Hello and welcome to the Intel Telco Cloud Academy. The purpose of this course is to introduce you to edge computing, explain what is driving the adoption of edge computing, discuss the demands edge computing places on computing platforms and finally show how Intel is delivering on those demands. At the end of this course, you will be ready for additional training that discusses the various Intel Smart Edge offerings in greater detail. In this session, we will begin by defining the Edge, discussing what is unique about the Intel Smart Edge offering. And finally, introduced the development of applications that run within a Smart Edge environment. By the end of this course, you should be able to define the Edge. You should also be able to determine why the Edges needed. And finally, you should be able to explain what makes Edge Computing an innovative model. Let's start by defining the Edge. Over the last 10 years, we've seen the emergence of the internet of things, where hundreds of millions, if not billions of devices ranging from cameras to sensors to refrigerators and robots are connected to the internet. This has led to an explosion of data being fed back into software applications typically hosted in cloud data centers, as businesses have moved more and more of their computing infrastructure there. That in turn has created a tremendous demand for network bandwidth and resulted in traffic bottlenecks. Even as Telecom companies have responded with improved infrastructure with 5G being a key piece. The laws of physics still limit the speed with which applications residing in data centers sometimes hundreds of miles away from the devices feeding the data can respond and act. This has led to the demand for more computing close to where the data is being generated, to what is now known as the Edge. Whether at branch offices of large enterprises, at factory locations, at retail stores or warehouses, or even in metropolitan areas. Computing at the edge is expected to deliver response times less than 10 milliseconds, a key requirement for many activities like security, industrial automation, traffic monitoring, telehealth, and immersive visual experiences. Data from and to Edge devices passed through many layers of Telecom infrastructure, each providing more bandwidth and reduced latency as you get closer to the Edge. First, there's the core network, then the regional data center, or a little further out the network Edge at the Telecom access points like the cell towers. Finally, the on premise computing resources that are closest to the end devices. This demand for Edge computing is estimated to be a $29 billion in market by 2025. More significantly the majority of the data handling by then is expected to happen outside the central data centers, where many applications reside today. To meet this growing demand at the Edge we're seeing new technologies come into play. Software needs to be re-architected to be cloud-native so it can be rapidly deployed to and managed at thousands of locations. New 5G networks that can handle the competing demands of multiple tenants or workloads and AI and machine learning models to efficiently route traffic between devices and within Edge nodes to deliver on the required quality of service. The vision is that all these technological advancements will lead to an Edge computing infrastructure that is near real-time and reliable in its response with capacity scaled up or down on demand available across geographies to support emerging use cases while being ecologically conscious and energy efficient. In other words, an Edge computing infrastructure that lowers the computing cost while providing added flexibility. So, what kind of applications have demanded the high bandwidth and low latency to bring more computing resources to the Edge? Security systems which rely heavily on video processing, monitoring, and controls of vehicles to manage traffic, factory automation including but not limited to automated mobile robots, and smart cities are just a few examples among many more. Alongside the growing demand for computing at Edge locations close to the devices that originate the data, there are technology inflections driving how that is implemented. Edge locations tend to be space and power-constrained, needing hyperconverged platforms that have computing networking and IO combined into small form factors. The Edge platforms also need to be deterministic with response times within set limits to support real-time applications like video streaming. The resources need to be scalable on demand, scaling down when demand is low to conserve power and scaling up when demand peaks. As these locations will number in the thousands, often deployed at remote locations, they need to be energy efficient and need to be managed at scale with hundreds and thousands of nodes across multiple countries. In short, Edge platform needs are very different from what are needed in the cloud, they need to be Edge native. As Edge services continue to gain momentum, businesses need a more efficient development approach to abstract complexity, simplified development, and deployment of infrastructure and apps for the Edge while reducing costs. Intel has been in the business of lowering computing costs for decades, from the advent of microprocessors through the standard off the shelf, X 86 servers that have powered corporate data centers and now the public cloud infrastructure. We've partnered with hundreds of companies in the ecosystem to supply all the vital components, the communication devices, the hardware platforms, the software infrastructure, the applications, and now bring that experience to bear in creating the Intel Smart Edge environment. Once this share, distributed compute infrastructure exists, a common containerized software framework can be deployed across the infrastructure from the Cloud to the Edge. Where workloads can be placed anywhere along the distributed compute infrastructure, wherever they are most efficiently run and the tools needed to develop, test, and quickly deploy applications will be common and integrated. In summary, the Edge has evolved to offer a distributed compute Edge platform as a service offering that appeals to developers and their customers by enabling the tools and infrastructure for them to rapidly build, test, and deploy applications at global scale, without having to build out their own dedicated infrastructure to do so. Now, that you have learned more about edge computing, watch the next video to learn more about Intel Smart Edge. [MUSIC]
