MobFogSim: Simulation of mobility and migration for fog computing

doi:10.1016/j.simpat.2019.102062

Simulation Modelling Practice and Theory

Volume 101, May 2020, 102062

https://doi.org/10.1016/j.simpat.2019.102062 Get rights and content

Abstract

Fog computing is an extension of the cloud towards the network edge that brings resources and services of computing in closer proximity to end users. This proximity provides several benefits such as reduced latency that improves user experience. However, user mobility may limit such benefits in practice, as the distance to a fog service may vary as a user moves from one location to another. Migration of a fog service may be one possible mitigation strategy, enabling the service to always be close enough to a user. Although many simulators exist for evaluating application behaviour and performance within a fog computing environment, none allows evaluation of service migration solutions to support mobility. MobFogSim is presented in this work to overcome this limitation. It extends iFogSim to enable modelling of device mobility and service migration in fog computing. MobFogSim is validated by comparing simulation results with those obtained from a real testbed where fog services are implemented as containers. Additional experiments are carried out in MobFogSim taking account of various mobility patterns of a user, derived from Luxembourg SUMO Traffic (LuST). We use an experiment-based approach to study the impact of user mobility on container migration in fog computing.

Introduction

The Internet has become the largest and most popular mechanism for communication among people, corporations, and governments around the world. Furthermore, a number of devices are connected to the Internet, consuming and generating data as well as offering a variety of computing services. Such devices can be fixed or mobile, for example carried by their users or attached to a vehicle. Nowadays, many applications and services running on fixed or mobile devices rely on remote services, as in cloud computing servers [1], [2], to store data and/or perform data processing. One of the limitations of using remote devices for storage and computing is the potentially large latency experienced by users. In general, data centres can be far away from the end device running the application, causing increased delays to access data and higher turnaround times for processing.

Fog computing [3] was proposed to overcome these limitations. Fog computing extends the cloud towards the network edge, distributing resources and services of computing as close as the user’s access point, thus only one hop away from end devices. It is worth highlighting that fog computing does not replace the cloud but rather complements it. Fog computing therefore does not only reduce network delays but also: (i) lowers bandwidth consumption; (ii) improves security and privacy; (iii) provides better context awareness; and (iv) enables uninterrupted services in case of intermittent connectivity to the cloud [4]. Devices hosting fog computing services are known as fog nodes, cloudlets, or micro data-centres (MDC).

User mobility may impair fog computing performance. This is because mobility causes a change of the access points, which may increase the delay to the fog service hosted in the original cloudlet/MDC [5]. When a mobile user changes access point, ideally their data and current applications being processed should migrate to the cloudlet at the new access point to minimise access delay. To accomplish this, we assume that the user has a virtual machine (VM) or a container, similarly to cloud computing services, that contains her/his processes and data. Understanding where each application (or its components) should run and where data should be kept involves a multi-layered infrastructure with heterogeneous devices and networks as well as applications that have heterogeneous requirements and can move along the infrastructure. Simulation can be a time- and cost-effective way to evaluate VM/container migration solutions in fog computing environments with mobile users.

In a previous work [6], we introduced mobility concepts to iFogSim in a preliminary support for mobility. In this paper, we present MobFogSim, an open-source³ simulator that extends the preliminary work from [6] to model more generalised aspects related to device mobility and VM/container migration in the fog, e.g., user position and speed, connection handoff, migration policies and strategies, to name a few. The contribution of this paper is threefold:

•
We discuss the design considerations and the implementation details of MobFogSim, highlighting aspects required to model device mobility and VM/container migration in fog computing;
•
We validate MobFogSim by comparing its container migration results with those obtained from a real testbed;
•
We study the impact of user mobility on container migration in fog computing. This is achieved by running simulations in MobFogSim where users move with different mobility patterns taken from Luxembourg SUMO Traffic (LuST). The approach can be generalised to other (similar) mobility patterns.

The rest of the paper is organised as follows. Section 2 provides a general background on VM/container migration in fog computing and describes the events that occur during connection handoff and VM/container migration. Section 3 briefly outlines the features available in iFogSim and describes the design considerations for VM/container migration modelling in MobFogSim. In Section 4 we provide implementation details of MobFogSim, comparing it with iFogSim. Section 5 describes the experiments that we carried out over a real testbed to obtain seed values for supporting simulation in MobFogSim. Results of container migration over the testbed are also described in this section. In Section 6 we validate MobFogSim by comparing its results against those from the testbed. Section 7 reviews existing fog computing simulators, describing difference with MobFogSim. Finally, Section 8 provides the key conclusions we can draw from the simulations.

Section snippets

Basic concepts

In this section, we briefly introduce fog computing, virtualisation and migration concepts as well as the migration model considered in the proposed simulator.

