Edge Infrastructure Research Articles

An eigenvalue‐based edge infrastructure for cloud‐based CDN

SummaryIn today's dynamic video landscape, an end user needs services to be delivered to any devices anytime with less delay over the Internet. Now users' expectation has changed; they want faster time‐to‐market, cost reduction, and the ability to adjust according to the evolving requirements, which are a limit for the traditional server‐based approach. The explosive growth of the internet multimedia application needs a new approach to content delivery to overcome the limitations of server‐based techniques. Cloud‐based content delivery networks (CCDNs) have recently started to emerge where contents are cached from the cloud storage and delivered through the distribution service to meet quality of services (QoS) of requested services. In this paper, we dealt with CCDN deployment problem and proposed a new eigenvalue‐based edge infrastructure for a network service provider to serve the users with a variation on proximity interest concerning operational cost and user QoS satisfaction. The edge infrastructure designing is a two‐step process: (a) ideal location search for placing edge server and (b) edge server placement and capacity provisioning. The performance of the proposed approach is appraised via modeling and simulation. Performance evaluation outcomes are exhibited to manifest the effectiveness and competitiveness of our approach when compared with existing algorithms.

A Mobility-Aware Vehicular Caching Scheme in Content Centric Networks: Model and Optimization

Edge caching is being explored as a promising technology to alleviate the network burden of cellular networks by separating the computing functionalities away from cellular base stations. However, the service capability of existing caching scheme is limited by fixed edge infrastructure when facing the uncertainties of users' requests and locations. The vehicular caching, which uses the moving vehicles as cache carriers, is regard as an efficient method to solve the problem above. This paper studies the effectiveness of vehicular caching scheme in content centric networks by developing optimization model towards the minimization of network energy consumption. Particularly, we model the interactions between caching vehicles and mobile users as a 2-D Markov process, in order to characterize the network availability of mobile users. Based on the developed model, we propose an online vehicular caching design by optimizing network energy efficiency. Specifically, the problem of caching decision making is firstly formulated as a fractional optimization model, towards the optimal energy efficiency. Using nonlinear fractional programming technology and Lyapunov optimization theory, we derive the theoretical solution for the optimization model. An online caching algorithm to enable the optimal vehicular caching is developed based on the solution. Finally, extensive simulations are conducted to examine the performance of our proposal. By comparison, our online caching scheme outperforms the existing scheme in terms of energy efficiency, hit ratio, cache utilization, and system gain.

SELFNET 5G mobile edge computing infrastructure: Design and prototyping

SummaryThis paper presents the design and prototype implementation of the SELFNET fifth‐generation (5G) mobile edge infrastructure. In line with the current and emerging 5G architectural principles, visions, and standards, the proposed infrastructure is established primarily based on a mobile edge computing paradigm. It leverages cloud computing, software‐defined networking, and network function virtualization as core enabling technologies. Several technical solutions and options have been analyzed. As a result, a novel portable 5G infrastructure testbed has been prototyped to enable the preliminary testing of the integrated key technologies and to provide a realistic execution platform for further investigating and evaluating software‐defined networking– and network function virtualization–based application scenarios in 5G networks.

Enabling Flexible Resource Allocation in Mobile Deep Learning Systems

Deep learning provides new opportunities for mobile applications to achieve higher performance than before. Rather, the deep learning implementation on mobile device today is largely demanding on expensive resource overheads, imposes a significant burden on the battery life and limited memory space. Existing methods either utilize cloud or edge infrastructure that require to upload user data, however, resulting in a risk of privacy leakage and large data transfers; or adopt compressed deep models, nevertheless, downgrading the algorithm accuracy. This paper provides DeepShark, a platform to enable mobile devices with the ability of flexible resource allocation in using commercial-off-the-shelf (COTS) deep learning systems. Compared to existing approaches, DeepShark seeks a balanced point between time and memory efficiency by user requirements, breaks down sophisticated deep model into code block stream and incrementally executes such blocks on system-on-chip (SoC). Thus, DeepShark requires significantly less memory space on mobile device and achieves the default accuracy. In addition, all referred user data of model processing is handled locally, thus to avoid unnecessary data transfer and network latency. DeepShark is now developed on two COTS deep learning systems, i.e., Caffe and TensorFlow. The experimental evaluations demonstrate its effectiveness in the aspects of memory space and energy cost.

