The field of Cloud Community is broad and deep. This new column will explore various communities progress on Cloud Computing, and will compare and contrast their approaches. Look for supporting material on the IEEE Cloud Computing Website (https://cloudcomputing.ieee.org/communities-of-practice).
TOSCA, the Topology and Orchestration Specification for Cloud Applications offers an OASIS-recognized, open standard domain-specific language (DSL) that enables portability and automated management of applications, services, and resources regardless of underlying cloud platform, software defined environment, or infrastructure. With a growing, interoperable eco-system of open source projects, solutions from leading cloud platform and service providers, and research, TOSCA empowers the definition and modeling of applications and their services (microservices or traditional services) across their entire lifecycle by describing their components, relationships, dependencies, requirements, and capabilities for orchestrating software in the context of associated operational policies. The authors introduce important TOSCA concepts and benefits in the context of commonly understood cloud use cases as a foundation to future discussions regarding advanced TOSCA concepts and additional breakthrough issues.
TOSCA, the Topology and Orchestration Specification for Cloud Applications offers an OASIS-recognized, open standard domain-specific language (DSL) that enables portability and automated management of applications, services, and resources regardless of underlying cloud platform, software defined environment, or infrastructure. With a growing, interoperable eco-system of open source projects, solutions from leading cloud platform and service providers, and research, TOSCA empowers the definition and modeling of applications and their services (microservices or traditional services) across their entire lifecycle by describing their components, relationships, dependencies, requirements, and capabilities for orchestrating software in the context of associated operational policies. The authors introduce important TOSCA concepts and benefits in the context of commonly understood cloud use cases as a foundation to future discussions regarding advanced TOSCA concepts and additional breakthrough issues.
Collecting data is an important task to build smart cities. This work proposes SensingBus, a system to collect data from sensors carried by urban buses. Using buses to move sensors allows each node to cover a wider area, at a negligible cost. SensingBus is based on a three-level architecture. At the first level, sensing nodes collect and send data to the second level, consisting of fog nodes. The fog nodes pre-process and deliver data to the third level, the cloud infrastructure, which stores and makes data externally available. The fog infrastructure, on the other hand, discards defective data, compresses information, and provides secure access points between fog and cloud. To validate SensingBus, we build a prototype and perform experiments to stress the fog nodes. We verify that each one can accommodate at least 20 simultaneous sensing nodes, an adequate number to sense a city such as Rio de Janeiro.
This article describes new ideas for applying security procedures to data and service management in cloud and fog computing. Management in cloud computing is presented in connection with cognitive systems supporting management tasks and securing important data. The application of cognitive and biometric features allows creation of personalized procedures oriented at particular users or a group of protocol participants.
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.
Editor-in-Chief Mazin Yousif discusses the prospects and challenges of biometrics-as-a-service.
Workload scaling is an approach to accelerating computation and thus improving response times by replicating the exact same request multiple times and processing it in parallel on multiple nodes and accepting the result from the first node to finish. This is not unlike a TV game show, where the same question is given to multiple contestants and the (correct) answer is accepted from the first to respond. This is different than traditional strategies for parallelization as used in, say, MapReduce workloads, where each node runs a subset of the overall workload. There are a variety of strategies that trade off metrics such as cost, utilization, performance, and interprocessor communication requirements. Performance modeling can help determine optimal approaches for different environments and goals. This is important, because poor performance can lead to application and domain-specific losses, such as e-commerce conversions and sales. Performance modeling and analysis plays an important role in designing and driving the selection of resource scaling mechanisms. Such modeling and analysis is complex due to time-varying workload arrival rates and request sizes, and even more complex in cloud environments due to the additional stochastic variation caused by performance interference due to resource sharing across co-located tenants. Moreover, little is known on how to multi-scale, i.e., dynamically and simultaneously scale resources vertically, horizontally, and through workload scaling. In this article, we first demonstrate the effectiveness of multi-scaling in reducing latency, and then discuss the performance modeling challenges, particularly for workload scaling.
Understanding the mechanisms by which cloud automation produces efficiency improvement lets organizations appropriately plan their investments in such automation-along with quality and performance improvements-to optimize operational efficiency.
Millions of private images are generated in various digital devices every day. The consequent massive computational workload makes people turn to cloud computing platforms for their economical computation resources. Meanwhile, the privacy concerns over the sensitive information contained in outsourced image data arise in public. In fact, once uploaded to cloud, the security and privacy of the image content can only presume upon the reliability of the cloud service providers. Lack of assuring security and privacy guarantees becomes the main barrier to further deployment of cloud based image processing systems. This paper studies the design targets and technical challenges lie in constructing cloud-based privacy-preserving image processing system. We explore various image processing tasks, including image feature detection, digital watermarking, content-based image search etc. The state-of-the-art techniques, including secure multiparty computation, and homomorphic encryption are investigated. A detailed taxonomy of the problem statement and the corresponding solutions is provided.
Fog and edge computing decentralize cloud computing but often depend on centralized cloud servers. There is an active consortium supporting architecture and standards as fog computing complements cloud computing.
