Search

Cloud computing can greatly enhance robotic applications, not only by complementing robotic resources (e.g., CPU/GPU, memory, storage), but also by providing global-scale highly available services, distributed application management solutions, proven development and deployment practices. However, several challenges have to be addressed in order to bridge the gap between cloud and robotic development, including ROS and cloud design assumptions, networking, and mobile robots. In this chapter we present ECRP, a Platform as a Service solution for building ROS-based cloud robotics applications.

Distributed cloud storage solutions are currently gaining high momentum in industry and academia. The enterprise data volume growth and the recent tendency to move as much as possible data to the cloud is strongly stimulating the storage market growth. In this context, and as a main requirement for cloud native applications, it is of utmost importance to guarantee resilience of the deployed applications and the infrastructure. Indeed, with failures frequently occurring, a storage system should quickly recover to guarantee service availability. In this paper, we focus on containerized cloud storage, proposing a resilience monitoring solution for the recently developed Rook storage operator. While, Rook brings storage systems into a cloud-native container platform, in this paper we design an additional module to monitor and evaluate the resilience of the Rook-based system. Our proposed module is validated in a production environment, with software components generating a constant load and a controlled removal of system elements to evaluate the self-healing capability of the storage system. Failure recovery time revealed to be 41 and 142 seconds on average for a 32GB and a 215GB object storage device respectively.

Over the last couple of decades, the demand for storage in the Cloud has grown exponentially. Distributed Cloud storage and object storage for the increasing share of unstructured data, are in high focus in both academic and industrial research activities. At the same time, efficient storage and the corresponding costs are often contrasting parameters raising a trade-off problem for any proposed solution. To this aim, classifying the data in terms of access probability became a hot topic. This paper introduces Hera Object Storage, a storage system built on top of OpenStack Swift that aims at selecting the most appropriate storage tier for any object to be stored. The goal of the multi-tiering storage we propose is to be automated and seamless, guaranteeing the required storage performance at the lowest possible cost. The paper discusses the design challenges, the proposed algorithmic solutions to the scope and, based on a prototype implementation it presents a basic proof-of-concept validation.

Network Functions Virtualization allows Communication Service Providers to extend their traditional service portfolio to new models of service offerings, such as Virtualized Network Functions as a Service (VNFaaS), in which network functions can be traded following the “on-demand” Cloud paradigm. Incremental deployment and interoperability with legacy infrastructure, in particular Wide Area Network (WAN) domains and enterprise services, are key requirements to make this vision come true in the short/medium term. This paper discusses the main challenges that need be addressed for the adoption of VNFaaS in production environments and is particularly focused on the integration of NFV and WAN. To this end, two components are proposed: Netfloc, to support traffic steering inside NFV infrastructure points of presence, and the WAN Infrastructure Connectivity Manager (WICM), to handle the integration of virtualized network functions with WAN connectivity services, as a composed end-to-end network service.

The Future Communication Architecture for Mobile Cloud Services: Mobile Cloud Networking (MCN) is a EU FP7 Large-scale Integrating Project (IP) funded by the European Commission. MCN project was launched in November 2012 for the period of 36 month. In total top-tier 19 partners from industry and academia commit to jointly establish the vision of Mobile Cloud Networking, to develop a fully cloud-based mobile communication and application platform.

The maturity reached by virtualisation technology enabled great innovation for efficient applications and services development and delivery, independent of the underlying hardware equipment, especially with the large deployment of off-the-shelf hardware based cloud infrastructures. In order to take advantage of this technology, the existing network functions have to be developed and adapted to the new paradigm. However, traditional telecom services are still implemented on dedicated hardware resulting in high deployment and maintenance costs compared to the other already cloudified services. ETSI Network Functions Virtualisation (NFV) aims to fill this gap by applying to telecom the virtualisation technologies. This paper introduces a set of three software architectures for efficient virtualisation of IP Multimedia Subsystem (IMS) in different operator environments responding to the high level requirements of the ETSI NFV use case for virtualizing operator core network functions. Additionally, a management architecture for simplifying the deployment and runtime orchestration of such a virtual service on top of a cloud infrastructure is presented. Furthermore, one of the IMS software architectures was implemented based on the Fraunhofer FOKUS Open IMS Core, measured and evaluated on top of an OpenStack cloud.

