incorporated into the circuit design.
Optimization that has guided parameter selection has ensured minimal
energy usage without degrading detection reliability. The proposed
OSV-BiSGA framework achieves an accuracy of 0.95, precision of
0.93, recall of 0.94, and F1-score of 0.94 at a population size of 30,
while reducing energy consumption to 40 J. Compared with Static One
Class SVM, PSO-Optimized IDS, and Always-On Deep Learning IDS,
the framework reduces energy usage by up to 63% while maintaining
superior detection performance.
Authors
Thomas Samraj Lawrence
Dambi Dollo University, Ethiopia
Keywords
Cybersecurity Circuits, Carbon Neutrality, Energy-Efficient Algorithms, Continuous Monitoring, Green Infrastructure