arXiv subjects
Publications and source records attributed to Rajkumar Buyya.
The chapter presents foundations of computing paradigms for realizing emerging IoT applications, especially fog and edge computing, their background, characteristics, architectures and open challenges.
Network slicing allows network operators to build multiple isolated virtual networks on a shared physical network to accommodate a wide variety of services and applications. With network slicing, service providers can provide a cost-efficient solution towards meeting diverse performance requirements of deployed applications and services. Despite slicing benefits, End-to-End orchestration and management of network slices is a challenging and complicated task. In this chapter, we intend to survey all the relevant aspects of network slicing, with the focus on networking technologies such as Software-defined networking (SDN) and Network Function Virtualization (NFV) in 5G, Fog/Edge and Cloud Computing platforms. To build the required background, this chapter begins with a brief overview of 5G, Fog/Edge and Cloud computing, and their interplay. Then we cover the 5G vision for network slicing and extend it to the Fog and Cloud computing through surveying the state-of-the-art slicing approaches in these platforms. We conclude the chapter by discussing future directions, analyzing gaps and trends towards the network slicing realization.
Resource management in Fog computing is very complicated as it engages significant number of diverse and resource constraint Fog nodes to meet computational demand of IoT-enabled systems in distributed manner. Its integration with Cloud triggers further difficulties in combined resource management. Different sensing frequency of IoT devices, distributed application structure and their coordination also influence resource management in Fog computing environment. For advancement of Fog and its resource management, the necessity of extensive research in beyond question. To develop and evaluate different ideas and resource management policies, empirical analysis on Fog environment is the key. Since Fog computing environment incorporates IoT devices, Fog nodes and Cloud datacenters along with huge amount of IoT-data and distributed applications, real-world implementation of Fog environment for research will be very costly. Moreover, modification of any entity in real-world Fog environment will be tedious. In this circumstance, simulation of Fog computing environment can be very helpful. Simulation toolkits not only provide frameworks to design customized experiment environment but also assist in repeatable evaluation. In this chapter we focus on delivering a tutorial on iFogSim toolkit for modelling and simulating Fog computing environments. We believe this chapter will offer researchers a simplified way to apply iFogSim in their research works.
Containers are standalone, self-contained units that package software and its dependencies together. They offer lightweight performance isolation, fast and flexible deployment, and fine-grained resource sharing. They have gained popularity in better application management and deployment in recent years and are being widely used by organizations to deploy their increasingly diverse workloads such as web services, big data, and IoT in either proprietary clusters or cloud data centres. This has led to the emergence of container orchestration platforms, which are designed to manage the deployment of containerized applications in large-scale clusters. The majority of these platforms are tailored to optimize the scheduling of containers on a fixed-sized private cluster but are not enabled to autoscale the size of the cluster nor to consider features specific to public cloud environments. In this work, we propose a comprehensive container resource management approach that has three different objectives. The first one is to optimize the initial placement of containers by efficiently scheduling them on existing resources. The second one is to autoscale the number of resources at runtime based on the current cluster's workload. The third one is a rescheduling mechanism to further support the efficient use of resources by consolidating applications into fewer VMs when possible. Our algorithms are implemented as a plugin-scheduler for Kubernetes platform. We evaluated our framework and the effectiveness of the proposed algorithms on an Australian national cloud infrastructure. Our experiments demonstrate that considerable cost savings can be achieved by dynamically managing the cluster size and placement of applications. We find that our proposed approaches are capable of reducing the cost by 58% when compared to the default Kubernetes scheduler.
The requirement of supporting both latency sensitive and computing intensive Internet of Things (IoT) applications is consistently boosting the necessity for integrating Edge, Fog and Cloud infrastructure. Although there are a number of real-world frameworks attempt to support such integration, they have many limitations from various perspectives including platform independence, security, resource management and multi-application assistance. To address these limitations, we propose a simplified but effective framework, named FogBus for facilitating end-to-end IoT-Fog(Edge)-Cloud integration. FogBus offers a platform independent interface to IoT applications and computing instances for execution and interaction. It not only assists developers in building applications but also helps users in running multiple applications at a time and service providers to manage their resources. In addition, FogBus applies Blockchain, authentication and encryption techniques to secure operations on sensitive data. Because of its lightweight and cross platform software systems, it is easy to deploy, scalable and cost e_cient. We demonstrate the effectiveness of our framework by creating a computing environment with it that integrates finger pulse oximeter as IoT devices with Smartphone-based gateway and Raspberry Pi-based Fog nodes for Sleep Apnea analysis. We also run several experiments on this computing environment varying FogBus settings. The experimental results show that different FogBus settings can improve latency, energy, network and CPU usage of the computing infrastructure.