Now's the time to think about what comes after 5G: We need to make sure the backbone of every network can support future demands for data - [Spectral Lines

5G technology, with its promises of self-driving vehicles and immersive virtual reality, will be a data-hungry generation of wireless communications. engineers have been so preoccupied with designing and building the low-latency networks for these emerging applications that they've neglected the rest of our vast, tangled telecom networks. The result is that there's now a growing gap between the capabilities of the fixed and mobile sides of these networks. • Think of the mobile side as the antennas and radio waves that deliver data to our devices. This is the side that has gotten a lot of attention in recent years with the advent of beamforming and millimeter waves. The fixed side is everything else—the cables, fibers, and switches that handle our long-distance communications. The United Nations' International Telecommunication Union (ITU), an agency that coordinates telecom infrastructure between countries, launched a focus group in August to address this emerging imbalance in wireless communications. • Right now, when people start deploying [5G], it's the mobile side, says Richard Li, the chief scientist of future networks at Huawei and the chairman of the ITU Network 2030 focus group. But the fixed network side is still 4G. They do not match. The upshot is that while the larger amounts of data heralded by 5G will zip through edge infrastructure without delay, once that same data reaches the less-advanced core infrastructure it could very well be throttled. • A big part of the problem is that the way data moves through our networks has been designed for efficiency on the mobile side. In the process, according to Li, our networks have become redundant and prone to clogging on the fixed side.

Deploying CPU-Intensive Applications on MEC in NFV Systems: The Immersive Video Use Case

Multi-access Edge Computing (MEC) will be a technology pillar of forthcoming 5G networks. Nonetheless, there is a great interest in also deploying MEC solutions in current 4G infrastructures. MEC enables data processing in proximity to end users. Thus, latency can be minimized, high data rates locally achieved, and real-time information about radio link status or consumer geographical position exploited to develop high-value services. To consolidate network elements and edge applications on the same virtualization infrastructure, network operators aim to combine MEC with Network Function Virtualization (NFV). However, MEC in NFV integration is not fully established yet: in fact, various architectural issues are currently open, even at standardization level. This paper describes a novel MEC in an NFV system which successfully combines, at management level, MEC functional blocks with an NFV Orchestrator, and can neutrally support any “over the top” Mobile Edge application with minimal integration effort. A specific ME app combined with an end-user app for the provision of immersive video services is presented. To provide low latency, CPU-intensive services to end users, the proposed architecture exploits High-Performance Computing resources embedded in the edge infrastructure. Experimental results showing the effectiveness of the proposed architecture are reported and discussed.

Opportunistic Edge Computing: Concepts, opportunities and research challenges

The growing need for low-latency access to computing resources has motivated the introduction of edge computing, where resources are strategically placed at the access networks. Unfortunately, edge computing infrastructures like fogs and cloudlets have limited scalability and may be prohibitively expensive to install given the vast edge of the Internet. In this paper, we present Opportunistic Edge Computing (OEC), a new computing paradigm that provides a framework to create scalable infrastructures at the edge using end-user contributed resources. One of the goals of OEC is to place resources where there is high demand for them by incentivizing people to share their resources. This paper defines the OEC paradigm and the involved stakeholders and puts forward a management framework to build, manage and monitor scalable edge infrastructures. It also highlights the key differences between the OEC computing models and the existing computing models and shed the light on early works on the topic. The paper also presents preliminary experimental results that highlight the benefits and the limitations of OEC compared to the regular cloud computing deployment and the Fog deployment. It finally summarizes key research directions pertaining to resource management in OEC environments.

Improving Efficiency of Edge Computing Infrastructures through Orchestration Models †

Edge computing is an effective paradigm for proximity in computation, but must inexorably face mobility issues and traffic fluctuations. While software orchestration may provide effective service handover between different edge infrastructures, seamless operation with negligible service disruption necessarily requires pre-provisioning and the need to leave some network functions idle for most of the time, which eventually results in large energy waste and poor efficiency. Existing consolidation algorithms are largely ineffective in these conditions because they lack context, i.e., the knowledge of which resources are effectively used and which ones are just provisioned for other purposes (i.e., redundancy, resilience, scaling, migration). Though the concept is rather straightforward, its feasibility in real environments must be demonstrated. Motivated by the lack of energy-efficiency mechanisms in cloud management software, we have developed a set of extensions to OpenStack for power management and Quality of Service, explicitly targeting the introduction of more context for applications. In this paper, we briefly describe the overall architecture and evaluate its efficiency and effectiveness. We analyze performance metrics and their relationship with power consumption, hence extending the analysis to specific aspects that cannot be investigated by software simulations. We also show how the usage of context information can greatly improve the effectiveness of workload consolidation in terms of energy saving.

Message Relaying and Collaboration Motivating for Mobile Crowdsensing Service: An Edge‐Assisted Approach

Group sensing is a kind of crowdsensing service where HD map producers motivate private cars in a local region to collect data from real world. Group sensing needs vehicles to communicate physically and drivers to collaborate strategically in a mobile or edge‐assisted environment. First, we consider collaboration module that motivates drivers to be participants; centralized and distributed motivating methods are discussed. Secondly, we consider communication module; two VANET‐based methods are proposed to achieve message relaying in edge infrastructure. To accomplish participants’ selection, three combinations of two modules are proposed and simulated based on a flexible framework. The results show that centralized selection could motivate collaboration at a low price but brings heavy communication overhead. Clustered selection requires more incentives and less communication overhead than centralized selection. Distributed selection is usually the first class choice because of its fine performances on both communicating and motivating.

