Resource Scheduling Framework Research Articles

CSL-driven and energy-efficient resource scheduling in cloud data center

High energy consumption in data center has serious impacts on environment. Energy-efficient scheduling under Customer Satisfaction Level (CSL) constraint has become a key problem of cloud computing in data centers. In this paper, a CSL-driven and energy-efficient resource scheduling (CDEERS) framework has been designed to optimize energy efficiency and CSL in cloud data centers. To achieve different goals in different CSL states, three scheduling strategies (aiming to minimize energy saving, maximize CSL and maximize CSL per energy, respectively) are auto-adaptively applied to consolidate resources according to CSL states. To identify CSL states, a metric based on Service Level Agreement (SLA) violation rate (MSVR) is designed and applied in the proposed method. Additionally, the Weighted Moving Average (WMA) model is applied to predict the future state of CSL and optimize the resource allocation. Simulation result shows that the MSVR improves energy efficiency (CSL per energy) by 51.1% and 30.4% compared with traditional metric based on workload (MW) and metric based on response time (MRT), respectively, during the whole test period. It reduces the SLA violation rate by 7.9% and the number of host overloads by 9.6%, respectively, while prediction mechanism is applied. It shows that CDEERS has better energy efficiency than these static scheduling methods with single objection in the condition of dynamic state of CSL.

Stochastic resource scheduling via bilayer dynamic Markov decision process in mobile cloud networks

In mobile cloud networks, the efficiency and the quality of service are mainly affected by the service delay, the drop rate of service requests and CPU utilization. For these reasons, we propose a real-time stochastic resource scheduling framework (R-SRSF) to realize pre-allocation of resources by bilayer dynamic markov decision processes (DMDPs). In R-SRSF, we divide the resource scheduling into two parts, the virtual machine (VM) basic configuration resources management and VM switching management. To this end, we firstly design a strategy transformation management algorithm (STMA) to control the VM basic configuration resources. Secondly, we design a scheme-changed drift-plus-penalty algorithm (SDPPA) to execute VM switching management. We also prove the convergence of SDPPA based on Lyapunov optimization theory. For better VM scheduling, we propose a stochastic dynamic policy adjustment algorithm to cooperate with SDPPA. The experimental results show that R-SRSF can reduce the service delay, expenditure and the drop rate of service requests. Moreover, R-SRSF also has a high CPU utilization and stability.

Cloud Resource Adaptive Scheduling Framework and Optimization Strategy Based on Swarm Intelligence

Resource scheduling framework is very important for the overall cloud service efficiency and service quality,which is the core module of cloud computing. This paper proposes an adaptive cloud computing resource scheduling framework based on swarm intelligence. The proposed adaptive framework includes resource deployment module, scheduling module, recommendation module, optimization module, and monitoring module.The simulation results show that the proposed framework is more efficient than the traditional framework in terms of task execution time, system load balancing and resource service quality, and can improve the service quality of cloud applications while improving resource utilization.

A methodological framework for cloud resource provisioning and scheduling of data parallel applications under uncertainty

Data parallel applications are being extensively deployed in cloud environments because of the possibility of dynamically provisioning storage and computation resources. To identify cost-effective solutions that satisfy the desired service levels, resource provisioning and scheduling play a critical role. Nevertheless, the unpredictable behavior of cloud performance makes the estimation of the resources actually needed quite complex. In this paper we propose a provisioning and scheduling framework that explicitly tackles uncertainties and performance variability of the cloud infrastructure and of the workload. This framework allows cloud users to estimate in advance, i.e., prior to the actual execution of the applications, the resource settings that cope with uncertainty. We formulate an optimization problem where the characteristics not perfectly known or affected by uncertain phenomena are represented as random variables modeled by the corresponding probability distributions. Provisioning and scheduling decisions – while optimizing various metrics, such as monetary leasing costs of cloud resources and application execution time – take fully account of uncertainties encountered in cloud environments. To test our framework, we consider data parallel applications characterized by a deadline constraint and we investigate the impact of their characteristics and of the variability of the cloud infrastructure. The experiments show that the resource provisioning and scheduling plans identified by our approach nicely cope with uncertainties and ensure that the application deadline is satisfied.

