Papers
Topics
Authors
Recent
Search
2000 character limit reached

Graph Neural Networks for the Offline Nanosatellite Task Scheduling Problem

Published 24 Mar 2023 in cs.LG, cs.AI, and math.OC | (2303.13773v3)

Abstract: This study investigates how to schedule nanosatellite tasks more efficiently using Graph Neural Networks (GNNs). In the Offline Nanosatellite Task Scheduling (ONTS) problem, the goal is to find the optimal schedule for tasks to be carried out in orbit while taking into account Quality-of-Service (QoS) considerations such as priority, minimum and maximum activation events, execution time-frames, periods, and execution windows, as well as constraints on the satellite's power resources and the complexity of energy harvesting and management. The ONTS problem has been approached using conventional mathematical formulations and exact methods, but their applicability to challenging cases of the problem is limited. This study examines the use of GNNs in this context, which has been effectively applied to optimization problems such as the traveling salesman, scheduling, and facility placement problems. More specifically, we investigate whether GNNs can learn the complex structure of the ONTS problem with respect to feasibility and optimality of candidate solutions. Furthermore, we evaluate using GNN-based heuristic solutions to provide better solutions (w.r.t. the objective value) to the ONTS problem and reduce the optimization cost. Our experiments show that GNNs are not only able to learn feasibility and optimality for instances of the ONTS problem, but they can generalize to harder instances than those seen during training. Furthermore, the GNN-based heuristics improved the expected objective value of the best solution found under the time limit in 45%, and reduced the expected time to find a feasible solution in 35%, when compared to the SCIP (Solving Constraint Integer Programs) solver in its off-the-shelf configuration

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. W. A. Shiroma, L. K. Martin, J. M. Akagi, J. T. Akagi, B. L. Wolfe, B. A. Fewell, and A. T. Ohta, “CubeSats: A bright future for nanosatellites,” Central European Journal of Engineering, vol. 1, pp. 9–15, Mar. 2011.
  2. B. Lucia, B. Denby, Z. Manchester, H. Desai, E. Ruppel, and A. Colin, “Computational nanosatellite constellations: Opportunities and challenges,” GetMobile: Mobile Comp. and Comm., vol. 25, p. 16–23, jun 2021.
  3. G. W. Nagel, E. M. L. de Moraes Novo, and M. Kampel, “Nanosatellites applied to optical earth observation: a review,” Ambiente e Agua - An Interdisciplinary Journal of Applied Science, vol. 15, p. 1, June 2020.
  4. N. Saeed, A. Elzanaty, H. Almorad, H. Dahrouj, T. Y. Al-Naffouri, and M.-S. Alouini, “Cubesat communications: Recent advances and future challenges,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 1839–1862, 2020.
  5. C. A. Rigo, L. O. Seman, E. Camponogara, E. M. Filho, and E. A. Bezerra, “Task scheduling for optimal power management and quality-of-service assurance in CubeSats,” Acta Astronautica, vol. 179, pp. 550–560, 2021.
  6. C. A. Rigo, L. O. Seman, E. Camponogara, E. M. Filho, and E. A. Bezerra, “A nanosatellite task scheduling framework to improve mission value using fuzzy constraints,” Expert Systems with Applications, vol. 175, p. 114784, 2021.
  7. L. O. Seman, B. F. Ribeiro, C. A. Rigo, E. M. Filho, E. Camponogara, R. Leonardi, and E. A. Bezerra, “An energy-aware task scheduling for quality-of-service assurance in constellations of nanosatellites,” Sensors, vol. 22, no. 10, 2022.
  8. E. Camponogara, L. O. Seman, C. A. Rigo, E. M. Filho, B. F. Ribeiro, and E. A. Bezerra, “A continuous-time formulation for optimal task scheduling and quality-of-service assurance in nanosatellites,” Computers & Operations Research, vol. 147, p. 105945, 2022.
  9. Y. Bengio, A. Lodi, and A. Prouvost, “Machine learning for combinatorial optimization: A methodological tour d’horizon,” European Journal of Operational Research, vol. 290, no. 2, pp. 405–421, 2021.
