Joint Traffic Prediction and Handover Design for LEO Satellite Networks with LSTM and Attention-Enhanced Rainbow DQN
Abstract
1. Introduction
- We propose a traffic prediction module based on long short−term memory (LSTM) networks, which accurately forecasts TTG traffic demands by leveraging historical traffic data, thereby enabling proactive and reliable handover decisions.
- We model the handover decision problem as a Markov Decision Process (MDP) and solve it using an attention−enhanced rainbow DQN, which optimizes handover policies by jointly considering satellite switching frequency, communication quality, and load distribution.
- We validate the proposed framework through extensive simulations using a realistic LEO satellite constellation model. The results show that the proposed ARTHF effectively reduces handover frequency, enhances service quality, and achieves a fair load distribution among the satellites.
2. System Model and Problem Formulation
2.1. System Model
2.2. Communication Model
2.3. Problem Formulation
3. Proposed Joint Traffic Prediction and Handover Design Framework
3.1. LSTM−Enabled Traffic Prediction
3.2. MDP Framework for Satellite Handover
- State space : The state space for each TTG is constructed based on the current link status and the load conditions derived from the predicted traffic. For TTG k, each state is represented as a matrix , where each row corresponds to one of the visible satellites. The seven columns capture the satellite’s service status , elevation angle , distance , remaining service time , SNR , normalized demand weight , and computed load information . Notably, the load information is obtained by combining the predicted traffic demand from Section 3.1 with the real−time satellite state through Equation (18), enabling each TTG to make decisions that are both adaptive and anticipatory.
- Action space : The action space defines the handover decisions available to the TTG in each time slot. Each action specifies the satellite selected by the TTG for handover.
- Reward function : The reward function quantifies the immediate reward given by the environment after the TTGs take action in state . This reward comprehensively considers the handover cost, the coverage quality of the TTG, and the load balancing between satellites, which is expressed as
- Discount factor : This determines the weight of future rewards relative to immediate rewards, with . A higher value places greater emphasis on long−term rewards.
3.3. Attention−Enhanced Rainbow DQN
4. Numerical Results
4.1. Simulation Settings
4.2. Performance Discussion
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations
LEO | Low Earth orbit |
NTN | Non−terrestrial network |
TN | Terrestrial network |
TTG | Terrestrial terminal group |
LSTM | Long short-term memory |
MDP | Markov Decision Process |
DQN | Deep Q network |
D3QN | Dueling-double-deep-Q-learning network |
ARTHF | Attention-enhanced rainbow-DQN-based joint traffic prediction and handover design framework |
6G | Sixth−generation |
SINR | Signal−to− interference −plus−noise ratio |
DRL | Deep reinforcement learning |
QoS | Quality of service |
SVR | Support vector regression |
CNN | Convolutional neural network |
GRU | Gated recurrent unit |
SIB | System information block |
