Joint Throughput And Energy Optimization In GSM Networks Using Watts–Strogatz Graph Modeling And Reinforcement Learning

Imam Qasim Mousa; Kheirolah Rahsepar Fard

doi:10.29284/rxynpc58

Authors

Imam Qasim Mousa Department of Computer Engineering and Information Technology, University of Qom, Ghadir boulevard, Qom, Iran
Kheirolah Rahsepar Fard Department of Computer Engineering and Information Technology, University of Qom, Ghadir boulevard, Qom, Iran

DOI:

https://doi.org/10.29284/rxynpc58

Keywords:

GSM cellular networks, energy efficiency, throughput optimization, Watts–Strogatz small-world graph, deep reinforcement learning

Abstract

In this paper, the problem of simultaneous optimization of throughput and energy consumption in GSM networks is studied as a multi-objective problem. For realistic modeling of the network structure, the cell topology is represented as a “small world” graph using the Watts–Strogatz stochastic graph model, and by exploring the graph, important structural and traffic features of each cell, including degree, centrality, traffic load, and QoS indices, are extracted. These features, together with the instantaneous channel information and the power status of the base stations, form the state space of a deep reinforcement learning agent. Using a neural network-based Q-value function approximation, the DRL agent learns control actions such as adjusting the transmit power, turning cells on/off, and routing traffic between neighboring cells in such a way that a reward function including normalized throughput, normalized energy consumption, and QoS violation penalty is maximized. Simulation results in the scenario of one macro cell and 12 micro cells with 200 to 2000 users show that the proposed method has a significant advantage over the three reference methods (basic, heuristic and classical Q-learning); so that the average cumulative reward of the DRL algorithm reached 3.41, while for Q-learning and the heuristic method it was 2.28 and 0.7, respectively, and for the basic method it was reported to be negative 3.55. Also, the network energy efficiency, in terms of the ratio of total throughput to base station power consumption, is maintained at a stable level of close to 2.5 for the proposed method, while this value is about 2.05 for Q-learning and 1.56 and 1.21 for the two non-intelligent methods, respectively. These results indicate that the combination of small-world graph modeling and deep reinforcement learning can provide an efficient framework for intelligent energy and capacity management in GSM networks.

References

[1] M. Marwani, and G. Kaddoum, “Graph neural networks approach for joint wireless power control and spectrum allocation,” IEEE Transactions on Machine Learning in Communications and Networking, vol. 2, pp. 717-732, 2024.

[2] Y. Lu, Z. Zhang, X. Xu, L. Liu, Q. Fu, J. Chen, and C. Chen, “GTD3-NET: A deep reinforcement learning-based routing optimization algorithm for wireless networks,” Peer-to-Peer Networking and Applications, vol. 18, no. 1, pp. 23, 2025.

[3] S. Mclaughlin, P. M. Grant, J. S. Thompson, H. Haas, D. I. Laurenson, C. Khirallah, Y. Hou, and R. Wang, “Techniques for improving cellular radio base station energy efficiency,” IEEE Wireless Communications, vol. 18, no. 5, pp. 10-17, 2011.

[4] C. A. Chan, W. Li, S. Bian, I. Chih-Lin, A. F. Gygax, C. Leckie, M. Yan, and K. Hinton, “Assessing network energy consumption of mobile applications,” IEEE Communications Magazine, vol. 53, no. 11, pp. 182-191, 2015.

[5] L. Chen, Y. Xu, F. Xu, Q. Hu, and Z. Tang, “Balancing the trade-off between cost and reliability for wireless sensor networks: a multi-objective optimized deployment method,” Applied Intelligence, vol. 53, no. 8, pp. 9148-9173, 2023.

[6] T. Zhang, J. Cao, Y. Chen, L. Cuthbert, and M. Elkashlan, “A small world network model for energy efficient wireless networks,” IEEE Communications Letters, vol. 17, no. 10, pp. 1928-1931, 2013.

[7] M. Vasuki, A. D. Kumar, and R. Prabhakaran, “A Study on GSM Mobile Phone Network in Graph Theory,” International Journal of Current Research and Modern Education, vol. 1, no. 1, pp. 772-783, 2016.

[8] H. F. Song, and X.-J. Wang, “Simple, distance-dependent formulation of the Watts-Strogatz model for directed and undirected small-world networks,” Physical Review E, vol. 90, no. 6, pp. 062801, 2014.

[9] Z. Zhu, "Particle swarm optimization with Watts-Strogatz model." pp. 506-513.

[10] M. Karimi, M. Harouni, E. I. Jazi, A. Nasr, and N. Azizi, "Improving monitoring and controlling parameters for Alzheimer’s patients based on IoMT," Prognostic models in healthcare: Ai and statistical approaches, pp. 213-237: Springer, 2022.

[11] A. A. Alaidany, and A. Lakizadeh, “Improving the Accuracy of Cancer Driver Gene Identification based on Dimensionality Reduction Using Deep AutoEncoders,” International Journal of Intelligent Engineering&Systems, vol. 18, no. 9, 2025.

[12] A. Ali A, M. Ali K, M. Marwah M, and F. Tibah, “A REVIEW OF MACHINE LEARNING IN BANKING RISK MANAGEMENT AND POSSIBLE RESEARCH TOPICS,” Journal of Engineering, Mechanics and Modern Architecture, vol. 4, no. 1, pp. 50-57, 2025.

