<\/p>\n
| Short name<\/span><\/span><\/th>\n | Deliverable<\/span><\/span><\/th>\n | Abstract<\/span><\/span><\/th>\n<\/tr>\n| SORUS-DRONE-A1.1-E1<\/span><\/td>\n | First version of the architecture<\/span><\/a><\/td>\n | The main objective of the three 6G-SORUS projects to study the integration of UAVs with RIS and vRAN. This integration can provide several benefits, including increased coverage and capacity, improved spectral and energy efficiency, and enhanced security and privacy. UAVs can be used as flying base stations to provide wireless coverage to areas where it is difficult or impossible to deploy traditional base stations. By using RIS, the UAVs can enhance the signal quality and coverage, while vRAN can provide dynamic resource allocation and efficient management of the wireless resources. This document describes the architectural elements for the integration of\nUAVs in the operation of the network.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A1.1-E2 (E5)<\/span><\/td>\n | Final version of the architecture<\/span><\/a><\/td>\n | This deliverable presents an integrated architecture combining UAVs, virtualized RAN (vRAN), and Reconfigurable Intelligent Surfaces to enable adaptive B5G\/6G networks. Through coordinated real-time and non-real-time control, UAVs operate as flying gNBs and RIS-assisted relays, dynamically extending coverage and optimizing network performance. Telemetry-driven optimization and seamless orchestration with vRAN and RIS demonstrate the potential of this approach for rapid deployment, capacity boosts, and resilient connectivity, establishing a foundation for intelligent, flexible future networks.<\/td>\n<\/tr>\n | SORUS-DRONE-A1.2-E1<\/span><\/td>\n | UAV Use Cases<\/span><\/a><\/td>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of unmanned aerial vehicles (UAV, UAS, drones) with virtualized radio access networks (vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation of a B5G network. The design and development of the UAV solution will be carried out taking into account the needs of the use cases that will allow the validation of the developments achieved in the other subprojects (vRAN and RIS), as well as the state of the art of technology related to drones, communications and AI-Edge Computing. The proposed solution will address the functionalities of the different use cases with a sufficient degree of flexibility and adaptability that will allow its operational implementation for demonstrations.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A2.1-E1<\/span><\/td>\n | UAV Profiling - Initial version<\/span><\/a><\/p>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of unmanned aerial vehicles (UAVs, UAS, drones) with virtualized radio access networks (vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation\nof a B5G network. | \nThe process of analyzing different solutions and defining prototypes for validation testing is carried out in the PROFILING phase. This document presents the conceptual and functional development of this PROFILING phase, as well as the preliminary results of the initial tests aimed at creating the tools required to achieve the goals of the\nproject.<\/span><\/td>\n<\/tr>\n SORUS-DRONE-A2.1-E2<\/span><\/td>\n | UAV Profiling - Intermediate Version<\/span><\/a><\/p>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of unmanned aerial vehicles (UAVs, UAS, drones) with virtualized radio access networks (vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation of a B5G network. | \nThe process of analyzing different solutions and defining prototypes for validation testing is carried out in the PROFILING phase. This document presents an iteration of the conceptual and functional development of this PROFILING phase, with results of\nan intermediate stage for the tests aimed at creating the tools required to achieve the goals of the project.<\/span><\/td>\n<\/tr>\n SORUS-DRONE-A2.1-E3<\/span><\/td>\n | UAV Profiling - Final Version<\/span><\/a><\/p>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of unmanned aerial vehicles (UAVs, UAS, drones) with virtualized radio access networks (vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation of a B5G network. The process of analyzing different solutions and defining prototypes for validation testing is carried out in the PROFILING phase. This document presents the final iteration of the conceptual and functional development of this PROFILING phase, with\nresults of final stages for the tests aimed at creating the tools required to achieve the\ngoals of the project.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A2.2-E1 (RE10)<\/span><\/td>\n | Network Optimization I: algorithms for the or-\nchestration of UAV 6G Networks<\/span><\/a><\/td>\n | The main objective of 6G-SORUS is to study the integration of UAVs with RIS and vRAN. This document describes a set of algorithms and techniques to be used when orchestrating a B5G scenario with drones. The document provides a review of the state of the art and an initial subset of techniques\nto apply. These are divided in three groups: general algorithms to be used by UAVs (path planning, localization, etc.), orchestration algorithms (i.e., algorithms to control the overall operation of the service), and techniques and algorithms to provide communications using drones.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A2.2-E2 (E11) <\/span><\/td>\n | Network Optimization II: algorithms for the or-\nchestration of UAV 6G Networks<\/a><\/td>\n | In previous deliverables, we explored the state-of-the-art in algorithms for the orchestration of Un-manned Aerial Vehicles (UAVs) within Beyond 5G (B5G) networks. Building on that foundational work, this document delves deeper into two critical areas: path planning and collision avoidance. We ex-amine advanced algorithms aimed at optimizing UAV trajectory and safety in complex environments, a challenge that becomes more pressing with the integration of UAVs into B5G systems. In addition to a thorough review of existing methodologies, we present novel contributions developed under the project, enhancing the reliability and efficiency of UAV orchestration, particularly in scenarios involving dynamic and dense environments where collision avoidance is crucial.