A distributed speed scaling and load balancing algorithm for energy efficient data centers

2022

IEEE Access

Self Cite

As the usage of mission-critical mobile applications increases in Industry 4.0, such as smart manufacturing and self-driving cars, the cloud computing paradigm and its supporting data centers have become more crucial. However, a common practice in the cloud data center computing industry tends to supply a surfeit of computing resources mainly for a robust quality-of-service (QoS). In this paper, we propose a simple real-time algorithm which combines a power-aware job assignment policy for a centralized job dispatcher and a power-and QoS-aware dynamic speed scaling policy for each physical machine (PM). The job assignment policy is called "Join the Least Power Consuming (LPC) Server" that routes an incoming cloud job to a server spending minimum power upon request. The server-side adaptive speed scaling policy expedites energy efficiency and satisfies response time-associated QoS condition. We call this policy "Minimizing Earliness (ME)" since it manages the server speed towards finishing jobs at their deadlines as precisely as possible, reducing the earliness of job completion. The design principle of LPC-ME combination supports both energy efficiency and service quality required in cloud data centers. Numerical experiments compare the proposed algorithm's power consumption and response time with those of existing popular policies and demonstrate better energy efficiency with negligible degradation of service quality.INDEX TERMS Cloud computing, data centers, energy efficiency, queueing analysis, resource management.

Section: B Real-time Operationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Power- and QoS-Aware Job Assignment With Dynamic Speed Scaling for Cloud Data Center Computing

2022

IEEE Access

Self Cite

“…Binding the QoS-related constraints implies that the metrics are maintained as a constant value, and suggests the need to investigate the stabilization of response times. Although some proposed methodologies [2,3,4] assume the stationarity of data traffic arrival processes, nonstationary properties, such as time-varying arrival rates from real data [5], make it difficult to analyze queueing system performance.…”

Section: Introductionmentioning

confidence: 99%

“…Modern data centers consume tremendous amounts of energy to supply networking, computing, and storage services to global IT companies. Concerns about energy consumption have prompted researchers to explore operational methods that maximize energy efficiency and satisfy a certain level of quality of service (QoS), [2,3,4]. QoS can be achieved by adding constraints that impose upper bounds for response time-related metrics, e.g., the mean virtual response time and the tail probability of the response time.…”

Section: Introductionmentioning

confidence: 99%

Stabilizing the virtual response time in single-server processor sharing queues with slowly time-varying arrival rates

2020

Ann Oper Res

Self Cite

Motivated by the work of Whitt [1], who studied stabilization of the mean virtual waiting time (excluding service time) in a GI t /GI t /1/F CF S queue, this paper investigates the stabilization of the mean virtual response time in a single-server processor sharing (PS) queueing system with a time-varying arrival rate and a service rate control (a GI t /GI t /1/P S queue). We propose and compare a modified square-root (SR) control and a difference-matching (DM) control to stabilize the mean virtual response time of a GI t /GI t /1/P S queue. Extensive simulation studies with various settings of arrival processes and service times show that the DM control outperforms the SR control for heavy-traffic conditions, and that the SR control performs better for lighttraffic conditions.

“…While their algorithms can achieve service level agreement (SLA), considering only mean response time is not sufficient in real situations . Ko and Cho propose a distributed algorithm considering the tail probability of the response time from G/G/1/PS queues. Kwon and Gautam suggest time‐stabilizing approaches for the queue length of a data center considering time‐varying arrival rates by formulating the problem as an MIP.…”

Section: Introductionmentioning

confidence: 99%

Energy efficiency of data center operating practices: Server clustering, powering on/off, and bang–bang control

2017

Networks

Self Cite

Data centers today account for up to 3% of all global electricity consumption and produce 200 million metric tons of CO 2 . Hence, improving energy efficiency is an important operational concern. This article examines common operating practices such as server clustering, powering on/off, and bang–bang control in terms of energy efficiency. Extending the mixed integer programming (MIP) formulation in a previous research study, we introduce new constraints reflecting the operating practices adopted for operational convenience. We develop an algorithmic strategy for constructing energy efficient clusters of servers using two upper bounds on the cluster size. Numerical experiments show that server clustering and bang–bang control do not diminish energy efficiency, and that powering on/off by itself is insufficient. Our results produce a conclusion that differs from the published literature on data center design and operations. © 2017 Wiley Periodicals, Inc. NETWORKS, Vol. 71(2), 107–119 2018