By Charlie Ashton
Wind River just published a new white paper titled “Distributed Edge Clouds Are Complex, But Must They Be Difficult?” (spoiler alert: the answer is No). If you’re involved with the planning of edge-hosted applications in telecom networks, you should consider this paper as required reading because it explains one of the most important challenges in this area and introduces a readily-available solution.
The plethora of recent industry conferences focused on edge computing topics highlights the interest from Communications Service Providers (CSPs) in new applications and services hosted at the edge of the network rather than in traditional cloud data centers. While some of these services, like cloud RAN or virtual RAN, are primarily intended to reduce operational costs, many promise improved top-line revenue because they’re all about delivering new kinds of services to new categories of customers.
Use cases as diverse as mobile HD video streaming, intelligent surveillance, immersive Augmented Reality (AR), smart stadia, industrial IoT and assisted driving represent new customers, new revenue streams and a chance to reverse the steady decline in Average Revenue per User (ARPU) that has afflicted the telecom industry for the past few years.
Distributed edge clouds provide cloud services (compute, storage and networking) close to the end-user device with integral system-wide management capabilities. The objective of distributing cloud services to the network edge is to reduce both latency and bandwidth requirements in access and backhaul networks. This not only improves application performance and network efficiency, but also supports the emerging set of new services.
With edge clouds scalable from small single-server solutions to large multi-server solutions, replicated hundreds or thousands of times and spread out over a wide area, the biggest challenge is manageability. CSPs need to efficiently manage thousands of distributed edge clouds over diverse network conditions in order to keep their operational costs under control while they reap the benefit of new revenue streams. Distributed edge clouds won’t be economically viable if their management is so complex that it results in soaring operational costs.
The new Wind River white paper outlines these management challenges in detail and explains how they are addressed by the OpenStack Foundation’s StarlingX project, which is based on seed code from the Wind River Titanium Cloud critical infrastructure platform. Going forward, Titanium Cloud will continue to deliver productized and commercially supported implementations of StarlingX, ensuring that CSPs can deploy cost-effective distributed edge cloud without any of the risks associated with proprietary solutions or vendor lock-in.
At Wind River, we’re delighted to be contributing to the realization of the distributed edge cloud concept which will unlock new business opportunities for innovative CSPs worldwide. If you’d like to know more about Titanium Cloud, please browse the information available online or contact Wind River to arrange a face-to-face discussion.