Yahya Al-Hazmi

BonFIRE: A Multi-cloud Test Facility for Internet of Services Experimentation

BonFIRE offers a Future Internet, multi-site, cloud testbed, targeted at the Internet of Services community, that supports large scale testing of applications, services and systems over multiple, geographically distributed, heterogeneous cloud testbeds. The aim of BonFIRE is to provide an infrastructure that gives experimenters the ability to control and monitor the execution of their experiments to a degree that is not found in traditional cloud facilities.

A monitoring system for federated clouds

Cloud computing mechanisms are steadily gaining significance in the field of IT infrastructure hosting and maintenance. To date, we have reached a point where a paradigm shift can be observed. An increasing number of IT players are rethinking the way the technical foundation of their offerings is operated from in-house datacenter hosting towards the outsourcing of infrastructure or services to specialized external cloud computing companies. With the emergence of more and more commercial cloud providers and offerings, combining resources from two or more providers - in order to benefit from factors like price differences, locality of resources, etc. - becomes increasingly feasible for consumers of cloud services. Therefore, it is desirable for such users to have an overarching monitoring system that aggregates a multitude of measurements from resources of different administrative domains in a unified manner. This paper introduces a comprehensive monitoring solution for federated clouds that provides data for both infrastructure providers and cloud users. This system does not only support monitoring resources from heterogeneous domains on both the network and infrastructure level, but moreover provides monitoring support that is able to operate across large numbers of end-to-end resources at the service as well as the application level. In this paper the design of this system as well as its implementation is discussed, and a validation of the system within the context of the European funded project BonFIRE is presented. The utility of the system is shown through the conduct of experimentation.

The Open-Multinet Upper Ontology Towards the Semantic-based Management of Federated Infrastructures

The Internet remains an unfinished work. There are several approaches to enhancing it that have been experimentally validated within federated testbed environments. To best gain scientific knowledge from these studies, reproducibility and automation are needed in all areas of the experiment life cycle. Within the GENI and FIRE context, several architectures and protocols have been developed for this purpose. However, a major open research issue remains, namely the description and discovery of the heterogeneous resources involved. To remedy this, we propose a semantic information model that can be used to allow declarative interoperability, build dependency graphs, validate requests, infer knowledge and conduct complex queries. The requirements for such an information model have been extracted from current international Future Internet research projects and the practicality of the model is being evaluated through initial implementations. The main outcome of this work is the definition of the Open-Multinet Upper Ontology and related sub-ontologies, which can be used to describe and manage federated infrastructures and their resources.

OpenStack Federation in Experimentation Multi-cloud Testbeds

There is an increasing number of cloud platforms emerging in both academia and industry. They often federate resources from multiple infrastructures in order to benefit from the unique features that each presents. After introducing the main capabilities and features of OpenStack, this article addresses the integration of OpenStack-based platforms into larger, heterogeneous multi-cloud infrastructures, taking the EU FP7 BonFIRE project as an integration use case. Ultimately, we aim to contribute to the state of the art and provide guidelines to integrators looking to federate Open Stack testbeds into more complex architectures.

Towards Semantic Monitoring Data Collection and Representation in Federated Infrastructures

The federation of infrastructures in the fields of Cloud and Future Internet (FI) test beds is evolving rapidly due to its multilateral benefits for end-users and infrastructure owners. However, interoperable monitoring data exchange across multiple administrative domains is a critical task to achieve as the heterogeneity of the used tools and interfaces arises. Several efforts have been done to unify interfaces but are task or domain specific. In this paper alternative, existing data models and collection protocols are reviewed. Their limitations to serve the need of a generic monitoring solution operating across federated, heterogeneous infrastructure are identified. This paper introduces an approach for unification of monitoring data collection and representation based on Semantic Web technologies. The main contribution of this paper is the design and implementation of an ontology-based information model for monitoring federated infrastructures. An initial validation has been achieved in a local cloud test bed, however, this solution is planned for a federation of multiple heterogeneous test beds within the context of the European Fed4FIRE project.

