aiqbench analysis
This paper treats wireless infrastructure as a delivery layer for AI inference, using analog RF mixing so resource-constrained edge devices can run neural-network matrix operations without storing the weights. Its main contribution is a joint beamforming optimization showing that multicast AI flows cost only about 5% in aggregate data rate, based on 3GPP channel simulations rather than hardware measurements. For AI readers, the open question is whether telecom operators will deploy this kind of analog computing, and whether accuracy and energy trade-offs hold up outside simulation.
Analog RF Computing for Integrated Data and AI Flows Over Wireless Networks
arXiv:2610.20841v1 Announce Type: cross Abstract: Many resource-constrained edge devices require artificial intelligence (AI) services but are not powerful enough to store or execute neural networks (NNs). Analog radio frequency (RF) computing addresses this limitation by letting a base station (BS) multicast a waveform encoding NN weights to different clients. Each client then multiplies the received weight-encoded waveform with its locally generated input-encoded waveform through a passive mixer in its RF frontend, thereby realizing the matrix-vector multiplications (MVMs) needed for AI inference with an extremely low power and memory requirement. This can enable telecom operators to provide AI inference services to the edge devices connected to their networks. In practice, however, this multicast AI flow must share the spectrum, power, and spatial resources with other data flows. This paper considers a multi-user multiple-input multiple-output (MU-MIMO) downlink scenario and studies the resulting relative aggregate data rate reduction from integrating the multicast AI flow with the unicast data flows. We formulate a joint beamforming problem for the data and AI flows to maximize the aggregate data rate subject to computing accuracy, client energy, total power, and hardware-related constraints. We develop a weighted minimum mean-square error (WMMSE)-based algorithm to solve the problem. Numerical results based on 3rd Generation Partnership Project (3GPP) channels show that the relative aggregate data rate reduction from integrating an AI flow with data flows is below 5% in representative settings. This indicates that telecom operators can use analog RF computing to provide edge AI services while providing data communication services simultaneously.
Abstract:Many resource-constrained edge devices require artificial intelligence (AI) services but are not powerful enough to store or execute neural networks (NNs). Analog radio frequency (RF) computing addresses this limitation by letting a base station (BS) multicast a waveform encoding NN weights to different clients. Each client then multiplies the received weight-encoded waveform with its locally generated input-encoded waveform through a passive mixer in its RF frontend, thereby realizing the matrix-vector multiplications (MVMs) needed for AI inference with an extremely low power and memory requirement. This can enable telecom operators to provide AI inference services to the edge devices connected to their networks. In practice, however, this multicast AI flow must share the spectrum, power, and spatial resources with other data flows. This paper considers a multi-user multiple-input multiple-output (MU-MIMO) downlink scenario and studies the resulting relative aggregate data rate reduction from integrating the multicast AI flow with the unicast data flows. We formulate a joint beamforming problem for the data and AI flows to maximize the aggregate data rate subject to computing accuracy, client energy, total power, and hardware-related constraints. We develop a weighted minimum mean-square error (WMMSE)-based algorithm to solve the problem. Numerical results based on 3rd Generation Partnership Project (3GPP) channels show that the relative aggregate data rate reduction from integrating an AI flow with data flows is below 5% in representative settings. This indicates that telecom operators can use analog RF computing to provide edge AI services while providing data communication services simultaneously.
We take a step toward wireless networks that can compute as well as communicate, using analog RF computing to deliver AI inference to resource-constrained edge devices while simultaneously serving conventional data transmission. This is a follow-up to our analog RF computing framework: https://arxiv.org/abs/2605.14331. To be presented at IEEE Globecom 2026
Information Theory (cs.IT); Emerging Technologies (cs.ET); Machine Learning (cs.LG); Signal Processing (eess.SP)
arXiv:2610.20841 [cs.IT]
(or arXiv:2610.20841v1 [cs.IT] for this version)
https://doi.org/10.48550/arXiv.2610.20841 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 323 words
