AI-Assisted Joint Search Approach for mmwave Cell Discovery Using Sparse MDT Data

High signal directivity and sensitivity to blockages make the mmWave base-station (BS) discovery a challenging problem in emerging networks. Existing solutions that rely on the exhaustive periodic-beam-sweeping have high latency and low mmWave cell discovery rate. Recent AI-based solutions address the above problems but rely on impractical assumption of having complete minimization of drive test (MDT) reports traces. This paper is the first to present an AI-based framework that can utilize very sparse MDT style data to enable NLoSaware low latency mmWave cell discovery, hereafter referred to as AI-enabled Sparse Data based MmWave cell discOvery and EN-DC activation framework (AISMO). We first gather MDT traces of mmWave users containing signal-strength and Radio-Link-Failure (RLF) indicators. We then augment this highly sparse MDT data using a variety of interpolation, domain knowledge, and AI-based techniques to create augmented mmWave coverage maps (mW-Amaps) while incorporating the NLoS conditions through the RLF traces that are inherently embedded in the data. The mW-Amaps are then used by the macro-BS to determine the optimal mmWave cell for a given user location. Results show that our proposed Weighted Nearest Neighbor Count (WNNC) approach outperforms other data sparsity alleviation techniques for mW-Amap creation with accuracy of 96%. Second best in terms of accuracy is a deep learning-based solution, that has almost 30$x$ faster training time than the WNNC. To evaluate AISMO's performance in a realistic 5G deployment scenario, we present a case study where AISMO is used to enable E-UTRAN New-Radio Dual-Connectivity (EN-DC) between macro-BS and mmWave small cells.