arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02495cs.NIcs.LG
收藏

非平稳条件下基于DRL的切片布局

DRL-based Slice Placement Under Non-Stationary Conditions

Orange Labs(Orange实验室);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所)

Jose Jurandir Alves Esteves, Amina Boubendir, Fabrice Guillemin, Pierre Sens

摘要:

我们考虑在线学习的最佳网络切片放置的假设下,切片请求到达根据非平稳泊松过程。我们提出了一个基于深度强化学习(DRL)的框架,结合启发式算法设计。我们专门设计了两个纯DRL算法和两个家庭的混合DRL启发式算法。为了验证它们的性能,我们在大规模运营商基础设施的背景下进行了大量的模拟。评价结果表明,所提出的混合DRL启发式算法需要三个数量级的学习情节比纯DRL实现收敛。这一结果表明,所提出的混合DRL启发式方法是更可靠的比纯DRL在一个真正的非平稳网络场景。

英文摘要:

We consider online learning for optimal network slice placement under the assumption that slice requests arrive according to a non-stationary Poisson process. We propose a framework based on Deep Reinforcement Learning (DRL) combined with a heuristic to design algorithms. We specifically design two pure-DRL algorithms and two families of hybrid DRL-heuristic algorithms. To validate their performance, we perform extensive simulations in the context of a large-scale operator infrastructure. The evaluation results show that the proposed hybrid DRL-heuristic algorithms require three orders of magnitude of learning episodes less than pure-DRL to achieve convergence. This result indicates that the proposed hybrid DRL-heuristic approach is more reliable than pure-DRL in a real non-stationary network scenario.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