Cloud Computing Infrastructure Research Articles

English

English

Achieving One Billion Key-Value Requests per Second on a Single Server

Distributed in-memory key-value stores (KVSs) have become a critical data-serving layer in cloud computing and big data infrastructure. Unfortunately, KVSs have demonstrated a gap between achieved and available performance, QoS, and energy efficiency on commodity platforms. Two research thrusts have focused on improving key-value performance: hardware-centric research has started to explore specialized platforms for KVSs, and software-centric research revisited the KVS application to address fundamental software bottlenecks. Unlike prior research focusing on hardware or software in isolation, the authors aimed to full-stack (software through hardware) architect high-performance and efficient KVS platforms. Their full-system characterization identifies the critical hardware/software ingredients for high-performance KVS systems and suggests optimizations to achieve record-setting performance and energy efficiency: 120~167 million requests per second (RPS) on a single commodity server. They propose a future many-core platform and via detailed simulations demonstrate the capability of achieving a billion RPS with a single server platform.

FluxEngine: A Flexible Processing System for Calculating Atmosphere–Ocean Carbon Dioxide Gas Fluxes and Climatologies

AbstractThe air–sea flux of greenhouse gases [e.g., carbon dioxide (CO2)] is a critical part of the climate system and a major factor in the biogeochemical development of the oceans. More accurate and higher-resolution calculations of these gas fluxes are required if researchers are to fully understand and predict future climate. Satellite Earth observation is able to provide large spatial-scale datasets that can be used to study gas fluxes. However, the large storage requirements needed to host such data can restrict its use by the scientific community. Fortunately, the development of cloud computing can provide a solution. This paper describes an open-source air–sea CO2 flux processing toolbox called the “FluxEngine,” designed for use on a cloud-computing infrastructure. The toolbox allows users to easily generate global and regional air–sea CO2 flux data from model, in situ, and Earth observation data, and its air–sea gas flux calculation is user configurable. Its current installation on the Nephalae Cloud allows users to easily exploit more than 8 TB of climate-quality Earth observation data for the derivation of gas fluxes. The resultant netCDF data output files contain >20 data layers containing the various stages of the flux calculation along with process indicator layers to aid interpretation of the data. This paper describes the toolbox design, which verifies the air–sea CO2 flux calculations; demonstrates the use of the tools for studying global and shelf sea air–sea fluxes; and describes future developments.

SDN orchestration architectures and their integration with Cloud Computing applications

Emerging cloud-based applications, running in geographically distributed data centers (DCs), generate new dynamic traffic patterns which claim for a more efficient management of the traffic flows. Geographically distributed DCs interconnection requires automatic and more dynamic provisioning and deletion of end-to-end (E2E) connectivity services, through heterogeneous network domains. Each network domain may use a different data transport technology but also a different control/management system. The fast development of Software Defined Networking (SDN) and the interworking with current control plane technologies such as Generalized Multi-protocol Label Switching (GMPLS), demand orchestration over the heterogeneous control instances to provide seamless E2E connectivity services to external applications (i.e. Cloud Computing applications).In this work, we present different orchestration architectures based on the SDN principles which use the Path Computation Element (PCE) as a fundamental component. In particular, a single SDN controller orchestration approach is compared with an orchestration architecture based on the Application Based Network Operations (ABNO) defined within the International Engineering Task Force (IETF), in order to find the potential benefits and drawbacks of both architectures. Finally, the SDN IT and Network Orchestration (SINO) platform which integrates the management of Cloud Computing infrastructure with the network orchestration, it is used to validate both architectures by evaluating their performance providing two inter-DC connectivity services: E2E connectivity and Virtual Machine (VM) migration.