The Internet of Things (IoT) represents a comprehensive environment that consists of a large number of smart devices interconnecting heterogeneous physical objects to the Internet. Many domains such as logistics, manufacturing, agriculture, urban computing, home automation, ambient assisted living and various ubiquitous computing applications have utilised IoT technologies. Meanwhile, Business Process Management Systems (BPMS) have become a successful and efficient solution for coordinated management and optimised utilisation of resources/entities. However, past BPMS have not considered many issues they will face in managing large scale connected heterogeneous IoT entities. Without fully understanding the behaviour, capability and state of the IoT entities, the BPMS can fail to manage the IoT integrated information systems. In this paper, we analyse existing BPMS for IoT and identify the limitations and their drawbacks based on Mobile Cloud Computing perspective. Later, we discuss a number of open challenges in BPMS for IoT.
Containers, enabling lightweight environment and performance isolation, fast and flexible deployment, and fine-grained resource sharing, have gained popularity in better application management and deployment in addition to hardware virtualization. They are being widely used by organizations to deploy their increasingly diverse workloads derived from modern-day applications such as web services, big data, and IoT in either proprietary clusters or private and public cloud data centers. This has led to the emergence of container orchestration platforms, which are designed to manage the deployment of containerized applications in large-scale clusters. These systems are capable of running hundreds of thousands of jobs across thousands of machines. To do so efficiently, they must address several important challenges including scalability, fault-tolerance and availability, efficient resource utilization, and request throughput maximization among others. This paper studies these management systems and proposes a taxonomy that identifies different mechanisms that can be used to meet the aforementioned challenges. The proposed classification is then applied to various state-of-the-art systems leading to the identification of open research challenges and gaps in the literature intended as future directions for researchers.
Many algorithms in workflow scheduling and resource provisioning rely on the performance estimation of tasks to produce a scheduling plan. A profiler that is capable of modeling the execution of tasks and predicting their runtime accurately, therefore, becomes an essential part of any Workflow Management System (WMS). With the emergence of multi-tenant Workflow as a Service (WaaS) platforms that use clouds for deploying scientific workflows, task runtime prediction becomes more challenging because it requires the processing of a significant amount of data in a near real-time scenario while dealing with the performance variability of cloud resources. Hence, relying on methods such as profiling tasks' execution data using basic statistical description (e.g., mean, standard deviation) or batch offline regression techniques to estimate the runtime may not be suitable for such environments. In this paper, we propose an online incremental learning approach to predict the runtime of tasks in scientific workflows in clouds. To improve the performance of the predictions, we harness fine-grained resources monitoring data in the form of time-series records of CPU utilization, memory usage, and I/O activities that are reflecting the unique characteristics of a task's execution. We compare our solution to a state-of-the-art approach that exploits the resources monitoring data based on regression machine learning technique. From our experiments, the proposed strategy improves the performance, in terms of the error, up to 29.89%, compared to the state-of-the-art solutions.
The Cloud computing paradigm has revolutionised the computer science horizon during the past decade and has enabled the emergence of computing as the fifth utility. It has captured significant attention of academia, industries, and government bodies. Now, it has emerged as the backbone of modern economy by offering subscription-based services anytime, anywhere following a pay-as-you-go model. This has instigated (1) shorter establishment times for start-ups, (2) creation of scalable global enterprise applications, (3) better cost-to-value associativity for scientific and high performance computing applications, and (4) different invocation/execution models for pervasive and ubiquitous applications. The recent technological developments and paradigms such as serverless computing, software-defined networking, Internet of Things, and processing at network edge are creating new opportunities for Cloud computing. However, they are also posing several new challenges and creating the need for new approaches and research strategies, as well as the re-evaluation of the models that were developed to address issues such as scalability, elasticity, reliability, security, sustainability, and application models. The proposed manifesto addresses them by identifying the major open challenges in Cloud computing, emerging trends, and impact areas. It then offers research directions for the next decade, thus helping in the realisation of Future Generation Cloud Computing.
