Analyse or Transmit: Utilising Correlation at the Edge with Deep Reinforcement Learning
Analyse or Transmit: Utilising Correlation at the Edge with Deep Reinforcement Learning
复制标题
分析或传输：通过深度强化学习利用边缘相关性
DOI：
10.1109/globecom46510.2021.9685166
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
and I. Dusparic
中科院分区：
文献类型：
--
作者：
J. Hribar;R. Shinkuma;G. Iosifidis;and I. Dusparic
数以百万计的传感器、摄像头、仪表和其他边缘设备部署在网络中，以收集和分析数据。在许多情况下，此类设备仅由能量收集（EH）供电，并且可用于分析所获取数据的能量有限。当边缘基础设施可用时，设备可以选择：在本地执行分析或将任务卸载到其他资源丰富的设备（如Cloudlet服务器）。然而，这样的选择在消耗的能量和准确性方面是有代价的。一方面，与本地处理数据所需的能量相比，传输原始数据可能导致更高的能量成本。另一方面，在服务器上执行数据分析可以提高任务的准确性。此外，由于多个设备发送的信息之间的相关性，如果一些边缘设备决定既不处理也不发送数据并保留能量，则准确性可能不会受到影响。对于这种情况，我们提出了一种基于深度强化学习（DRL）的解决方案，能够学习和调整策略，以适应EH模式引起的时变能量到达。我们利用两个数据集，一个用于对EH设备可以收集的能量进行建模，另一个用于对相机之间的相关性进行建模。此外，我们将建议的解决方案的性能进行比较，三个基线政策。我们的研究结果表明，与传统方法相比，我们可以将准确性提高15%，同时防止中断。
Millions of sensors, cameras, meters, and other edge devices are deployed in networks to collect and analyse data. In many cases, such devices are powered only by Energy Harvesting (EH) and have limited energy available to analyse acquired data. When edge infrastructure is available, a device has a choice: to perform analysis locally or offload the task to other resource-rich devices such as cloudlet servers. However, such a choice carries a price in terms of consumed energy and accuracy. On the one hand, transmitting raw data can result in a higher energy cost in comparison to the required energy to process data locally. On the other hand, performing data analytics on servers can improve the task's accuracy. Additionally, due to the correlation between information sent by multiple devices, accuracy might not be affected if some edge devices decide to neither process nor send data and preserve energy instead. For such a scenario, we propose a Deep Reinforcement Learning (DRL) based solution capable of learning and adapting the policy to the time-varying energy arrival due to EH patterns. We leverage two datasets, one to model energy an EH device can collect and the other to model the correlation between cameras. Furthermore, we compare the proposed solution performance to three baseline policies. Our results show that we can increase accuracy by 15% in comparison to conventional approaches while preventing outages.