September 10, 2015

The Future of the Cloud

  • Clougherty M.
  • Hilt V.

Whether one considers the start of the current cloud era as the 1999 debut of or the introduction of Amazon Web Services in 2006, there is little doubt that cloud computing has had a profound impact on our lives over a span of only 10 to 15 years. No longer is it necessary for companies to install complex and expensive equipment with dedicated network connectivity in order to serve their customers cloud computing allows services and content to be offered globally and accessed by anyone with access to the Internet. Furthermore, with the availability of pay as you go cloud infrastructure services like AWS, the barriers to market entry for new services are effectively eliminated; a handful of talented software developers are now able to build service offerings capable of serving millions of users without huge upfront investment in computing infrastructure. As a result, an entirely new cloud-based economy has emerged. This first cloud era was built as a regionally centralized cloud, with applications running in a handful of massive warehouse scale data centers within key geographic regions North and South America, Europe, Middle East and Africa, and Asia Pacific. While this centralization had the benefit of economies of scale, it was ill-suited to support services that require performance guarantees in terms of latency or bandwidth considerations, as distance and number of network hops generally impairs the ability to offer such control or assurances. Furthermore, geo-political security issues challenge the centralized cloud approach, as governments and enterprises require that their data remains within or avoids certain political boundaries. As a result, we believe that we are on the cusp of the emergence of a new type of cloud that addresses the needs of the everything digital era by providing local delivery of these services while maintaining the critical aspect of global reach by interconnecting and federating local cloud resources with the centralized cloud infrastructure to form a new global-local cloud continuum. This trend is already well underway in the area of content delivery. Over the last decade, the dramatic increase in the delivery of high quality video content via the Internet outpaced the ability of the Internet to economically meet the associated bandwidth demands. As a result, global Content Delivery Networks CDNs have been created that effectively allow content providers to bypass the Internet backbone by delivering content from a network of geographically distributed caches that are proximal to users and thereby optimize delivery. As we move into the age of near real time digital automation, in which applications and services increasingly require low latency and/or high performance interactivity with humans and devices, functionality will need to be placed as close to the end users or devices as economically possible. This necessitates the creation of a highly distributed cloud infrastructure with edge clouds based on new cloud technology optimized for high performance and dynamic operation. Intelligent algorithms will determine optimal placement of applications within this distributed infrastructure based on knowledge of the needs of the services, availability of appropriate resources, and the location of users and devices. This is by no means a static system, however. Applications and services will continuously adapt to changing user needs, shifting usage patterns including rapid and extreme changes in popularity, the mobility of end users and devices, changing network conditions, and these applications will be constantly updated with new functionalities. This dynamicity in applications, services and demand will require the new global-local cloud to be a learning, automated, and self-optimizing computing and processing digital fabric for the new era.

Recent Publications

August 09, 2017

A Cloud Native Approach to 5G Network Slicing

  • Francini A.
  • Miller R.
  • Sharma S.

5G networks will have to support a set of very diverse and often extreme requirements. Network slicing offers an effective way to unlock the full potential of 5G networks and meet those requirements on a shared network infrastructure. This paper presents a cloud native approach to network slicing. The cloud ...

August 01, 2017

Modeling and simulation of RSOA with a dual-electrode configuration

  • De Valicourt G.
  • Liu Z.
  • Violas M.
  • Wang H.
  • Wu Q.

Based on the physical model of a bulk reflective semiconductor optical amplifier (RSOA) used as a modulator in radio over fiber (RoF) links, the distributions of carrier density, signal photon density, and amplified spontaneous emission photon density are demonstrated. One of limits in the use of RSOA is the lower ...

July 12, 2017

PrivApprox: Privacy-Preserving Stream Analytics

  • Chen R.
  • Christof Fetzer
  • Le D.
  • Martin Beck
  • Pramod Bhatotia
  • Thorsten Strufe

How to preserve users' privacy while supporting high-utility analytics for low-latency stream processing? To answer this question: we describe the design, implementation and evaluation of PRIVAPPROX, a data analytics system for privacy-preserving stream processing. PRIVAPPROX provides three properties: (i) Privacy: zero-knowledge privacy (ezk) guarantees for users, a privacy bound tighter ...