To the issue of optimizing cloud computing based on their cost

А.Yu. Doroshenko, O.S. Novak


The paper offers an approach to the architectural settings of parallel computing on the cloud platform, which allows in semi-automatic mode to perform optimization of a parallel program with the goal function of minimum cost of computations. To solve the optimization problem, it is proposed to use linear programming and an available software solver, which with the help of the method of branches and boundaries in semi-automatic mode selects the value of the architecture parameters of the program configuration which significantly affect the cost of calculations. Therefore, the method of auto-tuning developed by the authors earlier is generalized and spread to the complex of services performed on the cloud platform. An analytical test was conducted on the model of cloud multiprocessor cluster, which presents the possibility of significantly reducing the cost of cloud computing due to the optimizations carried out.

Prombles in programming 2020; 4: 14-21


cloud platforms; parallel calculations; optimization methods; linear programming; cost of computations


Duan Yucong, Fu Guohua, Zhou Nianjun, Sun Xiaobing, Narendra Nanjangud, Hu Bo (2015). "Everything as a Service (XaaS) on the Cloud: Origins, Current and Future Trends". 2015 IEEE 8th International Conference on Cloud Computing. IEEE. P. 621-628. CrossRef

Singh Jatinder, Powles Julia, Pasquier, Thomas, Bacon Jean (July 2015). "Data Flow Management and Compliance in Cloud Computing". IEEE Cloud Computing. 2(4). P. 24-32. CrossRef

Zelenyuk V. (2013). "A scale elasticity measure for directional distance function and its dual: Theory and DEA estimation". European Journal of Operational Research. 228(3). P. 592-600. CrossRef

Azizi S., Shojafar M., Abawajy J. and Buyya R. "GRVMP: A Greedy Randomized Algorithm for Virtual Machine Placement in Cloud Data Centers," in IEEE Systems Journal

Anatoliy Doroshenko, Pavlo Ivanenko, Oleksandr Novak, and Olena Yatsenko, A Mixed Method of Parallel Software Auto-Tuning Using Statistical Modeling and Machine Learning in: 14th International Conference, ICTERI 2018, Kyiv, Ukraine. CrossRef

May 14-16, 2018 (Vadim Ermolayev, Mari Carmen Suárez-Figueroa, Vitaliy Yakovyna, Heinrich C. Mayr, Mykola Nikitchenko, Aleksander Spivakovsky (Eds.)), Revised Selected Papers, Series: Communications in Computer and Information Science, Springer, Vol. 1007, 2019.

Doroshenko A., Ivanenko P., Novak O., Starushyk O. Autotuning of parallel programs using the data analysis system IBM Watson Analytics. Problems of Program-ming. 2018. N 1. P. 46-54. CrossRef

Neil Savage. Going serverless. Communications of the ACM. 2018. Vol. 61(2). P. 15-16. CrossRef

Andon P.I. et al. (2017). Methods of alge-braic programming. Formal methods of parallel program development. Kyiv: Naukova dumka. (in Russian)

Gleixner Ambros, Hendel Gregor, Gamrath Gerald, Achterberg Tobias, Bastubbe Michael, Berthold Timo, Christophel Philipp M., Jarck Kati, Koch Thorsten, Linderoth Jeff, L'ubbecke Marco, Mittelmann Hans D., Ozyurt Derya, Ralphs Ted K., Salvagnin Domenico and Shinano Yuji. MIPLIB 2017: Data-Driven Compilation of the 6th Mixed-Integer Programming Library. 2020 Mathematical Programming Computation. CrossRef

Rimmi Anand, Divya Aggarwal & Vijay Kumar (2017). A comparative analysisof optimization solvers. Journal of Statistics and Management Systems. 20:4. P. 623-635. CrossRef

A Comparative Analysis of Optimization Solvers. Available from: ht-tps:// 314750497_A_Comparative_Analysis_of_Optimization_Solvers [accessed Nov 14 2020].



  • There are currently no refbacks.