Edge Provisioning with Flexible Server Placement

We present $\sf {Tentacle}$ , a decision support framework to provision edge servers for online services providers (OSPs). $\sf {Tentacle}$ takes advantage of the increasingly flexible edge server placement, which is enabled by new technologies such as edge computing platforms, cloudlets and network function virtualization, to optimize the overall performance and cost of edge infrastructures. The key difference between $\sf {Tentacle}$ and traditional server placement approaches lies on that $\sf {Tentacle}$ can discover proper unforeseen edge locations which significantly improve the efficiency and reduce the cost of edge provisioning. We show how $\sf {Tentacle}$ effectively identifies promising edge locations which are close to a collection of users merely with inaccurate network distance estimation methods, e.g., geographic coordinate (GC) and network coordinate systems (NC). We also show how $\sf {Tentacle}$ comprehensively considers various pragmatic concerns in edge provisioning, such as traffic limits by law or ISP policy, edge site deployment and resource usage cost, over-provisioning for fault tolerance, etc., with a simple optimization model. We simulate $\sf {Tentacle}$ using real network data at global and county-wide scales. Measurement-driven simulations show that with a given cost budget $\sf {Tentacle}$ can improve user performance by around 10-45 percent at global scale networks and 15-35 percent at a country-wide scale network.

On Using Micro-Clouds to Deliver the Fog

The cloud is scalable and cost-efficient, but it isn't ideal for hosting all applications. Fog computing proposes an alternative of offloading some computation to the edge. Which applications to offload, where to send them, and when this should occur isn't entirely clear yet due to a lack of understanding of potential edge infrastructures. Through a number of experiments, the authors showcase the feasibility and readiness of micro-clouds formed by collections of Raspberry Pis to host a range of fog applications, particularly for network-constrained environments.

A Scalable Framework for Provisioning Large-Scale IoT Deployments

Internet of Things (IoT) devices are usually considered external application dependencies that only provide data or process and execute simple instructions. The recent emergence of IoT devices with embedded execution environments allows practitioners to deploy and execute custom application logic directly on the device. This approach fundamentally changes the overall process of designing, developing, deploying, and managing IoT systems. However, these devices exhibit significant differences in available execution environments, processing, and storage capabilities. To accommodate this diversity, a structured approach is needed to uniformly and transparently deploy application components onto a large number of heterogeneous devices. This is especially important in the context of large-scale IoT systems, such as in the smart city domain. In this article, we present LEONORE, an infrastructure toolset that provides elastic provisioning of application components on resource-constrained and heterogeneous edge devices in large-scale IoT deployments. LEONORE supports push-based as well as pull-based deployments. To improve scalability and reduce generated network traffic between cloud and edge infrastructure, we present a distributed provisioning approach that deploys LEONORE local nodes within the deployment infrastructure close to the actual edge devices. We show that our solution is able to elastically provision large numbers of devices using a testbed based on a real-world industry scenario.

CONCERT: a cloud-based architecture for next-generation cellular systems

Cellular networks are one of the corner stones of our information-driven society. However, existing cellular systems have been seriously challenged by the explosion of mobile data traffic, the emergence of machine-type communications and the flourish of mobile Internet services. In this article, we propose CONCERT (CONvergence of Cloud and cEllulaR sysTems), a converged edge infrastructure for future cellular communications and mobile computing services. The proposed architecture is constructed based on the concept of control/data (C/D) plane decoupling. The data plane includes heterogeneous physical resources such as radio interfacing equipment, computational resources, and software-defined switches. The control plane jointly coordinates physical resources to present them as virtual resources, over which software-defined services including communications, computing, and management can be deployed in a flexible manner. Moreover, we introduce new designs for physical resources placement and task scheduling, so that CONCERT can overcome the drawbacks of the existing baseband-up centralization approach and better facilitate innovations in next-generation cellular networks. These advantages are demonstrated with application examples on the radio access networks (RANs) with C/D decoupled air interface, delay sensitive machine-type communications, and real-time mobile cloud gaming. We also discuss some fundamental research issues arising with the proposed architecture to illuminate future research directions.

Functional Genomics Down Under: RNAi Screening in the Victorian Centre for Functional Genomics

The Victorian Centre for Functional Genomics (VCFG) is an RNAi screening facility housed at the Peter MacCallum Cancer Centre in Melbourne, Australia. The Peter Mac is Australia's largest dedicated Cancer Research Institute, home to a team of over 520 scientists that focus on understanding the genetic risk of cancer, the molecular events regulating cancer growth and dissemination and improving detection through new diagnostic tools (www.petermac.org). Peter Mac is a well recognised technology leader and established the VCFG with a view to enabling researchers Australia and New Zealand-wide access to cutting edge functional genomics technology, infrastructure and expertise. This review documents the technology platforms operated within the VCFG and provides insight into the workflows and analysis pipelines currently in operation.