Toshiba (United Kingdom)

Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on theoretical analysis and simulations, with limited investigation into real-world deployment. To bridge the gap and support practical DRL deployment for network management, we first present an orchestration framework that integrates ETSI Multi-access Edge Computing (MEC) with Open RAN, enabling seamless adoption of DRL-based strategies across different time scales while enhancing agent lifecycle management. We then identify three critical challenges hindering DRL's real-world deployment, including asynchronous requests from unpredictable or bursty traffic, adaptability and generalization across heterogeneous topologies and evolving service demands, and prolonged convergence and service interruptions due to exploration in live operational environments. To address these challenges, we propose a three-fold solution strategy: advanced time-series integration for handling asynchronized traffic, flexible architecture design such as multi-agent DRL and incremental learning to support heterogeneous scenarios, and simulation-driven deployment with transfer learning to reduce convergence time and service disruptions. Lastly, the feasibility of the MEC-O-RAN architecture is validated on an urban-wide testing infrastructure, and two real-world use cases are presented, showcasing the three identified challenges and demonstrating the effectiveness of the proposed solutions.

Federated Learning (FL) enables model training across distributed clients while preserving data privacy, yet client limitations in restricted computational power, memory, storage, and bandwidth, pose significant challenges for FL training and execution efficiency. This paper introduces FedMapTCS, a novel hybrid method that enhances FL communication efficiency by integrating FedMap, a technique for gradually learning a sparse FL model, with time-correlated sparsification (TCS) and error accumulation. This approach allows clients to collaboratively train an increasingly sparse global model, reducing communication overhead from the start of the training by selectively transmitting only necessary parameters each round. Extensive evaluation in both independent and identically distributed (IID) and non-IID settings demonstrates that FedMapTCS reduces communication bits by over 60% compared to the FedMap baseline and over 85% compared to federated averaging (FedAvg), while maintaining comparable model performance in IID settings. Under non-IID settings, FedMapTCS achieves better accuracy with up to 3.25× fewer rounds than FedMap, and achieves similar accuracy with 24.7% fewer parameters, highlighting its adaptability to heterogeneous data while maintaining performance. This communication efficiency gain positions FedMapTCS as a promising and effective solution for resource-constrained FL environments.

Ensuring reliable and low-latency communication in offshore wind farms is critical for efficient monitoring and control, yet remains challenging due to the harsh environment and lack of infrastructure. This paper investigates a flying base station (FBS) approach for wide-area monitoring and control in the UK Hornsea offshore wind farm project. By leveraging mobile, flexible FBS platforms in the remote and harsh offshore environment, the proposed system offers real-time connectivity for turbines without the need for deploying permanent infrastructure at sea. We develop a detailed and practical end-to-end latency model accounting for five key factors: flight duration, connection establishment, turbine state information upload, computational delay, and control transmission, to provide a holistic perspective often missing in prior studies. Furthermore, we combine trajectory planning, beamforming, and resource allocation into a multi-objective optimization framework for the overall latency minimization, specifically designed for large-scale offshore wind farm deployments. Simulation results verify the effectiveness of our proposed method in minimizing latency and enhancing efficiency in FBS-assisted offshore monitoring across various power levels, while consistently outperforming baseline designs.

Over the past decade, visible light positioning has become increasingly important for precise localization systems, yet its widespread adoption is limited due to the necessity of modifying existing lighting systems. This article presents HueLoc, a novel method that bypasses this issue by using inherent features of light, such as the dominant colors in white light-emitting diode (LED) lights, and employs affordable, energy-efficient hue sensors for location services. We propose that by extracting the power at dominant wavelengths of LEDs, these can be uniquely identified using a specifically designed signature. The unique signatures can be used by mobile objects for spatial awareness and further localization using the proposed regression-based learning approach. Our experiments demonstrate that HueLoc attains a location-mapping accuracy of 100% and achieves decimeter-level localization precision with a moving object in uncontrolled lighting conditions. Moreover, these unique signatures can be combined with other RF-based technologies to enhance their localization accuracy. As an example, this article details the integration of Bluetooth features with light signatures using a three-stage incremental learning approach. The experimental results show that this fusion method significantly improves Bluetooth localization by over 75%, overcoming challenges associated with severe indoor multipath and achieving highly precise location accuracy within decimeters.

This study presents an empirical investigation into the energy consumption of discriminative and generative AI models within real-world MLOps pipelines. For discriminative models, we examine various architectures and hyperparameters during training and inference and identify energy-efficient practices. For generative AI, large language models (LLMs) are assessed, with a focus primarily on energy consumption across different model sizes and varying service requests. Our study employs software-based power measurements, ensuring ease of replication across diverse configurations, models, and datasets. We analyse multiple models and hardware setups to uncover correlations among various metrics, identifying key contributors to energy consumption. The results indicate that, for discriminative models, optimising architectures, hyperparameters, and hardware can significantly reduce energy consumption without sacrificing performance. For LLMs, energy efficiency depends on balancing model size, reasoning complexity, and request-handling capacity, as larger models do not necessarily consume more energy when utilisation remains low. This analysis provides practical guidelines for designing green and sustainable ML operations, emphasising energy consumption and carbon-footprint reductions while maintaining performance. This paper can serve as a benchmark for accurately estimating total energy use across different types of AI models.

