International Journal of Cloud Computing (15 papers in press)
Task Scheduling and Virtual Resource Optimizing in Hadoop YARN-based Cloud Computing Environment
by Frederic Nzanywayingoma
Abstract: we are living in the data world where a high volume of data is changing the way things used to be in traditional IT industry. Big Data is being generated everywhere around us at all times by cameras, mobile devices, sensors, and software logs with large amount of data in units of hundreds of terabytes to petabytes. Therefore, to analyze these massive data, new skills, intensive applications and storage clusters are needed. Apache Hadoop is one of the most recently popular tools developed for big data processing. It has been deployed by many giant companies to stream large files in big datasets. The main purpose in this paper is to analyze different scheduling algorithms that can help to achieve better performance, efficiency and reliability of Hadoop YARN environment. We describe some task schedulers which consider different levels of Hadoop such as FIFO (First In First Out) scheduler, fair scheduler, delay scheduler, deadline constraint scheduler, dynamic priority scheduling, capacity scheduler, and we analyze the performance of these widely used Hadoop task schedulers based on the following elements: makespan; turnaround time; and throughput. A reliable scheduling algorithm is suggested which can work efficiently in Hadoop environments. To conclude this paper, the experimental results were given.
Keywords: Hadoop; MapReduce; Task Scheduling; YARN; HDFS; JobTracker; TaskTracker.
Special Issue on: ICA CON 2016 & 2017 A Collaborative Community of Leaders Cloud Computing in Education
Extreme Value Analysis for Capacity Design
by Szilard Bozoki, Andras Pataricza
Abstract: Cloud computing has become the fundamental platform for service offerings. Such services frequently face peaks in their variable workload. Thus, the cloudification of critical applications with strict Service Level Agreements (e.g. performability) need a properly engineered capacity to withstand peak loads. A core problem is the prediction of the value of peaks, especially in bursty workloads. They originate in the cumulative effect of hard-to-predict rare and extreme events. Luckily, system monitoring collects enough vital information for a prediction by statistical methods. Extreme value analysis focuses on the prediction of future peaks.
This paper investigates the use of extreme value theory for capacity planning in cloud platforms and services and assesses the technical metrology aspects as well.
Keywords: cloud computing; performability engineering; capacity design; extreme value analysis; Facebook Prophet.
Enhancing NoSQL datastores with fine-grained context-aware access control: a preliminary study on MongoDB
by Pietro Colombo, Elena Ferrari
Abstract: NoSQL datastores are getting increasing attention by companies
and organization for the ease and efficiency of handling high volumes of
heterogeneous and unstructured data. Nowadays the majority of these systems
are available as cloud based services, this potentially favors their use even
among small companies that could not afford the management of server farms
for local cluster based solutions. However, besides all their benefits in terms
of performance, availability and scalability as well as support for advanced
analysis forms, NoSQL datastores also have some weaknesses, such as poor
natively provided support for data protection. Recent surveys show that several
companies consider the poor support for security features of NoSQL databases
as a valid reason not to use them . In this paper, we do a first step
to overcome these weaknesses by first proposing a roadmap to enhance the
data protection functionalities of NoSQL datastores. Then, we illustrate our
preliminary experience of designing an enhanced access control mechanism for
MongoDB (http://www.mongodb.org), which, according to recent surveys 
ranks as the most popular NoSQL database.
Keywords: NoSQL datastores; Context awareness; Fine grained access control; MongoDB.
Towards Standard PaaS Implementation APIs
by Eman Hossny, Sherif Khattab, Fatma Omara, Hesham Hassan
Abstract: Platform as a Service (PaaS) supports application developers with the ability to implement and deploy their applications in the cloud. Several heterogeneous PaaS platforms are available, such as Google AppEngine (GAE), Windows Azure, Cloud Foundry, and OpenShift. Each PaaS provider has its own proprietary implementation and deployment APIs. The heterogeneity of these APIs makes developers worry about their application portability and interoperability. The work in this paper concerns about the heterogeneity of different PaaS implementation APIs. Standard PaaS implementation APIs, called Std-PaaS APIs, have been proposed to solve the application portability problem. Std-PaaS APIs allow developers to develop generic cloud application by writing their applications once and deploying many times on heterogeneous PaaS providers. Std-PaaS APIs have been evaluated using two case studies, in which generic APIs for cloud persistent-storage service and NoSQL datastore service have been developed and used to develope applications to be deployed onto GAE and Windows Azure.