  10. M. Karimi-Mamaghan, M. Mohammadi, P. Meyer, A. M. Karimi-Mamaghan, and E.-G. Talbi, “Machine learning at the service of meta-heuristics for solving combinatorial optimization problems: A state-of-the-art,” European Journal of Operational Research, vol. 296, no. 2, pp. 393–422, 2022.
  11. B. M. Pacheco, L. O. Seman, and E. Camponogara, “Deep-learning-based early fixing for gas-lifted oil production optimization: Supervised and weakly-supervised approaches,” 2023.
  12. Q. Han, L. Yang, Q. Chen, X. Zhou, D. Zhang, A. Wang, R. Sun, and X. Luo, “A GNN-guided predict-and-search framework for mixed-integer linear programming,” Mar. 2023. arXiv:2302.05636 [math].
  13. A. Parmentier and V. T’Kindt, “Structured learning based heuristics to solve the single machine scheduling problem with release times and sum of completion times,” European Journal of Operational Research, vol. 305, no. 3, pp. 1032–1041, 2023.
  14. W. Guo, M. Vanhoucke, and J. Coelho, “A prediction model for ranking branch-and-bound procedures for the resource-constrained project scheduling problem,” European Journal of Operational Research, vol. 306, no. 2, pp. 579–595, 2023.
  15. Y. Yang, N. Boland, B. Dilkina, and M. Savelsbergh, “Learning generalized strong branching for set covering, set packing, and 0–1 knapsack problems,” European Journal of Operational Research, vol. 301, no. 3, pp. 828–840, 2022.
  16. J. Zhang, C. Liu, X. Li, H.-L. Zhen, M. Yuan, Y. Li, and J. Yan, “A survey for solving mixed integer programming via machine learning,” Neurocomputing, vol. 519, pp. 205–217, 2023.
  17. E. B. Khalil, C. Morris, and A. Lodi, “MIP-GNN: A data-driven framework for guiding combinatorial solvers,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 10219–10227, June 2022. Number: 9.
  18. M. A. Boschetti and V. Maniezzo, “Matheuristics: using mathematics for heuristic design,” 4OR, vol. 20, pp. 173–208, June 2022.
  19. J. Wang, X. Zhu, D. Qiu, and L. T. Yang, “Dynamic scheduling for emergency tasks on distributed imaging satellites with task merging,” IEEE Transactions on Parallel and Distributed Systems, vol. 25, no. 9, pp. 2275–2285, 2013.
  20. J. Wang, E. Demeulemeester, and D. Qiu, “A pure proactive scheduling algorithm for multiple earth observation satellites under uncertainties of clouds,” Computers & Operations Research, vol. 74, pp. 1–13, Oct. 2016.
  21. J. Cui and X. Zhang, “Application of a multi-satellite dynamic mission scheduling model based on mission priority in emergency response,” Sensors, vol. 19, p. 1430, Jan. 2019. Number: 6 Publisher: Multidisciplinary Digital Publishing Institute.
  22. C. A. Rigo, L. O. Seman, E. Camponogara, E. M. Filho, E. A. Bezerra, and P. Munari, “A branch-and-price algorithm for nanosatellite task scheduling to improve mission quality-of-service,” European Journal of Operational Research, vol. 303, no. 1, pp. 168–183, 2022.
  23. M. Kruber, M. E. Lübbecke, and A. Parmentier, “Learning when to use a decomposition,” in Integration of AI and OR Techniques in Constraint Programming (D. Salvagnin and M. Lombardi, eds.), Lecture Notes in Computer Science, (Cham), pp. 202–210, 2017.
  24. J. J. Hopfield and D. W. Tank, “‘Neural’ computation of decisions in optimization problems,” Biological Cybernetics, vol. 52, pp. 141–152, July 1985.
  25. K. A. Smith, “Neural networks for combinatorial optimization: A review of more than a decade of research,” INFORMS Journal on Computing, vol. 11, pp. 15–34, Feb. 1999.
