Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems

@misc{yu2026analog,
  title = {{Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems}},
  author = {Wentao Yu and Vincent W. S. Wong},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2605.14331},
  eprint = {2605.14331},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.14331},
}

TY  - UNPB
TI  - Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems
AU  - Wentao Yu
AU  - Vincent W. S. Wong
PY  - 2026
DA  - 2026/10/02
PB  - arXiv
DO  - 10.48550/arxiv.2605.14331
UR  - https://arxiv.org/abs/2605.14331
AB  - Modern edge devices increasingly rely on neural networks for intelligent applications. However, conventional digital computing-based edge inference requires substantial memory and energy consumption. In analog radio frequency (RF) computing, a base station (BS) encodes the weights of the neural networks and broadcasts the RF waveforms to the clients. Each client reuses its passive mixer to multiply the received weight-encoded waveform with a locally generated input-encoded waveform. This enables wireless receivers to perform the matrix-vector multiplications (MVMs) that account for most of the computation burden in edge inference with ultra-low energy consumption. Unlike conventional downlink transmissions which are optimized for communications, analog RF computing requires a computing-centric physical layer that controls both the analog MVM accuracy and the energy consumption for inference. Motivated by this, in this paper, we propose a physical layer design framework for analog RF computing in MU-MIMO wireless systems. We derive tractable models for computing accuracy and energy consumption for inference, formulate a joint BS beamforming and client-side scaling problem subject to computing accuracy, transmit power, and hardware constraints, and develop a low-complexity algorithm to solve the non-convex problem. The proposed design provides client- and layer-specific accuracy control for both uniform- and mixed-precision inference. Simulations under 3GPP specifications show that analog RF computing can significantly reduce client-side energy consumption by nearly two orders of magnitude compared to digital computing, while mixed-precision inference requires even lower energy consumption than uniform-precision inference. Overall, these results establish analog RF computing over wireless networks as a promising paradigm for energy-efficient edge inference.
ER  -