<\/td>\n<\/tr>\n | SORUS-DRONE-A3.1-E1 (E12)<\/span><\/td>\n | Initial Performance Evaluation<\/span><\/a><\/td>\n | In this deliverable, we conduct an in-depth analysis of strategies aimed at enhancing Beyond 5G (B5G) scenarios through the integration of Unmanned Aerial Vehicles (UAVs) and Reconfigurable Intelligent Surfaces (RIS). Our investigation focuses on critical Key Performance Indicators (KPIs) such as coverage probability, end-to-end delay, or power consumption. We systematically explore the dynamic interplay between these metrics under various influential factors shaping the B5G landscape, offering foundational insights into optimizing the deployment of UAVs and RIS.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A3.1-E2 (E13)<\/span><\/td>\n | Performance evaluation: final<\/span><\/a><\/td>\n | This deliverable advances the project\u2019s overarching goal of integrating UAVs, Reconfigurable Intelligent Surfaces (RIS), and virtualized RAN (vRAN) to enable intelligent, adaptive, and resource-efficient B5G\/6G networks. By demonstrating how UAVs can autonomously map wireless coverage using probabilistic modeling and uncertainty-driven exploration, it establishes a critical foundation for mobility-aware network optimization. The generated coverage maps can inform RIS configurations, guide vRAN resource allocation, and support on-demand UAV deployments for dynamic connectivity extension. Together, these capabilities contribute to a coordinated orchestration framework where UAV-based sensing, RIS-enabled propagation control, and vRAN virtualization converge to deliver\nhighly flexible, energy-efficient, and self-optimizing next-generation wireless networks.<\/td>\n<\/tr>\n | SORUS-DRONE-A3.2-E1<\/span><\/td>\n | UAV Design<\/span><\/a><\/td>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of unmanned aerial vehicles (UAVs, UAS, drones) with virtualized radio access networks\n(vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation of a B5G network. The design and development of the UAV solution will be carried out in accordance with the needs of the use cases that will validate the developments achieved in the other subprojects (vRAN and RIS), as well as the state-of-the-art technology related to drones, communications, and AI-Edge Computing. This document describes the design and elements of the First Prototype to be built for the project.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A3.2-E2<\/span><\/td>\n | UAV Initial Prototype<\/span><\/a><\/td>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of unmanned aerial vehicles (UAVs, UAS, drones) with virtualized radio access networks\n(vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation of a B5G network. The design and development of the UAV solution will be carried out in accordance with the needs of the use cases that will validate the developments achieved in the other subprojects (vRAN and RIS), as well as the state-of-the-art technology related to drones, communications, and AI-Edge Computing. This document describes the specifications and preliminary tests of the First Prototype built for the project.<\/span><\/td>\n<\/tr>\n | SORUS-DRONE-A3.2-E3<\/span><\/td>\n | UAV Final Prototype<\/span><\/a><\/p>\n | The SORUS-DRONES project focuses on the challenges posed by the integration of\nunmanned aerial vehicles (UAVs, UAS, drones) with virtualized radio access networks\n(vRAN) and reconfigurable intelligent surfaces (RIS) in the deployment and operation\nof a B5G network. The design and development of the UAV solution will be carried out\nin accordance with the needs of the use cases that will validate the developments\nachieved in the other subprojects (vRAN and RIS), as well as the state-of-the-art\ntechnology related to drones, communications, and AI-Edge Computing.\nThis document describes the specifications and preliminary tests of the First Prototype\nbuilt for the project.<\/td>\n<\/tr>\n | SORUS-RAN-A1.1-E1<\/span><\/td>\n | First version of the architecture<\/span><\/a><\/td>\n | The main objective of the three 6G-SORUS projects to study the integration of UAVs with RIS and vRAN. This integration can provide several benefits, including increased coverage and capacity, improved spectral and energy efficiency, and enhanced security and privacy. UAVs can be used as flying base stations to provide wireless coverage to areas where it is difficult or impossible to deploy traditional base stations. By using RIS, the UAVs can enhance the signal quality and coverage, while vRAN can provide dynamic resource allocation and efficient management of the wireless resources. This document describes the architectural elements for the integration of\nvRAN in the operation of the network.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A1.1-E2 (E5)<\/span><\/td>\n | Final version of the architecture<\/span><\/a><\/td>\n | Este entregable examina la evoluci\u00f3n de las arquitecturas de las Redes de Acceso Radio (RAN) y el papel fundamental de la Inteligencia Artificial en la configuraci\u00f3n de las redes m\u00f3viles modernas y futuras. Se traza la transici\u00f3n desde 3G hasta 5G, destacando c\u00f3mo el aumento en las demandas de rendimiento ha impulsado la integraci\u00f3n de funcionalidades habilitadas por IA, tales como Redes Autoorganizadas, predicci\u00f3n de tr\u00e1fico, gesti\u00f3n proactiva de recursos, detecci\u00f3n de anomal\u00edas y autorrecuperaci\u00f3n de la red. Sobre esta base, el entregable presenta un marco arquitect\u00f3nico que separa las capas de control en tiempo real y no en tiempo real, aline\u00e1ndose con los principios de vRAN y O-RAN para permitir una integraci\u00f3n escalable y flexible con tecnolog\u00edas como Veh\u00edculos A\u00e9reos No Tripulados (UAVs) y Superficies Inteligentes Reconfigurables (RIS).