EPS: Energy-Efficient Pricing and Resource Scheduling in LTE-A Heterogeneous Networks

Many operators offer long term evolution-advanced (LTE-A) service for broadband wireless access, where they deploy diverse base stations to form a heterogeneous network (HetNet). It is critical to manage downlink resource to improve LTE-A performance. The paper studies the issues of energy saving and dynamic pricing in resource scheduling, and proposes an Energy-efficient Pricing and resource Scheduling (EPS) framework. It considers a HetNet scenario where picocells are densely deployed in each macrocell, and divides users into three classes for charge. EPS clusters picocells into groups, and selects a coordinator to arrange the service in each group, so as to share loads of picocells and save energy of base stations. Then, it adopts a two-layer scheduling strategy to allot resource to each flow based on its user class, channel quality, and packet delay. By using peak and off-peak rates, EPS adaptively adjusts the amount of money charged to each user to balance between operator profit and network utilization. Simulation results verify that EPS keeps high profit and throughput, and also saves more energy in LTE-A HetNets.

A multi-objective framework for energy resource scheduling in active distribution networks

ABSTRACTPurpose: The purpose of this paper is to investigate the impacts of electric vehicles' (EVs) charging/discharging decisions in energy resources scheduling problem of active distribution networks. Design/methodology/approach: The problem under study is modelled as a two-stage optimisation problem in which the main requirements of EV owners are introduced as an objective function of the first stage. The total energy costs and the emission factor are considered as the main criteria of the second stage. The output generation schedules of distributed generation (DG) technologies together with the charging/discharging schedule of EVs are proposed as decision variables of the energy scheduling problem. Therefore, some effective methods are presented to model the uncertainties associated with these variables. Findings: The results proved that an efficient compromise can be reached between the emission factor and the energy cost of the system. In addition, it has been emphasised on the importance of such comprehensive energy scheduling frameworks. Originality/value: This paper contributes by: (a) providing a multi-objective framework for energy scheduling of active distribution networks, (b) extracting the mathematical model of this two-stage problem and (c) employing a linearised optimisation model to reach its global optimal solution.

Effect of Risk Aversion on Reserve Procurement With Flexible Demand Side Resources From the ISO Point of View

In this study, a two-stage stochastic programming joint day-ahead energy and reserve scheduling model to address uncertainty in wind power generation is developed. Apart from the generation side, the demand side is also eligible as a reserve resource and is modeled through responsive load aggregations, as well as large industrial loads that directly participate in the scheduling procedure. The main contribution of this paper is the inclusion of a risk metric, namely the conditional value-at-risk, which renders a conceptually different resource scheduling framework. The proposed model is employed in order to analyze the behavior of energy and reserve scheduling by both generation and demand for a risk-averse independent system operator. To reach practical conclusions, the proposed methodology is tested on the real non-interconnected insular power system of Crete, Greece, which is characterized by a significant penetration of wind power generation.

A Pricing-Aware Resource Scheduling Framework for LTE Networks

Long term evolution (LTE) is a standard widely used in cellular networks today. Both resource scheduling and pricing are two critical issues. However, existing studies address them separately, making the goals of improving system performance and increasing operator revenue conflicting. This paper proposes a pricing-aware resource scheduling (PARS) framework to conquer this conflict. It classifies users into three levels and has scheduling and pricing modules, which are installed in a base station and the core network of LTE, respectively. The scheduling module uses three-layer schedulers to assign resource to a flow by considering its packet delay, traffic amount, channel condition, and user level. The pricing module uses price elasticity of demand in economics to adaptively adjust the amount of money charged to users. Through experiments by LTE-Sim, we show that PARS achieves a good balance between performance and revenue, and provides quality of service for the flows with strict delay concerns.

