Abstracts:Advertisement.

Abstracts:Cloud computing has proven to be extremely useful in practice.1,2 Both the cloud-service-provider industry and its business, scientific, and consumer applications have grown exponentially. However, there are also benefits to be gained from viewing cloud computing abstractly: understanding its fundamental behaviors, but also its limitations. After a five-year run, this is the last issue of IEEE Cloud Computing. However, it is to be hoped that this final article contains the seeds of some ideas that others will find interesting and productive, so as to continue research to formalize such a theory. In effect, this article lays the foundation for future research by encapsulating much of this column's last five years into a comprehensive, integrated theoretical framework.

Abstracts:Because of cloud-computing development, choosing cloud services can be complicated and time-consuming for customers. To facilitate cloud service delivery, the authors propose a cloud service broker that resides in the multicloud model, provides automated selection of suitable cloud services, and assures the best performance, reliability, and cost efficiency.

Abstracts:Cloud federation is an emergent cloud-computing paradigm that allows services from different cloud systems to be aggregated in a single pool. To support secure data sharing in a cloud federation, anonymization services that obfuscate sensitive datasets under differential privacy have been recently proposed. However, by outsourcing data protection to the cloud, data owners lose control over their data, raising privacy concerns. This is even more compelling in multi-query scenarios in which maintaining privacy amounts to controlling the allocation of the so-called privacy budget. In this paper, we propose a blockchain-based approach that enables data owners to control the anonymization process and that enhances the security of the services. Our approach relies on blockchain to validate the usage of the privacy budget and adaptively change its allocation through smart contracts, depending on the privacy requirements provided by data owners. Prototype implementation with the Hyperledger permissioned blockchain validates our approach with respect to privacy guarantee and practicality.

Abstracts:Disclosing personal data for a purpose not known by data subjects is a practice that the 2018 European Union General Data Protection Regulation (GDPR) is supposed to prevent. This article gives an overview of the major aspects of GDPR related to provision, use, and maintenance of cloud services and technologies.

Abstracts:With the expansion of storage components in cloud data centers, component failures become prevalent. Although data replication can be exploited to protect against data loss, unfortunately, each time storage components fail, the burden incurred by the data block restoration process is not negligible. Re-replication should be performed in a careful manner to avoid creating a load imbalance on the remaining storage datanodes while maintaining the reliability level. In this paper, we propose PRTuner, which forecasts resource utilization for the whole cluster and tunes the re-replication rate dynamically and proactively in order to minimize performance impacts on regular cluster jobs while ensuring the reliability of the system. PRTuner also enhances proactive re-replication with an additional reactive feature that minimizes performance degradation in the case of inaccurate prediction. Simulation results demonstrate that PRTuner is able to minimize performance impacts on regular cluster jobs for both highly and lightly utilized clusters while maintaining the systems reliability.

Abstracts:In this paper, we describe a novel paradigm to pre-provision virtual machines (VMs) in an energy-efficient manner for cloud elastic applications. Our approach is based on the definition of dynamic context for VMs, which can be easily updated by software orchestration tools. We show the feasibility of our approach and improvement over existing state of the art with an experimental setup.

Abstracts:Hardware accelerators are available on the cloud for enhanced analytics. Next-generation clouds aim to bring enhanced analytics using accelerators closer to user devices at the edge of the network for improving quality of service (QoS) by minimizing end-to-end latencies and response times. The collective computing model that utilizes resources at the cloudedge continuum in a multi-tier hierarchy comprising the cloud, edge, and user devices is referred to as fog computing. This article identifies challenges and opportunities in making accelerators accessible at the edge. A holistic view of the fog architecture is key to pursuing meaningful research in this area.

Abstracts:Data centers should be among the most automated, robust environments on the planet. Instead, they often remain stuck in the past as agglomerations of outdated technologies. It is time to take this problem seriously and directly address the needs of data centers for modern automation and control through analytics-driven methods.

Abstracts:Blockchains, a decentralized storage technique, have many applications, including in reengineering cloud datacenters. This article proposes a conceptual model for fusing blockchains and cloud computing for additional value creation. The proposed model comprises three deployment modes: Cloud over Blockchain (CoB), Blockchain over Cloud (BoC), and Mixed Blockchain-Cloud (MBC). The article also highlights the potential benefits of such a fusion and outlines a number of future research directions.