Abstract
In this work, we propose and evaluate an online scheduler prototype based on machine learning algorithms. Online job-flow scheduler should make scheduling and resource allocation decisions for individual jobs without any prior knowledge of the subsequent job queue (i.e., online). We simulate and generalize this task to a more formal 0–1 Knapsack problem with unknown utility functions of the knapsack items. In this way we evaluate the implemented machine learning-based solution to classical combinatorial optimization algorithms. A hybrid machine learning and dynamic programming - based approach is proposed to consider and strictly satisfy the knapsack constraint on the total weight. As a main result the proposed hybrid solution showed efficiency comparable to the greedy knapsack approximation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bharathi, S., Chervenak, A.L., Deelman, E., Mehta, G., Su, M., Vahi, K.: Characterization of scientific workflows. In: 2008 Third Workshop on Workflows in Support of Large-Scale Science, pp. 1–10 (2008)
Rodriguez, M.A., Buyya, R.: Scheduling dynamic workloads in multi-tenant scientific workflow as a service platforms. Future Gener. Comput. Syst. 79(P2), 739–750 (2018)
Kurowski, K., Nabrzyski, J., Oleksiak, A., Weglarz, J.: multicriteria aspects of grid resource management. In: Nabrzyski, J., Schopf, J.M., Weglarz J. (eds.) Grid Resource Management. State of the Art and Future Trends, pp. 271–293. Kluwer Academic Publishers. (2003)
Toporkov, V., Yemelyanov, D.: Coordinated and hindsight resources allocation in distributed computing. In: Proceedings - 2019 20th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT (2019)
Toporkov, V., Yemelyanov, D., Toporkova, A.: Coordinated global and private job-flow scheduling in grid virtual organizations. J. Simul. Model. Pract. Theor. 107, 102228 (2021)
Sukhoroslov, O., Nazarenko, A., Aleksandrov, R.: An experimental study of scheduling algorithms for many-task applications. J. Supercomput. 75, 7857–7871 (2019)
Samimi, P., Teimouri, Y., Mukhtar M.: A combinatorial double auction resource allocation model in cloud computing. J. Inf. Sci. 357(C), 201–216 (2016)
Rodero, I., Villegas, D., Bobroff, N., Liu, Y., Fong, L., Sadjadi, S.: Enabling interoperability among grid meta-schedulers. J. Grid Comput. 11(2), 311–336 (2013)
Shmueli, E., Feitelson, D.G.: Backfilling with lookahead to optimize the packing of parallel jobs. J. Parallel Distrib. Comput. 65(9), 1090–1107 (2005)
Khemka, B., et al.: Resource management in heterogeneous parallel computing environments with soft and hard deadlines. In: Proceedings of 11th Metaheuristics International Conference (MIC 2015) (2015)
Netto, M.A.S., Buyya, R.: A flexible resource co-allocation model based on advance reservations with rescheduling support. In: Technical Report, GRIDSTR-2007-17, Grid Computing and Distributed Systems Laboratory, The University of Melbourne, Australia (2007)
Toporkov, V., Toporkova, A., Yemelyanov, D.: Slot co-allocation optimization in distributed computing with heterogeneous resources. In: Del Ser, J., Osaba, E., Bilbao, M.N., Sanchez-Medina, J.J., Vecchio, M., Yang, X.-S. (eds.) IDC 2018. SCI, vol. 798, pp. 40–49. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99626-4_4
Toporkov, V., Yemelyanov, D.: Optimization of resources selection for jobs scheduling in heterogeneous distributed computing environments. In: Shi, Y., et al. (eds.) ICCS 2018. LNCS, vol. 10861, pp. 574–583. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93701-4_45
Toporkov, V., Yemelyanov, D.: Scheduling optimization in heterogeneous computing environments with resources of different types. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds.) DepCoS-RELCOMEX 2021. AISC, vol. 1389, pp. 447–456. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76773-0_43
Xu, S., Panwar, S.S., Kodialam, M.S., Lakshman, T.V.: Deep neural network approximated dynamic programming for combinatorial optimization. In: AAAI Conference on Artificial Intelligence, pp. 1684–1691 (2020)
Nomer, H.A.A., Alnowibet, K.A., Elsayed, A., Mohamed, A.W.: Neural knapsack: a neural network based solver for the knapsack problem. In: IEEE Access, vol. 8, pp. 224200–224210 (2020)
Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural Combinatorial Optimization with Reinforcement Learning. In: International Conference on Learning Representations (2017)
Yang, F., Jin, T., Liu, T., Sun, X., Zhang, J.: Boosting dynamic programming with neural networks for solving NP-hard problems. In: Proceedings of The 10th Asian Conference on Machine Learning, PMLR, vol. 95, pp. 726–739 (2018)
Yang, X., et al.: A review: machine learning for combinatorial optimization problems in energy areas. Algorithms 15, 205 (2022)
Bengio, Y., Lodi, A., Prouvost, A.: Machine learning for combinatorial optimization: a methodological tour d’horizon. Eur. J. Oper. Res. 290(2), 405–421 (2021)
Acknowledgements
This work was supported by the Russian Science Foundation project no. 22-21-00372.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Toporkov, V., Yemelyanov, D., Bulkhak, A. (2023). Machine Learning-Based Online Scheduling in Distributed Computing. In: Wyrzykowski, R., Dongarra, J., Deelman, E., Karczewski, K. (eds) Parallel Processing and Applied Mathematics. PPAM 2022. Lecture Notes in Computer Science, vol 13827. Springer, Cham. https://doi.org/10.1007/978-3-031-30445-3_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-30445-3_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30444-6
Online ISBN: 978-3-031-30445-3
eBook Packages: Computer ScienceComputer Science (R0)