Toward scalable cloud data center simulation using high‐level architecture

Abstract

Existing simulators are designed to simulate a few thousand nodes due to the tight integration of modules. Thus, with limited simulator scalability, researchers/developers are unable to simulate protocols and algorithms in detail, although cloud simulators provide geographically distributed data centers environment but lack the support for execution on distributed systems.In this paper, we propose a distributed simulation framework referred to as CloudSimScale. The framework is designed on top of highly adapted CloudSim with communication among different modules managed using IEEE Std 1516 (high-level architecture). The underlying modules can now run on the same or different physical systems and still manage to discover and communicate with one another. Thus, the proposed framework provides scalability across distributed systems and interoperability across modules and simulators. KEYWORDSbroker, cloud computing, CloudSim, distributed simulation, HLA, RTI INTRODUCTIONCloud data centers provide services in the form of infrastructure-as-a-service (IaaS), platform-as-a-service (PaaS), and software-as-a-service (SaaS). With flexible resource provisioning model on back-end data centers, it allows users to deploy applications from anywhere using dynamically allocated resources as per requirements in the service-level agreement. The most well-known cloud service providers are Amazon EC2 * , Microsoft Azure † , Google cloud ‡ , and IBM § with emerging cloud-based applications like content delivery, navigation systems, social networks, and many more.Evidently, the main contribution of cloud computing is the provision of a dynamic virtual environment that scales transparently to support a large number of users concurrently. This comes with provisioning of cloud services in pay-as-you-go-model, while the cloud providers are responsible for ensuring the quality of services. In general, it is difficult Abbreviations: IaaS, infrastructure-as-a-service; HLA, high-level architecture; RTI, runtime infrastructure; LRC, local RTI components; CRC, central RTI component; CIS, cloud information service.Recent contributions in cloud simulation environment mainly focus on scheduling algorithms, VM migrations, software-defined networking-based networking, and energy efficiency. However, there is limited work toward scalability of existing simulators. Most of them at most support simulation with a few thousands of nodes. Due to this limitation, researchers often find it difficult to simulate realistic data center models. In this paper, we have proposed CloudSim-Scale based on CloudSim to provide access to a scalable environment for researchers. The framework decouples existing CloudSim modules so that they can be independently placed on different systems. Thus, to support the resulting intercommunication among the modules, a separate layer of HLA-RTI is implemented. Furthermore, CloudSimScale allows the integration of various simulators to facilitate researchers in simulating complex scenarios. For instance, internet of things (IoT)/edge s...

Data interoperability between DDS and HLA through a dynamically reconfigurable gateway

“…Ghazouani et al suggest semantic techniques to ease multi‐cloud service heterogeneity 40 . In Reference 41, HLA is employed in a proposed framework to improve scalability for cloud simulations.…”

CloudSim express: A novel framework for rapid low code simulation of cloud computing environments

“…10 Another approach attempts to reduce the effort required for developing scaling simulations by adopting IEEE standards for interoperability. 36 However, it still requires considerable programming effort to implement the scenario. Another proposal suggests simplifying existing simulation approaches by providing flexible combinations of different functional components.…”

“…Most such approaches allow implementing end‐to‐end simulations without coding involved, or with a reduced amount of code 10 . Another approach attempts to reduce the effort required for developing scaling simulations by adopting IEEE standards for interoperability 36 . However, it still requires considerable programming effort to implement the scenario.…”

Evolution towards Smart and Software-Defined Internet of Things

“…New IoT frameworks, designs, and products need to be tested and verified before they are deployed or rolled out at a large scale into the production environment [85]. Creating a testing environment with a large number of IoT devices and a huge network may not always be a viable solution financially as well as technically [86].…”