Network slicing at the radio access network (RAN) domain, called RAN slicing, requires elasticity, efficient resource sharing, and customization. In this scenario, radio resource scheduling (RRS) is responsible for dealing with scarce and limited frequency spectrum resources available at the RAN domain while fulfilling the slice intents. The wide variety of scenarios supported in 5G and beyond 5G networks makes the RRS problem in RAN slicing scenario a significant challenge. This paper proposes an intent-aware reinforcement learning method to perform the RRS function in a RAN slicing scenario. The slice’s quality of service intents is described in a common intent model in a service-level agreement. The proposed method tries to prevent intent faults by making the management of radio resources available among slices. This method uses slices’ and users’ equipment network metrics in the observation space. The proposed method is evaluated under different network conditions and outperforms different baselines considering the slices’ intents fulfillment.

We consider the problem of channel estimation in low-resolution multiple-input multiple-output (MIMO) systems operating at millimeter wave (mmWave) and present a deep transfer learning (DTL) approach that exploits previously trained models to speed up site adaptation. The proposed model is composed of a feature extractor and a regressor, with only the regressor requiring training for the new environment. The DTL approach is evaluated using two 3D scenarios where ray-tracing is performed to generate the mmWave MIMO channels used in the simulations. Under the defined testing setup, the proposed DTL approach can reduce the computational cost of the training stage without decreasing the estimation accuracy.

Digital twins are an important technology for advancing mobile communications, specially in use cases that require simultaneously simulating the wireless channel, 3D scenes and machine learning. Aiming at contributing towards a solution to this demand, this work describes a modular co-simulation methodology called CAVIAR, for implementing the virtual counterpart of a digital twin system. Here, CAVIAR is upgraded to support a message passing library and facilitate using different 6G-related simulators. The main contributions of this work are the detailed description of different CAVIAR architectures, the implementation of this methodology to assess a 6G use case of UAV-based search and rescue mission (SAR), and the generation of benchmarking data about the computational resource usage. For executing the SAR co-simulation we adopt five open-source solutions: the physical and link level network simulator Sionna, the simulator for autonomous vehicles AirSim, scikit-learn for training a decision tree for MIMO beam selection, Yolov8 for the detection of rescue targets and NATS for message passing. Results for the implemented SAR use case suggest that the methodology can run in a single machine, with the main demanded resources being the CPU processing and the GPU memory.

In power distribution systems, some works evaluated the adoption of smart devices for more a efficient fault handling, evaluated in simulated environments. However, such critical systems need to be evaluated considering real-world issues. Therefore, this paper describes a Data Acquisition (DAQ) system with communication capability, designed to test multi-agent solutions devoted to power distribution system. Long-range communication is enabled by the TSCH mode of the IEEE 802.15.4e, with upper layers defined by IPv6. We consider as constraints time-to-market, signal quality and sampling latency, because of that the system is based on the Linux-compatible Raspberry Pi, which allows reusing a myriad of software, benefiting time-to-market. Linux may result in uncertainties in the sampling of signals. To handle it, we detail the hardware and software approaches to acquire signals. We show the signals are provided to the application without sample loss, and low noise level, such that the measured error is less than 1% compared to a perfectly sampled signal. The harmonic distortions are smaller than the recommended maximum of 5% of the 50/60 Hz waveform, which indicates the circuitry does not significantly impact the measurement of this parameter. Concerning the latency, we measured values in the range of a few microseconds. It should be as low as possible, preferably in the order of sub-milliseconds to allow detecting and analyzing phenomena, such as traveling waves. Lastly, an evaluation setup is presented to demonstrate a smart procedure to restore the energy service in power distribution systems.

We propose an SNR estimation procedure for systems that transmit frequency-multiplexed analog signals in a channel. It is agnostic to the type of radio signal transmitted, can be performed without increasing the required bandwidth, and without interrupting the transmission of the signals. We simulate the transmission of frequency-multiplexed OFDM signals in an optical channel with intensity modulation of the laser and direct detection, where we show the accuracy of the estimation comparing the estimated SNR to the analytical SNR of the channel. We also evaluate the performance by applying the estimated SNR to derive a pre-emphasis used to transmit the signals. In a first evaluation scenario, the OFDM signals transmitted at higher carrier frequencies without pre-emphasis present lower SNR because of the channel response. In contrast, in a second scenario, all the signals present very close SNR due to the pre-emphasis deployed, which could allow optimizing signal transmission by maximizing the minimum SNR at the channel output.