Abstract

This paper proposes a novel graph-reinforced learning approach for autonomous interplanetary power routing in Mars missions. We present Neuro Graph-PPO, a hybrid framework combining Graph Neural Networks (GNN) and Proximal Policy Optimization (PPO) to optimize energy paths in Martian micro grids. The model integrates outage forecasting, tariff prediction, load prioritization, and anomaly detection using machine learning and deep learning modules. A fully functional Python implementation is provided and tested in simulated Mars-based grid environments.

References

1. [1.] X. Liu, Y. Zhang, and M. Shahidehpour, “Decentralized Energy Management of Networked Microgrids in the Presence of Communication Failures,” IEEE Transactions on Smart Grid, vol. 12, no. 3, pp. 2447–2458, May 2021. [Online]. Available: https://doi.org/10.1109/TSG.2021.3051493
2. [2.] H. He, J. Chen, and W. Liu, “Deep Reinforcement Learning-Based Load Frequency Control for Power Systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 7, pp. 3040–3051, Jul. 2022. [Online]. Available: https://doi.org/10.1109/TNNLS.2021.309641
3. [3.] M. N. O. Sadiku, S. M. Musa, and O. D. Olaleye, “Machine Learning Applications in Smart Grid: A Survey,” IEEE Sensors Journal, vol. 20, no. 14, pp. 7658–7668, Jul. 2020. [Online]. Available: https://doi.org/10.1109/JSEN.2020.2987772
4. [4.] Y. Wang, H. Liu, and Y. Tan, “Transformer-Based Deep Learning Model for Short-Term Electricity Load Forecasting,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 5, pp. 1886–1897, May 2022. [Online]. Available: https://doi.org/10.1109/TNNLS.2021.3069539
5. [5.] J. Liang, Z. Chen, and Y. Wang, “Maximum Power Point Tracking for Photovoltaic Systems Using Proximal Policy Optimization,” IEEE Transactions on Industrial Electronics, vol. 68, no. 6, pp. 4964–4974, Jun. 2021. [Online]. Available: https://doi.org/10.1109/TIE.2020.2996723
6. [6.] L. Chen, X. Liu, and Y. Li, “Anomaly Detection for Power Quality Events Using Deep Autoencoders,” IEEE Access, vol. 8, pp. 193875–193885, 2020. [Online]. Available: https://doi.org/10.1109/ACCESS.2020.3032987
7. [7.] R. Cheng, Y. Jin, and M. Olhofer, “Genetic Algorithms for Large-Scale Optimization: A Survey,” IEEE Transactions on Evolutionary Computation, vol. 25, no. 2, pp. 243–263, Apr. 2021. [Online]. Available: https://doi.org/10.1109/TEVC.2020.2991563
8. [8.] M. A. A. Faruque, S. Abdullah, and M. A. Mahmud, “ShortTerm Renewable Energy Forecasting Using Machine Learning Techniques: A Comparative Study,” IEEE Transactions on Smart Grid, vol. 12, no. 5, pp. 4523–4533, Sep. 2021. [Online]. Available: https://doi.org/10.1109/TSG.2021.3068820
9. [9.] B. Liu, Y. Wang, and H. Zhao, “Secure Energy Trading in Industrial IoT Using Blockchain and Deep Reinforcement Learning,” IEEE Transactions on Industrial Informatics, vol. 18, no. 1, pp. 516–526, Jan. 2022. [Online]. Available: https://doi.org/10.1109/TII.2021.3064567.