No abstract

No abstract

No abstract

No abstract

No abstract

Automated resource provisioning techniques enable the implementation of elastic services, by adapting the available resources to the service demand. This is essential for reducing power consumption and guaranteeing QoS and SLA fulfillment, especially for those services with strict QoS requirements in terms of latency or response time, such as web servers with high traffic load, data stream processing, or real-time big data analytics. Elasticity is often implemented in cloud platforms and virtualized data-centers by means of auto-scaling mechanisms. These make automated resource provisioning decisions based on the value of specific infrastructure and/or service performance metrics. This paper presents and evaluates a novel predictive auto-scaling mechanism based on machine learning techniques for time series forecasting and queuing theory. The new mechanism aims to accurately predict the processing load of a distributed server and estimate the appropriate number of resources that must be provisioned in order to optimize the service response time and fulfill the SLA contracted by the user, while attenuating resource over-provisioning in order to reduce energy consumption and infrastructure costs. The results show that the proposed model obtains a better forecasting accuracy than other classical models, and makes a resource allocation closer to the optimal case.

The interconnection of the different geographically dispersed cloud and fog infrastructures is a key issue for the development of the fog technology. Although most existing cloud providers and platforms offer some kind of connectivity services to allow the interconnection with external networks, these services exhibit many limitations and they are not suitable for fog computing environments. In this work we present a hybrid fog and cloud interconnection framework, which allows the automatic provision of cross-site virtual networks to interconnect geographically distributed cloud and fog infrastructures. This framework provides a scalable and multi-tenant solution, and a simple and generic interface for instantiating, configuring and deploying Layer 2 and Layer 3 overlay networks across heterogeneous fog and cloud platforms, with abstraction from the underlying cloud/fog technologies and network virtualization technologies. Keywords: Heterogeneous Fog and Cloud Interconnection; Virtual Network Provisioning; Layer 2 and Layer 3 Overlay Networks; Scalability and Multi-Tenancy Support.Fog computing paradigm [1] is emerging as a key enabling technology for the Internet of Things (IoT), by broadening the scope of cloud platforms and services to the edge of the network, and allowing the efficient and agile deployment of mobile applications with strict geo-distribution, location awareness, and low latency requirements. Other similar paradigms to fog computing are ETSI Mobile Edge Computing [2] and Berkeley Cloudlets [3]. As shown in Figure 1, fog computing extends the cloud computing model by including an additional layer between the cloud and the mobile devices. In this three layer architecture (device-fog-cloud), a fog computing node is a small to medium size computing infrastructure that includes compute, storage and networking elements and is usually located at the premises of the end mobile users (e.g. shopping centers, airports, tourist attractions, etc.), and fog instances are physical or virtualized resources, deployed on top of the fog node infrastructure, that run the applications consumed by these end users, and can be accessed by mobile devices at one-hop distance over the wireless network. In addition, various fog nodes can also be connected to a central cloud, that could provide coordination between the different fog infrastructures, and some other additional services, such as extra computing capacity, large database management, off-line data processing for business intelligence, etc. This central cloud can be implemented as a commercial cloud provider (e.g. Amazon EC2, Microsoft Azure, Google Cloud, etc.) or as a public or private cloud managed by a cloud management platform [4] (e.g. OpenNebula, OpenStack, etc.) Some important features that must be considered in the design of a fog computing architecture are the following: a) multi-tenancy and isolation, since fog nodes must support the coexistence of several applications belonging to different tenants, and guarantee isolation among them; c) scalability ...

In this paper we analyze the deployment of generic clustered services on top of a virtualized infrastructure layer that combines a VM manager (the OpenNebula engine) and a cloud resource provider (Amazon EC2). The use of this virtualization layer between the service and the physical infrastructure extends the classical benefits of VM platforms to distributed infrastructures. Additionally, the integration of the cloud in this layer allows us to give additional capacity to the services using an external provider, thus complementing the local infrastructure without notice from the users or affecting the service workload. This flexible approach, which separates the resource provisioning from the service management, provides important benefits: elastic service capacity to adapt it to its dynamic workload; physical infrastructure partitioning to isolate it from other running services; and support for heterogeneous configurations tailored for each service class. The feasibility of the proposed approach is analyzed for two different clustered services: a classical computing cluster and a web server.