.png){kind=icon}
.png){kind=icon}
Return
Multiobjective task scheduling in cloud computing using hybrid algorithm (HRLM)
.png){kind=icon}
PRE
AI
DOI：10.1016/j.simpat.2026.103305.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Cloud computing scheduling of tasks is NP-complete problem that has to be handled effectively in terms of cost, deadlines and energy usage. In this paper, it is hypothesized that a hybrid multi-objective task scheduling algorithm based on CloudSim is proposed as a hybrid of the Reinforcement Learning (RL) and Particle Swarm Optimization (PSO) algorithm named HRLM (Hybrid Reinforcement Learning-Metaheuristic). Tests of up to 1000 tasks show that makespan, cost, and utilization are improved over baselines. Findings indicate the originality of combining RL and PSO to achieve energy-aware and deadline-sensitive cost-effective cloud scheduling. The analysis of the performance is detailed and the simulation scenarios are extended to justify the effectiveness of the proposed approach.
Journal
IF:
4.6
Papers:
2.6K
Citations:
4.8K
