Open Access

ARTICLE

Improved Harris Hawks Optimization Algorithm Based Data Placement Strategy for Integrated Cloud and Edge Computing

V. Nivethitha^*, G. Aghila

National Institute of Technology Puducherry, Karaikal, 609609, India

* Corresponding Author: V. Nivethitha. Email:

Intelligent Automation & Soft Computing 2023, 37(1), 887-904. https://doi.org/10.32604/iasc.2023.034247

Received 11 July 2022; Accepted 04 February 2023; Issue published 29 April 2023

Abstract

Cloud computing is considered to facilitate a more cost-effective way to deploy scientific workflows. The individual tasks of a scientific workflow necessitate a diversified number of large states that are spatially located in different datacenters, thereby resulting in huge delays during data transmission. Edge computing minimizes the delays in data transmission and supports the fixed storage strategy for scientific workflow private datasets. Therefore, this fixed storage strategy creates huge amount of bottleneck in its storage capacity. At this juncture, integrating the merits of cloud computing and edge computing during the process of rationalizing the data placement of scientific workflows and optimizing the energy and time incurred in data transmission across different datacentres remains a challenge. In this paper, Adaptive Cooperative Foraging and Dispersed Foraging Strategies-Improved Harris Hawks Optimization Algorithm (ACF-DFS-HHOA) is proposed for optimizing the energy and data transmission time in the event of placing data for a specific scientific workflow. This ACF-DFS-HHOA considered the factors influencing transmission delay and energy consumption of data centers into account during the process of rationalizing the data placement of scientific workflows. The adaptive cooperative and dispersed foraging strategy is included in HHOA to guide the position updates that improve population diversity and effectively prevent the algorithm from being trapped into local optimality points. The experimental results of ACF-DFS-HHOA confirmed its predominance in minimizing energy and data transmission time incurred during workflow execution.

---

Keywords

---