Research Article
Comparative Analysis of Random Forest and Bayesian Support Vector Machine for Signal-to-Noise Prediction in Satellite-Terrestrial Networks
Issue:
Volume 13, Issue 1, June 2026
Pages:
1-22
Received:
7 August 2026
Accepted:
20 August 2026
Published:
22 September 2026
Abstract: The convergence of terrestrial wireless and satellite communication systems within Satellite–Terrestrial Integrated Networks (STINs) for sixth-generation (6G) communications has increased the need for accurate and adaptive link performance prediction. Conventional analytical and empirical propagation models often fail to capture the nonlinear effects of atmospheric impairments, particularly rain attenuation in tropical regions. This study evaluates two supervised machine learning algorithms, Random Forest (RF) and Support Vector Machine (SVM), for predicting the signal-to-noise ratio (SNR), a key wireless communication link budget parameter. Rain rate, rain attenuation, and link budget were used as input variables with propagation datasets collected from ten climatically diverse locations across Nigeria. The datasets were partitioned into training, validation, and testing sets using a 70:15:15 ratio, while Bayesian optimization determined the optimal hyper-parameters of both models. Performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Squared Error (MSE), coefficient of determination (R2), regression analysis, and actual-versus-predicted time-series comparisons. Results show that both models accurately captured the nonlinear relationship between propagation parameters and SNR across all study locations. However, SVM consistently outperformed RF, recording lower RMSE, MAE, and MSE values in nine of the ten locations and achieving R2 values between 0.99 and 1.00. SVM also tracked severe fading events caused by intense rain attenuation more accurately, whereas RF exhibited larger deviations during deep fades. Minna was the only location where RF produced lower prediction errors. These findings demonstrate that SVM provides superior prediction accuracy and generalization for SNR estimation under tropical propagation conditions, making it a reliable tool for wireless link budget prediction and future 6G satellite–terrestrial network planning.
Abstract: The convergence of terrestrial wireless and satellite communication systems within Satellite–Terrestrial Integrated Networks (STINs) for sixth-generation (6G) communications has increased the need for accurate and adaptive link performance prediction. Conventional analytical and empirical propagation models often fail to capture the nonlinear effec...
Show More
Research Article
Energy-Efficient Joint User Selection and Power Allocation Optimization for MU-MIMO Systems with Limited Feedback
Issue:
Volume 13, Issue 1, June 2026
Pages:
23-44
Received:
30 June 2026
Accepted:
4 October 2026
Published:
14 November 2026
DOI:
10.11648/j.wcmc.20261301.12
Downloads:
Views:
Abstract: Multi-user multiple-input multiple-output (MU-MIMO) technology is widely regarded as a key enabler for next-generation wireless communication systems (WCS), since it exploits spatial degrees of freedom to increase system throughput without requiring additional bandwidth. However, realizing these gains in practice depends on effective base station (BS)-to-user association and transmit power allocation policies, and on accurate channel state information (CSI) for interference-suppressing precoding. Because uplink feedback bandwidth is limited, base stations in practical MU-MIMO deployments typically operate with only partial CSI, which weakens interference suppression, lowers the signal-to-interference-plus-noise ratio (SINR), and ultimately reduces both the achievable data rate and the energy efficiency (EE) of the system. At the same time, the growing energy demand of wireless networks makes energy-efficient design, rather than throughput alone, an increasingly urgent objective. Motivated by this gap, this paper investigates the joint optimization of user selection and power allocation for maximizing system EE in MU-MIMO systems operating under limited feedback, subject to constraints on maximum transmit power and quality of service (QoS). The resulting optimization problem is formulated as a mixed-integer nonlinear programming (MINLP) model, which is both non-convex and NP-hard, making it intractable to solve directly. To overcome this difficulty, fractional programming is used to recast the problem into an equivalent subtractive form, after which an iterative algorithm is developed that combines a modified Kuhn-Munkres algorithm for optimal user selection with a Lagrangian dual decomposition technique for optimal power allocation. Extensive simulation results show that the proposed algorithm consistently achieves higher system EE and throughput than existing energy-efficient joint user selection and power allocation (JUSPA) schemes under limited feedback, while converging within a small number of iterations and incurring only modest computational overhead. These findings confirm that explicitly accounting for the impact of limited feedback on SINR, rather than assuming perfect CSI, is essential for realizing energy-efficient resource allocation in practical MU-MIMO networks.
Abstract: Multi-user multiple-input multiple-output (MU-MIMO) technology is widely regarded as a key enabler for next-generation wireless communication systems (WCS), since it exploits spatial degrees of freedom to increase system throughput without requiring additional bandwidth. However, realizing these gains in practice depends on effective base station (...
Show More
,
Vincent Andrew Akpan*
