• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议> >An Incentive Mechanism Design for Efficient Edge Learning by Deep Reinforcement Learning Approach
【24h】

An Incentive Mechanism Design for Efficient Edge Learning by Deep Reinforcement Learning Approach

机译：通过深度强化学习方法进行高效边缘学习的激励机制设计

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Emerging technologies and applications have generated large amounts of data at the network edge. Due to bandwidth, storage, and privacy concerns, it is often impractical to move the collected data to the cloud. With the rapid development of edge computing and distributed machine learning (ML), edge-based ML called federated learning has emerged to overcome the shortcomings of cloud-based ML. Existing works mainly focus on designing efficient learning algorithms, few works focus on designing the incentive mechanisms with heterogeneous edge nodes (EN) and uncertainty of network bandwidth. The incentive mechanisms affect various tradeoffs: (i) between computation and communication latency, and thus (ii) between the edge learning time and payment consumption. We fill this gap by designing an incentive mechanism that captures the tradeoff between latency and payment. Due to the network dynamics and privacy protection, we propose a deep reinforcement learning-based (DRL-based) solution that can automatically learn the best pricing strategy. To the best of our knowledge, this is the first work that applies the advances of DRL to design the incentive mechanism for edge learning. We evaluate the performance of the incentive mechanism using trace-driven experiments. The results demonstrate the superiority of our proposed approach as compared with the baselines.
机译：新兴技术和应用程序已经在网络边缘生成了大量数据。由于带宽，存储和隐私问题，将收集的数据移动到云中通常是不切实际的。随着边缘计算和分布式机器学习（ML）的快速发展，克服了基于云的ML的缺点，出现了称为联合学习的基于边缘的ML。现有工作主要集中在设计高效的学习算法上，很少工作集中在设计具有异构边缘节点（EN）和网络带宽不确定性的激励机制。激励机制影响各种折衷：（i）在计算和通信等待时间之间，因此（ii）在边缘学习时间和支付消耗之间。我们通过设计一种激励机制来弥补这一差距，该机制捕获了延迟和支付之间的折衷。由于网络的动态变化和隐私保护，我们提出了一种基于深度强化学习（基于DRL）的解决方案，该解决方案可以自动学习最佳定价策略。据我们所知，这是第一项利用DRL的先进技术设计边缘学习激励机制的工作。我们使用跟踪驱动的实验评估激励机制的性能。结果表明，与基线相比，我们提出的方法具有优越性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号