DRL-Based Antenna Position Optimization For MA-Assisted OTFS System Under Imperfect CSI

2026-04-26

AI Summary

This work addresses the vulnerability of Orthogonal Time Frequency Space (OTFS) systems to deep fading under imperfect channel state information (CSI). To mitigate this issue, the study introduces movable antennas into OTFS for the first time and proposes a joint optimization framework. Specifically, it employs Sparse Bayesian Learning with Variational Inference (SBLVI) to enhance CSI estimation accuracy and subsequently formulates an antenna placement optimization problem based on the refined CSI estimates. A deep reinforcement learning (DRL) approach is then leveraged to adaptively adjust antenna positions with wavelength-level precision. The proposed method significantly improves channel gain and demonstrates substantial performance gains over conventional fixed-antenna configurations.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search
• Machine Learning: Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this paper, we introduce movable antenna (MA) technology into orthogonal time frequency space (OTFS) systems to enable wavelength-level antenna position optimization under imperfect channel state information (CSI), thereby mitigating deep fading. To accurately acquire CSI, we develop a sparse Bayesian learning method with variational inference (SBLVI) method. Based on estimated CSI, we formulate an MA position optimization problem with the objective of maximizing channel gain. Due to the highly non-convex character of the problem, we further develop a deep reinforcement learning (DRL) strategy to intelligently optimize MA positions. Simulation results show that the proposed SBLVI method significantly improves channel estimation accuracy over benchmark methods, and MA position optimization based on estimated CSI achieves substantially higher channel gains than the fixed-position antenna (FPA), demonstrating the effectiveness of the proposed MA-assisted OTFS system.

Problem

• antenna position optimization
• imperfect CSI
• OTFS
• deep fading
• movable antenna

Innovation

• movable antenna
• OTFS
• imperfect CSI
• sparse Bayesian learning
• deep reinforcement learning