Ever since the first automation provided by the introduction of the Strowger telephone exchange in the late 19th century, networks have been increasingly automated. Fast forward to 2022, and the challenge facing network providers is scaling up this level of automation considering massive increases in complexity, new levels of agility to operate services, and rising demand from customers within the modern telecommunications ecosystem. This article describes a significant new industry-academia partnership to address these challenges: Next Generation Converged Digital Infrastructure (NG-CDI) is creating a vision for the building and operation of a future-proof network infrastructure and its autonomic management. In this article, we highlight three exemplar activities within the NG-CDI research program that illustrate the benefits of taking a highly collaborative interdisciplinary approach and show how academia and industry working closely together have delivered a range of direct and positive impacts on business.

Collection and analysis of distributed (cloud) computing workloads allows for a deeper understanding of user and system behavior and is necessary for efficient operation of infrastructures and applications. The availability of such workload data is however often limited as most cloud infrastructures are commercially operated and monitoring data is considered proprietary or falls under GPDR regulations. This work investigates the generation of synthetic workloads using Generative Adversarial Networks and addresses a current need for more data and better tools for workload generation. Resource utilization measurements such as the utilization rates of Content Delivery Network (CDN) caches are generated and a comparative evaluation pipeline using descriptive statistics and time-series analysis is developed to assess the statistical similarity of generated and measured workloads. We use CDN data open sourced by us in a data generation pipeline as well as back-end ISP workload data to demonstrate the multivariate synthesis capability of our approach. The work contributes a generation method for multivariate time series workload generation that can provide arbitrary amounts of statistically similar data sets based on small subsets of real data. The presented technique shows promising results, in particular for heterogeneous workloads not too irregular in temporal behavior.

This article argues that low latency, high bandwidth, device proliferation, sustainable digital infrastructure, and data privacy and sovereignty continue to motivate the need for edge computing research even though its initial concepts were formulated more than a decade ago.

This chapter presents four case studies each illustrating an implementation of one or more RECAP subsystems. The first case study illustrates how RECAP can be used for infrastructure optimisation for a 5G network use case. The second case study explores application optimisation for virtual content distribution networks (vCDN) on a large Tier 1 network operator. The third case study looks at how RECAP components can be embedded in an IoT platform to reduce costs and increase quality of service. The final case study presents how data analytics and simulation components, within RECAP, can be used by a small-to-medium-sized enterprise (SME) for cloud capacity planning.

Partitioning and distributing deep neural networks (DNNs) across end-devices, edge resources and the cloud has a potential twofold advantage: preserving privacy of the input data, and reducing the ingress bandwidth demand beyond the edge. However, for a given DNN, identifying the optimal partition configuration for distributing the DNN that maximizes performance is a significant challenge. This is because the combination of potential target hardware resources that maximizes performance and the sequence of layers of the DNN that should be distributed across the target resources needs to be determined, while accounting for user-defined objectives/constraints for partitioning. This paper presents Scission, a tool for automated benchmarking of DNNs on a given set of target device, edge and cloud resources for determining optimal partitions that maximize DNN performance. The decision-making approach is context-aware by capitalizing on hardware capabilities of the target resources, their locality, the characteristics of DNN layers, and the network condition. Experimental studies are carried out on 18 DNNs. The decisions made by Scission cannot be manually made by a human given the complexity and the number of dimensions affecting the search space. The benchmarking overheads of Scission allow for responding to operational changes periodically rather than in real-time. Scission is available for public download 1 .

The objective of the work package "Data Collection, Visualization and Analysis" of RECAP is to provide the necessary tools for managing and refining the data needed for the rest of the work packages. This includes the collection as well as the generation of data. Within this work package, the task of Artificial Workload Generation is responsible for the generation of a collection of datasets with artificial workloads, that complement the real data traces collected from industrial partners. Moreover, because publicly available workload data is scarce we provide the data as public data sets. This document is a companion report to deliverable which is of type “dataset”. The aim of the report is to describe the collection of datasets that constitute D5.3 and the mathematical techniques (structural time series models, generative adversarial networks, and workload based on traffic propagation) by which one can artificially generate and/or augment such datasets. The datasets described include real data traces collected by industrial partners and artificial data traces generated by the use of statistical models and neural networks. Each published data set can be used by the scientific and industrial community as a starting point for the modelling and experimental validation of distributed edge and cloud applications, facilitating the repeatability of the results.