Design considerations

MobFogSim is a simulator that extends iFogSim to model aspects related to device mobility and VM/container migration in fog computing. We had already incorporated new features into iFogSim in a previous work [6]. In this paper, we extend that preliminary version to cover a wider set of parameters as well as to support mobility by integrating our simulator with the mobility tool Simulation of Urban Mobility (SUMO) [9]. These modifications, which allow more generalised mobility simulations in fog

Implementation details

In this section, we discuss the most noteworthy aspects relative to the implementation of MobFogSim. In Section 4.1, we report the main Java classes that make MobFogSim an extension of iFogSim with support to device mobility and VM/container migration. Then, in Section 4.2, we focus on the simulation events and their flow within the migration and handoff procedure. Finally, Section 4.3 illustrates how we extended the preliminary version of MobFogSim to support realistic user’s mobility patterns.

Simulator calibration and container migration over a real testbed

The objective of this section is twofold. Firstly, in Sections 5.1–5.3, we describe the experiments that we carried out over a real testbed to calibrate MobFogSim (i.e., to obtain realistic input values for the next simulations). Such a testbed, which is depicted in Fig. 14 and is detailed in the following sections, is the same that was used in [13] to evaluate container migration techniques in fog computing. Secondly, in Section 5.4, we report from [13] the main container migration results

MobFogSim evaluation

In this section, we evaluate MobFogSim. Specifically, Section 6.1 validates our simulator by comparing its results of container migration with those from the real testbed. Then, in Section 6.2, we employ MobFogSim to assess how user’s mobility impacts on container migration in the fog. To this purpose, we run simulations where users move with different realistic mobility patterns taken from urban buses of Luxembourg.

Related work

In this section, we review the state-of-the-art simulators for fog computing environments and highlight the comprehensiveness and novelty of MobFogSim. Table 4 summarises the main characteristics of these simulators, with a focus on mobility support.

VirtFogSim [21] does not model aspects such as VM/container migration, energy consumption, or pricing. However, it dynamically tracks the energy-delay application performance against abrupt changes due to failures or device mobility, e.g.,

Conclusions

The need to support VM/container migration in fog computing (particularly for mobile users) has been outlined in this paper. Migration can take account of geographical location of cloudlets with reference to the user, the direction and speed of travel of the user, and the network characteristics between the user and the cloudlet. The migration process has been described as a set of events (identified in a number of different scenarios), taking account of both migration and handoff strategies.

Acknowledgments

The authors would like to thank the following agencies for partially supporting this research: Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); the São Paulo Research Foundation (FAPESP), grant #2015/16332-8; the INCT of the Future Internet for Smart Cities funded byCNPq proc. 465446/2014-0, Coordenação de Aperfeiçoamento de Pessoal de NÃvel Superior - Brasil (CAPES) - Finance Code 001, FAPESP proc. 14/50937-1, and FAPESP proc. 15/24485-9; the Italian Ministry of Education

References (26)

N. Fernando et al.
Mobile cloud computing: A Survey
Future Generat. Comput. Syst.
(2013)
M. Aazam et al.
Cloud of Things: Integration of IoT With Cloud Computing
(2016)
F. Bonomi et al.
Fog Computing and Its Role in the Internet of Things
Proceedings of the 1st MCC Workshop on Mobile Cloud Computing
(2012)
C. Puliafito et al.
Fog computing for the internet of things: a survey
ACM Trans. Int. Technol.
(2019)
L.F. Bittencourt et al.
Mobility-Aware application scheduling in fog computing
IEEE Cloud Comput.
(2017)
M.M. Lopes et al.
MyiFogSim: A simulator for virtual machine migration in fog computing
Proceedings of the 6th International Workshop on Clouds and (eScience) Applications Management (CloudAM). Companion Proceedings of the 10th International Conference on Utility and Cloud Computing
(2017)
C. Puliafito et al.
Fog Computing for the Internet of Mobile Things: Issues and Challenges
Proceedings of the IEEE 3rd International Conference on Smart Computing (SMARTCOMP)
(2017)
D. Gonçalves et al.
Proactive Virtual Machine Migration in Fog Environments
Proceedings of the IEEE Symposium on Computers and Communications (ISCC)
(2018)
M. Behrisch et al.
SUMO - Simulation of Urban Mobility: An Overview
Proceedings of the 3rd International Conference on Advances in System Simulation (SIMUL)
(2011)
H. Gupta et al.
iFogSim: A Toolkit for modeling and simulation of resource management techniques in the internet of things, edge and fog computing environments
Software: Pract. Exper.
(2017)

R.N. Calheiros et al.

Cloudsim: A Toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms

Softw. Practice Exper.

(2011)

L.F. Bittencourt et al.

