Performance modeling of load‐balancing algorithms using neural networks

Ahmad, Ishfaq; Mehrotra, Kishan G.; Mohan, Chilukuri K.; Ranka, Sanjay; Ghafoor, Arif

doi:10.1002/cpe.4330060502

Cited by 10 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the container migration process, the container migration cost mainly consists of two parts: the network delay caused by the transmission of intermediate and final result data between any edge nodes and the migration time of the container itself [8], that is, the downtime. The downtime is mainly affected by the container memory size [28]; therefore, this study uses the following equation to calculate the migration cost incurred when container Ci migrates from edge node N i to N j .…”

Section: Migration Cost Modelmentioning

confidence: 99%

Service Reliability Based on Fault Prediction and Container Migration in Edge Computing

Liu,

Kang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With improvements in the computing capability of edge devices and the emergence of edge computing, an increasing number of services are being deployed on the edge side, and container-based virtualization is used to deploy services to improve resource utilization. This has led to challenges in reliability because services deployed on edge nodes are pruned owing to hardware failures and a lack of technical support. To solve this reliability problem, we propose a solution based on fault prediction combined with container migration to address the service failure problem caused by node failure. This approach comprises two major steps: fault prediction and container migration. Fault prediction collects the log of services on edge nodes and uses these data to conduct time-sequence modeling. Machine-learning algorithms are chosen to predict faults on the edge. Container migration is modeled as an optimization problem. A migration node selection approach based on a genetic algorithm is proposed to determine the most suitable migration target to migrate container services on the device and ensure the reliability of the services. Simulation results show that the proposed approach can effectively predict device faults and migrate services based on the optimal container migration strategy to avoid service failures deployed on edge devices and ensure service reliability.

show abstract

Section: Migration Cost Modelmentioning

confidence: 99%

Service Reliability Based on Fault Prediction and Container Migration in Edge Computing

Liu,

Kang,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The migration cost is mainly formed by two components, namely the network latency caused by the transmission of intermediate and final data between two edge nodes and the The downtime is mainly affected by the memory size of containers, and the larger the memory, the longer the downtime [22]. Compared with network latency and downtime, the migration decision delay is negligible [23]. So, when a container c i is migrated from EN n j to n j , the migration cost M ig i cost can be defined as follows.…”

Section: B Lbjc Container Migration Modelmentioning

confidence: 99%

Container Migration Mechanism for Load Balancing in Edge Network Under Power Internet of Things

Shao

Guo

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As a novel computing technology closer to business ends, edge computing has become an effective solution for delay sensitive business of power Internet of Things (IoT). However, the uneven spatial and temporal distribution of business requests in edge network leads to a significant difference in business busyness between edge nodes. Due to the natural lightweight and portability, container migration has become a critical technology for load balancing, thereby optimizing the resource utilization of edge nodes. To this end, this paper proposes a container migration-based decision-making (CMDM) mechanism in power IoT. First, a load differentiation matrix model between edge nodes is constructed to determine the timing of container migration. Then, a container migration model of load balancing joint migration cost (LBJC) is established to minimize the impact of container migration while balancing the load of edge network. Finally, the migration priority of containers is determined from the perspective of resource correlation and business relevance, and by introducing a pseudo-random ratio rule and combining the local pheromone evaporation with global pheromone update at the same time, a migration algorithm based on modified Ant Colony System (MACS) is designed to utilize the LBJC model and thus guiding the choice of possible migration actions. The simulation results show that compared with genetic algorithm (GA) and Space Aware Best Fit Decreasing (SABFD) algorithm, the comprehensive performance of CMDM in load balancing joint migration cost is improved by 7.3% and 12.5% respectively. INDEX TERMS container migration, load balancing, migration cost, Edge computing, power Internet of things.

show abstract

“…MLP neural networks have been widely used for a number of applications including performance modeling [48,51], job scheduling [52], load balancing [53], design space exploration [54,55], and OC bio-optical inversion [29,30,[56][57][58][59][60][61][62][63][64]. A common finding among these studies is that a key to successful MLP applications is empirical tuning of MLP algorithms in terms of network architecture, data pre-processing, and application-specific feature selection.…”

Section: Related Workmentioning

confidence: 99%

A high‐performance computing framework for Monte Carlo ocean color simulations

Kajiyama

D’Alimonte

Cunha

2016

Concurrency and Computation

View full text Add to dashboard Cite

Summary This paper presents a high‐performance computing (HPC) framework for Monte Carlo (MC) simulations in the ocean color (OC) application domain. The objective is to optimize a parallel MC radiative transfer code named MOX, developed by the authors to create a virtual marine environment for investigating the quality of OC data products derived from in situ measurements of in‐water radiometric quantities. A consolidated set of solutions for performance modeling, prediction, and optimization is implemented to enhance the efficiency of MC OC simulations on HPC run‐time infrastructures. HPC, machine learning, and adaptive computing techniques are applied taking into account a clear separation and systematic treatment of accuracy and precision requirements for large‐scale MC OC simulations. The added value of the work is the integration of computational methods and tools for MC OC simulations in the form of an HPC‐oriented problem‐solving environment specifically tailored to investigate data acquisition and reduction methods for OC field measurements. Study results highlight the benefit of close collaboration between HPC and application domain researchers to improve the efficiency and flexibility of computer simulations in the marine optics application domain. © 2016 The Authors. Concurrency and Computation: Practice and Experience Published by John Wiley & Sons, Ltd.

show abstract

Performance modeling of load‐balancing algorithms using neural networks

Cited by 10 publications

References 18 publications

Service Reliability Based on Fault Prediction and Container Migration in Edge Computing

Service Reliability Based on Fault Prediction and Container Migration in Edge Computing

Container Migration Mechanism for Load Balancing in Edge Network Under Power Internet of Things

A high‐performance computing framework for Monte Carlo ocean color simulations

Contact Info

Product

Resources

About