Transferable Knowledge for Low-Cost Decision Making in Cloud Environments

Abstract

Users of Infrastructure as a Service (IaaS) are increasingly overwhelmed with the wide range of providers and services offered by each provider. As such, many users select services based on description alone. An emerging alternative is to use a decision support system (DSS), which typically relies on gaining insights from observational data in order to assist a customer in making decisions regarding optimal deployment of cloud applications. The primary activity of such systems is the generation of a prediction model (e.g. using machine learning), which requires a significantly large amount of training data. However, considering the varying architectures of applications, cloud providers, and cloud offerings, this activity is not sustainable as it incurs additional time and cost to collect data to train the models. We overcome this through developing a Transfer Learning (TL) approach where knowledge (in the form of a prediction model and associated data set) gained from running an application on a particular IaaS is transferred in order to substantially reduce the overhead of building new models for the performance of new applications and/or cloud infrastructures. In this paper, we present our approach and evaluate it through extensive experimentation involving three real world applications over two major public cloud providers, namely Amazon and Google. Our evaluation shows that our novel two-mode TL scheme increases overall efficiency with a factor of 60% reduction in the time and cost of generating a new prediction model. We test this under a number of cross-application and cross-cloud scenarios.

Price and Performance of Cloud-hosted Virtual Network Functions: Analysis and Future Challenges

“…Such data, obviously, comes at a cost, especially for large-scale infrastructures. Consequently, further efforts are needed to reduce such costs through either improved machine learning techniques (e.g., [28]) or through data augmentation from external sources such as CloudHarmony [29].…”

Artificial Intelligence as a Service

“…Easier sharing and pre-trained models also provide the foundations for transfer learning, referring to a method in which a model and associated data developed for a particular task are used as a building block to solve a different problem (Samreen et al 2020).…”

Optimizing Deep Learning Inference on Embedded Systems Through Adaptive Model Selection

“…Optimizing Deep Learning Inference on Embedded Systems 1:23 ℧achine learning has been employed for various optimization tasks, including code optimization [7, 8, 10, 11, 22, 48, 49, 67, 70, 74ś79, 81], task scheduling [12,16,20,21,45,55,56], cloud deployment [59,60], network management [72], etc. Our approach is closely related to ensemble learning where multiple models are used to solve an optimization problem.…”