Keywords: PaaS; Vendor lock-in; Standard API.
About PaaS Security
by Donghoon Kim, Henry Schaffer, Mladen Vouk
Abstract: Platform as a Service (PaaS) provides middleware resources to cloud customers. As demand for PaaS services increases, so do concerns about the security of PaaS. This paper discusses principal PaaS security and integrity requirements, and vulnerabilities and the corresponding countermeasures. We consider three core cloud elementsmulti-tenancy, isolation, and virtualization and how they relate to PaaS services and security trends and concerns such as user and resource isolation, side-channel vulnerabilities in multi-tenant environments, and protection of sensitive data.
Keywords: Cloud computing; Security Vulnerability; Countermeasures; PaaS; Multi-tenancy; Isolation; Viturlization; Data security & Integrity; Big data.
Optimized deployment of critical applications in Infrastructure-as-a-Service clouds
by Imre Kocsis, Zoltán Ádám Mann, Dávid Zilahi
Abstract: In this paper, we extend the classic data center allocation optimization problem for critical tenant applications that need guarantees on the required resource capacities. We identify a set of representative, user-issuable constraints and new optimization objectives and establish a mathematical and corresponding integer programming formulation. Using a typical Network Function Virtualization application as a case study, we show the viability of the approach and present an initial scalability assessment. Our results demonstrate the advantage of combining the conflicting objectives of the tenants and the provider in a single optimization problem.
Keywords: data center allocation optimization; virtual machine placement; Infrastructure as a Service; integer linear programming; Network Function Virtualization; deployment of critical applications.
UniConnect: A Hosted Collaboration Platform for the Support of Teaching and Research in Universities
by Soehnke Grams
Abstract: Between 2003 and 2013 the number of students in Germany has risen by 29.58 (Statistisches Bundesamt, 2015). Due to a lack of resources, lecturers and funding, the active involvement of this increasing amount of students has become a difficult endeavour. The possibilities of an activating learning approach are limited due to courses with mass event characteristics and a uni-directional communication flow from the lecturer to the students. Against this backdrop, UniConnect provides a possible solution to this challenge in providing a collaboration platform based on IBM Connections, which is hosted by the University Competence Center for Collaboration Technologies (UCT). This paper describes the UniConnect platform and the initiative behind it and provides a use case for how IBM Connections can be successfully used to support teaching and research. The initiative can also be seen as a best practice example for a partnership between a university and specialised company partners in the software industry.
Keywords: collaboration; education; university; cscw; digital workplace; IBM; GIS; ISW.
Data Analysis Based Capacity Planning of VCL Clouds
by Agnes Salanki, Gergő Kincses, Laszlo Gonczy, Imre Kocsis
Abstract: Virtual computing labs dramatically changed education methodology with transforming traditional classroom- and lab-based learning models to selfpaced asynchronous ones. The Apache Virtual Computing Lab (VCL) platform allows students to reserve and use virtual machines (VMs) with a predefined configuration and software setup. In essence, it offers an educational cloud that provides preconfigured lab environments in Desktop as a Service style. At our university, four courses of a specialization branch are available in this form. While maintaining VCL, we faced the challenges of short- and longterm capacity planning. We analyzed high-level reservation and platform-level monitoring data of five semesters and built mathematical models of workload and resource utilization based on our observations. The main contribution of this study are data-driven approaches for (i) prediction reservation patterns of students as course deadlines approach; (ii) a regressionbased estimate of typical resource utilization of VMs; (iii) elaboration of an optimized schedule of deadlines to avoid rejected reservation queries or a burst out to a public cloud. Applying these methods, fine-tuning of VM configurations and scheduling of upcoming semesters became possible, even in case of methodical/technical educational changes (e.g. modified course schedules, increasing number of attendees.
Keywords: VCL; Educational cloud; Capacity planning; Workload shaping; Linear regression; User behavior prediction.