A Survey on Resiliency Techniques in Cloud Computing Infrastructures and Applications

Today’s businesses increasingly rely on cloud computing, which brings both great opportunities and challenges. One of the critical challenges is resiliency: disruptions due to failures (either accidental or because of disasters or attacks) may entail significant revenue losses (e.g., US$ 25.5 billion in 2010 for North America). Such failures may originate at any of the major components in a cloud architecture (and propagate to others): 1) the servers hosting the application; 2) the network interconnecting them (on different scales, inside a data center, up to wide-area connections); or 3) the application itself. We comprehensively survey a large body of work focusing on resilience of cloud computing, in each (or a combination) of the server, network, and application components. First, we present the cloud computing architecture and its key concepts. We highlight both the infrastructure (servers, network) and application components. A key concept is virtualization of infrastructure (i.e., partitioning into logically separate units), and thus we detail the components in both physical and virtual layers. Before moving to the detailed resilience aspects, we provide a qualitative overview of the types of failures that may occur (from the perspective of the layered cloud architecture), and their consequences. The second major part of the paper introduces and categorizes a large number of techniques for cloud computing infrastructure resiliency. This ranges from designing and operating the facilities, servers, networks, to their integration and virtualization (e.g., also including resilience of the middleware infrastructure). The third part focuses on resilience in application design and development. We study how applications are designed, installed, and replicated to survive multiple physical failure scenarios as well as disaster failures.

Mobile Cloud Computing Model and Big Data Analysis for Healthcare Applications

Mobile devices are increasingly becoming an indispensable part of people’s daily life, facilitating to perform a variety of useful tasks. Mobile cloud computing integrates mobile and cloud computing to expand their capabilities and benefits and overcomes their limitations, such as limited memory, CPU power, and battery life. Big data analytics technologies enable extracting value from data having four Vs: volume, variety, velocity, and veracity. This paper discusses networked healthcare and the role of mobile cloud computing and big data analytics in its enablement. The motivation and development of networked healthcare applications and systems is presented along with the adoption of cloud computing in healthcare. A cloudlet-based mobile cloud-computing infrastructure to be used for healthcare big data applications is described. The techniques, tools, and applications of big data analytics are reviewed. Conclusions are drawn concerning the design of networked healthcare systems using big data and mobile cloud-computing technologies. An outlook on networked healthcare is given.

Cloud Computing and IT Infrastructure Outsourcing

Cloud Computing has caught the imagination of the CIOs across the world with rapid scalability being the most important feature of Cloud Computing, with very high degree of provisioning capability from the Cloud vendors in comparison to on premise IT infrastructure. It provides for the shift of spend from capital expenditure in IT budgets to a more flexible and manageable operating expenditure for the CIOs. However, as an emergent technology, there are initial adoption level concerns that are associated with Cloud Computing in most of the companies. Infrastructure as a Service or (IaaS) adoptions have not been high especially in the large companies which continue to opt for traditional IT Infrastructure Outsourcing. This paper compares Cloud Computing (Infrastructure as a Service - IaaS) adoption, outlined through two cases of Cloud (IaaS), with traditional IT Infrastructure Outsourcing outlined through four cases studies of traditional IT Outsourcing.

CBC2: A Cloud-based Botnet Command and Control

The most important issue for a Bot is to conceal its commander source so that the analyzer could not find the commander if the Bot is under analysis. In this paper we propose a mechanism for managing the Botnet C&C communication based on Cloud Computing infrastructures. The proposed mechanism provides a hierarchical organization of managerial nodes while all of these nodes are deployed on current Cloud providers. The main goal of this paper is to introduce the new threats that can be utilized by malware developers as a persistence mechanism. To evaluate our work, we have, semi-formally, analyzed four features (Stealthy, Effectiveness, Efficiency, and Robustness) of the mechanism and show that in most of the times the C&C can remain anonymous. Since, knowing the future threads is the best way to prepare for, and then the paper represents the possible countermeasures against the proposed mechanism.Keywords: BotCloud, Botnets, Botnet Persistence Mechanism, Cloud-based Botnet, Cloud-based C&C