In cloud environments High Availability characteristics are established by the usage of failover software (like e.g. HAProxy, Keepalive or Pacemaker). Though these tools enable automatic recovery of cloud services from outages, the recovery can still be very slow if it is not configured adequately. In this paper we developed a "Recovery Time Test" to determine if recovery time depends on configuration of the failover software and how recovery time depends on configuration settings. Another goal of the Recovery Time Test is to determine the factor by which recovery time can be decreased by a given configuration. As proof of concept, we applied the Recovery Time Test to an OpenStack cloud environment which is controlled by the Pacemaker failover software. Pacemaker mean recovery time can take a value between 110 and 160 seconds, if the tool is configured badly. We found that with a proper configuration Pacemaker mean recovery time can be reduced significantly to a value between 15 and 20 seconds.

In this paper we present an idea of a propriety Software Defined residential Network (SDrN) and we show as a use case, a multicast streaming service that can be hosted on such networks. To verify the feasibility of the service in the context of quality of service, we offer to the providers of online streaming services (in some cases the ISPs themselves), APIs to control and validate the QoS of the users in the service. The QoS control APIs were tested on SDN based simulation environment.

In this paper we consider how energy efficiency aspects can be added to Openstack. With the objective of devising an energy efficient resource manager for Openstack, we first analyze resource and energy utilization on our cloud resources. We observe that there is a large fixed cost associated with server usage patterns and powering down servers is necessary to achieve energy savings. Following this we consider migration mechanisms which are necessary to perform load consolidation: we find that hybrid live migration has the necessary robustness to be part of a sophisticated load management solution. Finally we discuss ongoing work on realizing a load manager for Openstack based on these observations.

Content Distribution Networks are mandatory components of modern web architectures, with plenty of vendors offering their services. Despite its maturity, new paradigms and architecture models are still being developed in this area. Cloud Computing, on the other hand, is a more recent concept which has expanded extremely quickly, with new services being regularly added to cloud management software suites such as OpenStack. The main contribution of this paper is the architecture and the development of an open source CDN that can be provisioned in an on-demand, pay-as-you-go model thereby enabling the CDN as a Service paradigm. We describe our experience with integration of CDNaaS framework in a cloud environment, as a service for enterprise users. We emphasize the flexibility and elasticity of such a model, with each CDN instance being delivered on-demand and associated to personalized caching policies as well as an optimized choice of Points of Presence based on exact requirements of an enterprise customer. Our development is based on the framework developed in the Mobile Cloud Networking (MCN) EU FP7 project, which offers its enterprise users a common framework to instantiate and control services. CDNaaS is one of the core support components in this project as is tasked to deliver different type of multimedia content to several thousands of users geographically distributed. It integrates seamlessly in the MCN service life-cycle and as such enjoys all benefits of a common design environment, allowing for an improved interoperability with the rest of the services within the MCN ecosystem.

This paper proposes a methodology to establish a billing model in a streaming service that can achieve high provider's profit and increased users' welfare. We relate three types of the service's topology: P2P (multicast), P2P-Cloud (hybrid) and Cloud (unicast) to different user profiles and analyze their effect on the provider's cost and profit. The evaluation shows that increased user cooperation, significantly decreases the provider's cloud infrastructure cost and make his profit highest when 50%-100% of the users cooperate. More cooperation increases the overall users' welfare in terms of monetary remuneration.

In the present days of rapid adoption of cloud services and varying cost models it is imperative to have a system which converts the cloud resource usage data into a measurable and payable cost. The system should be able to collect the cloud resource usage data, process it against a dynamically determined rate to get a charge for which the customer could be billed upon. These operations need to be done in a secured manner with appropriate authentication and authorization checks. As the cloud services are still evolving, the rating, charging and billing components for cloud are at a nascent stage of its maturity. In this paper we are describing a novel modular and micro services based design & architecture for developing a dynamic rating, charging and billing for cloud service providers with emphasis being given to the validation of the architecture through mathematical modeling and the implementation experience of the micro services.

The fast growing development of Network Function Virtualization (NFV) trends and the remarkable progress of Software Defined Networking (SDN) have yielded a synergy between both, towards the provision of convergent networking solutions. Since the traditional networking principles were not designed according to the NFV principles, a work has emerged dedicated to protocol redesign among the academic fellows and the industry representatives. A typical example that has been introduced in such eco-system is the concept of network service chaining, as a composition of virtual network functions stitched together in a logically ordered fashion, to create an integral networking service that can be owned by network administrators, programmers, cloud- and telco-operators. This appoints SDN as an essential technology enabler in administering advanced traffic steering techniques, thanks to the SDN controller's capability to dynamically manage VNFs virtual connections and underlying dataplane flows. Despite the rapid progression, the strategies for traffic steering in NFV environment, are still facing imminent challenges to be addressed. This paper joins NFV and SDN technology into a novel traffic steering solution based on open source reference implementations (such as SDK for SDN, virtual Traffic Classifier, virtual Media Transcoder, and WAN Infrastructure Connection Manager) designed with performance and network optimizations in mind. We have successfully deployed and tested the system prototype in a real datacenter. The evaluation results of the prototype system: (1) validated the presented chain use cases, (2) affirmed an efficient performance and scalability of the chaining method, and (3) certified good quality of video traffic transmission and transcoding.