Towards virtual machine migration in fog computing

Proceedings of the 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC)

(2015)

C. Puliafito et al.

Container migration in the fog: A Performance evaluation

MDPI Sensors

(2019)

Cited by (89)

EneA-FL: Energy-aware orchestration for serverless federated learning
2024, Future Generation Computer Systems
Federated Learning (FL) represents the de-facto standard paradigm for enabling distributed learning over multiple clients in real-world scenarios. Despite the great strides reached in terms of accuracy and privacy awareness, the real adoption of FL in real-world scenarios, in particular in industrial deployment environments, is still an open thread. This is mainly due to privacy constraints and to the additional complexity stemming from the set of hyperparameters to tune when employing AI techniques on bandwidth-, computing-, and energy-constrained nodes. Motivated by these issues, we focus on scenarios where participating clients are characterised by highly heterogeneous computing capabilities and energy budgets proposing EneA-FL, an innovative scheme for serverless smart energy management. This novel approach dynamically adapts to optimise the training process while fostering seamless interaction between Internet of Things (IoT) devices and edge nodes. In particular, the proposed middleware provides a containerised software module that efficiently manages the interaction of each worker node with the central aggregator. By monitoring local energy budget, computational capabilities, and target accuracy, EneA-FL intelligently takes informed decisions about the inclusion of specific nodes in the subsequent training rounds, effectively balancing the tripartite trade-off between energy consumption, training time, and final accuracy. Finally, in a series of extensive experiments across diverse scenarios, our solution demonstrates impressive results, achieving between 30% and 60% lower energy consumption against popular client selection approaches available in the literature while being up to 3.5 times more efficient than standard FL solutions.
FedHealthFog: A federated learning-enabled approach towards healthcare analytics over fog computing platform
2024, Heliyon
The emergence of federated learning (FL) technique in fog-enabled healthcare system has leveraged enhanced privacy towards safeguarding sensitive patient information over heterogeneous computing platforms. In this paper, we introduce the FedHealthFog framework, which was meticulously developed to overcome the difficulties of distributed learning in resource-constrained IoT-enabled healthcare systems, particularly those sensitive to delays and energy efficiency. Conventional federated learning approaches face challenges stemming from substantial compute requirements and significant communication costs. This is primarily due to their reliance on a singular server for the aggregation of global data, which results in inefficient training models. We present a transformational approach to address these problems by elevating strategically placed fog nodes to the position of local aggregators within the federated learning architecture. A sophisticated greedy heuristic technique is used to optimize the choice of a fog node as the global aggregator in each communication cycle between edge devices and the cloud. The FedHealthFog system notably accounts for drop in communication latency of 87.01%, 26.90%, and 71.74%, and energy consumption of 57.98%, 34.36%, and 35.37% respectively, for three benchmark algorithms analyzed in this study. The effectiveness of FedHealthFog is strongly supported by outcomes of our experiments compared to cutting-edge alternatives while simultaneously reducing number of global aggregation cycles. These findings highlight FedHealthFog's potential to transform federated learning in resource-constrained IoT environments for delay-sensitive applications.
Analyzing the performance of persistent storage for fault-tolerant stateful fog applications
2023, Journal of Systems Architecture
In this paper, we analyze the scalability and performance of a persistent, fault-tolerant storage approach that provides data availability and consistency in a distributed container-based architecture with intended use in industrial control applications. We use simulation to evaluate the performance of this storage system in terms of scalability and failures. As the industrial applications considered have timing constraints, the simulation results show that for certain failure patterns, it is possible to determine whether the storage solution can meet critical deadlines. The presented approach is applicable for evaluating timing constraints also of other container-based critical applications that require persistent storage.
EdgeSimPy: Python-based modeling and simulation of edge computing resource management policies
2023, Future Generation Computer Systems
The increasing popularity of applications with tight latency requirements has motivated research on Edge Computing, which positions computing resources near data sources at the Internet’s edge. Despite the emergence of simulation tools that make prototype validation less complex, time-consuming, and expensive, researchers and practitioners still face significant challenges when developing resource management strategies for the edge, as existing simulators fall short in providing a fine-grained model of edge applications provisioning. To overcome this challenge, we propose EdgeSimPy, a simulation framework written in Python for modeling and evaluating resource management policies in Edge Computing environments. EdgeSimPy features a modular architecture that incorporates several functional abstractions for edge servers, network devices, and applications with built-in models for user mobility, application composition, and power consumption that allow the simulation of various scenarios. Furthermore, we propose a novel conceptual model that accurately represents the entire lifecycle of edge applications and ensures seamless integration with real application traces. In addition to submitting EdgeSimPy to an in-depth verification that checks the simulator implementation, we discuss case studies that show EdgeSimPy in action in different large-scale scenarios.
Resilience and load balancing in Fog networks: A Multi-Criteria Decision Analysis approach
2023, Microprocessors and Microsystems
The advent of Cloud Computing enabled the proliferation of Internet-of-Things (IoT) applications for smart environments. However, the distance of these resources makes them unsuitable for delay-sensitive applications. Hence, Fog Computing has emerged to provide such capabilities in proximity to end devices through distributed resources. These limited resources can collaborate to serve distributed IoT application workflows using the concept of stateless micro Fog service replicas, which provides resiliency and maintains service availability in the face of failures. Load balancing supports this collaboration by optimally assigning workloads to appropriate services, i.e., distributing the load among Fog nodes to fairly utilize compute and network resources and minimize execution delays. In this paper, we propose using ELECTRE, a Multi-Criteria Decision Analysis (MCDA) approach, to efficiently balance the load in Fog environments. We considered multiple objectives to make service selection decisions, including compute and network load information. We evaluate our approach in a realistic unbalanced topological setup with heterogeneous workload requirements. To the best of our knowledge, this is the first time ELECTRE-based methods are used to balance the load in Fog environments. Through simulations, we compared the performance of our proposed approach with traditional baseline methods that are commonly used in practice, namely random, Round-Robin, nearest node, and fastest service selection algorithms. In terms of the overall system performance, our approach outperforms these methods with up to 67% improvement.
FedSDM: Federated learning based smart decision making module for ECG data in IoT integrated Edge–Fog–Cloud computing environments
2023, Internet of Things (Netherlands)
Massive data collection in modern systems has paved the way for data-driven machine learning, a promising technique for creating reliable and robust statistical models. By combining the data into centralized storage to develop a reliable learning model, there are concerns with privacy, ownership, and strict rules. It is self-evident that the samples in the typical machine learning centralized server paradigm have vastly different probability distributions of data supplied by each user. As a result, the typical model needs to be personalized for critical medical applications, and the deployment needs an efficient mechanism that can adapt to varying user inputs. Due to the heterogeneous and dynamic nature of critical medical IoT applications in such Edge/Fog scenarios, the privacy of patients become a crucial problem. Federated Learning, the model trained on diversity helps in addressing these concerns when used. This paper proposes the integration of Federated Learning for distributed Edge–Fog–Cloud architecture in the IoT smart healthcare sector. This paper presents FedSDM, the Federated Learning-based Smart Decision Making framework for the ECG data in microservice-based IoT medical applications. This proposal makes use of the advantages of Edge/Fog computing for real-time critical applications. It deploys the Federated Learning model at the Edge, Fog, and Cloud layers for performance comparison. The parameters considered for performance evaluation are energy consumption, network usage, cost, execution time, and latency. The proposed method shows that Edge-based deployment outperforms Fog and Cloud in terms of energy consumption, network usage, cost, execution time, and latency (i.e.) 0.3%, 2%, 15%, 11%, and 3% when compared with Fog and 1.6%, 31%, 41%, 24 % and 85% against Cloud respectively.

