A Monte Carlo Simulation Dataset for Robust LCMV Beamforming Under Constraint Mismatch and Snapshot Deficiency

This dataset provides Monte Carlo simulated covariance matrices for evaluating robust linearly constrained minimum variance (LCMV) beamforming algorithms under practical constraint uncertainty. The considered scenarios focus on snapshot-deficient conditions and direction-of-arrival (DOA) mismatch, which commonly arise in real-world array signal processing systems and often lead to catastrophic performance degradation when hard constraints are enforced.Each sample corresponds to an independent narrowband uniform linear array realization with one desired signal and multiple interferers. The dataset includes estimated sample covariance matrices, estimated steering vectors, and ground-truth signal and interference covariance components, enabling reproducible and fair performance evaluation. Key simulation parameters such as snapshot number, interference power, and DOA mismatch levels are systematically varied to support comprehensive robustness analysis.This dataset is intended for benchmarking conventional, robust, and learning-based LCMV beamforming methods, with particular emphasis on tail performance and failure behavior under imperfect constraints.