Communication service providers (CSPs) face competitive pressure to increase infrastructure utilization and reduce operational costs while at the same time maximize bandwidth and maintain quality of service for end users. Content Distribution Networks (CDNs) are widely used to achieve these goals by optimally distributing content to cache servers at the edge, access and core networks. More recently, virtualization and cloud computing are being used to deploy and utilize virtual Content Delivery Networks (vCDNs) to reduce costs and increase elasticity while avoiding performance, quality, reliability and availability limitations that characterize traditional CDNs. In order to study the effectiveness of virtual cache placements and optimal distribution over a real-world large-scale vCDN infrastructure, we model and simulate BT's network using a novel parallel simulation framework. Results show that virtual cache placement impacts on the number of accepted requests, resource consumption (compute and network), and end-user network latency. We also present a trade-off analysis between infrastructure provider utility and service customer utility to quantity the number and distribution of these virtual cache placements and to determine the optimal number of virtual cache servers that should be deployed.

The REliable CApacity Provisioning and enhanced remediation for distributed cloud applications (RECAP) project aims to advance cloud and edge computing technology, to develop mechanisms for reliable capacity provisioning, and to make application placement, infrastructure management, and capacity provisioning autonomous, predictable and optimized. This paper presents the RECAP vision for an integrated edge-cloud architecture, discusses the scientific foundation of the project, and outlines plans for toolsets for continuous data collection, application performance modeling, application and component auto-scaling and remediation, and deployment optimization. The paper also presents four use cases from complementing fields that will be used to showcase the advancements of RECAP.

One of the key goals of Network Functions Virtualization (NFV) is achieving energy efficiency through workload consolidation. A good example for maximizing energy savings is the Virtualization of Content Delivery Networks (vCDNs) NFV use case where the video streaming workloads exhibit significant difference between prime-time and non-prime-time usage of the infrastructure. This paper examines the practical challenges in maximizing energy efficiency for vCDN workloads. This paper proposes an open NFV architectural framework for conveying content virality information from Cloud applications such as YouTube, Twitter and mechanisms for leveraging it to maximize the energy efficiency for vCDN workloads. This paper also proposes a more general architecture for any Cloud/NFV application that may experience virality.

Due: Friday, July 24, 2015 (11:59pm EDT) Full Paper Due: Friday, July 31, 2015 (11:59pm EDT) Notification of Acceptance: Friday, November 20, 2015 (11:59pm EDT) IEEE COMSOC MMTC E-Letter http://www.comsoc.org/~mmc/ 49/55 Vol.10, No.4, July 2015 Call for Papers IEEE 83rd Vehicular Technology Conference (IEEE VTC2016-Spring) 15-18 May 2016, Nanjing, China www.vtc2016spring.org The 2016 IEEE 83rd Vehicular Technology Conference will be held in Nanjing, China, 15-18 May 2016. Over the past six decades, VTC has established itself as one of the premier conferences in the world on mobile communications and vehicular technology. As the first-ever VTC to be held in mainland China, VTC 2016-Spring will feature world-class technical sessions, workshops, and tutorials in, but not limited to, the following technical areas:

This article sets out the opportunity and the role of Ethernet within large-scale carrier networks. Carrier Ethernet can greatly reduce the consequences of the complexity associated with the large scale and broad scope of carriers' networks by being a cost-effective replacement for SONET/SDH. However, in order to achieve this, carrier Ethernet needs to provide the equivalent level of transparency, simplicity, and reliability currently achieved by SONET/SDH, and the emerging IEEE Ethernet standards for PBB and PBB-TE are well suited to this role. These technologies are an ideal complement to IP/MPLS for which they can provide highly cost-effective managed and guaranteed bit pipes.