Containerization in VCL using Docker
by Young-Hyun Oh
Abstract: Apache Virtual Computing Lab (VCL) has been widely used by academic areas because it is a free, open-source, and general-purpose cloud computing platform that supports various types of provisioning modules including physical bare-metal machines, lab computers, and virtual machines hosted on several different hypervisors. Since VCL was flexibly designed from the beginning, it can support a new cloud computing platform by simply adding a new modularly constructed code for the platform to VCL. To increase the accessibility and scalability of VCL, this paper introduces a containerization technique in VCL using Docker. We present a new development of a Docker provisioning module for VCL that takes the advantages of the state-of-the-art containerization technique. Unlike traditional hypervisor virtualization, Docker removes the overhead for the additional emulation or hypervisor layer. Instead Docker adds an application deployment engine on top of the virtualized container execution environment and uses the operating system's normal system call interface to run containers. Thus, our Docker VCL provisioning module can provide faster startup and be more efficient than other hypervisor-based VCL provisioning modules.
Keywords: VCL; docker; containerization; provisioning; cloud computing platform.
Cloud-based Environment in Support of IoT Education
by Anand Singh, Yannis Viniotis
Abstract: Students taking an IoT curriculum need to acquire skills (among others) in areas as (a) developers of IoT applications, (b) architects of IoT systems, and, (c) administrators of such systems. At North Carolina State University, we have developed a cloud-based environment to support the development of such skills. The environment is based on IBMs Watson IoT Cloud Platform and uses components such as Intels Edison Boards, Raspberry Pis, Cisco IoT gateways, TI boards, sensors/actuators, and GitHub, to give students an end-to-end experience in all aspects of IoT solution and system development. In this paper, we discuss the challenges we faced, how we overcame them, feedback from students and plans for our next steps.
Keywords: IoT systems; Cloud platforms; Edge Computing; Curriculum development.
Special Issue on: ICBDCC2017 Big Data and Cloud Computing Technologies
A New Key Generation Technique Using GA for Enhancing Data Security in Cloud Environment
by D. I. George Amalarethinam, H.M. LEENA
Abstract: Cloud computing is the distributed and centralized network with the collection of interconnected systems with a provision of providing the resources based on pay-per-use. This facility of ubiquitous computing attracts the user towards the usage of various services. One of the major issues in cloud is Security. When the users deploy the services for storing their sensitive data in the cloud, protecting their data is a crucial task. Cryptography plays an important role in securing data. Symmetric algorithms of Cryptography are more suitable when large amount of data is to be stored. Instead Asymmetric algorithms are preferred for encrypting the keys rather than the data because of its less speed. The technique for generating or selecting the key plays a vital role in securing the data. Genetic Algorithms is a powerful tool for solving the most of the optimization problems like The Traveling Salesperson Problem, Knapsack Problem, Scheduling Problem etc., The proposed Genetic algorithm is used for generating a best key which satisfies the specified fitness function. The generated key is sent to the Asymmetric Addition Chaining Cryptographic Algorithm (ACCA) for encryption. The encrypted key can be used by any one of the Symmetric Algorithms like AES, DES, Blowfish for encrypting large volume of data.
Keywords: Cloud Computing; Security; Cryptography; Encryption; Key Generation; Genetic Algorithms; Optimization Problems; Fitness Function; Data Security; Addition Chaining.
Confidential Storage of Medical Images A Chaos Based Encryption Approach
by Mohamed Parvees M Y, Abdul Samath J, Parameswaran Bose B
Abstract: The recent developments in telehealth increase the demands of clinical and non-clinical services which lead to work on medical image security to provide better teleradiology services. One of the mandatory characteristics of the image security is confidentiality. The traditional block and stream ciphers are suitable for encrypting small data or the file which is not having redundant information. Hence, this study proposes an encryption algorithm to provide confidentiality to medical images using chaotic maps. The different enhanced chaotic economic maps (ECEM) are derived by substituting sine and cosine functions in basic chaotic economic map (CEM) equation. The ECEMs are studied in detail with respect to their bifurcate nature and Lyapunov exponents to achieve greater robustness in encryption. The improved maps generate different chaotic sequences which are employed in confusing, swapping and diffusing 16-bit DICOM image pixels, thereby assure confidentiality. After scrambling, the different security analyses such as statistical, entropy, differential, key space, key sensitivity, cropping attack, noise attack, decryption efficacy analysis are performed to prove the effectiveness of the proposed algorithm.
