Machine Learning-Based Runtime Scheduler for Mobile Offloading Framework

Eom, Heungsik; Juste, Pierre St.; Figueiredo, Renato; Tickoo, Omesh; Illikkal, Ramesh; Iyer, Ravishankar K.

doi:10.1109/ucc.2013.21

Cited by 43 publications

(23 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Offloading techniques make decisions statically based on prespecified rules, or dynamically based on context changes [17]. Dynamic decisions can be made using machine learning techniques [18] or based on analytical models [16,17,19,20]. Spectra [19] employs computation offloading to balance between performance and energy consumption.…”

Section: B Computation Offloadingmentioning

confidence: 99%

Cloud-Assisted Computation Offloading to Support Mobile Services

Elgazzar

Martin

Hassanein

2016

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

The widespread use and increasing capabilities of mobiles devices are making them a viable platform for offering mobile services. However, the increasing resource demands of mobile services and the inherent constraints of mobile devices limit the quality and type of functionality that can be offered, preventing mobile devices from exploiting their full potential as reliable service providers. Computation offloading offers mobile devices the opportunity to transfer resourceintensive computations to more resourceful computing infrastructures. We present a framework for cloud-assisted mobile service provisioning to assist mobile devices in delivering reliable services. The framework supports dynamic offloading based on the resource status of mobile systems and current network conditions, while satisfying the user-defined energy constraints. It also enables the mobile provider to delegate the cloud infrastructure to forward the service response directly to the user when no further processing is required by the provider. Performance evaluation shows up to 6x latency improvement for computation-intensive services that do not require large data transfer. Experiments show that the operation of the cloud-assisted service provisioning framework does not pose significant overhead on mobile resources, yet it offers robust and efficient computation offloading.

show abstract

Section: B Computation Offloadingmentioning

confidence: 99%

Cloud-Assisted Computation Offloading to Support Mobile Services

Elgazzar

Martin

Hassanein

2016

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

show abstract

“…Their evaluation shows that several real-time applications, including face recognition, arcade game, and language translation, achieve significant gains through offloading. A machine learning-based runtime scheduler is proposed to make offloading decisions based on previous behaviors and current conditions [18]. The most recent work on task scheduling in mobile clouds [17] aims to minimize the total energy consumed consumption of an application in mobile device under a hard completion time constraint.…”

Section: Related Workmentioning

confidence: 99%

An energy-efficient scheduling scheme for time-constrained tasks in local mobile clouds

Shi

Yang

et al. 2016

Pervasive and Mobile Computing

View full text Add to dashboard Cite

An energy-efficient scheduling scheme for time-constrained tasks in local mobile clouds, Pervasive and Mobile Computing (2015), http://dx. ABSTRACTMobile Cloud Computing (MCC) enables mobile devices to use resource providers other than mobile devices themselves to host the execution of mobile applications. Various mobile cloud architectures and scheduling algorithms have been studied recently. However, how to utilize MCC to enable mobile devices to run complex real-time applications while keeping high energy efficiency remains a challenge. In this paper, firstly, we introduce the local mobile clouds formed by nearby mobile devices and give the mathematical models of the mobile devices and their applications. Secondly, we formulate the scheduling problem in local mobile clouds. After describing the resource discovery scheme and the adaptive, probabilistic scheduling algorithm, we finally validate the performance of the proposed algorithm by simulation experiments.

show abstract

“…In our previous work [10], we studied a runtime scheduler for mobile offloading framework through detailed measurement experiments. With an OpenCL-based mobile offloading framework [16], we performed various experiments using four different OpenCL workload kernels used in a variety of areas such as image processing and simulations.…”

Section: A Offloading Performancementioning

confidence: 99%

“…In this approach, a machine learning classifier makes decisions of whether mobile computations should be offloaded to external resources, or executed locally. To this end, we extend our previous work on offline machine learning-based runtime scheduler [10], and develop a novel online scheduling module in which any appropriate machine learning classifier can be utilized for the runtime offloading scheduler. Furthermore, MALMOS provides an online training mechanism for the machine learning-based runtime scheduler such that it supports a policy that dynamically adapts scheduling decisions at runtime based upon the observation of previous offloading decisions and their correctness.…”

Section: Introductionmentioning

confidence: 99%

MALMOS: Machine Learning-Based Mobile Offloading Scheduler with Online Training

Eom

Figueiredo

Cai

et al. 2015

2015 3rd IEEE International Conference on Mobile Cloud Computing, Services, and Engineering

Self Cite

View full text Add to dashboard Cite

This paper proposes and evaluates MALMOS, a novel framework for mobile offloading scheduling based on online machine learning techniques. In contrast to previous works, which rely on application-dependent parameters or predefined static scheduling policies, MALMOS provides an online training mechanism for the machine learning-based runtime scheduler such that it supports a flexible policy that dynamically adapts scheduling decisions based on the observation of previous offloading decisions and their correctness. To demonstrate its practical applicability, we integrated MALMOS with an existing Java-based, offloading-capable code refactoring framework, DPartner. Using this integration, we performed quantitative experiments to evaluate the performance and cost for three machine learning algorithms: instance-based learning, perceptron, and naïve Bayes, with respect to classifier training time, classification time, and scheduling accuracy. Particularly, we examined the adaptability of MALMOS to various network conditions and computing capabilities of remote resources by comparing the scheduling accuracy with two static scheduling cases: threshold-based and linear equation-based scheduling policies. Our evaluation uses an Android-based prototype for experiments, and considers benchmarks with different computation/communication characteristics, and different computing capabilities of remote resources. The evaluation shows that MALMOS achieves 10.9%∼40.5% higher scheduling accuracy than two static scheduling policies.

show abstract

Machine Learning-Based Runtime Scheduler for Mobile Offloading Framework

Cited by 43 publications

References 13 publications

Cloud-Assisted Computation Offloading to Support Mobile Services

Cloud-Assisted Computation Offloading to Support Mobile Services

An energy-efficient scheduling scheme for time-constrained tasks in local mobile clouds

MALMOS: Machine Learning-Based Mobile Offloading Scheduler with Online Training

Contact Info

Product

Resources

About