.png){kind=icon}
.png){kind=icon}
Return
Blockchain-enabled hybrid evolutionary scheduling for cloud resource optimization
.png){kind=icon}
PRE
AI
DOI：10.1007/s00607-025-01574-0.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Cloud computing task scheduling faces critical challenges in simultaneously optimizing multiple conflicting objectives while ensuring security and transparency. This paper presents a novel blockchain-enabled multi-objective scheduling framework that integrates Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Firefly, and Ant Colony Optimization (ACO) algorithms. The framework addresses five key objectives: makespan minimization, cost reduction, security enhancement, load balancing, and energy efficiency. Smart contracts on a private Ethereum network ensure tamper-proof task allocation and transparent billing. Experimental evaluation using CloudSim demonstrates significant performance improvements: 23% makespan reduction, 18% cost savings, 15% energy consumption decrease, and 99.2% security score achievement compared to traditional methods. The blockchain integration introduces only 2.8% communication overhead while providing unprecedented security and auditability. Results indicate that hybrid evolutionary algorithms outperform single-objective approaches by 35% in convergence speed and 28% in solution quality under high-load scenarios, establishing a robust foundation for secure cloud resource management.
Keywords:
Cloud computing
Task scheduling
Blockchain
Multi-objective optimization
Evolutionary algorithms
Swarm intelligence
Smart contracts
Energy efficiency
Load balancing