Tutorial: Combining Edge and Cloud for Smart Cities Applications

Abstract

Cloud computing traditionally serves IoT applications by providing storage for generated data, and CPU power to produce value for their businesses. However, the growth of IoT is affecting the way traditional cloud architectures work. The increased amount of data to be transferred is creating bottlenecks while increasing the latency. Furthermore, sending such a big amount of data to a cloud environment in very short periods of time is inefficient, apart from cumbersome and expensive. This implies that much of this data must be aggregated at the “end points” where data is collected. And here is where Edge computing comes in. Edge Computing is not devised as a competitor to cloud; it is envisioned as the perfect ally for a broad spectrum of applications for which traditional Cloud Computing is not sufficient. Combining the edge approach with IoT sensors and Cloud would add flexibility and choices for customers. This tutorial will answer these questions:1.What problems does edge computing solve?2.How can we take advantage of the edge computing?3.How does edge computing and cloud computing work together?It will also present current technologies for designing hybrid platforms (edge, cloud) for IoT applications. The tutorial will also present a generic platform for intelligent IoT applications based on a shareable backbone infrastructure composed of three layers: IoT objects, edge devices and cloud infrastructure. Our framework:•delivers machine learning models (MLM) learned in the cloud over data streams collected by the edge, from IoT devices.•supports lightweight learning algorithms that can execute on the edge and self-adapt without any synchronisation with the cloud.The platform delivers the following functionalities:1.Coordinate application deployment from the cloud to the edge. The platform will target cloud, edge and IoT devices. IoT applications can be deployed, configured, operated and maintained, using a shared infrastructure, where several applications can coexist.2.Continuously integrate, deploy and maintain MLMs on edge devices. Learning, which requires considerably more resources, will take place in the cloud and the learned models will be deployed at the edge. This will considerably decrease the response time and the necessary bandwidth between the cloud and edge layer, since real-time data processing will take place close to the IoT devices. With this functionality, the edge triggers the learning process, although it is performed in the cloud.3.Use lightweight, yet powerful, machine learning models that can be setup by, and deployed on, resource constrained devices that are typically used by edge devices. This alternative is possible for some IoT applications for which the learning process is light enough to run on the edge. With this functionality, the edge is more autonomous, its intelligence is “improved” locally.