Joint affinity aware grouping and virtual machine placement

The Non-Affinity Aware Grouping based resource Allocation (NAGA) method toward the General VMPlacement (GP) problem enables (1) some VMs to be co-located onto the same PM while the VMs are required to be placed onto distinct PMs; and (2) some VMs to be dispersedly placed onto distinct PMs while the VMs are required to be co-located onto the same PM, leading to a serious performance degradation of application running over multiple VMs in cloud computing. In this work we study an Affinity Aware VM Placement (AAP) problem and propose a Joint Affinity AwareGrouping and Bin Packing (JAGBP) method to remedy the deficiency of the NAGA method. We firstly introduce affinity of VMs to identify affinity relationships to VMs which are required to be placed with a special VM placement pattern, such as colocation or disperse placement, and formulate the AAP problem. Then, we propose an affinity aware resource scheduling framework, and provide methods to obtain and identify the affinity relationships between VMs, and the JAGBP method. Lastly, we present holistic evaluation experiments to validate the feasibility and evaluate the performance of the proposed methods. The results demonstrate the significance of introduced affinity and the effectiveness of JAGBP method.

Accelerating Particle Swarm Optimization Algorithm Based on MOOC Framework for Resource Scheduling in Physical Teaching

Accelerating Particle Swarm Optimization Algorithm Based on MOOC Framework for Resource Scheduling in Physical Teaching

EARTH: Energy-aware autonomic resource scheduling in cloud computing

In Cloud computing, data centers gain popularity as an effective platform for scheduling of resources and hosting cloud applications. However, tremendous amount of energy is consumed by these data centers which leads to high operational costs and contributes towards carbon footprints to the environment. Therefore, there is need of energy aware cloud based framework which schedules computing resources automatically by considering energy consumption as a QoS parameter itself. In this paper, we present fuzzy logic based energy-aware autonomic resource scheduling framework for cloud for energy efficient scheduling of cloud computing resources in data centers. We have evaluated the proposed framework in CloudSim based simulation environment and real cloud environment. The experimental results show that the proposed framework performs better in terms of resource utilization and energy consumption along with other QoS parameters.

Resource provisioning and scheduling in clouds: QoS perspective

Resource provisioning of appropriate resources to cloud workloads depends on the quality of service (QoS) requirements of cloud applications and is a challenging task. In cloud environment, heterogeneity, uncertainty and dispersion of resources encounter a problem of allocation of resources, which cannot be addressed with existing resource management frameworks. Resource scheduling, if done after efficient resource provisioning, will be more effective and the cloud resources would be scheduled as per the user requirements (QoS) on provisioned resources. Execution of cloud workloads should be as per QoS parameters to fully satisfy the cloud consumer. Therefore, based on QoS parameters, it is mandatory to predict and verify the resource provisioning before actual resource scheduling. In this paper, a resource provisioning and scheduling framework has been presented which caters to provisioned resource distribution and scheduling of resources. Cloud workloads have been re-clustered using k-means-based clustering algorithm after firstly clustering them through workload patterns to identify the QoS requirements of a workload, and then based on identified QoS requirements resources are provisioned before actual scheduling. Further, scheduling has been done based on different scheduling policies. Finally, the performance of the proposed framework has been evaluated in both real and simulated cloud environment and experimental results show that the framework provisions and schedules resource efficiently by considering energy consumption, execution cost and execution time as QoS parameters.

Re-Stream: Real-time and energy-efficient resource scheduling in big data stream computing environments

To achieve high energy efficiency and low response time in big data stream computing environments, it is required to model an energy-efficient resource scheduling and optimization framework. In this paper, we propose a real-time and energy-efficient resource scheduling and optimization framework, termed the Re-Stream. Firstly, the Re-Stream profiles a mathematical relationship among energy consumption, response time, and resource utilization, and obtains the conditions to meet high energy efficiency and low response time. Secondly, a data stream graph is modeled by using the distributed stream computing theories, which identifies the critical path within the data stream graph. Such a methodology aids in calculating the energy consumption of a resource allocation scheme for a data stream graph at a given data stream speed. Thirdly, the Re-Stream allocates tasks by utilizing an energy-efficient heuristic and a critical path scheduling mechanism subject to the architectural requirements. This is done to optimize the scheduling mechanism online by reallocating the critical vertices on the critical path of a data stream graph to minimize the response time and system fluctuations. Moreover, the Re-Stream consolidates the non-critical vertices on the non-critical path so as to improve energy efficiency. We evaluate the Re-Stream to measure energy efficiency and response time for big data stream computing environments. The experimental results demonstrate that the Re-Stream has the ability to improve energy efficiency of a big data stream computing system, and to reduce average response time. The Re-Stream provides an elegant trade-off between increased energy efficiency and decreased response time effectively within big data stream computing environments.

