Ericsson (Canada)

Although the energy footprint of cloud infrastructures is becoming a critical concern, mainstream orchestration platforms such as Kubernetes (K8s) continue to prioritize performance over power efficiency. By default, K8s employs static CPU pinning for latency-sensitive services to ensure predictable performance and prevent resource contention. However, during service idle periods, residual background activities—such as runtime threads and maintenance tasks—occupy the assigned cores, preventing them from entering deep idle states (e.g., C6) and leading to unnecessary power consumption. This paper introduces EC6, a lightweight, idle-aware scheduling policy for K8s that consolidates idle services onto a reserved single CPU core, allowing other cores to transition into deep C-states during service inactivity. Upon resumption of service activity, EC6 transparently restores services to their original CPU cores with minimal latency, ensuring resource allocation constraints (i.e.,, number of CPU cores) are maintained. Experimental evaluations show that EC6 increases per-core C6 residency by up to $30 \%$ and reduces idle power consumption by up to $13.6 \%$ compared to K8s’ default container scheduling policy, without compromising performance. This demonstrates its effectiveness in improving energy proportionality in cloud-native environments while preserving service quality.

Skull-induced phase aberrations and signal attenuation limit the performance of transcranial ultrasound imaging, typically confining applications to the temporal region. While adaptive beamforming techniques mostly offer partial correction, they typically lack access to point-specific skull thickness data essential for accurate skull-induced phase aberration compensation. This work presents a skull thickness mapping framework that provides more precise thickness measurements to adjust speed-of-sound (SOS) per probe location, improving phase aberration correction for trans-skull ultrasound applications, including transcranial ultrasound imaging, offering a solution for ultrasound-based transcranial systems. Using 800 CT scans from the MosMed Expanded Brain CT Dataset, cranial bone was segmented via thresholding, and surface meshes were generated through Marching Cubes reconstruction. Skull thickness was estimated by multi-directional ray casting between outer and inner bone boundaries, projected onto 3D surfaces as color-coded thickness maps. Rigid registration using Iterative Closest Point aligned individual skulls to a common anatomical reference, enabling the computation of region-specific mean thickness distributions and variability measures. When implemented in a custom ultrasound platform with a matrix array transducer, the proposed method improved phase aberration correction accuracy compared to fixed-SOS models. By enabling location-specific SOS adjustments, this framework provides a practical and adaptable method for full-skull transcranial ultrasound imaging.

Reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for enhancing wireless communication by dynamically controlling signal propagation in the environment. However, their efficient deployment relies on accurate channel state information (CSI), which leads to high channel estimation overhead due to their passive nature and the large number of reflective elements. In this work, we solve this challenge by proposing a novel framework that leverages a pre-trained open-source foundation model (FM) named large wireless model (LWM) to process wireless channels and generate versatile and contextualized channel embeddings. These embeddings are then used for the joint optimization of the BS beamforming and RIS configurations. To be more specific, for joint optimization, we design a deep reinforcement learning (DRL) model to automatically select the BS beamforming vector and RIS phase-shift matrix, aiming to maximize the spectral efficiency (SE). This work shows that a pre-trained FM for radio signal understanding can be fine-tuned and integrated with DRL for effective decision-making in wireless networks. It highlights the potential of modality-specific FMs in real-world network optimization. According to the simulation results, the proposed method outperforms the DRL-based approach and beam sweeping-based approach, achieving 9.89% and 43.66% higher SE, respectively.

Distributed machine learning has been developed to address the need for training data processing that has outpaced the increase in server computing power. As processing needs continue to grow, for example, AI-native radio access network (RAN) in 5G/6G networks, it is worth considering ways to promote and improve the efficiency of distributed machine learning. In this study, we focus on improving its energy consumption, while taking advantage of the latest developments in efficiency, especially its combination with split learning.We focus on client selection in the context of asynchronous distributed machine learning, namely asynchronous federated split learning (AFSL), involving heterogeneous clients with non-IID data, some of which may be stragglers or power-limited.To reduce the processing overhead of asynchronous updates while minimizing the impact on accuracy, we propose a clustering and selection scheme. Our approach aims to accelerate convergence and minimize energy consumption by selecting clients that best represent the overall training data in each round.Numerical results are presented on two datasets to highlight the effectiveness of the proposed mechanisms, achieving approximately 23% energy savings on the first dataset and 38% on the second, while meeting the performance targets with fewer training rounds and reduced network overheads.