Guest editorial: large-scale Web virtualized environment

Virtualization-based paradigms like cloud computing provide a powerful model that allows to simply and securely connect users to information resources on-demand and anywhere. Modern Web applications are increasingly hosted in a cloud-computing infrastructure, able to communicate and interact with external mobile devices. Such applications should dynamically scale in response to changes in the workload to guarantee service level agreements. This trend brought about a number of new modeling, design and implementation issues for Web applications. Solving these key issues requires both first-class theoretical research and careful experimental evaluation to show that model predictions are faithful to observed application behavior. Results need to be validated in the context of hybrid provisioning on multiple, heterogeneous virtualized platforms and cloud stacks. In particular, Web-based information systems rely on models and tools for representing, integrating and linking data or resources from heterogeneous sources or platforms. This special issue received many submissions from researchers and practitioners working on Web environments analyzing the impact of virtualization on them. After two rounds of review, eventually eight high quality papers were chosen. The paper titled “MUBaaS: Mobile Ubiquitous Brokerage as a Service” presents a cloudbased application middleware, called Mobile Ubiquitous Brokerage as a Service (MUBaaS), which enables n-devices of a user to access multiple cloud services endpoints in soft-real time. This is achieved by proposing distributed brokers that coordinates the transactions of the user while taking load balancing into account. Pilot evaluations of the proposed architecture prove real-time application synchronization with reasonable scalability. The use of multiple World Wide Web (2016) 19:1–3 DOI 10.1007/s11280-015-0366-9

Android Application to Enhance Performance of Internship Program Implementing Cloud Computing Platform and Infrastructure

Cloud computing is a model for enabling convenient, on-demand network access to the shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services). It can be operated efficiently with minimal management effort or service provider interaction. The objective of this study was to improve performance of a mobile application by developing a new system to manage the internship program of senior students at the university level. This application runs on Android OS and using Cloud computing platform and infrastructure to replace the existing one that was using local or university database server and infrastructure. The result of this study created a new version of mobile application which is more agile, less cost and more productive than the existing one by implementing Cloud computing platform and infrastructure. Moreover, it can increase performance to monitor activities of each intern, provide online guidance from intern's advisors and finally it can summarize score of each intern according to the university rubric, all data above are handled and stored on Mobile Cloud Server.

Bandit Framework for Systematic Learning in Wireless Video-Based Face Recognition

Video-based object or face recognition services on mobile devices have recently garnered significant attention, given that video cameras are now ubiquitous in all mobile communication devices. In one of the most typical scenarios for such services, each mobile device captures and transmits video frames over wireless to a remote computing cluster (a.k.a. “cloud” computing infrastructure) that performs the heavy-duty video feature extraction and recognition tasks for a large number of mobile devices. A major challenge of such scenarios stems from the highly varying contention levels in the wireless transmission, as well as the variation in the task-scheduling congestion in the cloud. In order for each device to adapt the transmission, feature extraction and search parameters and maximize its object or face recognition rate under such contention and congestion variability, we propose a systematic learning framework based on multi-user multi-armed bandits. The performance loss under two instantiations of the proposed framework is characterized by the derivation of upper bounds for the achievable short-term and long-term loss in the expected recognition rate per face recognition attempt against the “oracle” solution that assumes a-priori knowledge of the system performance under every possible setting. Unlike well-known reinforcement learning techniques that exhibit very slow convergence when operating in highly-dynamic environments, the proposed bandit-based systematic learning quickly approaches the optimal transmission and cloud resource allocation policies based on feedback on the experienced dynamics (contention and congestion levels). To validate our approach, time-constrained simulation results are presented via: (i) contention-based H.264/AVC video streaming over IEEE 802.11 WLANs and (ii) principal-component based face recognition algorithms running under varying congestion levels of a cloud-computing infrastructure. Against state-of-the-art reinforcement learning methods, our framework is shown to provide $17.8\%\sim 44.5\%$ reduction of the number of video frames that must be processed by the cloud for recognition and $11.5\%\sim 36.5\%$ reduction in the video traffic over the WLAN.

A Survey on Virtual Network Embedding in Cloud Computing Centers

Bridging virtualized environments with physical environments, virtual network plays an important role in Cloud Computing infrastructures. How to allocate physical resources for virtual nodes/links to construct virtual network is known as Virtual Network Embedding (VNE) problem. It is a crucial issue that draws wide attention. This paper surveys existing VNE methods and algorithms and how they work under different application scenarios. First, a survey of differ- ent VNE objective metrics is presented; then several VNE algorithms are presented and categorized; finally, the perfor- mance of different VNE solutions are compared and discussed.

