Predicting Failures Using Neural Networks and Quantum Optimization Techniques in Concentrated Solar Power Plants: A Case Study of Morocco Noor Ouarzazate Complex
Meriem LMOUBARIKI
Abstract. The Noor Ouarzazate complex in Morocco is one of the biggest concentrated solar power plants in Africa and makes 580 MW of electricity. However, there have been a lot of anomalies with the plant’s operations. Examples include : mirrors get dusty every day, sensors are exposed to very high and low temperatures, and molten salt eats through storage containers at 565°C. Existing machine learning approaches consume 15 to 50 watts per cycle, which makes continuous monitoring unfeasible. This setup exhibits an integration of firing neural networks with quantum algorithmic tuning. Our neuromorphic methodology evaluates data using discontinuous spike events, demonstrating 94.7% accuracy while consuming only 2.3 microjoules of power every cycle. This network utilizes 847 times less energy than alternative networks. The integration of quantum-inspired algorithms in scheduling resulted in a 32% reduction in costs and an 18% increase in equipment durability. We studied 18 months of operational logs from 7,400 heliostats to analyze the reliability of the system. It could predict failures with 91.3% accuracy 48 to 72 hours in advance. This is the first application that uses both neuromorphic computing and quantum-inspired optimization to improve renewable energy infrastructure. This can assist Morocco succeed in its goal of getting 52% of its electrical power from sources that are sustainable by twenty-first century.
Keywords
Moroccan Energy Sector, Neural Architectures, QAOA Scheduling Methods, Smart Neural Models, Early Warning Systems, Energy Savings, Noor Complex, North Africa, Predictive Maintenance, Equipment Failure Prediction, Quantum Algorithms
Published online 4/25/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Meriem LMOUBARIKI, Predicting Failures Using Neural Networks and Quantum Optimization Techniques in Concentrated Solar Power Plants: A Case Study of Morocco Noor Ouarzazate Complex, Materials Research Proceedings, Vol. 64, pp 224-231, 2026
DOI: https://doi.org/10.21741/9781644904091-28
The article was published as article 28 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Moroccan Agency for Sustainable Energy, Noor Ouarzazate Solar Complex: Technical Overview, MASEN Publications, Rabat (2024).
[2] SolarPower Europe, Morocco Solar Market Report 2025, Brussels, Belgium (2025).
[3] P. Lunghi, S. Silvestrini, D. Dold, T. Boschetti, M. Lavagna, Energy efficiency analysis of Spiking Neural Networks for space applications, Astrodyn. 9 (2025) 909-932. https://doi.org/10.1007/s42064-024-0256-y
[4] E. Gul, G. Baldinelli, J. Wang, D. Bartocci, F. Fantozzi, Artificial intelligence based forecasting and optimization model for concentrated solar power system with thermal energy storage, Appl. Energy 382 (2025) 125210. https://doi.org/10.1016/j.apenergy.2024.125210
[5] A. Marangis, N. Nikolaou-Straatman, C. Vasilopoulos, T. Tsoutsos, Trend-Based Predictive Maintenance and Fault Detection Analytics for Photovoltaic Power Plants, Solar RRL (2024). https://doi.org/10.1002/solr.202400473
[6] C. Pingulkar, A. Joshi, AI-Powered Predictive Maintenance for Solar Energy Systems, Int. J. Prog. Res. Eng. Manage. Sci. 5(10) (2024) 1245-1252.
[7] M. Ledmaoui, A. El Aziz, A. El Maghraoui, A. Arrhioui, A. Hammouch, Review of Recent Advances in Predictive Maintenance and Cybersecurity for Solar Plants, Sensors 25(1) (2025) 206. https://doi.org/10.3390/s25010206
[8] S. Kumar, M. Tiwari, AI-based predictive maintenance of solar photovoltaics systems: a comprehensive review, Energy Inform. 8 (2025) 15. https://doi.org/10.1186/s42162-025-00594-6
[9] Z. Yan, Z. Bai, Reconsidering the energy efficiency of spiking neural networks, arXiv:2409.08290 (2024).
