Spatio-temporal fragmentation-aware time-varying service provisioning in computing power networks based on model-assisted reinforcement learning
Journal of Optical Communications and Networking · 01.11.2023 · 15 (11) · 788
DOI: 10.1364/jocn.498951 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Optical Communications and Networking, online erschienen am 03.10.2023. Verfasst von Huangxu Ma und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: National Natural Science Foundation of China, State Key Laboratory of Information Photonics and Optical Communications, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Widespread application of AI with high computing requirements has promoted the rapid development of cloud and edge computing. Ubiquitous computing resources need to be interconnected through high-performance IP and optical networks. Computing power networks (CPNs) have been studied as an IP/optical cross-layer architecture to provide on-demand computing services. The service provisioning in CPNs can be modeled as a virtual optical network embedding problem; however, the time-varying characteristics of service requirements increase the complexity. In particular, there can be stranded computing or bandwidth resources that are isolated in the spatio-temporal dimension and therefore difficult for other requests to utilize. This phenomenon is referred to as spatio-temporal resource fragmentation, which will lead to inefficient use of resources and higher energy consumption. To meet the time-varying requirements and achieve an energy-efficient CPN, in this paper, we first analyze the main reason for spatio-temporal resource fragmentation and excess energy consumption in cross-layer CPNs, which is the mismatched embedding scheme and the inappropriate scheduling order. Therefore, an auxiliary-graph-model-assisted edge-featured graph-attention-network-enabled DRL algorithm, DeepDefrag, is studied to solve the problem. Its core highlight is co-optimizing the scheduling and embedding of time-varying virtual networks along with the awareness of resource fragmentation. In addition, an integer linear programming algorithm is developed to determine the performance bounds. We validate DeepDefrag through a series of ablation studies and comparison algorithms under different numbers of requests. The results show that DeepDefrag can achieve >26.4% lower energy consumption for CPNs compared with the DRL-based baseline. Moreover, it is shown to generalize well across requests and networks.
Förderung
- National Natural Science Foundation of China
- State Key Laboratory of Information Photonics and Optical Communications
- Fundamental Research Funds for the Central Universities
- BUPT Excellent Ph.D. Students Foundation
- BUPT Innovation and Entrepreneurship Support Programs
- Xiaomi Young Talents Program
- Science Foundation Ireland
Zitieren
APA
Ma, H., Zhang, J., Gu, Z., Kilper, D. C., & Ji, Y. (2023). Spatio-temporal fragmentation-aware time-varying service provisioning in computing power networks based on model-assisted reinforcement learning. Journal of Optical Communications and Networking, 15(11), 788. https://doi.org/10.1364/jocn.498951
Vancouver
Ma H, Zhang J, Gu Z, Kilper DC, Ji Y. Spatio-temporal fragmentation-aware time-varying service provisioning in computing power networks based on model-assisted reinforcement learning. Journal of Optical Communications and Networking. 2023;15(11):788. doi:10.1364/jocn.498951
BibTeX
@article{Ma2023,
author = {Ma, Huangxu and Zhang, Jiawei and Gu, Zhiqun and Kilper, Daniel C. and Ji, Yuefeng},
title = {Spatio-temporal fragmentation-aware time-varying service provisioning in computing power networks based on model-assisted reinforcement learning},
journal = {Journal of Optical Communications and Networking},
year = {2023},
volume = {15},
number = {11},
pages = {788},
doi = {10.1364/jocn.498951}
}
EUVIMED