In this paper, we introduce a novel approach for estimating the direction of arrival (DoA) in fully-connected hybrid analog/digital receivers. The key insight is that the analog combiner projects received signals onto the spatial sector it spans, causing signals from DoAs outside this sector to be significantly attenuated or nullified. Based on this observation, we develop two algorithms to ensure full spatial coverage and enhance DoA estimation accuracy. The first algorithm performs coarse estimates using an exhaustive set of analog combiners, each covering distinct subspaces that collectively span the entire space. To improve the precision of these estimates, we propose a second, iterative algorithm that progressively narrows the search window until convergence is achieved. Cramér-Rao lower bounds on the root-mean-square error of the proposed algorithms are derived and the superiority of these algorithms over their existing counterparts is established through numerical simulations.

Sixth generation (6G) wireless technology is anticipated to introduce Integrated Sensing and Communication (ISAC) as a transformative paradigm. ISAC unifies wireless communication and RADAR or other forms of sensing to optimize spectral and hardware resources. This paper presents a pioneering framework that leverages ISAC sensing data to enhance beam selection processes in complex indoor environments. By integrating multi-modal transformer models with a multi-agent contextual bandit algorithm, our approach utilizes ISAC sensing data to improve communication performance and achieves high spectral efficiency (SE). Specifically, the multi-modal transformer can capture inter-modal relationships, enhancing model generalization across diverse scenarios. Experimental evaluations on the DeepSense 6G dataset demonstrate that our model outperforms traditional deep reinforcement learning (DRL) methods, achieving superior beam prediction accuracy and adaptability. In the single-user scenario, we achieve an average SE regret improvement of 49.6% as compared to DRL. Furthermore, we employ transfer reinforcement learning to reduce training time and improve model performance in multi-user environments. In the multi-user scenario, this approach enhances the average SE regret, which is a measure to demonstrate how far the learned policy is from the optimal SE policy, by 19.7% compared to training from scratch, even when the latter is trained 100 times longer.

In mmWave wireless networks, signal blockages present a significant challenge due to the susceptibility to environmental moving obstructions. Recently, the availability of visual data has been leveraged to enhance blockage prediction accuracy in mmWave networks. In this work, we propose a Vision Transformer (ViT)-based approach for visual-aided blockage prediction that intelligently switches between mmWave and Sub-6 GHz frequencies to maximize network throughput and maintain reliable connectivity. Given the computational demands of processing visual data, we implement our solution within a hierarchical fog-cloud computing architecture, where fog nodes collaborate with cloud servers to efficiently manage computational tasks. This structure incorporates a generative AI-based compression technique that significantly reduces the volume of visual data transmitted between fog nodes and cloud centers. Our proposed method is tested with the real-world DeepSense 6G dataset, and according to the simulation results, it achieves a blockage prediction accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 2. 7 8 \%}$</tex> while reducing bandwidth usage by 70.31 %.

This paper addresses energy-efficient processing in the Open Radio Access Network (O-RAN) within the O-RAN Cloud (O-Cloud) infrastructure, focusing on optimal processor power scaling while scheduling packets under delay constraints. Traditionally, real-time packet scheduling tends to be suboptimal, as it prioritizes processing capacity over energy efficiency. To address this issue, we formulate a Mixed Integer Programming (MIP) model and develop a heuristic approach, along with a Convolutional Neural Network(CNN) for real-time scheduling. To enhance the CNN model, we introduce the CNN Binary Search Scheduling (CNN-BSS) algorithm, guided by the heuristic solution. Simulations show a 29.17 % reduction in energy consumption, significantly outperforming conventional methods.

The user-centric, cell-free wireless network is a promising next-generation communication system, but signal synchronization issues arise due to distributed access points and lack of cellular structure. We propose a novel method to recover synchronous pilot reception by introducing new pilot sequences and a matched filter window, enabling orthogonality even with asynchronous reception. Our approach mimics synchronous transmission by extending training sequences. Analysis shows asynchronous reception’s impact on channel estimation, and our method significantly improves performance with a small increase of training time overhead. Results demonstrate a 7.26 dB reduction in normalized mean square error and 40% increase in data rate, achieving performance levels comparable to the synchronous case.