GNSS | Global navigation satellite system |
LSF | Large−scale fading |
ITU−R | International telecommunication union radio communications sector |
AWGN | Additive white Gaussian noise |
STK | Satellite tool kit |
RF | Radio frequency |
EIRP | Effective isotropic radiated power |
HPBW | Half−power beamwidth |
References
- Yaacoub, E.; Alouini, M.S. A key 6G challenge and opportunity—Connecting the base of the pyramid: A survey on rural connectivity. Proc. IEEE 2020, 108, 533–582. [Google Scholar] [CrossRef]
- Kodheli, O.; Lagunas, E.; Maturo, N.; Sharma, S.K.; Shankar, B.; Montoya, J.F.M.; Duncan, J.C.M.; Spano, D.; Chatzinotas, S.; Kisseleff, S.; et al. Satellite communications in the new space era: A survey and future challenges. IEEE Commun. Surv. Tutor. 2020, 23, 70–109. [Google Scholar] [CrossRef]
- Yang, Z.; Zeng, M.; Fei, Z. Attention-Enhanced Rainbow DQN for Cell Reselection in Satellite Communication Networks. In Proceedings of the 2024 16th International Conference on Wireless Communications and Signal Processing (WCSP), Hefei, China, 24–26 October 2024; pp. 999–1005. [Google Scholar]
- De Sanctis, M.; Cianca, E.; Araniti, G.; Bisio, I.; Prasad, R. Satellite communications supporting internet of remote things. IEEE Internet Things J. 2015, 3, 113–123. [Google Scholar] [CrossRef]
- Sun, T.; Shi, L. Load balancing and carrier-to-noise ratio based handover algorithm for LEO satellite network. In Proceedings of the 2023 IEEE 11th International Conference on Information, Communication and Networks (ICICN), Xi’an, China, 17–20 August 2023; pp. 207–211. [Google Scholar]
- Chen, J.; Wei, Z.; Wang, Y.; Sang, L.; Yang, D. A service-adaptive multi-criteria vertical handoff algorithm in heterogeneous wireless networks. In Proceedings of the 2012 IEEE 23rd International Symposium on Personal, Indoor and Mobile Radio Communications-(PIMRC), Sydney, Australia, 9–12 September 2012; pp. 899–904. [Google Scholar]
- Dai, C.Q.; Liu, Y.; Fu, S.; Wu, J.; Chen, Q. Dynamic handover in satellite-terrestrial integrated networks. In Proceedings of the 2019 IEEE Globecom Workshops (GC Wkshps), Waikoloa, HI, USA, 9–13 December 2019; pp. 1–6. [Google Scholar]
- He, S.; Wang, T.; Wang, S. Load-aware satellite handover strategy based on multi-agent reinforcement learning. In Proceedings of the GLOBECOM 2020-2020 IEEE Global Communications Conference, Taipei, China, 7–11 December 2020; pp. 1–6. [Google Scholar]
- Cao, Y.; Lien, S.Y.; Liang, Y.C. Deep reinforcement learning for multi-user access control in non-terrestrial networks. IEEE Trans. Commun. 2020, 69, 1605–1619. [Google Scholar] [CrossRef]
- Cai, Y.; Wu, S.; Luo, J.; Jiao, J.; Zhang, N.; Zhang, Q. Age-oriented access control in GEO/LEO heterogeneous network for marine IoRT: A deep reinforcement learning approach. IEEE Internet Things J. 2022, 9, 24919–24932. [Google Scholar] [CrossRef]
- Agyapong, P.K.; Iwamura, M.; Staehle, D.; Kiess, W.; Benjebbour, A. Design considerations for a 5G network architecture. IEEE Commun. Mag. 2014, 52, 65–75. [Google Scholar] [CrossRef]
- Sun, H.; Liu, H.X.; Xiao, H.; Ran, B. Short Term Traffic Forecasting Using the Local Linear Regression Model 2002. Available online: https://escholarship.org/uc/item/540301xx (accessed on 1 March 2025).
