Data Processing on Edge and Cloud: A Performability Evaluation and Sensitivity Analysis

Santos, Lucas; Cunha, Benedito; Fé, Iure; Vieira, Marco; Silva, Francisco Airton Pereira da

doi:10.1007/s10922-021-09592-x

Cited by 27 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Of course, some parameters have a greater impact on metrics than others. In this case, it should be valuable to carry out a sensitivity analysis [ 51 , 52 , 53 ] to find out where the appraiser should invest in optimizing the system’s behavior. Another topic is the abstraction that the model allows obtaining.…”

Section: Simulation Resultsmentioning

confidence: 99%

Performability Evaluation of Load Balancing and Fail-over Strategies for Medical Information Systems with Edge/Fog Computing Using Stochastic Reward Nets

Nguyen

Fé

Brito

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The aggressive waves of ongoing world-wide virus pandemics urge us to conduct further studies on the performability of local computing infrastructures at hospitals/medical centers to provide a high level of assurance and trustworthiness of medical services and treatment to patients, and to help diminish the burden and chaos of medical management and operations. Previous studies contributed tremendous progress on the dependability quantification of existing computing paradigms (e.g., cloud, grid computing) at remote data centers, while a few works investigated the performance of provided medical services under the constraints of operational availability of devices and systems at local medical centers. Therefore, it is critical to rapidly develop appropriate models to quantify the operational metrics of medical services provided and sustained by medical information systems (MIS) even before practical implementation. In this paper, we propose a comprehensive performability SRN model of an edge/fog based MIS for the performability quantification of medical data transaction and services in local hospitals or medical centers. The model elaborates different failure modes of fog nodes and their VMs under the implementation of fail-over mechanisms. Sophisticated behaviors and dependencies between the performance and availability of data transactions are elaborated in a comprehensive manner when adopting three main load-balancing techniques including: (i) probability-based, (ii) random-based and (iii) shortest queue-based approaches for medical data distribution from edge to fog layers along with/without fail-over mechanisms in the cases of component failures at two levels of fog nodes and fog virtual machines (VMs). Different performability metrics of interest are analyzed including (i) recover token rate, (ii) mean response time, (iii) drop probability, (iv) throughput, (v) queue utilization of network devices and fog nodes to assimilate the impact of load-balancing techniques and fail-over mechanisms. Discrete-event simulation results highlight the effectiveness of the combination of these for enhancing the performability of medical services provided by an MIS. Particularly, performability metrics of medical service continuity and quality are improved with fail-over mechanisms in the MIS while load balancing techniques help to enhance system performance metrics. The implementation of both load balancing techniques along with fail-over mechanisms provide better performability metrics compared to the separate cases. The harmony of the integrated strategies eventually provides the trustworthiness of medical services at a high level of performability. This study can help improve the design of MIS systems integrated with different load-balancing techniques and fail-over mechanisms to maintain continuous performance under the availability constraints of medical services with heavy computing workloads in local hospitals/medical centers, to combat with new waves of virus pandemics.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Performability Evaluation of Load Balancing and Fail-over Strategies for Medical Information Systems with Edge/Fog Computing Using Stochastic Reward Nets

Nguyen

Fé

Brito

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Redes de Petri permitem modelar propriedades de concorrência e sincronia de sistemas [Santos et al 2021]. A Figura 2 representa um modelo SPN, para a arquitetura proposta na Figura 1.…”

Section: Modelo De Spnunclassified

Modelagem e Análise da Comunicação em VANETs com uso de RSUs

Macêdo¹,

Carvalho²,

Andrade³

et al. 2022

Anais Do XXI Workshop Em Desempenho De Sistemas Computacionais E De Comunicação (WPerformance 2022)

Self Cite

View full text Add to dashboard Cite

Escalabilidade e processamento paralelo são características inerentes às redes veiculares ou VANETs (Vehicular Ad hoc NETworks). A implementação de VANETs pode envolver elevado custo e por serem sistemas críticos, possuem requisitos específicos que exigem configurações heterogêneas. O crescimento da rede aumenta a complexidade e fica propenso a erros, tais como disseminação de dados, perda de pacotes e atraso. Dado o custo de implementação de VANETs, as ferramentas de simulação surgem como alternativa para avaliar configurações apropriadas. Simuladores permitem verificar interações complexas em diversas configurações, compreender o comportamento do sistema e propor otimizações. A análise prévia permite dimensionar corretamente o sistema e minimizar o custo envolvido, seja na ampliação, seja na redução da quantidade de dispositivos. Este trabalho apresenta um modelo Stochastic Petri Net voltado para VANETs com Road Side Units (RSU), onde foram avaliadas as métricas tempo médio de resposta (MRT), probabilidade de descarte de mensagens, taxa de utilização da camada network WIFI e taxa de utilização da camada Edge RSU. A bateria de testes foi executada com variações na taxa chegada de requisições. A partir do estudo realizado foi possível verificar que a alta performance na camada Wifi deixa subutilizada a camada Edge RSU.

show abstract

“…System designers often adopt sensitivity analysis to evaluate how “sensitive” a metric is to changes in the model [ 49 ]. The parameters to be changed are defined using an experiment plan.…”

Section: Sensitivity Analysis With Doementioning

confidence: 99%

IoT Sensor Networks in Smart Buildings: A Performance Assessment Using Queuing Models

Santos

Soares

Nguyen

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Smart buildings in big cities are now equipped with an internet of things (IoT) infrastructure to constantly monitor different aspects of people’s daily lives via IoT devices and sensor networks. The malfunction and low quality of service (QoS) of such devices and networks can severely cause property damage and perhaps loss of life. Therefore, it is important to quantify different metrics related to the operational performance of the systems that make up such computational architecture even in advance of the building construction. Previous studies used analytical models considering different aspects to assess the performance of building monitoring systems. However, some critical points are still missing in the literature, such as (i) analyzing the capacity of computational resources adequate to the data demand, (ii) representing the number of cores per machine, and (iii) the clustering of sensors by location. This work proposes a queuing network based message exchange architecture to evaluate the performance of an intelligent building infrastructure associated with multiple processing layers: edge and fog. We consider an architecture of a building that has several floors and several rooms in each of them, where all rooms are equipped with sensors and an edge device. A comprehensive sensitivity analysis of the model was performed using the Design of Experiments (DoE) method to identify bottlenecks in the proposal. A series of case studies were conducted based on the DoE results. The DoE results allowed us to conclude, for example, that the number of cores can have more impact on the response time than the number of nodes. Simulations of scenarios defined through DoE allow observing the behavior of the following metrics: average response time, resource utilization rate, flow rate, discard rate, and the number of messages in the system. Three scenarios were explored: (i) scenario A (varying the number of cores), (ii) scenario B (varying the number of fog nodes), and (iii) scenario C (varying the nodes and cores simultaneously). Depending on the number of resources (nodes or cores), the system can become so overloaded that no new requests are supported. The queuing network based message exchange architecture and the analyses carried out can help system designers optimize their computational architectures before building construction.

show abstract

Data Processing on Edge and Cloud: A Performability Evaluation and Sensitivity Analysis

Cited by 27 publications

References 35 publications

Performability Evaluation of Load Balancing and Fail-over Strategies for Medical Information Systems with Edge/Fog Computing Using Stochastic Reward Nets

Performability Evaluation of Load Balancing and Fail-over Strategies for Medical Information Systems with Edge/Fog Computing Using Stochastic Reward Nets

Modelagem e Análise da Comunicação em VANETs com uso de RSUs

IoT Sensor Networks in Smart Buildings: A Performance Assessment Using Queuing Models

Contact Info

Product

Resources

About