arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01025cs.NIcs.LGcs.SYeess.SY
收藏

用于移动边缘计算中节点过载保护的结构感知强化学习

Structure-aware reinforcement learning for node-overload protection in mobile edge computing

McGill University(麦吉尔大学);Montreal Institute of Learning Algorithms(蒙特利尔学习算法研究所);Ericsson(爱立信)

Anirudha Jitani, Aditya Mahajan, Zhongwen Zhu, Hatem Abou-zeid, Emmanuel T. Fapi, Hakimeh Purmehdi

摘要:

移动边缘计算(MEC)是指将计算能力和应用程序置于网络边缘的概念,提供诸如减少处理客户端请求的延迟,减少网络拥塞和提高应用程序性能等好处。当集群中的一个或多个边缘服务器过载时,MEC的性能和可靠性会显著下降。特别是当服务器由于过载而崩溃时,它会导致MEC中的服务失败。在这项工作中,自适应接纳控制策略,以防止边缘节点过载。这种方法是基于最近提出的低复杂度的RL(强化学习)算法称为SALMUT(结构感知学习多个队列),它利用了结构的最佳准入控制策略在多类队列的平均成本设置。我们扩展的框架工作在折扣成本设置的节点过载保护问题。使用模拟两种不同设置-计算机模拟和Docker测试床中的真实部署的几种场景来验证所提出的解决方案。我们的经验评估表明,SALMUT产生的总折扣成本类似于最先进的深度RL算法,如PPO(近端策略优化)和A2 C(优势演员评论),但需要一个数量级更少的时间来训练,输出易于解释的策略,并可以在线方式部署。

英文摘要:

Mobile Edge Computing (MEC) refers to the concept of placing computational capability and applications at the edge of the network, providing benefits such as reduced latency in handling client requests, reduced network congestion, and improved performance of applications. The performance and reliability of MEC are degraded significantly when one or several edge servers in the cluster are overloaded. Especially when a server crashes due to the overload, it causes service failures in MEC. In this work, an adaptive admission control policy to prevent edge node from getting overloaded is presented. This approach is based on a recently-proposed low complexity RL (Reinforcement Learning) algorithm called SALMUT (Structure-Aware Learning for Multiple Thresholds), which exploits the structure of the optimal admission control policy in multi-class queues for an average-cost setting. We extend the framework to work for node overload-protection problem in a discounted-cost setting. The proposed solution is validated using several scenarios mimicking real-world deployments in two different settings - computer simulations and a docker testbed. Our empirical evaluations show that the total discounted cost incurred by SALMUT is similar to state-of-the-art deep RL algorithms such as PPO (Proximal Policy Optimization) and A2C (Advantage Actor Critic) but requires an order of magnitude less time to train, outputs easily interpretable policy, and can be deployed in an online manner.

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。

↑