Multi-parametric and priority driven particle swarm (MPPPSO) optimized task scheduling approach for improving performance of fog computing system

Fog computing architecture provides real-time support for service distribution in a smart and IoT-based network. Various industries, hospitals, hostels, and smart environments use the same architecture over cloud computing to optimize the performance and reliability of service distribution. Fog comp...

Full description

Saved in:
Bibliographic Details
Published in:Progress in artificial intelligence Vol. 14; no. 3; pp. 301 - 318
Main Authors: Monika, Sehrawat, Harkesh
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2025
Springer Nature B.V
Subjects:
Algorithms
Architecture
Artificial Intelligence
Cloud computing
Computational Intelligence
Computer architecture
Computer Imaging
Computer Science
Control
Data Mining and Knowledge Discovery
Deadlines
Edge computing
Failure
Failure rates
Geographical distribution
Hostels
Mechatronics
Methods
Natural Language Processing (NLP)
Parameter sensitivity
Particle swarm optimization
Pattern Recognition and Graphics
Real time
Regular Paper
Reliability
Resource allocation
Robotics
Scheduling
Smart houses
Task scheduling
Vision
Fog computing
Scheduling
Particle swarm optimization
Resource allocation
ISSN:2192-6352, 2192-6360
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fog computing architecture provides real-time support for service distribution in a smart and IoT-based network. Various industries, hospitals, hostels, and smart environments use the same architecture over cloud computing to optimize the performance and reliability of service distribution. Fog computing ensures the handling of geographic distribution, heterogeneous systems, and high-performing computing to achieve the same. But as the load increases over the network, the architecture faces various issues including high processing time, wait time, and task failure in the real environment. In this paper, a load-sensitive and multi-parameter adaptive priority driven swarm model is presented to optimize the performance and reliability of fog computing. The proposed algorithm is implied within the middle layer to optimize the resource allocation at the earlier stage. A dynamic and featured evaluation of fog devices and a parametric mapping of generated tasks are performed to reduce the failure rate and delay in the fog computing environment. Task priority, load, and deadline are the key parameters considered to optimize resource allocation and task scheduling in the real environment. The proposed model is compared against conventional and recent task scheduling methods. These methods include FCFS, SJF, Greedy, Priority-based, Jamil et al., Max–Min, and Aladwani et al. approaches. The experiments are conducted in multiple scenarios with different load and fog devices. The proposed MPPPSO model claimed a significant reduction of 13.38% against FCFS, 15.25% against SJF, 12.88% against Greedy, 9.47% Priority based methods, 8.95% against Jamil et al., 12.81% against Max–Min and 2.31% against Aladwani et al. methods. The results demonstrate that the PSO displays the least effective performance, with a maximum failure rate of 13.18%. The documented failure rates are 12.57% for ACO, 9.46% for ABC, 8.63% for GWO, and 5.67% for WOA algorithms. The proposed MPPPSO algorithm exhibits superior reliability, with a failure rate of 4.23%. The overall results identified a significant improvement in performance and reliability against state-of-art methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2192-6352
2192-6360
DOI:10.1007/s13748-025-00366-z