View all citing articles on Scopus

¹: Carlo Puliafito and Diogo Gonçalves share the first author role in this paper.

²: Part of this research was conducted while Carlo Puliafito was also affiliated to the University of Florence (DINFO), Italy, and visiting student at Cardiff University, UK.

View full text

MobFogSim: Simulation of mobility and migration for fog computing

Abstract

Introduction

Section snippets

Basic concepts

Design considerations

Implementation details

Simulator calibration and container migration over a real testbed

MobFogSim evaluation

Related work

Conclusions

Acknowledgments

Future Generat. Comput. Syst.

Cloud of Things: Integration of IoT With Cloud Computing

Fog Computing and Its Role in the Internet of Things

Proceedings of the 1st MCC Workshop on Mobile Cloud Computing

Fog computing for the internet of things: a survey

ACM Trans. Int. Technol.

Mobility-Aware application scheduling in fog computing

IEEE Cloud Comput.

MyiFogSim: A simulator for virtual machine migration in fog computing

Proceedings of the 6th International Workshop on Clouds and (eScience) Applications Management (CloudAM). Companion Proceedings of the 10th International Conference on Utility and Cloud Computing

Fog Computing for the Internet of Mobile Things: Issues and Challenges

Proceedings of the IEEE 3rd International Conference on Smart Computing (SMARTCOMP)

Proactive Virtual Machine Migration in Fog Environments

Proceedings of the IEEE Symposium on Computers and Communications (ISCC)

SUMO - Simulation of Urban Mobility: An Overview

Proceedings of the 3rd International Conference on Advances in System Simulation (SIMUL)

iFogSim: A Toolkit for modeling and simulation of resource management techniques in the internet of things, edge and fog computing environments