WattsApp: Power-Aware Container Scheduling

Mehta, Hemant Kumar; Harvey, Paul; Rana, Omer F.; Buyya, Rajkumar; Varghese, Blesson

doi:10.1109/ucc48980.2020.00027

Cited by 12 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mehta et al [13] proposed WattsApp to minimize power cap violations in servers. WattsApp predicted future power consumption by analyzing historical CPU and memory usage, the number of network requests, and disk I/O using a linear regression-based neural network (NN).…”

Section: Related Workmentioning

confidence: 99%

Efficient Container Scheduling With Hybrid Deep Learning Model for Improved Service Reliability in Cloud Computing

Jeon,

Park,

Jeong

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In a cloud computing environment, the container scheduling technique ensures reliability for containerized applications by selecting nodes that satisfy various resource requirements and then deploying containers. If the initial resources of a container are over-allocated, resources may be wasted, or other containers that are waiting in a scheduling queue may not be allocated. However, if resources are underallocated, service disruptions may occur due to node overbooking, and service reliability cannot be ensured. Therefore, in this study, a forecasted resource-evaluating scheduler (FoRES) is proposed as a container scheduling technique that ensures resource efficiency and service reliability. FoRES predicts future CPU and memory usage by using a time-series decomposition-based hybrid forecasting (DeHyFo) model that combines multiple linear regressions with the LightTS model. FoRES then calculates the optimal scheduling decisions that minimize idle resources and node overload by applying an efficient resource utilization (SERU) scoring function to the predicted resource usage. Evaluating the performance of FoRES based on various scenarios improved resource efficiency and service reliability by up to 2.07 and 2.32 times, respectively, compared with existing scheduling techniques, even if the initial resources of the container were inefficiently allocated.INDEX TERMS Cloud computing, container scheduling, deep learning, resource efficiency, service reliability, time-series forecasting.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Container Scheduling With Hybrid Deep Learning Model for Improved Service Reliability in Cloud Computing

Jeon,

Park,

Jeong

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Cluster power consumption is related to machine resource utilization and the status of machines. Besides the dynamic power consumption caused by task execution, machines also have static power consumption [16,17]. The basic idea is that fewer machines running in the cluster results in higher average resource utilization.…”

Section: A Scheduling Algorithm Considering User Fairness and Energy ...mentioning

confidence: 99%

SAUFEE: a datacenter task scheduling algorithm considering user fairness and energy efficiency

Peng,

Yan,

et al. 2024

International Conference on Communication, Information, and Digital Technologies (CIDT2024)

View full text Add to dashboard Cite

The data center uses virtualization and isolation technologies to provide flexible and efficient services for multi-tenants. One of the most challenging aspect of resource sharing is task scheduling. During the scheduling process, it is crucial to ensure fairness in user resource usage and achieve high cluster utilization and energy efficiency. However, the heterogeneity of resources and the variations in user demands make it extremely difficult to provide an effective scheduling solution. In this paper, we propose an efficient heuristic scheduling algorithm called SAUFEE, which trades off the resource requirement of multi-tenants and cluster power consumption. First, we introduce a user fairness model, which prioritizes the tasks of users with the least resource allocation in each scheduling round, ensuring fairness among them. Next, we propose a resource utilization model to schedule user tasks to reduce resource waste. Additionally, idle machines are shut down to save overall cluster energy consumption. The simulation experiment results show that our algorithm increases the number of running tasks by 3.3% and the CPU utilization by 3.4% while ensuring fairness. Our algorithm plays an important role in improving cluster energy efficiency and user fairness.

show abstract

“…Containers are very popular for deploying workloads. This paper [7] proposes a tool WattsApp that can estimate the power of containers for power-aware container scheduling to minimize the power cap violated by servers, because power-aware container scheduling does not degrade the performance of all running containers on the server, it is more effective than power capping. WattsApp proposes a software-based, architecture-independent, non-invasive neural network model, which estimates the power of the container through the statistics of various resource utilization of the container and the power of the entire server.…”

Section: Related Workmentioning

confidence: 99%

DCMigrationALG: A Power-Aware Data Center Container Migration Algorithm

Zou,

Feng,

Tang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In order to make full use of the power capacity of the data center when deploying servers in the data center, the deployment method of data center power over-provisioning is adopted. By using the hypothetical power capacity of the data center instead of the actual power capacity to deploy servers, we can deploy more servers to improve power utilization and space utilization. However, in some cases, when the servers under the same power supply component reach a higher power level at the same time, the real-time power of the power supply component will exceed the rated power, affecting service operation and causing heavy losses. In response to the above problems, we propose DCMigrationALG: a power-aware data center container migration algorithm. This algorithm uses container migration to migrate the containers under the power supply component to other power supply components, thereby reducing the real-time power of the power supply component and ensuring power security. We conduct experiments in a real computer room environment to prove the effectiveness of our algorithm.

show abstract

WattsApp: Power-Aware Container Scheduling

Cited by 12 publications

References 21 publications

Efficient Container Scheduling With Hybrid Deep Learning Model for Improved Service Reliability in Cloud Computing

Efficient Container Scheduling With Hybrid Deep Learning Model for Improved Service Reliability in Cloud Computing

SAUFEE: a datacenter task scheduling algorithm considering user fairness and energy efficiency

DCMigrationALG: A Power-Aware Data Center Container Migration Algorithm

Contact Info

Product

Resources

About