Deep Neural Control Module (DNCM)AI-Driven Adaptive Deep LearningControl Framework for Islanded DCMicrogrids in Space Habitats and UAVs

Adnan Haider Zaidi

doi:10.18535/ijsrm/v13i06.ec10

Abstract

Islanded DC microgrids are pivotal for ensuring autonomous, resilient, and efficient power systems in space habitats and unmanned aerial vehicles (UAVs). Recent research and development by NASA, Boeing, and the U.S. Air Force have focused on integrating solar photovoltaic (PV) systems with advanced energy storage solutions to support off-grid operations. This paper presents a comprehensive and uniquely conceptualized model that combines deep learning, artificial intelligence algorithms, and advanced optimization techniques for the control, stability, error detection, and power optimization of Islanded DC Microgrids used in space habitats and UAVs.

References

Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L . Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017. [Online]. Available: https://arxiv.org/abs/1706.03762Google Scholar ↗
V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing Atari with deep reinforcement learning,” arXiv preprint arXiv:1312.5602, 2013. [Online]. Available:Google Scholar ↗
https://arxiv.org/abs/1312.5602Google Scholar ↗
S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [Online]. Available: https://www.bioinf.jku.at/publications/older/2604.pdfGoogle Scholar ↗
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016. [Online]. Available: https://arxiv.org/abs/1609.02907Google Scholar ↗
Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems (NeurIPS), 2012. [Online]. Available:Google Scholar ↗
https://proceedings.neurips.cc/paperfiles/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b− Paper.pdfGoogle Scholar ↗
E. Bompard, R. Napoli, and F. Xue, “Analysis of structural vulnerabilities in power transmission grids,” IEEE Transactions on Smart Grid, vol. 4, no. 1, pp. 316–323, 2013. [Online]. Available:Google Scholar ↗
https://ieeexplore.ieee.org/document/6346363Google Scholar ↗
NASA Glenn Research Center, “Power Management and Distribution for Space,” NASA, 2023. [Online]. Available: https://www.nasa.gov/glennresearch/power-management-and-distribution-pmad/Google Scholar ↗
Boeing Research and Technology, “Microgrid Technology for Autonomous Systems,” Boeing, 2022. [Online]. Available:Google Scholar ↗
https://www.boeing.com/features/2022/11/microgrid-research-11-22.pageGoogle Scholar ↗
U.S. Air Force Research Laboratory (AFRL), “Next-Generation Energy Management Systems,” AFRL, 2022. [Online]. Available:Google Scholar ↗
https://www.afrl.af.mil/News/Article-Display/Article/2818767/afrladvances-smart-energy-grid-technologies-for-space-and-air-operations/Google Scholar ↗
NASA Jet Propulsion Laboratory, “Artificial Intelligence in Spacecraft Power Systems,” NASA JPL, 2021. [Online]. Available:Google Scholar ↗
https://www.jpl.nasa.gov/news/nasa-uses-ai-to-manage-spacecraft-powerGoogle Scholar ↗

[refR-1] Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L . Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017. [Online]. Available: https://arxiv.org/abs/1706.03762Google Scholar ↗

[refR-2] V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller, “Playing Atari with deep reinforcement learning,” arXiv preprint arXiv:1312.5602, 2013. [Online]. Available:Google Scholar ↗

[refR-3] https://arxiv.org/abs/1312.5602Google Scholar ↗

[refR-4] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [Online]. Available: https://www.bioinf.jku.at/publications/older/2604.pdfGoogle Scholar ↗

[refR-5] T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016. [Online]. Available: https://arxiv.org/abs/1609.02907Google Scholar ↗

[refR-6] Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems (NeurIPS), 2012. [Online]. Available:Google Scholar ↗

[refR-7] https://proceedings.neurips.cc/paperfiles/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b− Paper.pdfGoogle Scholar ↗

[refR-8] E. Bompard, R. Napoli, and F. Xue, “Analysis of structural vulnerabilities in power transmission grids,” IEEE Transactions on Smart Grid, vol. 4, no. 1, pp. 316–323, 2013. [Online]. Available:Google Scholar ↗

[refR-9] https://ieeexplore.ieee.org/document/6346363Google Scholar ↗

[refR-10] NASA Glenn Research Center, “Power Management and Distribution for Space,” NASA, 2023. [Online]. Available: https://www.nasa.gov/glennresearch/power-management-and-distribution-pmad/Google Scholar ↗

[refR-11] Boeing Research and Technology, “Microgrid Technology for Autonomous Systems,” Boeing, 2022. [Online]. Available:Google Scholar ↗

[refR-12] https://www.boeing.com/features/2022/11/microgrid-research-11-22.pageGoogle Scholar ↗

[refR-13] U.S. Air Force Research Laboratory (AFRL), “Next-Generation Energy Management Systems,” AFRL, 2022. [Online]. Available:Google Scholar ↗

[refR-14] https://www.afrl.af.mil/News/Article-Display/Article/2818767/afrladvances-smart-energy-grid-technologies-for-space-and-air-operations/Google Scholar ↗

[refR-15] NASA Jet Propulsion Laboratory, “Artificial Intelligence in Spacecraft Power Systems,” NASA JPL, 2021. [Online]. Available:Google Scholar ↗

[refR-16] https://www.jpl.nasa.gov/news/nasa-uses-ai-to-manage-spacecraft-powerGoogle Scholar ↗