Flexible SLAs in the Cloud with a Partial Utility-Driven Scheduling Architecture

Abstract

Current clouds SLAs include compensation for customers (i.e. resource renters) with credits when average availability drops below a certain point. However, this credit scheme is too inflexible because consumers lose a non measurable quantity of performance and are only compensated later (i.e. in the next charging cycle). We propose to schedule cloud isolation and execution units, i.e. virtual machines (VMs), driven by the partial utility of applying a certain amount of resources (CPU, memory or bandwidth) to a given VM. This partial utility metric, specified by the customer, allows the provider to transfer resources between VMs. This is particularly relevant for private clouds where resources are not so abundant. We have defined a cost model that incorporates the partial utility the client gives to a certain level of depreciation when VMs are allocated in an overcommit environment. CloudSim, a state of the art cloud simulator, was extended to support our partial utility-driven scheduling model. Using simulation scenarios with synthetic and real workloads, we show that our proposed scheduling strategy brings benefits to providers (i.e. revenue, resource utilization) and clients (i.e. workloads' execution time) by incorporating a SLAbased depreciation of computational power, allowing for more VMs to be allocated.

Partial Utility-Driven Scheduling for Flexible SLA and Pricing Arbitration in Clouds

“…This paper extends a previous one [17] by (i) enhancing and detailing the cost model and discussing how different utility matrices can be compared; (ii) comparing the proposed strategy with a more comprehensive list of utility-oblivious algorithms; (iii) detailing the implementation in CloudSim; (iv) presenting the results of a larger set of datacenter configurations. In summary the contributions of this work are the following:…”

Resource management for meteorological service in cloud‐edge computing: A survey

“…Relate work Key point Cost-aware resource scheduling 63-66 63 Allocation cost for task scheduling 64 Multiobjective task scheduling 65 Optimal resource scheduling 66 Workload balancing Efficiency-aware resource scheduling 67-69 67 Task scheduling 68 To enhance the efficiency of resource scheduling 69 Providing the cloud resources dynamically Energy-aware resource scheduling 70-72 70 VM scheduling and allocation of task 71 VM scheduling 72 Reducing power consumption of a data center scheduling to control the order of execution. The tasks are executed in the VM according to a predefined policy sequence.…”

Energy Efficient Cloud Service Provisioning: Keeping Data Center Granularity in Perspective

“…The higher the RF, the more influence the adaptiveness factor has on the EE value, and mare important it is to stablish it properly. RF can be determined in the SLAs according to the user incentives (previously addressed for cycle-sharing [58]) and service requirements (previously addressed for virtual machines [59] and Java applications [60]). …”