  26. Q. Cappart, D. Chételat, E. Khalil, A. Lodi, C. Morris, and P. Veličković, “Combinatorial optimization and reasoning with graph neural networks,” Sept. 2022. arXiv:2102.09544 [cs, math, stat].
  27. E. Khalil, H. Dai, Y. Zhang, B. Dilkina, and L. Song, “Learning combinatorial optimization algorithms over graphs,” in Advances in Neural Information Processing Systems, vol. 30, Curran Associates, Inc., 2017.
  28. M. Gasse, D. Chételat, N. Ferroni, L. Charlin, and A. Lodi, “Exact combinatorial optimization with graph convolutional neural networks,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  29. J.-Y. Ding, C. Zhang, L. Shen, S. Li, B. Wang, Y. Xu, and L. Song, “Accelerating primal solution findings for mixed integer programs based on solution prediction,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 1452–1459, 2020. Issue: 02.
  30. V. Nair, M. Alizadeh, and others, “Neural large neighborhood search,” in Learning Meets Combinatorial Algorithms at NeurIPS2020, 2020.
  31. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” Feb. 2017. arXiv:1609.02907.
  32. W. Hamilton, Z. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” 2017. arXiv:1706.02216.
  33. C. A. Rigo, E. Morsch Filho, L. O. Seman, L. Loures, and V. R. Q. Leithardt, “Instance and data generation for the offline nanosatellite task scheduling problem,” Data, vol. 8, no. 3, 2023.
  34. K. Bestuzheva, M. Besançon, W.-K. Chen, A. Chmiela, T. Donkiewicz, J. v. Doornmalen, L. Eifler, O. Gaul, G. Gamrath, A. Gleixner, L. Gottwald, C. Graczyk, K. Halbig, A. Hoen, C. Hojny, R. v. d. Hulst, T. Koch, M. Lübbecke, S. J. Maher, F. Matter, E. Mühmer, B. Müller, M. E. Pfetsch, D. Rehfeldt, S. Schlein, F. Schlösser, F. Serrano, Y. Shinano, B. Sofranac, M. Turner, S. Vigerske, F. Wegscheider, P. Wellner, D. Weninger, and J. Witzig, “The SCIP Optimization Suite 8.0,” ZIB-Report 21-41, Zuse Institute Berlin, Dec. 2021.
  35. G. M. Marcelino, S. Vega-Martinez, L. O. Seman, L. Kessler Slongo, and E. A. Bezerra, “A critical embedded system challenge: The FloripaSat-1 mission,” IEEE Latin America Transactions, vol. 18, no. 2, pp. 249–256, 2020.
  36. B. M. Pacheco, L. O. Seman, C. A. Rigo, and E. Camponogara, “Floripasat milps,” Sept. 2023.
  37. D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (Y. Bengio and Y. LeCun, eds.), 2015.
  38. F. Wilcoxon, “Individual comparisons by ranking methods,” Biometrics Bulletin, vol. 1, no. 6, pp. 80–83, 1945.
  39. K. Smith-Miles and S. Bowly, “Generating new test instances by evolving in instance space,” Computers & Operations Research, vol. 63, pp. 102–113, Nov. 2015.
  40. Y. Malitsky, M. Merschformann, B. O’Sullivan, and K. Tierney, “Structure-preserving instance generation,” in Learning and Intelligent Optimization (P. Festa, M. Sellmann, and J. Vanschoren, eds.), Lecture Notes in Computer Science, (Cham), pp. 123–140, 2016.
  41. G. Yehuda, M. Gabel, and A. Schuster, “It’s not what machines can learn, it’s what we cannot teach,” in Proceedings of the 37th International Conference on Machine Learning, pp. 10831–10841, PMLR, Nov. 2020. ISSN: 2640-3498.
  42. E. M. Filho, V. d. P. Nicolau, K. V. d. Paiva, and T. S. Possamai, “A comprehensive attitude formulation with spin for numerical model of irradiance for CubeSats and Picosats,” Applied Thermal Engineering, vol. 168, p. 114859, 2020.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up