TM-MOAOA: a two-stage task scheduling approach using TOPSIS and multi-objective Archimedes optimization in fog-cloud environment

The explosive growth of the Internet of Things (IoT) has introduced significant challenges in real-time data processing, placing substantial pressure on fog and cloud computing infrastructures. Efficient and rapid task processing is essential to manage the massive volume of heterogeneous tasks with...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Computing Ročník 107; číslo 7; s. 155
Hlavní autori: Khaledian, Navid, Razzaghzadeh, Shiva, Moazzami, Setareh, Kivi, Parisa Norouzi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Vienna Springer Vienna 01.07.2025
Springer Nature B.V
Predmet:
Algorithms
Artificial Intelligence
Cloud computing
Computer Appl. in Administrative Data Processing
Computer Communication Networks
Computer Science
Data processing
Deadlines
Decision making
Deep learning
Energy consumption
Energy efficiency
Fault tolerance
Fuzzy logic
Genetic algorithms
Heuristic
Information Systems Applications (incl.Internet)
Internet of Things
Load balancing
Load distribution (forces)
Machine learning
Methods
Multiple criterion
Multiple objective analysis
Operating costs
Optimization algorithms
Particle swarm optimization
Performance measurement
Real time
Regular Paper
Resource allocation
Scheduling
Software Engineering
Task scheduling
Workloads
Cloud computing
Makespan
Multi-objective Archimedes optimization
Load balancing
Multi-criteria decision making
ISSN:0010-485X, 1436-5057
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The explosive growth of the Internet of Things (IoT) has introduced significant challenges in real-time data processing, placing substantial pressure on fog and cloud computing infrastructures. Efficient and rapid task processing is essential to manage the massive volume of heterogeneous tasks with varying priority levels. This study proposes a two-stage framework for optimizing load balancing and task scheduling in cloud and fog environments. The framework integrates Multi-Criteria Decision-Making (MCDM) with the Multi-Objective Archimedes Optimization Algorithm (MOAOA). In the first stage, MCDM prioritizes tasks based on key factors such as estimated execution time and deadlines. MOAOA schedules the prioritized tasks within the cloud environment in the second stage. This innovative integration of MCDM and MOAOA enables multi-dimensional optimization for load distribution and resource allocation in distributed IoT systems, thereby enhancing Quality of Service (QoS) and reducing operational costs. Simulation results demonstrate statistically significant improvements in key performance metrics, including makespan, cost, and processing speed. Specifically, compared to baseline algorithms such as Optimal Fuzzy Load Balancing (OFLB), Hybrid Grey Wolf and Improved Particle Swarm Optimization Algorithm (HGWIPSOA), and Multi-objective Cat Swam Optimization Fault tolerant Load Balancing (MCSOFLB), the proposed approach achieves an average reduction of 26.75% in makespan, 22.48% in cost, and a 7.42% improvement in processing speed.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0010-485X
1436-5057
DOI:10.1007/s00607-025-01513-z