Kyong Hoon Kim

Power Aware Scheduling of Bag-of-Tasks Applications with Deadline Constraints on DVS-enabled Clusters

Power-aware scheduling problem has been a recent issue in cluster systems not only for operational cost due to electricity cost, but also for system reliability. As recent commodity processors support multiple operating points under various supply voltage levels, Dynamic Voltage Scaling (DVS) scheduling algorithms can reduce power consumption by controlling appropriate voltage levels. In this paper, we provide power-aware scheduling algorithms for bag-of-tasks applications with deadline constraints on DVS-enabled cluster systems in order to minimize power consumption as well as to meet the deadlines specified by application users. A bag-of-tasks application should finish all the sub-tasks before the deadline, so that the DVS scheduling scheme should consider the deadline as well. We provide the DVS scheduling algorithms for both time-shared and space-shared resource sharing policies. The simulation results show that the proposed algorithms reduce much power consumption compared to static voltage schemes.

Power-aware provisioning of Cloud resources for real-time services

Reducing energy consumption has been an essential technique for Cloud resources or datacenters, not only for operational cost, but also for system reliability. As Cloud computing becomes emergent for Anything as a Service (XaaS) paradigm, modern real-time Cloud services are also available throughout Cloud computing. In this work, we investigate power-aware provisioning of virtual machines for real-time services. Our approach is (i) to model a real-time service as a real-time virtual machine request; and (ii) to provision virtual machines of datacenters using DVFS (Dynamic Voltage Frequency Scaling) schemes. We propose several schemes to reduce power consumption and show their performance throughout simulation results.

Power-aware provisioning of virtual machines for real-time Cloud services

Reducing power consumption has been an essential requirement for Cloud resource providers not only to decrease operating costs, but also to improve the system reliability. As Cloud computing becomes emergent for the Anything as a Service (XaaS) paradigm, modern real‐time services also become available through Cloud computing. In this work, we investigate power‐aware provisioning of virtual machines for real‐time services. Our approach is (i) to model a real‐time service as a real‐time virtual machine request; and (ii) to provision virtual machines in Cloud data centers using dynamic voltage frequency scaling schemes. We propose several schemes to reduce power consumption by hard real‐time services and power‐aware profitable provisioning of soft real‐time services. Copyright

Managing Cancellations and No-Shows of Reservations with Overbooking to Increase Resource Revenue

Advance reservation allows users to request available nodes in the future, whereas economy provides an incentive for resource owners to be part of the Grid, and encourages users to utilize resources optimally and effectively. In this paper, we use overbooking models from Revenue Management to manage cancellations and no-shows of reservations in a Grid system. Without overbooking, the resource owners are faced with a prospect of loss of income and lower system utilization. Thus, the models aim to find an ideal limit that exceeds the maximum capacity, without incurring greater compensation cost. Moreover, we introduce several novel strategies for selecting which bookings to deny, based on compensation cost and user class level, namely Lottery, Denied Cost First (DCF), and Lower Class DCF. The result shows that by overbooking reservations, a resource gains an extra 6-9% in the total net revenue.

Fair resource sharing in hierarchical virtual organizations for global grids

In global grid computing, users and resource providers organize various virtual organizations (VOs) to share resources and services. A VO organizes other sub-VOs for the purpose of achieving the VO goal, which forms hierarchical VO environments. Resource providers and VOs agree upon VO resource sharing policies, such as resource sharing amount. Thus, users in lower-layer VOs can access resources in higher-layer VOs to accomplish their common goals. In this paper, we deal with fair resource allocation problem in hierarchical VOs, so that an appropriate proportion of a VO resource for each lower-layer VO is analyzed. In addition, we provide a resource allocation scheme based on these predefined proportions. Simulation results show that the proposed approach gives better fairness as well as performance compared with other schemes.

Minimizing Cost of Virtual Machines for Deadline-Constrained MapReduce Applications in the Cloud

As Cloud computing provides Anything as a Service (XaaS), many applications can be developed and run on the Cloud without concerns of platforms. Data-incentive applications are also easily developed on virtual machines provided by the Cloud. In this work, we investigate cost-effective resource provisioning for MapReduce applications with deadline constraints, as the MapReduce programming model is useful and powerful in developing data-incentive applications. When users want to run MapReduce applications, they submit jobs to a Cloud resource broker which allocates appropriate virtual machines with consideration of SLAs (Service-Level Agreements). The goal of resource provisioning in this paper is to minimize the cost of virtual machines for executing MapReduce applications without violating their deadlines to be finished by. We propose two resource provisioning approaches: one based on listed pricing policies and the other based on deadline-aware tasks packing. Throughout simulations, we evaluate and analyze them in various ways.

Using Revenue Management to Determine Pricing of Reservations

Grid economy provides a mechanism or incentive for resource owners to be part of the Grid, and encourages users to utilize resources optimally and effectively. Advance reservation technique allows users to request resources in the future. However, few research has been done on determining pricing of such reservations. In this paper, we present a novel approach of using revenue management (RM) to determine pricing of reservations in Grids in order to increase pro ts. Hence, the aim of RM is to periodically update the prices in response to market demands, by charging different fares to different customers for a same resource. We evaluate the effectiveness of RM and show that by segmenting customers, charging them with different pricing schemes and protecting resources for them who are willing to pay more, will result in an increase of total revenue for that resource. Moreover, using RM techniques ensure that resources are allocated to applications that are highly valued by the users.

Reward-based allocation of cluster and grid resources for imprecise computation model-based applications

Utility-based resource management is becoming an emerging issue as the utilisation of cluster resources in Grid computing is growing rapidly. In this paper, we provide a new Imprecise Computation IC application model for flexible reward-based Grid resource management. An application in the proposed model consists of multiple independent jobs, in which each job has two parts: mandatory part for the minimum quality and optional part for additional computations. This application model can be applied to QoS-related Grid applications and used in adaptive resource management. We also provide scheduling algorithms for resource allocation of the IC applications based on reward. The profitable optional execution time is analysed for both space-shared and time-shared scheduling policies. Simulation results show that the proposed schemes are beneficial to both users and resource providers in terms of application acceptance rate and total reward.

Policy-based Resource Allocation in Hierarchical Virtual Organizations for Global Grids

In previous years, many studies have been conducted on grid computing, in which users and resource providers organize various virtual organizations (VOs) to share resources and services. A VO organizes other sub-VOs for the purpose of achieving the VO goal, which forms the hierarchical VO environment. In this paper, we model and formalize the resource allocation problem in hierarchical VOs. Resource providers and VOs agree upon the VO resource sharing policy, such as resource sharing amount and resource usage cost for VOs. We provide the resource allocation scheme of a VO resource broker to minimize the total cost in order to meet a users job deadline. In addition, we deal with several cost adjustment methods in resource providers to utilize their resources efficiently in hierarchical VOs

Hierarchical Real-Time Scheduling Framework for Imprecise Computations

Hierarchical scheduling frameworks provide ways for composing large and complex real-time systems from independent sub-systems. In this paper, we consider the imprecise reward-based periodic task model in a compositional scheduling framework. Thus, we introduce the imprecise periodic resource model to characterize the imprecise resource allocations, and the interface model to abstract the imprecise real-time requirements of the component. The schedulability analysis of mandatory parts is analyzed to meet the minimum requirement of tasks. In addition, we provide a scheduling algorithm for guaranteeing a certain amount of reward, which makes it feasible to compose multiple imprecise components efficiently.