Ivan Breskovic

SLA-Aware Application Deployment and Resource Allocation in Clouds

Provisioning resources as a service in a scalable on-demand manner is a basic feature in Cloud computing technology. Service provisioning in Clouds is based on Service Level Agreements (SLAs) representing a contract signed between the customer and the service provider stating the terms of the agreement including non-functional requirements of the service specified as Quality of Service (QoS), obligations, and penalties in case of agreement violations. On the one hand SLA violation should be prevented to avoid costly penalties and on the other hand providers have to efficiently utilize resources to minimize cost for the service provisioning. Thus, scheduling strategies considering multiple SLA parameters and efficient allocation of resources are necessary. Recent work considers various strategies with single SLA parameters. However, those approaches are limited to simple workflows and single task applications. Scheduling and deploying service requests considering multiple SLA parameters such as amount of CPU required, network bandwidth, memory and storage are still open research challenges. In this paper, we present a novel scheduling heuristic considering multiple SLA parameters for deploying applications in Clouds. We discuss in details the heuristic design and implementation and finally present detailed evaluations as a proof of concept emphasizing the performance of our approach.

Revealing the MAPE loop for the autonomic management of Cloud infrastructures

Cloud computing is the result of the convergence of several concepts, ranging from virtualization, distributed application design, Grid computing, and enterprise IT management. Efficient management of Cloud computing infrastructures faces with the contradicting goals like unlimited scalability, provision of Service Level Agreements (SLAs), extensive use of virtualization, energy efficiency and minimization of the administration overhead by humans. Thus, autonomic computing seems to be one of the promising paradigms for the implementation of the management infrastructures for Clouds. However, currently available autonomic systems do not consider the characteristics of Clouds, e.g., virtualization layer, and thus are not easily applicable to Cloud infrastructures. In this paper we discuss first steps towards revealing the current MAPE (Monitoring, Analysis, Planning, Execution) loops for the application to Cloud infrastructures. We present novel techniques for the adequate monitoring of Clouds, discuss the approach for the knowledge management and present our solutions for facilitating SLA generation and management.

Automatic SLA Matching and Provider Selection in Grid and Cloud Computing Markets

Cloud computing is a novel computing paradigm that offers data, software, and hardware services in a manner similar to traditional utilities such as water, electricity, and telephony. Usually, in Cloud and Grid computing, contracts between traders are established using Service Level Agreements (SLAs), which include objectives of service usage. However, due to the rapidly growing number of service offerings and the lack of a standard for their specification, manual service selection is a costly task, preventing the successful implementation of ubiquitous computing on demand. In order to counteract these issues, automatic methods for matching SLAs are necessary. In this paper, we introduce a method for finding semantically equal SLA elements from differing SLAs by utilizing several machine learning algorithms. Moreover, we utilize this method to enable automatic selection of optimal service offerings for Cloud and Grid users. Finally, we introduce a framework for automatic SLA management, present a simulation-based evaluation, and demonstrate several significant benefits of our approach for Cloud and Grid users.

Creating standardized products for electronic markets

Cloud computing is supposed to offer resources (i.e., data, software, and hardware services) in a manner similar to traditional utilities such as water, electricity, gas, and telephony. However, the current Cloud market is fragmented and static, preventing the successful implementation of ubiquitous computing on demand. In order to address the issue of fragmentation, commodity Cloud marketplaces have been suggested. However, as those marketplaces still suffer from being static (i.e., not being capable to adapt to changing market conditions and to the dynamics of user requirements for services), they do not operate at the optimal point. In this paper, we address this issue by channeling demand and supply into a few standardized services that are automatically adapted to user requirements in regular time intervals. For this, we utilize clustering algorithms and monitor the requirements of users. In order to avoid any cost to the user through these adaptations, we automatically adapt service level specifications of users to newly defined standardized goods. Using a simulation framework, we evaluate our approach and show its benefits to end users.

Towards Self-Awareness in Cloud Markets: A Monitoring Methodology

Currently, the Cloud landscape is a fragmented, static and shapeless market that hinders the paradigms ability to fulfil its promise of ubiquitous computing on tap and as a commodity. In this paper, we present our vision of an autonomic self-aware Cloud market platform, and argue that autonomic market platforms for Clouds can step up to the challenge of todays status quo. As our first steps towards achieving this vision, we present a market monitoring methodology, which includes a series of realistic market goals, sets of extractable metrics from a market platform and how to map (i.e. combine and transform) metrics to access goal performance such that autonomic adaption of the market could be undertaken. We have extended a known market simulator for distributed infrastructures (Grid Sim) with relevant sensors. To demonstrate the usefulness of our approach, we simulate a sudden cease in demand for goods in our market platform.

Collaboration and coordination in the context of informal care (CCCiC 2014)

Past and current research studies recurrently acknowledge the relevance of technological developments to support informal caregivers with their activities and responsibilities. These studies highlight the demands associated with caregiving and suggest that further research in the area is needed to better understand such demands and to figure out more effective ways for technologies to support people who deal with them. In Europe, especial attention has been dedicated to informal caregivers for the past few years, due to indicators showing that more than 80% of the care for frail and old people, one of the major groups of care receivers in the region, is informally provided by family members and friends. The same scenario can be found across different continents, corroborating the relevance of the subject. Therefore, this workshop seeks contributions exploring issues of collaboration and coordination in the context of informal care. Early stage research studies in the area as well as contributions exploring the design and evaluation of computer technologies for it are most welcome.

Achieving Market Liquidity Through Autonomic Cloud Market Management

Due to the large variety in computing resources, Cloud markets often suffer from a low probability of finding matches between consumers’ bids and providers’ asks, resulting in low market liquidity. The approach of service level agreement (SLA) templates (i.e., templates for electronic contracts) is a mean to reduce this variety as it channels the demand and supply. However, until now, the SLA templates used were static, not able to reflect changes in users’ requirements. To address this shortcoming, we introduce an adaptive approach for automatically deriving public SLA templates based on the requirements of market participants. To achieve this goal, we utilize clustering algorithms for grouping similar requirements and learning methods for adapting the public SLA templates to observed changes of market conditions. To assess the benefits of the approach, we conduct a simulation-based evaluation and formalize a utility and cost model. Our results show that the use of clustering algorithms and learning algorithms improves the performance of the adaptive SLA template approach.

Collaboration and Coordination in the Context of Informal Care (CCCiC): Concepts, Methods, and Technologies

Increasing attention is currently paid to informal care and the physical, emotional, and psychological burden stemming from it. Research findings suggest that such a burden might be intensified when informal caregivers are at older ages. Aiming at reducing the burden associated with informal care, some research studies have focused on developing innovative technologies to support caregivers with their activities and responsibilities. These studies highlight the importance of understanding the many variables that characterise different care situations, emphasizing the relevance of user-centered and participatory design approaches. Following up the successful first edition of the CCCiC workshop held at the 2014 ACM CSCW conference in Baltimore, this workshop elaborates on the resulting roadmap for future research in the domain: concepts, methods, and technologies. This workshop seeks contributions exploring issues of collaboration and coordination for informal care addressing concepts emerging from field research, methodological challenges, work-in-progress, and the design and evaluation of technological solutions.