Due to the surge in the volume of data generated and rapid advancement in Artificial Intelligence (AI) techniques like machine learning and deep learning, the existing traditional computing models have become inadequate to process an enormous volume of data and the complex application logic for extracting intrinsic information. Computing accelerators such as Graphics processing units (GPUs) have become de facto SIMD computing system for many big data and machine learning applications. On the other hand, the traditional computing model has gradually switched from conventional ownership-based computing to subscription-based cloud computing model. However, the lack of programming models and frameworks to develop cloud-native applications in a seamless manner to utilize both CPU and GPU resources in the cloud has become a bottleneck for rapid application development. To support this application demand for simultaneous heterogeneous resource usage, programming models and new frameworks are needed to manage the underlying resources effectively. Aneka is emerged as a popular PaaS computing model for the development of Cloud applications using multiple programming models like Thread, Task, and MapReduce in a single container .NET platform. Since, Aneka addresses MIMD application development that uses CPU based resources and GPU programming like CUDA is designed for SIMD application development, here, the chapter discusses GPU PaaS computing model for Aneka Clouds for rapid cloud application development for .NET platforms. The popular opensource GPU libraries are utilized and integrated it into the existing Aneka task programming model. The scheduling policies are extended that automatically identify GPU machines and schedule respective tasks accordingly. A case study on image processing is discussed to demonstrate the system, which has been built using PaaS Aneka SDKs and CUDA library.
Dynamic nature of the cloud environment has made distributed resource management process a challenge for cloud service providers. The importance of maintaining the quality of service in accordance with customer expectations as well as the highly dynamic nature of cloud-hosted applications add new levels of complexity to the process. Advances to the big data learning approaches have shifted conventional static capacity planning solutions to complex performance-aware resource management methods. It is shown that the process of decision making for resource adjustment is closely related to the behaviour of the system including the utilization of resources and application components. Therefore, a continuous monitoring of system attributes and performance metrics provide the raw data for the analysis of problems affecting the performance of the application. Data analytic methods such as statistical and machine learning approaches offer the required concepts, models and tools to dig into the data, find general rules, patterns and characteristics that define the functionality of the system. Obtained knowledge form the data analysis process helps to find out about the changes in the workloads, faulty components or problems that can cause system performance to degrade. A timely reaction to performance degradations can avoid violations of the service level agreements by performing proper corrective actions including auto-scaling or other resource adjustment solutions. In this paper, we investigate the main requirements and limitations in cloud resource management including a study of the approaches in workload and anomaly analysis in the context of the performance management in the cloud. A taxonomy of the works on this problem is presented which identifies the main approaches in existing researches from data analysis side to resource adjustment techniques.
Big data applications involving the analysis of large datasets becomes a critical part of many emerging paradigms such as smart cities, social networks and modern security systems. Cloud computing has developed as a mainstream for hosting big data applications by its ability to provide the illusion of infinite resources. However, harnessing cloud resources for large-scale big data computation is application specific to a large extent. In this paper, we propose a system for large-scale fingerprint matching application using Aneka, a platform or developing scalable applications on the Cloud. We present the design and implementation of our proposed system and conduct experiments to evaluate its performance using resources from Microsoft Azure. Experimental results demonstrate that matching time for biometric information such as fingerprints in large-scale databases can be reduced substantially using our proposed system.
This paper proposes an architectural framework for the efficient orchestration of containers in cloud environments. It centres around resource scheduling and rescheduling policies as well as autoscaling algorithms that enable the creation of elastic virtual clusters. In this way, the proposed framework enables the sharing of a computing environment between differing client applications packaged in containers, including web services, offline analytics jobs, and backend pre-processing tasks. The devised resource management algorithms and policies will improve utilization of the available virtual resources to reduce operational cost for the provider while satisfying the resource needs of various types of applications. The proposed algorithms will take factors that are previously omitted by other solutions into consideration, including 1) the pricing models of the acquired resources, 2) and the fault-tolerability of the applications, and 3) the QoS requirements of the running applications, such as the latencies and throughputs of the web services and the deadline of the analytical and pre-processing jobs. The proposed solutions will be evaluated by developing a prototype platform based on one of the existing container orchestration platforms.
