Florian Schreiner

QoS-aware elastic cloud brokering for IMS infrastructures

Cloud computing management supports are becoming more and more important not only in the fields of IT infrastructures for Internet applications and services, but steadily also in the field of telecommunication services and infrastructures. More and more telecommunication service providers have adopted IP Multimedia Subsystems (IMS) to consolidate their service infrastructures towards converged, all-IP, access network independent Next Generation Networks (NGNs). Although modern NGN service environments have the potential to greatly reduce new telecommunication services time-to-market, until now significant upfront investments into computational resources are required, that is still often a risk for the enterprise, with unsure return on invest. The application of cloud computing technologies to IMS-based service infrastructures enables new pay-per-use cost models, so IMS service providers may be charged for what they use only, significantly lowering the risk of bad investments. This work presents the design and implementation of a cloud brokering system for IMS services, capable of simultaneously interworking with multiple cloud infrastructures. We developed a Cloud Broker Engine (CBE) able to dynamically up/down-scale cloud resources across multiple cloud platforms. Our CBE is capable of coping with dynamic load situations and QoS requirements optimizing resource utilization across different cloud infrastructures: it enables QoS assurance and optimizes resource consumption across multiple cloud providers.

Management of SOA based NGN service exposure, service discovery and service composition

Next generation telecommunication network operators securely opening up their network capabilities and services to third party service providers require flexible service delivery platforms. Policy based service exposure, service discovery and service composition mechanisms are required to offer chargeable services and service building blocks to external entities in a customizable way. Based on research and developments conducted while prototyping solutions for the Open SOA Telco Playground, a unique IMS based NGN testbed for realizing SOA based NGN service delivery platforms, this work proposes the eXtended POlicy based, Semantically enabled sErvice bRoker (XPOSER). XPOSER provides novel NGN service exposition mechanisms. It enables intent-based NGN service discovery and allows for user-centric, automated service composition. Utilizing SOA based Operation Support Systems this work explains requirements and solutions for dynamically managing NGN service compositions by tightly linking service creation, service fulfillment and service assurance mechanisms already at service composition time.

Towards Standardized and Automated Fault Management and Service Provisioning for NGNs

The IP Multimedia Subsystem (IMS), already widely recognized as a fundamental core component of Next Generation Networks (NGNs), enables proliferation of a huge variety of value added services. Simultaneous to the emergence of triple play services there is a strong need for establishing standardized methodologies for service fulfillment and assurance, maintaining service execution parameters at advertised levels. Traditional Operations Support Systems (OSS) are not adequate for managing NGNs. This work shows experiences gained from implementing OSS for NGNs. It describes a solution that combines extensive NGN development expertise with a new generation, of policy-based, service oriented OSS solutions in order to provide enhanced levels of automation and reliability to the NGN service delivery and session control environment. Primary focus of this approach is put on service assurance and service fulfillment mechanisms for remote monitoring, automated control and configuration of standard compliant IMS infrastructures, such as the Open Source IMS Core (OSIMS) based Open IMS Playground. This work describes state of the art NGN OSS design principles and knowledge attained by integration of standardized fault management as well as service and subscriber provisioning procedures showing how the full cycle from service deployment to service advertisement to service execution can be delivered in an automated way.

From IMS Management to SOA Based NGN Management

Although IP Multimedia Subsystem (IMS) based Next Generation Networks (NGNs) are already emerging as the common session control platform for converging fixed, mobile and cable networks, harmonized solutions for the management of these converged platforms have still got to be developed. This document describes a hands-on approach to NGN Management. Started with IMS specific management systems, succeeding research had to take into account the importance of the management of NGN SDPs as well. This work shows that the hybrid nature of an NGN, where services can be delivered at the IMS layer, by SIP signaling mechanisms, as well as at the SDP, via Web Services, requires a harmonized management approach. Taking into account Service Oriented Architecture (SOA) principles and policy based model driven architectures, this work shows that a unification of service composition and service management already at the workflow creation level, bares significant benefits in terms of automation and harmonization. Following the SOA paradigm, the approach presented here does not differentiate between business process management (BPM) and management process management. Focusing on Telemanagement Forum’s enhanced Telecom Operations Map service fulfillment and service assurance operations, this document describes an New Generation Software and Services (NGOSS) based implementation of a unified Operation Support System (OSS) for NGNs that encompasses many problems of former stovepipe management solutions in terms of automation, flexibility and manageability.

Modular exposure of next generation network services to enterprises and testbed federations

This paper describes how next generation network and IP multimedia subsystem services provided by Telco networks as well as testbeds and testbed federations can be used in a modular fashion to compose high level multimedia services. The IP multimedia subsystem, specified by the 3rd generation partnership projects (3GPP and 3GPP2), was developed to address next generation network convergence challenges and end-user requirements. As an all-IP overlay network architecture, it aims at providing a platform for provisioning services in a secure and controllable manner, merging the paradigms and technologies of the Internet with the cellular and fixed telecommunication worlds and was also adopted for the Next generation network architecture of ETSI TISPAN. In this paper we will outline the requirements on service description, service discovery and service orchestration in next generation networks and distributed testbed environments. We will further describe how to make use of service building blocks to expose network functionalities towards higher service abstraction layers. We will finally display our findings in the light of the Open SOA Telco Playground, one of the Fraunhofer FOKUS testbeds that represents today a first approach to the practical implementation of the ideas described.