[13] M. Stasiak, M. Glabowski, A. Wisniewski, and P. Zwierzykowski, Modeling and Dimensioning of Mobile Wireless Networks: From GSM to LTE: John Wiley&Sons, 2010.

[14] Y. Liu, and L. Li, "Efficient Graph Sequence Reinforcement Learning for Traveling Salesman Problem." pp. 256-267.

[15] M. Z. Rafique, and M. Abulaish, "Graph-based learning model for detection of SMS spam on smart phones." pp. 1046-1051.

[16] M. Karimi, Z. Karimi, M. Khosravi, Z. Delaram, M. H. Dehsheikhim, S. A. Najafabadi, M. A. Aliabadi, and N. Tavakoli, “Feature Selection Methods in Big Medical Databases: A Comprehensive Survey,” International Journal of Theoretical&Applied Computational Intelligence, pp. 181-209, 2025.

[17] S. Georgousis, M. P. Kenning, and X. Xie, “Graph deep learning: State of the art and challenges,” IEEe Access, vol. 9, pp. 22106-22140, 2021.

[18] O. Jouini, K. Sethom, A. Namoun, N. Aljohani, M. H. Alanazi, and M. N. Alanazi, “A survey of machine learning in edge computing: Techniques, frameworks, applications, issues, and research directions,” Technologies, vol. 12, no. 6, pp. 81, 2024.

[19] A. Rahman, T. Debnath, D. Kundu, M. S. I. Khan, A. A. Aishi, S. Sazzad, M. Sayduzzaman, and S. S. Band, “Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities,” AIMS Public Health, vol. 11, no. 1, pp. 58, 2024.

[20] M. Harouni, M. Karimi, A. Nasr, H. Mahmoudi, and Z. Arab Najafabadi, "Health monitoring methods in heart diseases based on data mining approach: A directional review," Prognostic models in healthcare: Ai and statistical approaches, pp. 115-159: Springer, 2022.

[21] S. Wen, B. Hu, and H.-K. Lam, “Reinforcement learning optimization for base station sleeping strategy in coordinated multipoint (CoMP) communications,” Neurocomputing, vol. 167, pp. 443-450, 2015.

[22] M. Ali, S. Qaisar, M. Naeem, and S. Mumtaz, “Energy efficient resource allocation in D2D-assisted heterogeneous networks with relays,” IEEE Access, vol. 4, pp. 4902-4911, 2016.

[23] A. Shahid, K. S. Kim, E. De Poorter, and I. Moerman, “Self-organized energy-efficient cross-layer optimization for device to device communication in heterogeneous cellular networks,” IEEE Access, vol. 5, pp. 1117-1128, 2017.

[24] J. Li, H. Wang, X. Wang, and Z. Li, “Optimized sleep strategy based on clustering in dense heterogeneous networks,” EURASIP Journal on Wireless Communications and Networking, vol. 2018, no. 1, pp. 290, 2018.

[25] Y. S. Nasir, and D. Guo, “Multi-agent deep reinforcement learning for dynamic power allocation in wireless networks,” IEEE Journal on selected areas in communications, vol. 37, no. 10, pp. 2239-2250, 2019.

[26] Z. Zhang, H. Qu, J. Zhao, and W. Wang, "Deep reinforcement learning method for energy efficient resource allocation in next generation wireless networks." pp. 18-24.

[27] C.-K. Hsieh, K.-L. Chan, and F.-T. Chien, “Energy-efficient power allocation and user association in heterogeneous networks with deep reinforcement learning,” Applied Sciences, vol. 11, no. 9, pp. 4135, 2021.

[28] Y. Azimi, S. Yousefi, H. Kalbkhani, and T. Kunz, “Energy-efficient deep reinforcement learning assisted resource allocation for 5G-RAN slicing,” IEEE Transactions on Vehicular Technology, vol. 71, no. 1, pp. 856-871, 2021.

[29] A. Mughees, M. Tahir, M. A. Sheikh, A. Amphawan, Y. K. Meng, A. Ahad, and K. Chamran, “Energy-efficient joint resource allocation in 5G HetNet using Multi-Agent Parameterized Deep Reinforcement learning,” Physical Communication, vol. 61, pp. 102206, 2023.

[30] H. Choi, T. Kim, S. Lee, H.-S. Choi, and N. Yoo, “Energy-Efficient Dynamic Enhanced Inter-Cell Interference Coordination Scheme Based on Deep Reinforcement Learning in H-CRAN,” Sensors (Basel, Switzerland), vol. 24, no. 24, pp. 7980, 2024.

[31] Y. Azimi, S. Yousefi, H. Kalbkhani, and T. Kunz, “Mobility aware and energy-efficient federated deep reinforcement learning assisted resource allocation for 5G-RAN slicing,” Computer Communications, vol. 217, pp. 166-182, 2024.

[32] V. Shilpa, and R. Ranjan, “Radio Resource Scheduling in 5G Networks Based on Adaptive Golden Eagle Optimization Enabled Deep Q-Net,” SN Computer Science, vol. 5, no. 5, pp. 517, 2024.

[33] H. Kim, and J. So, “Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks,” Sensors, vol. 25, no. 13, pp. 4017, 2025.

[34] H. QU, Z. ZHU, J. ZHAO, R. TANG, L. WANG, and Z. CAO, “Energy-efficient joint relay selection and resource allocation scheme for mobile relay aided device-to-device communication,” 电子与信息学报, vol. 39, no. 10, pp. 2464-2471, 2017.