The cloud computing paradigm offers on-demand services over the Internet and supports a wide variety of applications. With the recent growth of Internet of Things (IoT) based applications the usage of cloud services is increasing exponentially. The next generation of cloud computing must be energy-efficient and sustainable to fulfil the end-user requirements which are changing dynamically. Presently, cloud providers are facing challenges to ensure the energy efficiency and sustainability of their services. The usage of large number of cloud datacenters increases cost as well as carbon footprints, which further effects the sustainability of cloud services. In this paper, we propose a comprehensive taxonomy of sustainable cloud computing. The taxonomy is used to investigate the existing techniques for sustainability that need careful attention and investigation as proposed by several academic and industry groups. Further, the current research on sustainable cloud computing is organized into several categories: application design, sustainability metrics, capacity planning, energy management, virtualization, thermal-aware scheduling, cooling management, renewable energy and waste heat utilization. The existing techniques have been compared and categorized based on the common characteristics and properties. A conceptual model for sustainable cloud computing has been proposed along with discussion on future research directions.
Disaster management demands a near real-time information dissemina-tion so that the emergency services can be provided to the right people at the right time. Recent advances in information and communication technologies enable collection of real-time information from various sources. For example, sensors deployed in the fields collect data about the environment. Similarly, social networks like Twitter and Facebook can help to collect data from people in the disaster zone. On one hand, inadequate situation awareness in disasters has been identified as one of the primary factors in human errors with grave consequences such as loss of lives and destruction of critical infrastructure. On the other hand, the growing ubiquity of social media and mobile devices, and pervasive nature of the Internet-of-Things means that there are more sources of outbound traffic, which ultimately results in the creation of a data deluge, beginning shortly after the onset of disaster events, leading to the problem of information tsunami. In addition, security and privacy has crucial role to overcome the misuse of the system for either intrusions into data or overcome the misuse of the information that was meant for a specified purpose. .... In this chapter, we provide such a situation aware application to support disaster management data lifecycle, i.e. from data ingestion and processing to alert dissemination. We utilize cloud computing, Internet of Things and social computing technologies to achieve a scalable, effi-cient, and usable situation-aware application called Cloud4BigData.
Cloud computing has been emerged in the last decade to enable utility-based computing resource management without purchasing hardware equipment. Cloud providers run multiple data centers in various locations to manage and provision the Cloud resources to their customers. More recently, the introduction of Software-Defined Networking (SDN) and Network Function Virtualization (NFV) opens more opportunities in Clouds which enables dynamic and autonomic configuration and provisioning of the resources in Cloud data centers. This paper proposes architectural framework and principles for Programmable Network Clouds hosting SDNs and NFVs for geographically distributed Multi-Cloud computing environments. Cost and SLA-aware resource provisioning and scheduling that minimizes the operating cost without violating the negotiated SLAs are investigated and discussed in regards of techniques for autonomic and timely VNF composition, deployment and management across multiple Clouds. We also discuss open challenges and directions for creating auto-scaling solutions for performance optimization of VNFs using analytics and monitoring techniques, algorithms for SDN controller for scalable traffic and deployment management. The simulation platform and the proof-of-concept prototype are presented with initial evaluation results.
Major cloud providers such as Microsoft, Google, Facebook and Amazon rely heavily on datacenters to support the ever-increasing demand for their computational and application services. However, the financial and carbon footprint related costs of running such large infrastructure negatively impacts the sustainability of cloud services. Most of existing efforts primarily focus on minimizing the energy consumption of servers. In this paper, we devise a conceptual model and practical design guidelines for holistic management of all resources (including servers, networks, storage, cooling systems) to improve the energy efficiency and reduce carbon footprints in Cloud Data Centers (CDCs). Furthermore, we discuss the intertwined relationship between energy and reliability for sustainable cloud computing, where we highlight the associated research issues. Finally, we propose a set of future research directions in the field and setup grounds for further practical developments.
Software-Defined Network (SDN) radically changes the network architecture by decoupling the network logic from the underlying forwarding devices. This architectural change rejuvenates the network-layer granting centralized management and re-programmability of the networks. From a security perspective, SDN separates security concerns into control and data plane, and this architectural recomposition brings up exciting opportunities and challenges. The overall perception is that SDN capabilities will ultimately result in improved security. However, in its raw form, SDN could potentially make networks more vulnerable to attacks and harder to protect. In this paper, we focus on identifying challenges faced in securing the data plane of SDN - one of the least explored but most critical components of this technology. We formalize this problem space, identify potential attack scenarios while highlighting possible vulnerabilities and establish a set of requirements and challenges to protect the data plane of SDNs. Moreover, we undertake a survey of existing solutions with respect to the identified threats, identifying their limitations and offer future research directions.