Data Placement Strategy of Data-Intensive Workflows in Collaborative Cloud-Edge Environment

Abstract

With the continuous development and integration of mobile communication and cloud computing technology, cloud-edge collaboration has emerged as a promising distributed paradigm to solve data-intensive workflow applications. How to improve the execution performance of data-intensive workflows has become one of the key issues in the collaborative cloud-edge environment. To address this issue, this paper built a data placement model with multiple constraints. Taking deadline and execution budget as the core constraints, the model is solved by minimizing the data access cost of workflow in the cloud-edge clusters. Subsequently, an immune genetic-particle swarm hybrid optimization algorithm (IGPSHO) is proposed to find the optimal replica placement scheme. Through simulation, compared with the classical immune genetic algorithm (IGA) and particle swarm optimization (PSO), the IGPSHO has obvious advantages in terms of workflow default rate, time-consuming ratio, and average execution cost when the workflow scale is large.