The fifth-generation (5G) mobile/cellular and timesensitive networking (TSN) technologies are widely recognized as the key to shaping smart manufacturing for Industry 4.0 and beyond. Converged operation of the two offers end-to-end real-time and deterministic connectivity over hybrid wired and wireless segments. On the other hand, the augmented reality (AR) technology provides various benefits for the manufacturing sector. To this end, this demonstration showcases AR-aided remote assistance use-case over a hybrid TSN and 5G system. The demonstration setup comprises off-the-shelf 5G and TSN devices, a near product-grade 5G system, and an AR solution based on smart glasses. The demonstration shows the viability of over-theair transmission of scheduled TSN traffic and real-time assistance for a local user from a remote environments. Performance results from the demonstration setup are also shown.

Error detection and correction are essential for ensuring robust and reliable operation in modern communication systems, particularly in complex transmission environments. However, discussions on these topics have largely been overlooked in semantic communication (SemCom), which focuses on transmitting meaning rather than symbols, leading to significant improvements in communication efficiency. Despite these advantages, semantic errors-stemming from discrepancies between transmitted and received meanings-present a major challenge to system reliability. This paper addresses this gap by proposing a comprehensive framework for detecting and correcting semantic errors in SemCom systems. We formally define semantic error, detection, and correction mechanisms, and identify key sources of semantic errors. To address these challenges, we develop a Gaussian process (GP)-based method for latent space monitoring to detect errors, alongside a human-inthe-loop reinforcement learning (HITL-RL) approach to optimize semantic model configurations using user feedback. Experimental results validate the effectiveness of the proposed methods in mitigating semantic errors under various conditions, including adversarial attacks, input feature changes, physical channel variations, and user preference shifts. This work lays the foundation for more reliable and adaptive SemCom systems with robust semantic error management techniques.

Security of data transported in telecommunication networks is of primary importance for internet service providers (ISP) as data safety is at the basis of the mutual trust with customers. People were looking for theoretically secure transmission techniques since a long-time to ensure long-term confidentiality of data flows exchanged on these networks. Besides advanced encryption algorithms and the recently proposed post-quantum cryptography (PQC), a physics-based technology using quantum key distribution (QKD) was proposed a long time ago to approach this objective. QKD recently gained a renewed interest with many research programs worldwide supported by public authorities, and some pre-industrial QKD systems delivered to the market. However, some constraints of optical transport networks make sometimes complicated the deployment of such QKD systems in the field, such as the need of a dedicated fiber infrastructure for QKD, or the impossibility for a quantum key to pass through an optical amplifier. In this paper, we report the transmission of a coherent 400-Gbps dual-polarization 16QAM channel that transports QKD-secured 100-GbEthernet data stream with other fifty-four WDM channels at 100-Gbps over 184-km of standard single mode fiber (SSMF) through three QKD links (of 66-km, 50-km and 66-km, respectively) and two trusted nodes. On the two longest sections of the link, the quantum key and WDM signals are propagated on two different fibers, while on the shortest section of 50-km the QKD signal and WDM comb co-propagate on a same fiber. Secret key rates (SKR) and quantum bit error rate (QBER) are measured and reported on each of the three fiber sections. Various analyses are carried out on the co-propagation section of 50-km: the SKR / QBER sensitivity to the optical power of the WDM comb, or to the optical signal-to-noise ratio (OSNR) of the WDM channels co-propagating with the quantum signal is studied. The unique arrangement of the most advanced QKD and WDM technologies reported here constitutes, in our opinion, a world first, and demonstrates that QKD and WDM solutions can coexist in already deployed optical transport networks.

Conversational Agents are increasingly integrated into our daily routines, assisting us with various tasks, from simple commands such as scheduling events to more complex conversational search interactions. Such conversational search systems are traditionally evaluated with word-overlap metrics such as F1 score and accuracy. The full-day workshop on Search-Oriented Conversational Artificial Intelligence (SCAI) at CHIIR 2024 explored the evaluation of conversational search systems from the user's perspective. This interactive workshop included multiple panel discussions and working groups focused on developing and discussing innovative, user-centered evaluation methods for these systems. This paper, co-authored by both organizers and participants of the workshop, presents a summary of the insights gathered from the panel discussions and working groups. Date : 14 March 2024. Website : https://scai.info/scai-2024/.

In the context of a smart industrial manufacturing scenario, where autonomous mobile robots (AMRs) from different manufacturers operate in shared environments, it is important to establish a method for verifying the integrity of the robots. To address this issue, we propose a novel framework for verifying the completion of tasks in multi-vendor robotic systems using proof-of-location and distributed ledger technologies. This approach ensures the trustworthiness and reliability of a multi-vendor robotic system. Using distributed ledger technology (DLT), robots can independently and cryptographically verify the completion of each other's tasks. Unlike traditional solutions that require several dedicated robots to participate in the verification process simultaneously, our proposed physical verification method is more efficient and does not require a typical "mining" stage. Additionally, it can be done asynchronously without adding extra burdens or delays to other ongoing tasks. Simulation results demonstrate that our approach can efficiently and effectively identify malicious robots in a multi-vendor robotic system.