Parallel Genetic Algorithms’ Implementation Using a Scalable Concurrent Operation in Python

Skorpil, Vladislav; Oujezský, Václav

doi:10.3390/s22062389

Cited by 9 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of how to parallelize a genetic algorithm depends on the following [25,26]: The parallel genetic algorithm (PGA) with distributed fitness evaluation [28] stands out as one of the pioneering and successful implementations of parallel genetic algorithms. This approach is often referred to as global parallelization, employing a client-server model or utilizing distributed fitness evaluation.…”

Section: Application Of Parallel Genetic Algorithms For the Synthesis...mentioning

confidence: 99%

Mathematical Models for the Design of GRID Systems to Solve Resource-Intensive Problems

Tynchenko,

Nelyub

et al. 2024

Mathematics

View full text Add to dashboard Cite

Artificial neural networks are successfully used to solve a wide variety of scientific and technical problems. The purpose of the study is to increase the efficiency of distributed solutions for problems involving structural-parametric synthesis of neural network models of complex systems based on GRID (geographically disperse computing resources) technology through the integrated application of the apparatus of evolutionary optimization and queuing theory. During the course of the research, the following was obtained: (i) New mathematical models for assessing the performance and reliability of GRID systems; (ii) A new multi-criteria optimization model for designing GRID systems to solve high-resource computing problems; and (iii) A new decision support system for the design of GRID systems using a multi-criteria genetic algorithm. Fonseca and Fleming’s genetic algorithm with a dynamic penalty function was used as a method for solving the stated multi-constrained optimization problem. The developed program system was used to solve the problem of choosing an effective structure of a centralized GRID system that was configured to solve the problem of structural-parametric synthesis of neural network models. To test the proposed approach, a Pareto-optimal configuration of the GRID system was built with the following characteristics: average performance–103.483 GFLOPS, cost–500 rubles per day, availability rate–99.92%, and minimum performance–51 GFLOPS.

show abstract

Section: Application Of Parallel Genetic Algorithms For the Synthesis...mentioning

confidence: 99%

Mathematical Models for the Design of GRID Systems to Solve Resource-Intensive Problems

Tynchenko,

Nelyub

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…In [27], the authors proposed the fine-grained and coarse-grained models by using the parallel GA. The authors used several workstations for testing the models.…”

Section: Related Workmentioning

confidence: 99%

Time Series-Based Edge Resource Prediction and Parallel Optimal Task Allocation in Mobile Edge Computing Environment

et al. 2023

View full text Add to dashboard Cite

The offloading of computationally intensive tasks to edge servers is indispensable in the mobile edge computing (MEC) environment. Once the tasks are offloaded, the subsequent challenges lie in buffering them and assigning them to edge virtual machine (VM) resources to meet the multicriteria requirement. Furthermore, the edge resources’ availability is dynamic in nature and needs a joint prediction and optimal allocation for the efficient usage of resources and fulfillment of the tasks’ requirements. To this end, this work has three contributions. First, a delay sensitivity-based priority scheduling (DSPS) policy is presented to schedule the tasks as per their deadline. Secondly, based on exploratory data analysis and inferred seasonal patterns in the usage of edge CPU resources from the GWA-T-12 Bitbrains VM utilization dataset, the availability of VM resources is predicted by using a Holt–Winters-based univariate algorithm (HWVMR) and a vector autoregression-based multivariate algorithm (VARVMR). Finally, for optimal and fast task assignment, a parallel differential evolution-based task allocation (pDETA) strategy is proposed. The proposed algorithms are evaluated extensively with standard performance metrics, and the results show nearly 22%, 35%, and 69% improvements in cost and 41%, 52%, and 78% improvements in energy when compared with MTSS, DE, and min–min strategies, respectively.

show abstract

Comprehensive Review of Metaheuristic Algorithms (MAs) for Optimal Control (OCl) Improvement

Mohammed,

Karataev,

Oshiga

et al. 2024

Arch Computat Methods Eng

View full text Add to dashboard Cite

Parallel Genetic Algorithms’ Implementation Using a Scalable Concurrent Operation in Python

Cited by 9 publications

References 8 publications

Mathematical Models for the Design of GRID Systems to Solve Resource-Intensive Problems

Mathematical Models for the Design of GRID Systems to Solve Resource-Intensive Problems

Time Series-Based Edge Resource Prediction and Parallel Optimal Task Allocation in Mobile Edge Computing Environment

Comprehensive Review of Metaheuristic Algorithms (MAs) for Optimal Control (OCl) Improvement

Contact Info

Product

Resources

About