[10] A. Pal, Z. Chai, J. Jiang, L. Li, C. Tan, Y. Shao, A. Pannone, A.I. Khan, S. Gupta, S. Datta, An ultra energy-efficient hardware platform for neuromorphic computing enabled by 2D-TMD tunnel-FETs, Nat. Commun. 15 (2024) 3392. https://doi.org/10.1038/s41467-024-46397-3
[11] Intel Corporation, Neuromorphic Computing with Loihi 2: Technical Overview, Intel Labs Technical Report, Santa Clara, CA (2024).
[12] Multiverse Computing, Quantum Digital Twin Project for Green Hydrogen Production, Technical Report, San Sebastian, Spain (2024).
[13] B. Ribeiro, F. Antunes, D. Perdigão, P. Fiadeiro, A. Roque, Convolutional Spiking Neural Networks: Advanced techniques and applications, Pattern Recognit. Lett. 189 (2025) 241-247. https://doi.org/10.1016/j.patrec.2024.08.002
[14] J. Eshraghian, M. Ward, E. Neftci, X. Wang, G. Lenz, G. Dwivedi, M. Bennamoun, D. Jeong, W.D. Lu, Training Spiking Neural Networks Using Lessons From Deep Learning, Proc. IEEE 111(9) (2023) 1016-1054.
[15] W. Fang, Z. Yu, Y. Chen, T. Masquelier, T. Huang, Y. Tian, Incorporating learnable membrane time constant to enhance learning of spiking neural networks, in: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada (2021) 2661-2671.
[16] R. Parmar, A. Kumar, The Promise of Spiking Neural Networks for Ubiquitous Computing, arXiv:2506.01737 (2025).
[17] P. Meinerzhagen, S. Nease, G. Orchard, Significant energy savings using neuromorphic hardware for edge AI applications, Nat. Mach. Intell. 6 (2024) 892-901.
[18] M. Schlegel, J. Surace, L. Ambrogioni, Quantum Computing as a Game Changer on the Path towards a Net-Zero Economy, Energies 17(5) (2024) 1039. https://doi.org/10.3390/en17051039
[19] D. Patterson, J. Gonzalez, Q. Le, C. Liang, L. Munguia, D. Rothchild, D. So, M. Texier, J. Dean, Carbon emissions and large neural network training, arXiv:2104.10350 (2021).
[20] African Development Bank, Morocco Noor Ouarzazate Solar Complex Project Phase III: Implementation Completion Report, AfDB Infrastructure Development Department, Abidjan, Côte d’Ivoire (2024).
[21] S. Williams, Brain-Mimicking Chips Cut AI Energy Thirst by Orders of Magnitude, IEEE Spectrum, November 2024.
[22] F. Liu, R. Wang, Y. Liu, X. Li, Y. Zhou, Fully memristive spiking neural network for energy-efficient graph learning, Sci. Adv. 11 (2025) eadp2345.
[23] A. Rahman, T. Islam, Machine learning applications in renewable energy systems: Current trends and future directions, Energy Inform. 8 (2025) 62.
[24] McKinsey & Company, Quantum computing just might save the planet: How quantum algorithms could accelerate the clean energy transition, New York, NY (2024).
[25] H. Bennani, Morocco Solar Power Potential Could Reach 4.35 GW by 2028, Morocco World News, Rabat, March 2025.
[26] M. Voudaskas, L. Kosmas, E. Psarra, K. Kalovrektis, D. Davazoglou, Spiking Neural Networks in Imaging: Opportunities and Challenges, Sensors 25(21) (2025) 6747. https://doi.org/10.3390/s25216747
[27] A. Shafiee, A. Nag, N. Muralimanohar, R. Balasubramonian, J.P. Strachan, M. Hu, R.S. Williams, V. Srikumar, ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars, in: 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), Seoul, South Korea (2016) 14-26.
[28] N. El Moussaoui, M. Zerhouni, Solar Energy Resource and Power Generation in Morocco: Current Status and Future Perspectives, Energies 13(10) (2024) 2590. https://doi.org/10.3390/en13102590
