Symbiotic Simulation System: Hybrid Systems Model Meets Big Data Analytics

Onggo, Bhakti Stephan; Mustafee, Navonil; Smart, Andi; Juan, Ángel A.; Molloy, Owen

doi:10.1109/wsc.2018.8632407

Cited by 38 publications

(18 citation statements)

References 36 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, these methods do not scale well [42]. Finally, coupled or symbiotic simulation and model based control have long been used in the modelling and optimization of distributed systems [25], [43], [44]. Many prior works have used hybrid simulation models to optimize decision making in dynamic systems.…”

Section: Related Workmentioning

confidence: 99%

“…Further optimization of QoS in such cases is hard and more intelligent schemes are required. Coupled-simulation (also referred as co-simulation or symbiotic simulation) and execution of tasks have been shown to be a promising approach for quickly obtaining an estimate of QoS parameters in the near future [23], [24], [25]. Specifically, coupled-simulation allows us to run a simulator in the background with the scheduling algorithms to facilitate decision making.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

COSCO: Container Orchestration Using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

Tuli

Poojara

Srirama

et al. 2022

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Intelligent task placement and management of tasks in large-scale fog platforms is challenging due to the highly volatile nature of modern workload applications and sensitive user requirements of low energy consumption and response time. Container orchestration platforms have emerged to alleviate this problem with prior art either using heuristics to quickly reach scheduling decisions or AI driven methods like reinforcement learning and evolutionary approaches to adapt to dynamic scenarios. The former often fail to quickly adapt in highly dynamic environments, whereas the latter have run-times that are slow enough to negatively impact response time. Therefore, there is a need for scheduling policies that are both reactive to work efficiently in volatile environments and have low scheduling overheads. To achieve this, we propose a Gradient Based Optimization Strategy using Back-propagation of gradients with respect to Input (GOBI). Further, we leverage the accuracy of predictive digital-twin models and simulation capabilities by developing a Coupled Simulation and Container Orchestration Framework (COSCO). Using this, we create a hybrid simulation driven decision approach, GOBI*, to optimize Quality of Service (QoS) parameters. Co-simulation and the back-propagation approaches allow these methods to adapt quickly in volatile environments. Experiments conducted using real-world data on fog applications using the GOBI and GOBI* methods, show a significant improvement in terms of energy consumption, response time, Service Level Objective and scheduling time by up to 15, 40, 4, and 82 percent respectively when compared to the state-of-the-art algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

COSCO: Container Orchestration Using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

Tuli

Poojara

Srirama

et al. 2022

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…Another promising approach to describe the interaction between a simulation model and its physical counterpart is 'symbiotic simulation' [1]. Such simulation systems are designed to support decisionmaking at operational levels by making use of (near) real-time data generated by the physical system and streamed to the development of the simulation model [28]. This topic is linked to the definition of Digital Twins described later in this study.…”

Section: Related Workmentioning

confidence: 99%

Multi-Agent Systems and Digital Twins for Smarter Cities

Clemen

Ahmady-Moghaddam

Lenfers

et al. 2021

Proceedings of the 2021 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

View full text Add to dashboard Cite

An intelligent combination of the Internet of Things (IoT) and approaches to modeling and simulation is one of the most challenging endeavors for future cities, manufacturing industries, and predictive maintenance. Digital Twins take on a unique role here. However, the question of what a Digital Twin is and what differentiates it from a regular model is still open. We present an experimental setup for integrating an existing simulation model of Hamburg's traffic system with the city's real-time sensor network. The Digital Twin is implemented using the large-scale multi-agent framework MARS. The entire process from the model description to retrieving real-time data from the IoT sensors and incorporating it in the simulation is presented. As a first prototypical example, a multi-modal mobility model was connected to real-world bike-sharing locations in Hamburg. We find that the combination of multi-agent systems and IoT sensors as a Digital Twin shows enormous potential for city planners, policy stakeholders, and other decision-makers. By correcting the course of a simulation via real-time data, the corridorof-uncertainty that is intrinsic to some simulation models' use can be reduced significantly. Furthermore, any divergence of simulated and sampled data can lead to a deeper understanding of complex adaptive systems like big cities. CCS CONCEPTS• Computing methodologies → Multi-agent systems; Simulation types and techniques.

show abstract

“…Finally, ML is a key constituent in the modelling of a digital twin, as it is stipulated for symbiotic simulation approaches, and further be referred to as the result of HSM in [15]. Here, ML enables a digital twin that is a virtual representation of a physical system, as it allows the systems simulation model under observation to adapt primarily according to the behaviour of variables controlled by the physical system in question, and not the intentions of the shareholder of the model.…”

Section: T Nmentioning

confidence: 99%

On the Usage of Deep Learning for Modelling Energy Consumption in Simulation Models

Woerrlein¹,

Straßburger²

2020

SNE

View full text Add to dashboard Cite

With the increasing availability of data, the desire to interpret that data and use it for behavioral predictions arises. Traditionally, simulation has used data about the real system for input data analysis or within datadriven model generation. Automatically extracting behavioral descriptions from the data and representing it in a simulation model is a challenge for these approaches. Machine learning on the other hand has proven successful in extracting knowledge from large data sets and transforming it into more useful representations. Combining simulation approaches with methods from machine learning seems, therefore, promising. Representing some aspects of a real system by a traditional simulation model and others by a model generated from machine learning, a hybrid system model (HSM) is generated. This paper discusses such HSMs and suggests a specific HSM incorporating a deep learning method for predicting the power consumption of machining jobs.

show abstract

Symbiotic Simulation System: Hybrid Systems Model Meets Big Data Analytics

Abstract: The version presented here may differ from the published version. If citing, you are advised to consult the published version for pagination, volume/issue and date of publication

Cited by 38 publications

References 36 publications

COSCO: Container Orchestration Using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

COSCO: Container Orchestration Using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

Multi-Agent Systems and Digital Twins for Smarter Cities

On the Usage of Deep Learning for Modelling Energy Consumption in Simulation Models

Contact Info

Product

Resources

About