EPCSAC - Extensible Platform for Cloud Scheduling Algorithm Comparison

• Tiago José Toledo Junior USP
• Sarita Bruschi USP

DOI: https://doi.org/10.5753/wscad_estendido.2020.14088

Resumo

When developing a new cloud scheduling algorithm, simulation is the most used approach to test the algorithm, mainly due to the impossibility of controlling all the cloud variables and also because of the costs involved. However, setting up the simulation environment can be a difficult task and each environment can be configured its own way, resulting in no easy way of reproducing the results with other published algorithms neither comparing both under the same circumstances. To solve both of these problems, we propose the EPCSAC, an online open-source platform that allows researchers to worry only about the creation of their algorithm. They are able to create a set of simulation parameters, test their algorithm under these parameters, and compare their results with other algorithms on the platform. This way, there is an improved reproducibility and a reduced overhead of development. Researchers may have access to the platform at epcsac.lasdpc.icmc.usp.br/.

Referências

Calheiros, R., Ranjan, R., De Rose, C., and Buyya, R. (2009). Cloudsim: A novel framework for modeling and simulation of cloud computing infrastructures and services.

Campos da Silva Filho, M., Oliveira, R., Monteiro, C., Inácio, P., and Freire, M. (2017). Cloudsim plus: A cloud computing simulation framework pursuing software engineering principles for improved modularity, extensibility and correctness. pages 400–406.

Duan, K., Fong, S., Siu, W., Song, W., and Guan, S.-U. (2018). Adaptive incremental genetic algorithm for task scheduling in cloud environments. Symmetry, 10:168.

Elhady, G. and Tawfeek, M. (2015). A comparative study into swarm intelligence algorithms for dynamic tasks scheduling in cloud computing. pages 362–369.

Shu, W., Wang, W., and Wang, Y. (2014). A novel energy-efcient resource allocation algorithm based on immune clonal optimization for green cloud computing. EURASIP Journal on Wireless Communications and Networking, 2014.

Sonkar, S. and Kharat, M. (2016). A review on resource allocation and vm scheduling techniques and a model for efcient resource management in cloud computing environment. pages 1–7.

Tsai, M.-H., Lai, K.-C., Chang, H.-Y., Chen, K., and Huang, K.-C. (2017). Pewss: A platform of extensible workow simulation service for workow scheduling research. Software: Practice and Experience, 48.