The technology described herein is directed towards monitoring path integrity of a wireless communications path between authorized entities, in which a reconfigurable intelligent surface is part of the signal path between a base station and a user equipment. In one example, an eavesdropping entity intercepts signals to and/or from a base station and user equipment via a reconfigurable intelligent surface, and redirects the intercepted signals to the intended receivers to continue communications. The change in the path from the redirected signals can be detected, e.g., via actual angle of arrival data that does not match expected angle of arrival data. The reconfigurable intelligent surface includes a delay detection network that detects impedance changes corresponding to differential phase changes among unit cells of the reconfigurable intelligent surface, which relates to the actual angle of arrival. In one implementation, generative adversarial network models are used in the monitoring of the signal path.

The technology described herein is directed towards implementations of artificial intelligence (AI)-controlled unit cell subarrays for an active reconfigurable intelligent surface. The reconfigurable intelligent surface integrates an AI model-controlled switch and power amplifier in each subarray of unit cells to selectively amplify the reflected signal, resulting in variable power levels of the reflected signal. The AI model adapts to changing conditions including signal characteristics in real-time, adjusting amplification levels based on various factors for optimizing communication quality, while conserving power consumption by only amplifying to a determined amplification level. Power is also saved by sharing the switch and power amplifier in each subarray of unit cells. Via the per subarray switch, the design provides a device for receiving and reflecting the electromagnetic signal as a signal amplified (or not) to an AI-determined level by coupling the RF energy, processing, and selectively amplifying or not amplifying the reflected signal per subarray.

The technology described herein is directed towards a reconfigurable intelligent surface that is controlled by an artificial intelligence/machine learning (AI/ML) model of a local tile controller. Adaptive shaping of a reconfigurable intelligent surface's geometry by the model produces a desired coverage pattern, including signal strength determined by a model-determined aperture of subarrays of unit cells, and beam direction via controlled phase shifts of the unit cells. Such on-demand reconfiguration adapts the surface for different operating conditions. Further, the model can repair (self-heal) a reconfigurable intelligent surface, by selecting a different aperture that does not include a failing subarray. Each model is locally trained based on local data, as well as federated learning data obtained from other models and aggregated at a centralized controller that learns a global model from the aggregated data. Model optimization via retraining is an ongoing process for continued model improvement.

The technology described herein is directed towards using time of flight data to validate path integrity of a wireless communications path between authorized entities, in which a reconfigurable intelligent surface is part of the signal path between a base station and a user equipment, and using signal strength data for evaluating whether the path is compromised. In one example, an eavesdropping entity can tap into part of the signals to and/or from a base station and user equipment via a reconfigurable intelligent surface. As part of monitoring for an eavesdropper, the path is validated based on the time of flight data, and the measured signal strength is evaluated with respect to the expected signal strength. A drop in the expected signal strength indicates a potential eavesdropper. In one implementation, generative adversarial network models are used in the monitoring of the signal path.

The technology described herein is directed towards designing and configuring a reconfigurable intelligent surface for deployment, based on a straightforward path-loss model having simplified input variables available to a designer, and having mitigated characterization complexity when compared to other path loss models. The relatively large distance that exists between the feed antenna and a reconfigurable intelligent surface facilitates approximation of certain factors, resulting in a practical solution for design and deployment of a reconfigurable intelligent surface of interest. The input variables include the geometry of the reconfigurable intelligent surface, receiver gain, transmitter gain, and the directivity of the transmitting antenna, which are parameters that are easily available to a designer for deploying a reconfigurable intelligent surface. A reconfigurable intelligent surface deployment position and/or size can be determined via an iterative optimization approach, to optimize the position and/or size based on a defined optimization cost expression.

Embodiments of the present disclosure provide method and apparatus for communication over RIS. A method performed by a network node includes transmitting at least one first reference signal to a user equipment (UE) via a reconfigurable intelligent surface (RIS). The RIS is enabled to reflect or beamform the at least one first reference signal. The method further includes receiving a first measurement result of the at least one first reference signal from the UE. The method further includes determining a best beam from the RIS to the UE based on the first measurement result. When transmitting a signal to the UE via the RIS, the signal is reflected or beamformed by the RIS according to the best beam from the RIS to the UE.

Base station antennas include a supplemental FSS structure with a metal grid layer and a printed circuit board layer stacked in a front to back direction and aligned in a longitudinal direction. The supplemental FSS structure resides between, in a longitudinal direction, a first FSS layer and a primary reflector. The supplemental FSS structure reflects and/or blocks RF energy from one of low band or mid-band radiating elements and passes RF energy from an array of mMIMO radiating elements in a higher frequency band than the low and mid-band radiating elements.

Aspects of the present disclosure provide an over-the-air (OTA) interferometer that enables redirecting, by a reconfigurable intelligent surface (RIS) to a destination, a signal that impinges the RIS at each of a plurality of time slots, thereby modulating the signal. The RIS is virtually divided into a plurality of RIS portions. In each time slot, phase components to be applied to the plurality of RIS portions are determined based on one or more phase values. The phase values may include an underlying phase related to redirecting a source signal, an additional phase related to data that an input operatively connected to the RIS aims to transmit to the destination by modulating the signal being redirected, and/or a further phase related to interference patterns that can help extract the data phase at the destination. The destination may demodulate the received signals based on the signal strength measurements.

Certain aspects of the present disclosure provide techniques for communicating with an ad hoc intelligent reflecting surface (IRS). A method that may be performed by a user equipment includes receiving signals from a network entity via an ad hoc IRS; configuring the IRS for communications between the UE and the network entity based at least in part on the received signals; and communicating with the network entity through the IRS.

An over-the-air measurement system for testing a reconfigurable intelligent surface (RIS) includes a signal generator circuit configured to generate at least one RF signal, at least one RF antenna configured to transmit the at least one RF signal and to receive at least one reflected RF signal, and a positioner unit configured to hold an RIS circuit in an adaptable position. The at least one RF antenna includes only one RF antenna or only one RF antenna array functioning both as transmitter and receiver of the at least one RF signal. The measurement system is configured such that far-field conditions of the at least one transmitted RF signal are provided at the RIS circuit, and that far-field conditions of the at least one reflected RF signal are provided at the at least one RF antenna. The measurement system is configured to analyze the signals to determine a reflection parameter.