Metrics of efficiency and productivity when using the evolutionary algorithm on desktopgrid
https://doi.org/10.15514/ISPRAS-2020-32(4)-9
Abstract
The scope of voluntary computing systems is constantly expanding. The BOINC system is currently the most famous for organizing volunteer computing. There are many scientific papers on the adaptation of various computational algorithms to the BOINC. The topic of the presented work is the effective adaptation of the evolutionary algorithm to voluntary computing systems. The reasons for productivity losses are considered, criteria and metrics for evaluating the quality of the algorithm are introduced. The content of the article consists of two main parts. The first part of the article discusses general metrics that can be used to assess the performance of various computational algorithms within BOINC. The problem of adaptation of the evolutionary algorithm is considered in the second part of the article. Two main problem-specific causes of productivity loss are considered: the effect of waiting for the last job and the effect of a common queue. Methods are proposed for quantitative assessment of the influence of various systemic effects on the performance of an evolutionary algorithm. The proposed metrics can be used in a comparative analysis of various job scheduling policies when performing calculations. The metrics can be calculated both during the actual and simulated calculations.
Supporting agencies: The author thanks Russian Foundation for Basic Research (grant №19-07-00911) for financial support.
About the Author
Nikolay Pavlovich KHRAPOV
Kharkevich Institute for Information Transmission Problems of the RAS
Russian Federation
Researcher
Russian Federation
Researcher
References
1. Berkeley Open Infrastructure for Network Computing. Available at: https://boinc.berkeley.edu/. Accessed 19.08.2020.
2. Манзюк М.О., Заикин О.С., Посыпкин М.А. CluboRUN: программный комплекс для использования свободных ресурсов вычислительных кластеров в boinc-расчетах. Информационные технологии и вычислительные системы, № 4, 2014 г., стр. 3-11. / Manzyuk M.O., Zaikin O.S., Posypkin M.A. CluBORun: tool for utilizing idle resources of computing clusters in BOINC computing. Informacionnye tekhnologii I vichslitel’nye sistemy (Journal of Information Technologies and Computing Systems, № 4, 2014, pp. 3-11 (in Russian).
3. Ivashko E., Golovin A., Partition algorithm for association rules mining in BOINC-based enterprise desktop grid. Lecture Notes in Computer Science, vol. 9251, 2015, pp. 268-272.
4. Posypkin M., Khrapov N. Branch and bound method on desktop grid systems. In Proc. of the 2017 IEEE Russia Section Young Researchers in Electrical and Electronic Engineering Conference, 2017, pp. 526-528.
5. Богачкова И.А., Заикин О.С., Кочемазов С.Е., Отпущенников И.В., Семёнов А.А. Применение алгоритмов решения проблемы булевой выполнимости к криптоанализу хэш-функций семейства MD. Прикладная дискретная математика. Приложение, № 8, 2015 г., стр. 139–142 / Bogachkova I.A., Zaikin O.S., Kochemazov S.E., Otpuschennikov I.V., Semenov A.A. Application of algorithms for solving the problem of Boolean satisfiability to cryptanalysis of hash functions of the MD family. Applied discrete mathematics. Application, № 8, 2015, pp. 139–142 (in Russian).
6. Vatutin E. Comparison of Decisions Quality of Heuristic Methods with Sequential Formation of the Decision in the Graph Shortest Path Problem. In Proc. of the Third International Conference BOINC-based High Performance Computing, 2017, pp. 67-76.
7. Khrapov N., Rozen V., Samtsevich A., Posypkin M., Sukhomlin V., Oganov A. Using virtualization to protect the proprietary material science applications in volunteer computing. Open Engineering, vol. 8, issue 1, 2018, pp. 57-60.
8. Храпов Н. П. Анализ причин потери производительности при адаптации эволюционного алгоритма к системам добровольных вычислений. Сборник научных трудов международного конгресса «Современные проблемы компьютерных и информационных наук», 2019 г., стр. 21-26. / Khrapov N.P. Analysis of the performance reasons for adapting the evolutionary algorithm to voluntary computing systems. In Proc of the International Congress on Modern Problems of Computer and Information Sciences], 2019, pp. 21-26 (in Russian).
Review
For citations:
KHRAPOV N.P. Metrics of efficiency and productivity when using the evolutionary algorithm on desktopgrid. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2020;32(4):133-140. (In Russ.) https://doi.org/10.15514/ISPRAS-2020-32(4)-9
Email this article 