What the study found
AGENT, an elitism-guided genetic algorithm for heterogeneous cloud task allocation, reduced makespan and outperformed several baseline scheduling methods in the tests reported. The abstract also states that the approach showed scalability and robustness.
Why the authors say this matters
The authors say the method matters because task scheduling in cloud infrastructure services is a critical problem, and minimizing makespan is important for efficient resource allocation. They also suggest that shorter makespan can mean shorter virtual machine operating time, and therefore energy efficiency should be investigated further.
What the researchers tested
The researchers proposed AGENT, which combines size-preserving elitism, feedback-based nonlinear parameter adaptation, and a multi-task-per-virtual-machine allocation model. They evaluated it in CloudSim Plus simulations using Amazon EC2 virtual machine setups and synthetic workloads, and they tested workloads of different sizes.
What worked and what didn't
AGENT achieved makespan improvements of 3.14% to 28.89% compared with HAGA, AIGA, SGA, Max-Min, and Min-Min on the reported synthetic workloads. It also performed well in scalability tests with near-optimal results. The abstract does not report cases where AGENT outperformed all methods in every setting, only that it outperformed the listed baselines across datasets.
What to keep in mind
The evaluation was simulation-based, not a direct measurement in a live cloud system. The abstract does not provide direct energy measurements, and it notes that energy efficiency should be studied in future work by taking direct measurements.
Key points
- AGENT is an elitism-guided genetic algorithm for heterogeneous cloud task allocation.
- The reported goal was to minimize makespan in Infrastructure as a Service cloud scheduling.
- In CloudSim Plus simulations, AGENT improved makespan by 3.14% to 28.89% over listed baselines.
- The abstract says AGENT showed scalability and robustness on workloads of different sizes.
- The authors note that lower makespan may imply shorter virtual machine operating time and possible energy savings, but direct measurements were not reported.
Disclosure
- Research title:
- AGENT improved makespan in heterogeneous cloud task allocation
- Authors:
- Muhammad Osama, Syed Shah Sultan Mohiuddin Qadri, Muhammad Bilal Riaz, Muhammad Farrukh Shahid
- Institutions:
- National University of Computer and Emerging Sciences, Çankaya University, VSB – Technical University of Ostrava
- Publication date:
- 2026-02-25
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.