Abstract:

In order to scientifically assess the spectrum effectiveness of low earth orbit constellations, the problems of insufficient adaptability of the traditional assessment framework and inaccurate estimation of KPIs under sparse data conditions were solved, a semantic knowledge-enhanced assessment method for spectrum effectiveness of low earth orbit constellations was proposed. A comprehensive multi-level, all-band, and multi-dimensional spectrum effectiveness assessment framework covering link level, system level, geographical level, and service application level was constructed. A KPI intelligent prediction agent model integrating semantic knowledge and machine learning was proposed to quantify text-like design parameters using SentenceTransformer, so as to rapidly and accurately predict KPIs under conditions of sparse data. A comprehensive subjective and objective assessment decision-making technique that integrated the AHP enhanced by the LLM with EWM was designed. Simulation results show that compared with those of traditional machine learning models, the KPIs of this model have significantly reduced prediction errors. The proposed framework can effectively quantify the effectiveness differences of different beam strategies under different geographical environments; the LLM-assisted weighting method successfully generates subjective weights with good consistency and interpretability, and combined with objective data to reach a comprehensive evaluation conclusion.

Key words: low earth orbit constellation, spectrum utilization efficiency, spectrum occupancy, evaluation algorithm, LLM