Multi-Cell Multi-Beam Prediction Using Auto-Encoder LSTM for mmWave Systems

Millimeter wave (mmWave) systems rely on communication in narrow beams for directional and spatial multiplexing gains. A key challenge realizing these is beam tracking, particularly environments with high mobility blockage. Additionally, wide-area mmWave cellular systems, user equipment (UE) devices must often simultaneously track signals from multiple cells, since links to individual cells can be unreliable. Models of the channel dynamics across are difficult derive first principles. In this work, we propose a fully data-driven approach based novel auto-encoder integrated long short term memory (LSTM) network, which predicts one time step future. The innovation use an pre-processing step, reduces dimensionality input– main multi-cell, multi-beam tracking. prediction capability proposed network verified compared common baseline predictors as well popular machine learning (ML) neural realistic system-level simulations using commercial ray-tracer. We observe that predictions utilizes auto-encoders reduction, offers significantly better best accuracy lower misalignment loss than approaches. also discuss outage proactive switching applications multi-cell prediction.