A Stochastic Model to Investigate Data CenterPerformance and QoS in Iaas CloudComputing Systems

Cloud data center management is a key problem due to the numerous and heterogeneous strategies that can be applied, ranging from the VM placement to the federation with other clouds. Performance evaluation of Cloud Computing infrastructures is required to predict and quantify the cost-benefit of a strategy portfolio and the corresponding Quality of Service (QoS) experienced by users. Such analyses are not feasible by simulation or on-thefield experimentation, due to the great number of parameters that have to be investigated. In this paper, we present an analytical model, based on Stochastic Reward Nets (SRNs), that is both scalable to model systems composed of thousands of resources and flexible to represent different policies and cloud-specific strategies. Several performance metrics are defined and evaluated to analyze the behavior of a Cloud data center: utilization, availability, waiting time, and responsiveness. A resiliency analysis is also provided to take into account load bursts. Finally, a general approach is presented that, starting from the concept of system capacity, can help system managers to opportunely set the data center parameters under different working conditions.

Spatial Tools for Supporting Regional e-Entrepreneurship

Abstract The paper studies the subject of exploiting GIS technology to support regional e-undertakings. The paper has been drawn up on the basis of a research conducted by team of the authors from the district of Czestochowa. The research resulted in elaboration of the concept of Regional Business Spatial Community (RBSC). The authors propose the establishment of e-community using Geographic Information Systems (GIS) accessible via the Cloud Computing infrastructure enhanced with online community software. The research reveal that the most predestinated unit for the role of a coordinator of the proposed undertaking is the Office of the City of Czestochowa having adequate legal standing, experience and authority coupled with the proper GIS software. The supportive role of domain experts has been reserved to the scientists from the Czestochowa University of Technology. There are also other organizations that should take part in the project – the companies supplying utilities for the City of Czestochowa. The aim of the project is an elaboration of comprehensive software platform facilitating the public utility infrastructure investments in the city. The project encompasses choosing and preparing the proper ICT tools for RBSC, elaboration of the procedures of needed investments and indicating rules of sharing the GIS software and spatial information among the stakeholders.

An Iaas Cloud System with FederationThreshold

Cloud information center management may be a key downside as a result of the various and heterogeneous methods which will be applied, starting from the VM placement to the federation with different clouds. Performance analysis of Cloud Computing infrastructures is needed to predict and quantify the cost-benefit of a method portfolio and therefore the corresponding Quality of Service (QoS) toughened by users. Such analyses aren't possible by simulation or on-the-field experimentation, as a result of the good variety of parameters that have to be compelled to be investigated. during this paper, we have a tendency to gift AN analytical model, supported random Reward Nets (SRNs), that's each ascendable to model systems composed of thousands of resources and versatile to represent totally different policies and cloud-specific methods. Many performance metrics ar outlined and evaluated to research the behavior of a Cloud information center: utilization, convenience, waiting time, and responsiveness. A resiliency analysis is additionally provided to require under consideration load bursts. Finally, a general approach is given that, ranging from the thought of system capability, will facilitate system managers to opportunely set the info center parameters below totally different operating conditions.

New Framework to Detect and Prevent Denial of Service Attack in Cloud Computing Environment

Cloud computing is the new buzz word in computer oriented services and in IT industry. But, even now cloud computing is in its infancy, there numerous challenges like performance, security, availability, etc. The infrastructure of cloud computing is potentially shared by millions of users , Denial of Service (DoS) attacks have become a major threat to cloud computing where it prevents the users from using cloud infrastructure services and this kind of attack can be made through legitimate or illegitimate cloud computing users. There are several approaches which have been proposed to overcome this DoS attack but most of these approaches gives attention to one only part of the problem and ignoring the other parts of the problem. In this paper, I propose a framework which concentrates on overcoming all the aspects of the problem, monitoring the flow of SYN packets by using a correlation engine or a flow traffic tool like snort, wireshark, is used for attack detection stage and to find the attack source, the time to live (TTL) and packet marking technique is used and for preventing, a honeypot method is used . I have also proposed a framework experimenting test bed for deploying this framework.