Energy based Efficient Resource Scheduling: A Step Towards Green Computing

Cloud Computing is an evolving area of efficient utilization of computing resources. Data centers accommodating Cloud applications ingest massive quantities of energy, contributing to high functioning expenditures and carbon footprints to the atmosphere. Hence, Green Cloud computing resolutions are required not only to save energy for the environment but also to decrease operating charges. In this paper, we emphasis on the development of energy based resource scheduling framework and present an algorithm that consider the synergy between various data center infrastructures (i.e., software, hardware, etc.), and performance. In specific, this paper proposes (a) architectural principles for energy efficient management of Clouds; (b) energy efficient resource allocation strategies and scheduling algorithm considering Quality of Service (QoS) outlooks. The performance of the proposed algorithm has been evaluated with the existing energy based scheduling algorithms. The experimental results demonstrate that this approach is effective in minimizing the cost and energy consumption of Cloud applications thus moving towards the achievement of Green Clouds.

A flexible resource allocation and scheduling framework for non-real-time polling service in IEEE 802.16 networks

This paper proposes an efficient yet simple design framework for achieving flexible resource allocation and packet scheduling for non-real-time polling service (nrtPS) traffic in IEEE 802.16 networks. By jointly considering the selective automatic repeat request mechanism at the media access control layer as well as the adaptive modulation and coding technique at the physical layer, the proposed framework enables a graceful tradeoff between resource utilization and packet delivery delay while maintaining the minimum throughput requirements of nrtPS applications. An analytical model is developed for parameter manipulation in the proposed framework, where some important performance metrics, such as inter-service time, delivery delay, goodput, and resource utilization, are investigated for performance evaluation. Simulation results are given to demonstrate the efficiency of the proposed framework and verify the accuracy of the analytical model.

Application-adaptive resource scheduling in a computational grid

Selecting appropriate resources for running a job efficiently is one of the common objectives in a computational grid. Resource scheduling should consider the specific characteristics of the application, and decide the metrics to be used accordingly. This paper presents a distributed resource scheduling framework mainly consisting of a job scheduler and a local scheduler. In order to meet the requirements of different applications, we adopt HGSA, a Heuristic-based Greedy Scheduling Algorithm, to schedule jobs in the grid, where the heuristic knowledge is the metric weights of the computing resources and the metric workload impact factors. The metric weight is used to control the effect of the metric on the application. For different applications, only metric weights and the metric workload impact factors need to be changed, while the scheduling algorithm remains the same. Experimental results are presented to demonstrate the adaptability of the HGSA.

QoS-adaptive bandwidth scheduling in continuous media streaming

In this paper, we present a QoS-adaptive admission control and resource scheduling framework for continuous media (CM) servers. The framework consists of two parts. One is a reserve-based admission control mechanism in which new streams, arriving during periods of congestion, are offered lower QoS, instead of being blocked. The other part is a scheduler for continuous media with dynamic resource allocation to achieve higher utilization than non-dynamic schedulers by effectively sharing available resources among contending streams and by reclamation which is a scheduler-initiated negotiation to reallocate resources among streams to improve overall QoS. This soft-QoS framework recognizes that CM applications can generally tolerate certain variations on QoS parameters; that is, it exploits the findings about human tolerance to degradation in quality of multimedia streams. Using our policy, we could increase the number of simultaneously running clients that could be supported and could ensure a good response ratio and better resource utilization under heavy traffic requirements. Our admission control and scheduling strategy provides three principle advantages over conventional mechanisms. First, it guarantees better total system utilization. Second, it provides better disk utilization and larger admission ratio for input CM streams, which is a major advantage. Third, it still presents acceptable play-out qualities compared to the conventional greedy admission control algorithm.