BESS-Aided Power Demand Reshaping for Distributed Green Edge Clouds
IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 23996-24012
DOI: 10.1109/tmc.2026.3731141 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Dongyu Zheng und 5 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, NSFC, Taishan Scholars Program.
Abstract (Originalsprache)
The rapidly growing edge computing market, supported by the edge cloud (EC) infrastructure, has imposed significant operating costs on EC operators (ECOs), particularly the energy cost. By incorporating green energy through the installation of solar photovoltaic panels and wind turbines, ECOs have great potentials in reducing their energy expenses. In this scenario, the battery energy storage system (BESS) is essential to store surplus green energy and discharge it during peak power periods, so as to make power demand reshaping and further minimize energy costs. Nevertheless, it remains open to determine how to effectively leverage green energy and BESS to reshape power demand in distributed ECs, especially under varying operational conditions. In this study, we characterize the energy scheduling problem in distributed green ECs with the objective of minimizing the energy costs. This problem presents significant challenges, including the inherent temporal and spatial coupling in the scheduling process, the demand for real-time decision-making under fluctuating power dynamics of green resources and ECs, and the critical need to balance energy savings against facility degradation within practical constraints. To solve this problem, we propose a multi-agent reinforcement learning based approach, along with a customized invalid action masking method to handle the inherent strong temporal and spatial coupling characteristics. This new method is capable of adapting to time-varying and fluctuating power from green resources and ECs while making real-time decisions regarding BESS charging/discharging operations. Experimental results obtained under realistic renewable energy generators and ECs settings demonstrate that our approach can significantly cut down the ECO’s energy cost (by up to 66%).
Förderung
- National Natural Science Foundation of China
- NSFC
- Taishan Scholars Program
Zitieren
APA
Zheng, D., Zhao, L., Liu, L., Tang, G., Min, G., & Guo, D. (2026). BESS-Aided Power Demand Reshaping for Distributed Green Edge Clouds. IEEE Transactions on Mobile Computing, 25(12), 23996-24012. https://doi.org/10.1109/tmc.2026.3731141
Vancouver
Zheng D, Zhao L, Liu L, Tang G, Min G, Guo D. BESS-Aided Power Demand Reshaping for Distributed Green Edge Clouds. IEEE Transactions on Mobile Computing. 2026;25(12):23996-24012. doi:10.1109/tmc.2026.3731141
BibTeX
@article{Zheng2026,
author = {Zheng, Dongyu and Zhao, Lu and Liu, Lei and Tang, Guoming and Min, Geyong and Guo, Deke},
title = {BESS-Aided Power Demand Reshaping for Distributed Green Edge Clouds},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {12},
pages = {23996--24012},
doi = {10.1109/tmc.2026.3731141}
}
EUVIMED