arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.02412cs.NIcs.LG
收藏

面向AI的切片:支持AI服务的网络切片在线学习框架

Slicing for AI: An Online Learning Framework for Network Slicing Supporting AI Services

College of Engineering, Qatar University(卡塔尔大学工程学院);College of Electrical Engineering, Mathematics, and Computer Science, TU Delft(代尔夫特理工大学电气工程、数学与计算机科学学院)

Menna Helmy, Alaa Awad Abdellatif, Naram Mhaisen, Amr Mohamed, Aiman Erbad

AI总结:

本文针对6G网络中AI服务的网络切片问题,提出在线学习框架优化资源分配,平衡准确性、延迟和成本等KPI,通过减少决策空间加速学习,实验证明能高效收敛到最优决策。

摘要:

即将到来的6G网络将拥抱一个由AI驱动服务的新领域,这需要创新的网络切片策略,即面向AI的切片,涉及创建定制化的网络切片以满足多样化AI服务的服务质量(QoS)需求。由于用户行为和移动网络的时变动态特性,这带来了挑战。因此,本文提出了一种在线学习框架,以优化AI服务的计算和通信资源分配,同时考虑其独特的关键性能指标(KPI),如准确性、延迟和成本。我们定义了一个在平衡冲突KPI的同时优化总准确性的问题,证明了其NP难度,并提出了一种在线学习框架以在动态环境中解决该问题。我们提出了一种基础在线解决方案和两种变体,采用预学习消除方法来减少决策空间以加速学习。此外,我们通过结合先验知识提出了一种有偏的决策空间子集选择方法,以在不牺牲性能的情况下提高学习速度,并提出了处理所选子集的两种替代方案。我们的结果展示了所提解决方案在收敛到最优决策方面的效率,同时减少了决策空间并提高了时间复杂度。

英文摘要:

The forthcoming 6G networks will embrace a new realm of AI-driven services that requires innovative network slicing strategies, namely slicing for AI, which involves the creation of customized network slices to meet Quality of service (QoS) requirements of diverse AI services. This poses challenges due to time-varying dynamics of users' behavior and mobile networks. Thus, this paper proposes an online learning framework to optimize the allocation of computational and communication resources to AI services, while considering their unique key performance indicators (KPIs), such as accuracy, latency, and cost. We define a problem of optimizing the total accuracy while balancing conflicting KPIs, prove its NP-hardness, and propose an online learning framework for solving it in dynamic environments. We present a basic online solution and two variations employing a pre-learning elimination method for reducing the decision space to expedite the learning. Furthermore, we propose a biased decision space subset selection by incorporating prior knowledge to enhance the learning speed without compromising performance and present two alternatives of handling the selected subset. Our results depict the efficiency of the proposed solutions in converging to the optimal decisions, while reducing decision space and improving time complexity.

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。

↑