One Method for Predicting Satellite Communication Terminal Service Demands Based on Artificial Intelligence Algorithms
Source abstract
Abstract
This paper presents a traffic demand prediction method based on deep learning algorithms, aiming to address the dynamic traffic demands in satellite communication and enhance resource management efficiency. Integrating Seq2Seq and LSTM networks, the method improves prediction accuracy and applicability, especially for mobile terminals such as aviation and maritime ones. Unlike traditional approaches, it does not require extensive statistical data and can be generalized to real-world systems, providing stable long-term traffic demand predictions. This study utilizes real-world flight data mapped to corresponding satellite beams, allowing the precise prediction of beam-specific traffic demands. The results show that aggregating historical demand data for beams with similar trends achieves an average predictive Mean Squared Error (MSE) of 0.0007 and a maximum MSE fluctuation of 0.014, significantly outperforming predictions based on average values in terms of stability and accuracy. This novel solution for resource management in satellite communication ensures efficient and accurate long-term traffic demand predictions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Stock Market Forecasting Methods · Forecasting Techniques and Applications · Energy Load and Power Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Telecommunication and Navigation Satellites, China Academy of Space Technology, Beijing 100094, China
Innovation Center for Satellite Communication System, China National Space Administration, Beijing 100094, China
Funding
Civil Aerospace Technologies
References (18)
Show source-provided references
1. Cho, K.C., Kim, T.Y., and Lee, J.S. (2008, January 11–13). User demand prediction-based resource management model in grid computing environment. Proceedings of the 2008 International Conference on Convergence and Hybrid Information Technology, Busan, Republic of Korea.10.1109/ICHIT.2008.196 ↗
2. Ortíz Gómez, F.G. (2021). Optimization of Cost and Capacity of Broadband Satellite System and Resources Management Using Machine Learning Techniques. [Ph.D. Thesis, Universidad Politécnica de Madrid].
3. Multi-Satellite Beam Hopping Based on Load Balancing and Interference Avoidance for NGSO Satellite Communication Systems10.1109/TCOMM.2022.3226190 ↗
4. Ferdowsi, A., and Whitefield, D. (2021, January 7–11). Deep learning for rain fade prediction in satellite communications. Proceedings of the 2021 IEEE Globecom Workshops (GC Wkshps), Madrid, Spain.10.1109/GCWkshps52748.2021.9682090 ↗
5. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting10.1016/j.asoc.2010.10.015 ↗
6. An Experimental Review on Deep Learning Architectures for Time Series Forecasting
7. Forecasting with artificial neural networks: The state of the art10.1016/S0169-2070(97)00044-7 ↗
8. Zhang, G.P. (2004). Methods for multi-step time series forecasting neural networks. Neural Networks in Business Forecasting, IGI Global.10.4018/978-1-59140-176-6 ↗
9. An, N.H., and Anh, D.T. (2015, January 23–25). Comparison of strategies for multi-step-ahead prediction of time series using neural network. Proceedings of the 2015 International Conference on Advanced Computing and Applications (ACOMP), Ho Chi Minh City, Vietnam.10.1109/ACOMP.2015.24 ↗
10. Taieb, S.B., and Hyndman, R.J. (2012). Recursive and Direct Multi-Step Forecasting: The Best of Both Worlds, Department of Econometrics and Business Statistics, Monash University.
11. Attention is all you need
12. Staudemeyer, R.C., and Morris, E.R. (2019). Understanding LSTM—A tutorial into long short-term memory recurrent neural networks. arXiv, preprint.
13. Ranzato, M.A., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., and Chopra, S. (2014). Video (language) modeling: A baseline for generative models of natural videos. arXiv.
14. Pascanu, R., Mikolov, T., and Bengio, Y. (2012). On the difficulty of training Recurrent Neural Networks. arXiv.
15. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
16. Karatzoglou, A., Jablonski, A., and Beigl, M. (2018, January 6–9). A Seq2Seq learning approach for modeling semantic trajectories and predicting the next location. Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, WA, USA.10.1145/3274895.3274983 ↗
17. Park, S.H., Kim, B.D., Kang, C.M., Chung, C.C., and Choi, J.W. (2018, January 26–30). Sequence-to-sequence prediction of vehicle trajectory via LSTM encoder-decoder architecture. Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China.10.1109/IVS.2018.8500658 ↗
18. Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model10.1016/j.enbuild.2021.111053 ↗