- Sapankevych, N.I.; Sankar, R. Time series prediction using support vector machines: A survey. IEEE Comput. Intell. Mag. 2009, 4, 24–38. [Google Scholar] [CrossRef]
- Li, M.; Wang, Y.; Wang, Z.; Zheng, H. A deep learning method based on an attention mechanism for wireless network traffic prediction. Ad Hoc Netw. 2020, 107, 102258. [Google Scholar] [CrossRef]
- Ko, T.; Raza, S.M.; Binh, D.T.; Kim, M.; Choo, H. Network prediction with traffic gradient classification using convolutional neural networks. In Proceedings of the 2020 14th International Conference on Ubiquitous Information Management and Communication (IMCOM), Taichung, China, 3–5 January 2020; pp. 1–4. [Google Scholar]
- Yu, L.; Li, M.; Jin, W.; Guo, Y.; Wang, Q.; Yan, F.; Li, P. STEP: A spatio-temporal fine-granular user traffic prediction system for cellular networks. IEEE Trans. Mob. Comput. 2020, 20, 3453–3466. [Google Scholar] [CrossRef]
- Liu, K.; Zhang, Y.; Lu, S. A Dynamic Spatio-Temporal Traffic Prediction Model Applicable to Low Earth Orbit Satellite Constellations. Electronics 2025, 14, 1052. [Google Scholar] [CrossRef]
- Li, J.; Wang, D.; Liu, L.; Wang, B.; Sun, C. Satellite ephemeris broadcasting architecture for 5G integrated leo satellite internet. In Proceedings of the 2022 IEEE 22nd International Conference on Communication Technology (ICCT), Nanjing, China, 11–14 November 2022; pp. 1437–1441. [Google Scholar]
- Propagation Data and Prediction Methods Required for the Design of Earth-Space Telecommunication Systems; Technical Report, 3rd Generation Partnership Project (3GPP). 2023. Available online: https://www.itu.int/dms_pubrec/itu-r/rec/p/R-REC-P.618-12-201507-S!!PDF-E.pdf (accessed on 1 July 2025).
- Characteristics of Precipitation for Propagation Modelling; Technical Report, 3rd Generation Partnership Project (3GPP). 2017. Available online: https://www.itu.int/rec/R-REC-P.837/en (accessed on 1 July 2025).
- TR 38.811: Study on New Radio (NR) to Support Non-Terrestrial Networks; Technical Report TR 38.811, 3rd Generation Partnership Project (3GPP). 2018. Available online: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=3234 (accessed on 1 July 2025).
- Villani, F.; Civico, R.; Pucci, S.; Pizzimenti, L.; Nappi, R.; De Martini, P.M. A database of the coseismic effects following the 30 October 2016 Norcia earthquake in Central Italy. Sci. Data 2018, 5, 53. [Google Scholar] [CrossRef] [PubMed]
- Jain, R.K.; Chiu, D.M.W.; Hawe, W.R. A Quantitative Measure of Fairness and Discrimination; Eastern Research Laboratory, Digital Equipment Corporation: Hudson, MA, USA, 1984; Volume 21, pp. 2022–2023. [Google Scholar]
Sub−Constellation | Orbital Altitude | Number of Satellites | Inclination | Number of Orbital Planes |
---|---|---|---|---|
1 | 540 km | 1584 | 53° | 72 |
2 | 550 km | 1584 | 53° | 72 |
3 | 560 km | 348 | 97.6° | 6 |
4 | 560 km | 172 | 97.6° | 4 |
5 | 570 km | 720 | 70° | 36 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Fan, D.; Zhou, S.; Luo, J.; Yang, Z.; Zeng, M. Joint Traffic Prediction and Handover Design for LEO Satellite Networks with LSTM and Attention-Enhanced Rainbow DQN. Electronics 2025, 14, 3040. https://doi.org/10.3390/electronics14153040
Fan D, Zhou S, Luo J, Yang Z, Zeng M. Joint Traffic Prediction and Handover Design for LEO Satellite Networks with LSTM and Attention-Enhanced Rainbow DQN. Electronics. 2025; 14(15):3040. https://doi.org/10.3390/electronics14153040
Chicago/Turabian StyleFan, Dinghe, Shilei Zhou, Jihao Luo, Zijian Yang, and Ming Zeng. 2025. "Joint Traffic Prediction and Handover Design for LEO Satellite Networks with LSTM and Attention-Enhanced Rainbow DQN" Electronics 14, no. 15: 3040. https://doi.org/10.3390/electronics14153040
APA StyleFan, D., Zhou, S., Luo, J., Yang, Z., & Zeng, M. (2025). Joint Traffic Prediction and Handover Design for LEO Satellite Networks with LSTM and Attention-Enhanced Rainbow DQN. Electronics, 14(15), 3040. https://doi.org/10.3390/electronics14153040