A Scalable Cloud-Sensor Architecture for the Internet of Things

Опубликовано 27 июня 2016, 21:48

Recent advances in IoT and pervasive and ubiquitous computing provide a glimpse into our future and reveal exciting visions of many "smart" things: smart cities, smart homes, smart cars, all in addition to smart spaces such as malls, workplaces, hotels, schools, and much more. Driven by a technological revolution offering "low-power many things and wireless almost everything", we could, in only a decade, envision and prototype impressive smart space systems that improve quality of life, enhance awareness of resources and the environment, and enrich users' experience. But prototyping is one thing; actual large-scale deployments are another. The massive scale of sensors and devices that will be deployed in highly populated smart cities of the future will be mind-boggling. Without an ecosystem and a scalable architecture in place, it will be difficult to manage or program such an expanding and massive IoT. In this talk, I will begin by raising the point about how we can estimate the Value of the IoT as we once estimated the value of the network. I will then introduce the Cloud-Edge-Beneath (CEB) architecture and present its salient scalability features. I will also discuss CEB's bi-directional waterfall optimization framework and show how it leads to "sentience-efficiency" - a new paradigm for realizing aggressive energy-efficiency. I will then present an event-driven programming model based on CEB and show how this model and CEB when combined foster a much-needed IoT programmability ecosystem. Finally, I will present a validation study demonstrating CEB's scaling behavior in face of IoT expansions (sensors and applications) and under dynamically increasing loads.