Year: 2023
Type: conference-paper
Abstract: Modern IEEE 802.11 (Wi-Fi) networks extensively rely on multiple-input multiple-output (MIMO) to significantly improve throughput. To correctly beamform MIMO transmissions, the access point needs to frequently acquire a beamforming matrix (BM) from each connected station. However, the size of the matrix grows with the number of antennas and subcarriers, resulting in an increasing amount of airtime overhead and computational load at the station. Conventional approaches come with either excessive computational load or loss of beamforming precision. For this reason, we propose SplitBeam, a new framework where we train a split deep neural network (DNN) to directly output the BM given the channel state information (CSI) matrix as input. The DNN is designed with an additional “bottleneck” layer to “split” the original DNN into a head model and a tail model, respectively executed by the station and the access point. The head model generates a compressed representation of the BM, which is then used by the AP to produce the BM using the tail model. We formulate and solve a bottleneck optimization problem (BOP) to keep computation, airtime overhead, and bit error rate (BER) below application requirements. We perform extensive experimental CSI collection with off-the-shelf Wi-Fi devices in two distinct environments and compare the performance of SplitBeam with the standard IEEE 802.11 algorithm for BM feedback and the state-of-the-art DNN-based approach LB-SciFi. Our experimental results show that SplitBeam reduces the beamforming feedback size and computational complexity by respectively up to 81 % and 84 % while maintaining BER within about 10−3of existing approaches. We also implement the SplitBeam DNNs on FPGA hardware to estimate the end-to-end BM reporting delay, and show that the latter is less than 10 milliseconds in the most complex scenario, which is the target channel sounding frequency in realistic multi-user MIMO scenarios. To allow full reproducibility, we will release our code and datasets to the community.
Institutions: Northeastern University, University of California, Irvine
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Collaborative Research: NeTS: Small: Reliable Task Offloading in Mobile Autonomous Systems Through Semantic MU-MIMO Control, Collaborative Research: CCRI: New: RFDataFactory: Principled Dataset Generation, Sharing and Maintenance Tools for the Wireless Community, Collaborative Research: NeTS: Small: Reliable Task Offloading in Mobile Autonomous Systems Through Semantic MU-MIMO Control, G3120737655, CCF: SHF: Small: Self-Adaptive Interference-Avoiding Wireless Receiver Hardware through Real-Time Learning-Based Automatic Optimization of Power-Efficient Integrated Circuits, G6098521345, G6114848347, CC* Integration-Small: A Software-Defined Edge Infrastructure Testbed for Full-stack Data-Driven Wireless Network Applications, RINGS: Internet of Things Resilience through Spectrum-Agile Circuits, Learning-Based Communications and Thermal Hardware Security, Collaborative Research: SWIFT: AI-based Sensing for Improved Resiliency via Spectral Adaptation with Lifelong Learning
OpenAlex ID: W4387544167