User privacy concerns are widely regarded as a key obstacle to the success of modern smart cyber-physical systems. In this paper, we analyse, through an example, some of the requirements that future data collection architectures of these systems should implement to provide effective privacy protection for users. Then, we give an example of how these requirements can be implemented in a smart home scenario. Our example architecture allows the user to balance the privacy risks with the potential benefits and take a practical decision determining the extent of the sharing. Based on this example architecture, we identify a number of challenges that must be addressed by future data processing systems in order to achieve effective privacy management for smart cyber-physical systems.
The guest editors of the IEEE Cloud Computing special issue on Biometrics-as-a-Service discuss the benefits and challenges of using cloud computing with biometric authentication systems as well as the articles included in this issue.
Cloud gaming has been attracting increasing attention in the game industry. Nevertheless, the benefits of cloud-gaming platforms in facilitating multiplayer games have not been widely discussed in the literature. This article reveals this emerging trend and discusses a supporting network architecture for multiplayer cooperative cloud gaming. The article further examines two existing modalities that adopt cooperation among neighboring players to optimize the quality of service in cloud-gaming services.
Is biometrics as a service the next giant leap, as Jeremy Rose asks? New trends in consumer applications seem to testify this revolution. However, it is worth wondering to what extent both company infrastructures and the market are actually ready for this. This article explores the potential of cloud-based biometrics (biometrics as a service) for smart cities and nations.
Software Defined Networking (SDN) is rapidly transforming the networking ecosystem of cloud computing data centers. However, replicating SDN-enabled cloud infrastructures to conduct practical research in this domain requires a great deal of effort and capital expenditure. In this paper, we present the CLOUDS-Pi platform, a small-scale cloud data center for doing research on software-defined clouds. As part of it, Open vSwitch (OVS) is integrated with Raspberry-Pis, low-cost embedded computers, to build up a network of OpenFlow switches. We provide two use cases and perform validation and performance evaluation. We also discuss benefits and limitations of CLOUDS-Pi in particular and SDN in general.
The mobility of people is one of the main critical aspects related to daily life in a city, causing both traffic congestion and pollution. Smart-mobility services based on vehicular cloud computing and the Internet of Things (IoT) are emerging as new solutions that can address such issues. In this context, the FIWARE acceleration program, along with the frontierCities initiative, paved the way toward the development of new smart-mobility services. This article discusses different performance indicators that must be considered for the design and development of smart-mobility services adopting FIWARE technology. To this end, the authors consider the home-office mobility of University of Messina personnel as a case study. In particular, after a preliminary analysis of traveling habits, the authors gained insights on how FIWARE can lead to agile development of smart-mobility services that can minimize traffic congestion, fuel consumption, and CO2 emissions.
Since the conception of cloud computing, ensuring its ability to provide highly reliable service has been of the upmost importance and criticality to the business objectives of providers and their customers. This has held true for every facet of the system, encompassing applications, resource management, the underlying computing infrastructure, and environmental cooling. Thus, the cloud-computing and dependability research communities have exerted considerable effort toward enhancing the reliability of system components against various software and hardware failures. However, as these systems have continued to grow in scale, with heterogeneity and complexity resulting in the manifestation of emergent behavior, so too have their respective failures. Recent studies of production cloud datacenters indicate the existence of complex failure manifestations that existing fault tolerance and recovery strategies are ill-equipped to effectively handle. These strategies can even be responsible for such failures. These emergent failures-frequently transient and identifiable only at runtime-represent a significant threat to designing reliable cloud systems. This article identifies the challenges of emergent failures in cloud datacenters at scale and their impact on system resource management, and discusses potential directions of further study for Internet of Things integration and holistic fault tolerance.
The smart city uses knowledge or rules mined from Internet of Things sensor data to promote the development of the city. This brings new opportunities and challenges, such as low delay and real-time services. This article proposes an edge cloud-assisted CPSS (cyber-physical-social system) framework for smart cities. This framework migrates some tasks from the cloud center to network edge devices and puts the services and resources closer to users, so as to provide lower-latency, real-time, more effective, and proactive services for residents and policymakers.
Although today's average cloud computing environment may incorporate security in most aspects of its design and infrastructure, the mere operation of the network exposes it to attacks. A typical attack starts with probing for weaknesses and/or vulnerabilities that can be exploited. And it is at this stage that the battle seems to be already lost, as the average network is insufficiently equipped-mostly for economic reasons-to even know that they are under probing, let alone thwart an attack. In many cases, cloud systems are caught unaware of situations where friends turn into foes, nullifying established security measures. Threats will always dwell on new (previously unknown) methods to compromise established security measures (i.e., a rat race between defenders and attackers, particularly well-resourced attackers). These methods largely fall outside the adapted models used by current security measures that protect cloud-based systems. After-the-fact analysis has driven security researchers to extend models to include assumptions about newly discovered threat(s). Solutions are then designed to deter these new threats. These models may also be generalized with additional measures mapping futuristic predictions-these are also referred to as known-unknowns.