The setup of distributed computing clusters and the installation of data analysis frameworks can be cumbersome and requires a great deal of knowledge in a plenitude of fields. We have developed DISCO, a service which is alleviating the data scientist from these hurdles. This paper shows up the competitiveness of DISCO with an existing solution.

The objective of this paper is to illustrate how to monetize infrastructures and services. This is achieved by a combination of measuring consumption, applying pricing strategies and client invoicing. Furthermore, a range of billing solutions are available in order to cover the Rating, Charging and Billing process. The focus here is on the comparison of solution based suitability, which depends on complexity of records and volume of transactions. RCB Cyclops, as an open source solution, is presented and evaluated in terms of data throughputs focusing on doubling host machines and yielding 70-80% boost in performance.

Sensitive data is increasingly being hosted online in ubiquitous cloud storage services. Recent advances in multi-cloud service integration through provider multiplexing and data dispersion have alleviated most of the associated risks for hosting files which are retrieved by users for further processing. However, for structured data managed in databases, many issues remain, including the need to perform operations directly on the remote data to avoid costly transfers. In this paper, we motivate the need for distributed stealth databases which combine properties from structure-preserving dispersed file storage for capacity-saving increased availability with emerging work on structure-preserving encryption for on-demand increased confidentiality with controllable performance degradation. We contribute an analysis of operators executing in map-reduce or map-carry-reduce phases and derive performance statistics. Our prototype, StealthDB, demonstrates that for typical amounts of personal structured data, stealth databases are a convincing concept for taming untrusted and unsafe cloud environments.

Running applications in the cloud efficiently requires much more than deploying software in virtual machines. Cloud applications have to be continuously managed: (1) to adjust their resources to the incoming load and (2) to face transient failures replicating and restarting components to provide resiliency on unreliable infrastructure. Continuous management monitors application and infrastructural metrics to provide automated and responsive reactions to failures (health management) and changing environmental conditions (auto-scaling) minimizing human intervention. In the current practice, management functionalities are provided as infrastructural or third party services. In both cases they are external to the application deployment. We claim that this approach has intrinsic limits, namely that separating management functionalities from the application prevents them from naturally scaling with the application and requires additional management code and human intervention. Moreover, using infrastructure provider services for management functionalities results in vendor lock-in effectively preventing cloud applications to adapt and run on the most effective cloud for the job. In this paper we discuss the main characteristics of cloud native applications, propose a novel architecture that enables scalable and resilient self-managing applications in the cloud, and relate on our experience in porting a legacy application to the cloud applying cloud-native principles.

Cloud-Native Applications (CNA) are designed to run on top of cloud computing infrastructure services with inherent support for self-management, scalability and resilience across clustered units of application logic. Their systematic design is promising especially for recent hybrid virtual machine and container environments for which no dominant application development model exists. In this paper, we present a case study on a business application running as CNA and demonstrate the advantages of the design experimentally. We also present Dynamite, an application auto-scaler designed for containerised CNA. Our experiments on a Vagrant host, on a private OpenStack installation and on a public Amazon EC2 testbed show that CNA require little additional engineering.

In the last years we have experienced a growing industrial interest in Mobile Cloud Networking (MCN) as the opportunity to exploit the cloud computing paradigm through Network Function Virtualization (NFV), primarily with the goal to reduce CAPEX/OPEX for future mobile networks deployment and operation. The gain from the point of view of infrastructure costs reduction is almost clear and recognized, while many technical challenges are still to be solved, especially with industry-mature solutions, due to the complexity of managing such type of infrastructures. In particular, the dynamicity and flexibility introduced by the virtualization of network functions add novel requirements on the service management and orchestration layers. In this perspective, this paper originally presents the architecture and primary implementation guidelines of the Mobile Cloud Networking framework developed within a large EU FP7 project. More specifically, it focuses on the innovative technical elements of our solution for service management and orchestration, namely i) orchestration strategies based on resource unit affinity and ii) compliance with emerging Open Cloud Computing Interface (OCCI) standards. To practically demonstrate the suitability of the proposed approach, a specific real use case has been implemented, i.e., the cloudification of the 3GPP IP Multimedia Subsystem (IMS), by reporting and analyzing the related performance results.