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

Abstract

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.

A Novel Two-Layered Reinforcement Learning for Task Offloading with Tradeoff between Physical Machine Utilization Rate and Delay

“…The platform optimized computation partitioning scheme and tunable parameter setting for getting a higher comprehensive performance, based on history-based platform-learned knowledge, developer-provided information and the platform-monitored environment conditions. Eom et al [16] proposed a framework for mobile offloading scheduling based on online machine learning. The framework provided an online training mechanism for the machine learning-based runtime scheduler, which supported a flexible policy.…”

Review on Compute Augmentation Techniques in Mobile Cloud Computing

“…Heungsik Eorn et al, [13] proposed MALMOS (Machine Learning-based Mobile Offloading Scheduler) framework with online training. MALMOS can be applied to any types of mobile offloading framework.…”

Autonomous Context-Based Service Optimization in Mobile Cloud Computing

“…One of the few solutions that enables online analysis is the MALMOS framework [46], which makes it possible to decide, with the application of machine learning technologies, when to offload applications from the mobile device to the cloud. For the offloading itself, the solution uses the DPartner environment (Java-based on-demand offloading framework).…”

“…As a result, there is no special learning mode, because training data can be collected during normal runtime. To estimate training phase duration, an adaptive online training mechanism is proposed in [46]. In our solution, such a strategy is not required and the system is simpler.…”