Abstract
Today, smart grids use small electronic nodes to run services, but deciding where to put each service is hard. If we use cheap nodes, we save energy, but they are slow and not very secure. If we use fast nodes, they use too much power. In this paper, we look at this problem with three goals: using less energy, lowering security risks, and cutting down time delays. We must also make sure no node gets too much work. To do this, we propose a memetic optimization method named M-NSGA-II. It improves the normal NSGA-II by adding a smart start, changing search speeds, and including a fast step to fix broken answers. This fix uses no extra objective evaluations, so it saves search time. We compared our method with five other methods. We tested them fairly using device parameters taken from published hardware datasheets on three network sizes. For normal and large networks, our M-NSGA-II was clearly the best. It improved the final scores by up to 31 percent. This shows our method works very well for real-world grids.
Keywords
electronic edge computing, evolutionary computation, memetic algorithm, multi-objective optimization, NSGA-II, service placement, smart grid
DOI Link
Publication Date
2026-01-01
Publication Title
Electronics (Switzerland)
Volume
15
Issue
19
Deposit Date
2026-11-09
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Additional Links
Recommended Citation
Javanmardi, S., & Pahlevanzadeh, B. (2026) 'A Memetic NSGA-II (M-NSGA-II) for Secure, Energy- and Latency-Aware Service Placement in Electronic Smart Grid Edge Networks', Electronics (Switzerland), 15(19). Available at: 10.3390/electronics15194361