Edge computing has evolved to be a promising avenue to enhance system computing capability by offloading processing tasks from the cloud to edge devices. In this article, we propose a multi-layer edge computing framework called EdgeFlow. In this framework, different nodes ranging from edge devices to cloud data centers are categorized into corresponding layers and cooperate for data processing. EdgeFlow can deal with the trade-off between the computing and communication capabilities so that the tasks can be assigned to each layer optimally. At the same time, resources are carefully allocated throughout the whole network to mitigate performance fluctuation. The proposed open-source data flow processing framework is implemented on a platform that can emulate various computing nodes in multiple layers and corresponding network connections. Evaluated on the face recognition scenario, EdgeFlow can significantly reduce task finish time and perform more tolerance to run-time variations, compared with pure cloud computing, pure edge computing, and Cloudlet. Potential applications of EdgeFlow, including network function virtualization, Internet of Things, and vehicular networks, are also discussed at the end of this article.

中文翻译：

---

EdgeFlow：5G 及更高版本边缘计算中的开源多层数据流处理


边缘计算已发展成为通过将处理任务从云卸载到边缘设备来增强系统计算能力的有前途的途径。在本文中，我们提出了一种称为 EdgeFlow 的多层边缘计算框架。在该框架中，从边缘设备到云数据中心的不同节点被划分到相应的层并协作进行数据处理。 EdgeFlow可以处理计算能力和通信能力之间的权衡，从而将任务最优地分配到每一层。同时，在整个网络中仔细分配资源以减轻性能波动。所提出的开源数据流处理框架是在一个可以模拟多层各种计算节点和相应网络连接的平台上实现的。在人脸识别场景上进行评估，与纯云计算、纯边缘计算和Cloudlet相比，EdgeFlow可以显着减少任务完成时间，并且对运行时变化具有更强的容忍度。本文最后还讨论了 EdgeFlow 的潜在应用，包括网络功能虚拟化、物联网和车载网络。