Application of Cloud-Based Simulation in Scientific Research

Application of Cloud-Based Simulation in Scientific Research

Mihailo Marinković (Telenor, Serbia), Sava Čavoški (MDS Information Engineering, Serbia) and Aleksandar Marković (University of Belgrade, Serbia)
DOI: 10.4018/978-1-4666-5784-7.ch012

Abstract

This chapter is a review of the literature related to the use of cloud-based computer simulations in scientific research. The authors examine the types and good examples of cloud-based computer simulations, offering suggestions for the architecture, frameworks, and runtime infrastructures that support running simulations in cloud environment. Cloud computing has become the standard for providing hardware and software infrastructure. Using the possibilities offered by cloud computing platforms, researchers can efficiently use the already existing IT resources in solving computationally intensive scientific problems. Further on, the authors emphasize the possibilities of using the existing and already known simulation models and tools in the cloud computing environment. The cloud environment provides possibilities to execute all kinds of simulation experiments as in traditional environments. This way, models are accessible to a wider range of researchers and the analysis of data resulting from simulation experiments is significantly improved.
Chapter Preview
Top

Introduction

In last couple of years, Cloud Computing has become a standard for delivering hardware and software infrastructure. It is based on a pay-per-use business model where resources are acquired only when really needed and customer pays only for resources actually used. Cloud computing represents the mechanism for dealing with the use of external services as part of the computational foundation (Tor-Morten, 2012). It provides scalable, distributed computer services as needed. The aim of cloud computing is to present a service layer for its users where all detailed logic is made transparent and drawn upon as needed. In general, cloud computing is recognized as an infrastructure where all underlying resources (storage, RAM, processors, load balancers etc.) are completely abstracted from the end user. This leads to the cloud provider/vendor to be in charge of performance, reliability and scalability. Gartner defines cloud computing as a style of computing in which scalable and elastic IT-enabled capabilities are delivered as a service using Internet technologies (Gartner, 2013). The National Institute of Standards and Technology (NIST) defines cloud computing as:

A model for enabling ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, storage, applications, and services) that can be rapidly provisioned and released with minimal management effort or service provider interaction (Peter & Grance, 2011).

The same authors list three service models: Infrastructure as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (SaaS). The same source, and also other authors (Jeffery & Neidecker-Lutz, 2010) provide five essential characteristics (On-demand self-service, Broad network access, Resource pooling, Rapid elasticity and Measured Service), and four deployment models (Private, Community, Public and Hybrid cloud). The introduction of Cloud Computing had a significant impact on all segments of IT industry, including computer-based modeling and simulation.

Cloud Computing Expert Group (Jeffery & Neidecker-Lutz, 2010) provided an overview of all main aspects of Cloud Computing (Figure 1).

Figure 1.

Main aspects of clouds (Adapted from [Jeffery & Neidecker-Lutz, 2010])

This chapter offers an overview of the existing cloud-based simulation software and explores the possibilities of using the existing simulation models and tools in this new environment. One of the hypotheses is that it is possible to reuse existing models and tools in cloud environment and also to improve them. In Cloud environment it is possible to execute all kinds of simulations, which are used in traditional environment, while models availability and analysis of results of simulation experiments can be significantly improved.

Simulation, in this context, refers to the process of creating abstract models out of real existing or future systems and their use for performing experiments. When computers are used for performing simulation experiments, then we are talking about computer simulation (Radenković, Stanojević, & Marković, 2010). Computing infrastructure is the foundation for computer simulation and has a significant impact on simulation model development process and simulation experiment execution. Computer simulation dates back to mainframe systems period and has been continuously improved and developed along with the development of IT infrastructure, services and technologies. The development of Cloud infrastructure and services has also impacted on the development in the field of computer modeling and simulation, mostly in simulation experiment execution techniques and analysis of data resulting from these experiments.

Top

Web Based Simulation

We may say that cloud computing is perceived as one of the most significant achievement for the entire IT industry. Cloud computing offers exactly this: the IT infrastructure and software as a service. The same applies to the simulation. The first step was the adjustment of the existing simulation tools for Internet use. Hence, in the following we will briefly address web-based simulations.

Key Terms in this Chapter

Simulation Software as a Service: Is a new way of using existing simulation tools in cloud environment. It involves a new emerging paradigm where simulation software and its associated data are hosted centrally in the cloud and researchers can use simulation software as “on-demand software.”

Discrete Event System Specification: A modular and hierarchical formalism for modeling and analyzing general systems that can be: discrete event systems, described by state transition tables, continuous state systems, described by differential equations, and hybrid continuous state and discrete event systems.

Multi-Tenant Architecture: Multi-tenancy refers to a principle in software architecture where a single instance of software runs on a server, serving multiple users (tenants).

Scientific Research: Entails the use of scientific methods and theories and their application to individual phenomenon.

Web-Based Simulation: Entails the integration of the Web technologies within the field of simulation in order to use simulation tools and perform simulation experiments on the Web.

Cloud-Based Simulation: Is an approach that provides a new way to utilize computing resources in the simulation, which means infrastructure, platform, and software for researchers and scientists that they use as a service.

Simulation Models: A special type of model implemented in one of the simulation languages suitable for performing experiments on their computers.

Service-Oriented Simulation Experiment: Uses cloud infrastructure and simulation software as service. The cloud system can automatically control and optimize needed resources depending on demand of experiment.

Complete Chapter List

Search this Book:
Reset