NSF Award
2434000
The growing stress from spectrum shortages and the increasing demand for wireless applications are propelling spectrum management into its fourth era. The "Pay-As-You-Go and Cooperative Sharing" vision is poised to be a promising new paradigm for spectrum management in Spectrum Era 4. In this vision, despite cooperation among wireless users, the information they can share is limited to user/application or system/protocol-level parameters (e.g., spectrum requirements, interference tolerance levels, wireless standards, and waveform types). However, signal-level information, representing instantaneous transmission details of individual data packets (e.g., channel coefficients), cannot be shared in a timely manner across different wireless networks due to delays in cross-network information exchange. This project aims to fill this critical gap by investigating interference mitigation techniques for wireless devices in the absence of signal-level interference information. The research team will design learning-based approaches for individual radio devices to decode their data packets in the presence of unknown interference. The team will also integrate the proposed interference mitigation algorithms into 5G Open Radio Access Networks (O-RANs) and evaluate their performance in realistic scenarios through comprehensive experimentation. Moreover, the project will promote the participation of women and students from underrepresented groups in wireless communications research. It will also enhance pedagogical activities by developing new course materials based on the research findings.<br/><br/>The research team will focus on three thrusts to enable transparent and concurrent spectrum utilization for heterogeneous wireless network systems by developing learning-based approaches capable of mitigating unknown interference. First, the team will design supervisory learning algorithms for interference mitigation by leveraging the reference symbols in physical-layer signal frames and the spatial degrees of freedoms provided by a radio device’s multiple antennas in sub-10GHz wireless systems, with the goal of enabling individual radio devices to decode data packets in the presence of unknown interference. Second, the team will design online-learning-based beamforming methods for interference mitigation in millimeter-wave (mmWave) systems, aiming to maximize transmission data rates despite interference with unknown signal-level features. Third, the team will integrate the proposed interference mitigation algorithms into a 5G O-RAN testbed and explore computational acceleration methods (e.g., using specialized hardware) to meet the real-time requirements. The proposed interference mitigation algorithms will be evaluated through comprehensive over-the-air experiments in realistic scenarios.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
