<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" article-type="Research Article" dtd-version="1.0"><front><journal-meta><journal-id journal-id-type="pmc">iarjet</journal-id><journal-id journal-id-type="pubmed">IARJET</journal-id><journal-id journal-id-type="publisher">IARJET</journal-id><issn>2708-5163</issn></journal-meta><article-meta><article-id pub-id-type="doi">https://doi.org/10.47310/iarjet.2025.v06i02.002</article-id><title-group><article-title>Interference Management and Coexistence between Terrestrial 5G Networks and Non-Geostationary Satellite Systems</article-title></title-group><contrib-group><contrib contrib-type="author"><name><given-names>AmaniY.K.</given-names><surname>Al-Mulla</surname></name></contrib><xref ref-type="aff" rid="aff-a" /></contrib-group><aff-id id="aff-a">Najaf Technical Institute, Al-Furat Al-Awsat Technical University, Najaf, Iraq</aff-id><abstract>The coexistence of terrestrial 5G networks with non-geostationary satellite (NGSO) systems introduces significant interference issues, as both systems operate in the Ku and Ka bands. The conventional coordination techniques used, fixed frequency planning, guard bands, and power control, lack the flexibility for dynamic beam steering and orbital changes. The paper presents a new hybrid model, GCTMARLMPC, that consists of a Graph Contrastive Transformer (GCT) for detecting interference with higher precision and Multi-Agent Reinforcement Learning with Model Predictive Control (MARLMPC) for introducing adaptive responses to interference. It uses the 5G Adaptive Beamforming with SNR Dataset from Kaggle, supplemented with artificial NGSO parameters (Interference Distance and Beam Overlap Ratio). The framework can be viewed as a graph of learned, discriminative embeddings, with dynamically configured power transmission, beam steering, and frequency allocation. The algorithm is developed in Python using the PyTorch and Stable Baselines libraries. According to the experimental findings, there is 97.2% accuracy in detecting interference and substantial gains in SINR, power efficiency, and network stability. The proposed framework is helpful to network operators, satellite service providers, and IoT applications, as it enables reliable, interference-resistant communication across shared spectrum.</abstract></article-meta></front><body /><back /></article>