Service-oriented testbed infrastructures and cross-domain federation for Future Internet research

This article outlines the necessity for federated service oriented testbeds in order to accommodate the requirements of Future Internet research. Extensive investigations have been carried out in the networking and grid computing area during the last decades. These activities have successfully instantiated a number of large scale collaborative network testbeds and network emulation testbeds. The article describes an architectural approach on how to design service oriented testbeds and federate them across the boundaries of administrative domains to provide testing and development platforms that serve the needs of Future Internet research not only on the networking layer but also in the service and control platform layers.

QoS-aware multi-cloud brokering for NGN services: Tangible benefits of elastic resource allocation mechanisms

Elastic mechanisms for rapidly scaling cloud resources according to dynamic workloads are essential characteristics of cloud computing. The dynamic selection of current optimal cloud services is one of the main objectives of cloud brokering mechanisms. Combined with capabilities for elastic cloud resource allocation, multi-cloud brokering mechanisms allow for dynamic selection and efficient utilization of cloud resources. The achieved efficiency of resource consumption under dynamically changing workloads and different QoS constraints is a key performance indicator of such systems. This paper evaluates the effects of multiple factors impacting the performance of such systems in a large-scale multi-cloud environment for research and experimentation of Future Internet technologies. It defines metrics for assessing the performance of multi-cloud brokering systems, against which a cloud brokering prototype for cloud-based NGN media streaming services is evaluated. By evaluating the impact of application- and cloud resource-specific effects, as well as the specific characteristics of realistic NGN workloads, a realistic estimation of potential cost-/resource savings and achievable QoS levels is provided.

Elasticity as a service for federated cloud testbeds

This paper presents the design, real-world deployment and evaluation of FOKUS Cloud Brokers core component, the Elasticity Engine. The engine enables Elasticity as a Service, by providing dynamic and optimized cloud resource allocation for federated cloud platform environments. Deployed and evaluated within the European large-scale, multi-site cloud experimental facility BonFIRE this work provides a realistic assertion of the performance of the Elasticity Engines cloud resource allocation performance. Being a very typical scenario for todays cloud platform users who are having the free choice to select amongst multiple cloud platform offerings, this work provides a rough, but realistic assertion on what can be expected of an elastic multi-cloud resource provisioning system in terms of performance.

Network-aware Cloud Brokerage for telecommunication services

Cross-domain Cloud Brokering mechanisms enable elastic and cost-efficient utilization of cloud resources distributed across multiple cloud platforms. They are allowing cloud service providers to cost-efficiently exploit the growing competition in the cloud provider market. Existing elastic cloud computing solutions are optimizing cloud resource utilization merely within a specific cloud provider platform. Optimized multi-site Cloud Brokering mechanisms on the other hand enable economically efficient cloud resource consumption. However, in order to satisfy QoS requirements of cloud-based, real-time multimedia telecommunication services, enhanced QoS assurance mechanisms for multi-site cloud brokers need to be in place. In this paper we optimize and evaluate the FOKUS Cloud Broker solution through experimentation in a multi-site cloud testing facility which allows experimentation under different networking conditions, i.e. over standard, best-effort internet connections across several cloud platforms in Europe, as well as under fully controllable network conditions. The result of this work shows the benefits of network-aware cloud brokering mechanisms. Moreover, this paper shows the terms under which additional real-time data on network performance is useful for enhancing cloud brokering mechanisms, especially for meeting QoS requirements of realtime communication services. This work also shows how initial, service-specific correlation of network, service and host performance parameters, furthermore improves the overall cloud brokering performance.

Optimization of Elastic Cloud Brokerage Mechanisms for Future Telecommunication Service Environments

Cloud computing mechanisms and cloud-based services are currently revolutionizing Web as well as telecommunication service platforms and service offerings. Apart from providing infrastructures, platforms and software as a service, mechanism for dynamic allocation of compute and storage resources on-demand, commonly termed as “elastic cloud computing” account for the most important cloud computing functionalities. Resource elasticity allows not only for efficient internal compute and storage resource consumption, but also, through so called hybrid cloud computing mechanisms, for dynamic utilization of external resources on-demand. This capability is especially useful in order to cost-efficiently cope with peakworkloads, allowing service providers to significantly reduce usually required over-provisioned service infrastructures, allowing for “pay-per-use” cost models. With a steadily growing number of cloud providers and with the proliferation of unified cloud computing interfaces, service providers are given free choice of flexibly selecting and utilizing cloud resources from different cloud providers. Cloud brokering systems allow for dynamic selection and utilization of cloud computing resources based on functional (e.g. QoS, SLA, energy consumption) as well as nonfunctional criteria (e.g. costs). The presented work focuses on enhanced cloud brokering mechanisms for telecommunication service platforms, enabling quality telecommunication service assurance, still optimizing cloud resources consumption, i.e. saving costs and energy. Furthermore this work shows that by combining cloud brokering mechanisms with standardized telecommunication service brokering mechanisms an even greater benefit for telecommunication service providers can be achieved as this enables an even better cost-efficiency since different user segments can seamlessly be served by allocating different cloud resources to them in a policy-driven manner.