Keywords: Patient confidentiality; Chaotic map; DICOM encryption; Medical images.
A Secure Encryption Scheme based on Certificateless Proxy Signature
by Sudharani Kamaraj
Abstract: Certificateless Public Key Cryptography (CL-PKC) scheme is introduced for solving the key escrow problems in the identity-based cryptography and eliminate the use of security certificates. By introducing the proxy signature concept in the certificateless cryptography scheme, this Certificateless Proxy Signature (CLPS) scheme has attracted the attention of more researchers. However, this scheme suffers due to the security issues and fails to achieve the unforgeability against the attacks. To overcome the security issues in the existing cryptographic scheme, this paper proposes an encryption scheme based on the certificateless proxy signature for sharing the sensitive data in the public cloud in a secure manner. The proposed scheme is proven to be unforgeable against the message attacks. When compared with the existing CLPS scheme without random oracles, the proposed scheme offers better data security while ensuring better data sharing performance. From the experimental Results, it was noticed that the proposed scheme requires minimum encryption and decryption time than that of existing scheme.
Keywords: : Access Control; Cloud computing; Certificateless Public Key Cryptography (CL-PKC); Data Confidentiality; Malicious KGC Attack; Proxy Signature; Public Key Replacement Attack.
Automatic Cloud Service Monitoring and Management with Prediction based Service Provisioning
by Kirit Modi
Abstract: Cloud computing provides an efficient, on-demand and scalable environment for the benefit of end users by offering cloud services as per SLAs (Service Level Agreement) on which both user and cloud service providers are mutually agreed. As the number of cloud users is increasing day by day, sometimes cloud service providers unable to offer service as per SLA which results in SLA violation. To detect SLA violation and to fulfill the user requirements from the service provider, cloud services should be monitored. The current cloud service provision based on the current workload. Due to unexpected future demands by the customers, the cloud service provider may not able to maintain the QoS what they promised and lead to SLA violations. Thus, it is needed to predict the future requirement of the customer and based on that cloud service provisioning must be done. Cloud service monitoring plays a critical role for both the customers and service providers as monitoring status helps service provider to improve their services at the same time it also helps the customers to know whether they are receiving the promised QoS or not as per the SLA. Most existing cloud service monitoring frameworks are developed towards service provider side. This raises the question of correctness and fairness of monitoring mechanism on the other hand if monitoring is applied at user side then it would become overhead to the clients. To manage such issue, an ontology based Automatic Cloud Services Monitoring and Management (ACSMM) with prediction based service provisioning approach is proposed in this paper, where cloud service monitoring and management is performed at cloud broker, which is an intermediate entity between the user and service provider. In this approach, when SLA violation is detected, it sends alert to both clients and service providers, and also generates the status report. Based on the status report, broker automatically reschedules the tasks to reduce the further SLA violation. In our framework, the cloud service provisioning is based on the predicting the future demands so that cloud service provider can handle the unexpected resources demands of the customers which will reduce the SLA violations.
Keywords: Cloud Service Monitoring; Service Level Agreement; Cloud Service; Ontology;Rescheduling; Prediction based Service Provisioning.
Special Issue on: ICA CON 2016 & 2017 A Collaborative Community of Leaders Cloud Computing in Education
Integrating Mobile Internet of Things and Cloud Computing towards Scalability: Lessons Learned from Existing Fog Computing Architectures and Solutions
by Paolo Bellavista, Antonio Corradi, Alessandro Zanni
Abstract: The primary objective of this paper is to present a fresh overview of the very recent literature about the integration of Mobile Internet of Things (MIoT) and cloud computing towards scalability, by specifically concentrating on solutions based on the exploitation of edge computing capabilities (fog computing) to effectively integrate device localities with the global cloud resources. In addition to surveying the state-of-the-art of fog computing for MIoT and cloud integration, the paper will propose an original architecture and classification of possible solutions in the field, by reporting lessons learned from the few existing experiences and by shedding new light on specific sub-fields of research where advancements are needed to effectively integrate huge numbers of geographically dispersed mobile devices and globally available cloud resources.
Keywords: Cloud Computing; Fog Computing; Internet of Things (IoT); Mobile IoT Support; Scalability.