A Predictive-Reactive Method for Improving the Robustness of Real-Time Data Services

Oh, Jisu; Kang, Kyoung-Don

doi:10.1109/tkde.2012.44

Cited by 9 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To guarantee Web application QoS, there is a trend of using feedback-control to compensate the inaccuracies of queuing models 10,11,30 or other proactive methods. 33 The combining of queuing-models and feedback controls is an effective and fast method to make the system follow a referenced average waiting time. 34 However, in existing feedback and feedforward hybrid control algorithms for QoS control of Web applications, the feedback controller is usually only used to amend the output of the feedforward controller (called parallel connection) which is not suitable for interval-charged Cloud VMs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Unequal‐interval based loosely coupled control method for auto‐scaling heterogeneous cloud resources for web applications

Cai

Liu

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Most existing quality of service (QoS) control algorithms of Web applications take into account Web Server or database connections which can be released immediately. However, many applications are deployed on virtual machines (VMs) or even Spot VMs elastically rented from public Clouds. To save costs, interval-priced VMs are not released until the ends of rented intervals. Such delays of control effects make existing methods rent or release excess VMs leading to overcontrol. Fluctuated prices make Spot VMs unreliable due to unexpected termination which makes fault-tolerant strategies crucial. In this article, an unequal-interval-based loosely coupled control method is proposed to improve the quality of service (QoS) control ability of fault-tolerant strategies. A queuing model with arrival-rate-adjustment coefficient is used to predict required capacity as a feedforward controller. Another two-threshold and queuing-model-based method is applied to update the coefficient as a loosely coupled feedback controller. Meanwhile, unequal-interval controller collaborating method is proposed to avoid overcontrol and react quickly to workload changes. Our approach is evaluated on both a simulation platform and a real Kubernetes Cluster. Experimental results illustrate that our approach decreases the percentage of waiting times larger than service level agreements with similar or lower rental costs compared with existing algorithms. K E Y W O R D S Cloud computing, feedback control, queuing model, resource provisioning, Spot VM 1 INTRODUCTION Cloud computing offers subscription-oriented services and it is widespread to rent Cloud virtual machines (VMs) elastically to support the running of Web applications. 1,2 VMs are generally priced by time intervals and the hour-based pricing model is especially popular in modern commercial public Clouds. Prices of On-demand VMs of Amazon EC2, Microsoft Azure, Aliyun, and so on are fixed. On the contrary, prices of Spot VMs of Amazon EC2 3,4 are dynamic because Spot VMs are auctioned by public Clouds. Spot VMs are cheaper than On-demand VMs but unreliable due to lease terminations when the current market price becomes higher than the bid. Most existing QoS control methods for Web applications only focus on resources inside one server or On-demand VMs. However, it is beneficial to rent Spot VMs to decrease VM rental costs. The principal goal of this article is to provision Spot and On-demand VMs elastically to minimize resource rental cost while guaranteeing the average waiting time of requests and

show abstract

Section: Related Workmentioning

confidence: 99%

“…To guarantee Web application QoS, there is a trend of using feedback‐control to compensate the inaccuracies of queuing models 10,11,30 or other proactive methods 33 . The combining of queuing‐models and feedback controls is an effective and fast method to make the system follow a referenced average waiting time 34 .…”

Section: Related Workmentioning

confidence: 99%

Unequal‐interval based loosely coupled control method for auto‐scaling heterogeneous cloud resources for web applications

Cai

Liu

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…It monitors the QoS and dynamically adjusts it to guarantee the required QoS specified by the database administrator. The FCSA has been used in the most referenced QoS Management Solutions such as (Kang, Son & Stankovic, 2003;Amirijoo, Hansson & Son, 2006;Ben Salem, Achour, Bouazizi, Bouaziz & Duvallet, 2013;Oh & Kang, 2013;Ben Salem, Bouazizi, Bouaziz & Duvallet, 2014). It has been also applied in other systems such as distributed multimedia systems (Alaya, Duvallet & Sadeg, 2009;Alaya, Duvallet & Sadeg, 2010) and geographic information systems (Hamdi, Bouazizi & Faiz, 2015) to guarantee a stabilized behavior of these systems without accurate model of the load.…”

Section: Quality Of Service Specificationmentioning

confidence: 99%

Model Driven Engineering for Quality of Service Management

M'barek

Baccouche

Ghezala

2016

Journal of Database Management

View full text Add to dashboard Cite

Real-time applications managing a large number of real-time data require the use of Real-time Database Management Systems (RTDBMS) to meet temporal constraints of both real-time data and transactions. However, a RTDBMS has a dynamic workload and may be frequently overloaded since the arrival times and workloads of user transactions are unpredictable. Therefore, Quality of Service management solutions have been proposed to guarantee the stability of RTDBMS even during unpredictable overload periods. While effective, the design and reuse of these solutions is challenging because they are not formally modeled and there is no tool neither a methodology that helps us design such solutions. To address these issues, the authors propose a design framework based on the Model-Driven Engineering approach providing a modeling architecture, a strategic methodology and a software tool to support modeling and reusing such solutions. The framework is implemented and tested for a real Qos management solution.

show abstract

“…QoD scaling via active load shedding [18] has been applied to real-time databases (RTDBs) [19,20] and stream management systems (DSMSs) [21,22] for performance management at runtime. A common approach for load shedding is to drop incoming data updates under overloading situation.…”

Section: Related Workmentioning

confidence: 99%

“…Because of its robustness against unpredictable workloads, feedback control theory has been extensively applied for the QoS management of various computing systems, including web servers [29], caching service [30], and email server [31]. Feedback control theory has also been used to support the timeliness of real-time transactions in real-time data services [2,19,32]. However, these works do not consider modern multicore environments.…”

Section: Related Workmentioning

confidence: 99%

QoS Management for Embedded Databases in Multicore-Based Embedded Systems

Kang

Chung

2015

Mobile Information Systems

View full text Add to dashboard Cite

With ubiquitous deployment of sensors and network connectivity, amounts of real-time data for embedded systems are increasing rapidly and database capability is required for many embedded systems for systematic management of real-time data. In such embedded systems, supporting the timeliness of tasks accessing databases is an important problem. However, recent multicore-based embedded architectures pose a significant challenge for such data-intensive real-time tasks since the response time of accessing data can be significantly affected by potential intercore interferences. In this paper, we propose a novel feedback control scheme that supports the timeliness of data-intensive tasks against unpredictable intercore interferences. In particular, we use multiple inputs/multiple outputs (MIMO) control method that exploits multiple control knobs, for example, CPU frequency and the Quality-of-Data (QoD) to handle highly unpredictable workloads in multicore systems. Experimental results, using actual implementation, show that the proposed approach achieves the target Quality-of-Service (QoS) goals, such as task timeliness and Quality-of-Data (QoD) while consuming less energy compared to baseline approaches.

show abstract

A Predictive-Reactive Method for Improving the Robustness of Real-Time Data Services

Cited by 9 publications

References 26 publications

Unequal‐interval based loosely coupled control method for auto‐scaling heterogeneous cloud resources for web applications

Unequal‐interval based loosely coupled control method for auto‐scaling heterogeneous cloud resources for web applications

Model Driven Engineering for Quality of Service Management

QoS Management for Embedded Databases in Multicore-Based Embedded Systems

Contact Info

Product

Resources

About