Cloud and Network Facilities Federation in BonFIRE

In recent years we have seen how Cloud Computing is changing the way of doing businesses and how services are delivered over the Internet. This disruption is a major challenge for Service Providers and Independent Software Vendors when creating new services and software applications for the Cloud. BonFIRE offers a federated, multi-site cloud testbed to support large-scale testing of applications, services and systems. This is achieved by federating geographically distributed, heterogeneous clouds testbeds where each exposes unique configuration and/or features while giving to the experimenters (users) an homogeneous way to interact with the facility. All those testbeds are controlled by a central set of services commonly denominated “Broker”. Additionally, BonFIRE is federated with different network facilities like the Virtual Wall, FEDERICA and AutoBAHN to provide high-level interfaces to network control functionality, in order to simulate diverse network QoS scenarios, enabling vertical federation.

DBcloud: Semantic Dataset for the cloud

In cloud environments, the process of matching requests from users with the available computing resources is a challenging task. This is even more complex in federated environments, where multiple providers cooperate to offer enhanced services, suitable for distributed applications. In order to resolve these issues, a powerful modeling methodology can be adopted to facilitate expressing both the request and the available computing resources. This, in turn, leads to an effective matching between the request and the provisioned resources. For this purpose, the Open-Multinet ontologies were developed, which leverage the expressive power of Semantic Web technologies to describe infrastructure components and services. These ontologies have been adopted in a number of federated testbeds. In this article, DBcloud is presented, a system that provides access to Open-Multinet open data via endpoints. DBcloud can be used to simplify the process of discovery and provisioning of cloud resources and services.

Towards Mobile Federated Network Operators

Mobile Network Operators provide wireless communication services to their customers using their own network infrastructures. For providers, in particular in low income countries, access to latest network functions to offer 4G/5G services can be a large burden as this is directly impacted by financial restrictions of operators. Although some network sharing solutions between operators to reduce the total cost of ownership exist in standards and literature, none address specific requirements of the operating environment of low income countries. In our approach, we are exploiting the raising interest in the cloudification of the related infrastructure, namely Network Function Virtualization (NFV) over Software Defined Networks (SDN), to allow each operator in these countries to offer specific network functions as a service in a federation in order to share them and to increase their revenue. Initial results are presented based on the development of a commercial toolkit (OpenSDNCore) and a federated testbed research project (TRESCIMO). As a result, we define the notion of a Mobile Federated Network Operator (MFNO) and provide an analysis of the underlying requirements for such a use case and potential approaches to address them.

Unified representation of monitoring information across federated cloud infrastructures

Nowadays one of the issues hindering the potential of federating cloud-based infrastructures to reach much larger scales is their standard management and monitoring. In particular, this is true in cases where these federated infrastructures provide emerging Future Internet and Smart Cities-oriented services, such as the Internet of Things (IoT), that benefit from cloud services. The contribution of this paper is the introduction of a unified monitoring architecture for federated cloud infrastructures accompanied by the adoption of a uniform representation of measurement data. The presented solution is capable of providing multi-domain compatibility, scalability, as well as the ability to analyze large amounts of monitoring data, collected from datacenters and offered through open and standardized APIs. The solution described herein has been deployed and is currently running on a community of 5 infrastructures within the framework of the European Project XIFI, to be extended to 12 more infrastructures.

Monitoring and measurement architecture for federated Future Internet experimentation facilities

Future Internet experimentation facilities and federations thereof are steadily gaining significance and have attracted the attention of academia and industry. They offer researchers as well as application/service developers and providers the opportunity to study and test the emerging Future Internet services and technologies in real-world, controlled, and cost-effective environments. Precise and dynamic monitoring information about the health, behavior and performance of infrastructure resources, as well as the services and applications under test are of importance for multiple stakeholders: facility providers, federation services, and experimenters (researchers and devel-opers). This paper introduces a monitoring and measurement architecture that operates across federated heterogeneous facilities aggregating a multitude of measurements from resources of different facilities and provides them in a unified manner. The solution is implemented in a federation of over 15 heterogeneous facilities and is offering multiple measurement and monitoring services at different granularity levels.