Ceph as WAN Filesystem – Performance and Feasibility Study through Simulation

Recent development in object based distributed file systems (DFS) such as Ceph, GlusterFS as well as the more established ones like Lustre, GPFS, etc. have presented new opportunities to setup next generation of storage infrastructure for cloud computing, big data, and Internet of Things (IoT). However, existing DFSs are typically deployed to Local Area Network (LAN) and generally used for high-performance computing. Extending these DFSs into geographically distributed sites such as Campus Area Network (CAN) and Wide Area Network (WAN) for enterprise applications presents completely different set of challenges and issues. Unlike most implementations that choose a traditional multi sites deployment, i.e., each site implements a virtual storage (via LAN) and links through RESTful APIs (via WAN), we attempt to create a single virtual storage over WAN using Ceph. In this paper, we demonstrate that a properly designed and configured virtualized environment is a valuable tool for researchers to simulate a distributed files system over WAN without an actual physical environment. By following a few guidelines, the read and write performance results in a simulated environment can indicate the trending of the read and write performance in the actual physical environment. This implies that the storage design can be verified prior to actual deployment and establish a performance baseline. An obvious benefit is the initial investment of a storage solution is lower. Furthermore, this paper discuss about the challenges of setting up such environment, the feasibility of using Ceph as a single virtual store, and some possible future works.

If you want to know about a hunter, study his prey: detection of network based attacks on KVM based cloud environments

Computational systems are gradually moving towards Cloud Computing Infrastructures, using the several advantages they have to offer and especially the economic advantages in the era of an economic crisis. In addition to this revolution, several security matters emerged and especially the confrontation of malicious insiders. This paper proposes a methodology for detecting the co-residency and network stressing attacks in the kernel layer of a Kvm-based cloud environment, using an implementation of the Smith-Waterman genetic algorithm. The proposed approach has been explored in a test bed environment, producing results that verify its effectiveness.

Design of Simulator for Cloud Computing Infrastructure and Service

Cloud computing that provides computational resource, platform and software as services is operated in cluster that is comprised of hundreds or thousands of servers. Thus, cloud computing providers may use various policies such as complex resource provisioning, allocation, configuration, and so on, to efficiently manage huge resources. In this environment, it is difficult to customize circumstance and to test and evaluate a hypothesis independently. To overcome these limitations, we provide SimCloudIS: simulator for cloud computing infrastructure and service. The SimCloudIS provides cloud system components such as the datacenter, host, VM, application, network and scheduling polices that are extendable and managed in independent layers. The network component supports packet based network communication which is based on the real network model, thereby facilitating simulation of internet based services. For evaluation, SimCloudIS provides a monitor that observes the status of all components and records them. The usefulness of SimCloudIS is demonstrated by involving a case study for dynamic allocation and relocation of VMs in a cloud environment and analyzing the result.

Wireless Data Center Management: Sensor Network Applications and Challenges

The modern data centers (DCs) are essential to fulfilling ever-evolving computational demands around cloud computing, big data, and IT infrastructure. These DCs are facilities (Figure 1) that house computer systems and associated components such as networking and storage systems. To operate a DC, power supplies, network connections, environmental controls (e.g., air conditioning, humidity), and security infrastructure are needed. Technology and business challenges such as virtualization, load consolidation, real-time troubleshooting, and service-level guarantees require a robust and adaptive server management plan for enterprise. The majority of DC issues are related to overutilization of resources, application failures, data security, power usage effectiveness (PUE), and infrastructure costs. This requires proactive solutions that are business intelligent and built over a network of sense points that are guaranteed to deliver reliable trends and measurements in a reliable and timely fashion. Since it is expensive to build new DCs, the best option is to improve usage of an existing facility through lower infrastructure overhead to deliver better resource management. An optimal sensor network would perform real-time sensor-data collection and deliver a) improved server rack utilization, b) improved DC cooling, and c) improved loadbalancing through dynamic capping of thermally constrained systems.