<\/td>\n<\/tr>\n | SORUS-RAN-A1.2-E1<\/span><\/td>\n | vRAN Use Cases<\/span><\/a><\/td>\n | This document corresponds to deliverable A1.2 - VRAN Use Cases - which is in the initial phase of the tasks described in the technical specifications. It describes three relevant vRAN use cases and studies the parameters of interest to optimize, the metrics to consider, and the different optimization objectives. Following the introduction, the primary goal is to identify scenarios where vRAN virtualization is an advantage over existing deployments. The deployment of multiple virtualized O-DUs on shared computing nodes is studied, as well as the advantages, disadvantages, and challenges of deploying different virtualized O-DUs on the same platform. The technical challenges of deploying multiple O-DUs at the computational level and shared hardware acceleration, as well as associated AI services at the Edge, are also described. The use of both Non-Real Time and Near-Real Time controllers is analyzed to improve resource allocation based on demand.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A2.1-E1<\/span><\/td>\n | Initial vRAN Profiling<\/span><\/a><\/td>\n | This document corresponds to deliverable A2.1 - vRAN Profiling - which is in the initial phase of the tasks described in the technical specifications. This document defines the elements used in the implementation of two testbeds to conduct various experiments aimed at obtaining energy consumption data. These data include both CPU and device consumption, allowing for separate comparison of energy consumption under the use cases outlined in the SORUS-RAN-A1.2 document. This has made it possible to appreciate, in terms of energy consumption reduction, that the hardware platform used plays a fundamental role in the total consumption, making it essential to select the appropriate platform based on the needs. At the same time, finding the right balance of MCS, airtime, and image resolution (if applicable) in each situation is essential to reduce energy consumption without compromising the end-user experience.<\/span><\/td>\n<\/tr>\n | SORUS-RAN A2.1-E2<\/span><\/td>\n | Final vRAN Profiling<\/span><\/a><\/td>\n | This document summarizes the existing features in vRAN environments and solutions through the proposed O-RAN architecture, which includes both non-real-time and near-real-time intelligent radio control. The problem of noisy neighbors is mainly addressed in this type of deployments with resource sharing. An experimental platform based on Docker is presented with which different experiments have been carried out to find the main reason for the exponential performance degradation with the increase of vBS. It has been concluded that secure computing weakly affects this increase (7%) and context switches account for 43% of the total overhead. However, the main problem lies in cache losses, which increase by 500% with five vBS.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A2.2-E1<\/span><\/td>\n | First version of joint optimization algorithms<\/span><\/a><\/td>\n | This deliverable deals with algorithms created for the optimisation of IoT networks to provide low-cost, high-bandwidth connectivity. For this purpose, an algorithm based on reconfigurable intelligent surfaces (RISs), called RISMA, has been developed, which jointly optimises the RIS parameters and the beamforming strategy at the transmitter from a theoretical perspective. In turn, an algorithm developed from the previous one, called Lo-RISMA, is presented, which aims to provide a solution to the cases where low resolution RISs are used through the study of the standarized mean square error (SMSE) to achieve an optimisation of the aggregate transmission rate of the system in the downlink.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A2.2-E2<\/span><\/td>\n | Final version of joint optimization algorithms<\/a><\/td>\n | This document corresponds to the deliverable SORUS-RAN-A2.2-E2, which is in the final phase of the tasks described in the technical specifications. The objective is to extend the previous work with a multi-user use case, as well as to numerically evaluate both the single-user and multi-user use cases using reconfigurable intelligent surfaces (RISs). The optimization aimed to minimize the sum of mean squared errors across all user nodes. To achieve this, the RIS parameters and the base station precoding are iteratively optimized separately. Additionally, two algorithms have been proposed: RISMA, as a low computational complexity solution to find optimal solutions in real time; and Lo-RISMA, designed for low-resolution metasurfaces, with high computational efficiency, ideal for devices with limited resources. The results show a 40% improvement compared to an MMSE precoder and a gain between 20% and 120% compared to a ZF precoder, depending on the network radius.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A2.3-E1 (E11)<\/span><\/td>\n | Algorithms for network optimization: selection and design<\/a><\/td>\n | \n | This deliverable presents an in-depth analysis of the state of the art in resource allocation and\nenergy-aware design for virtualized Radio Access Networks (vRAN). We review and categorize existing approaches, focusing on AI-driven optimization techniques, mobility modeling, and energy-efficient infrastructure management, highlighting their strengths, limitations, and open challenges. Building upon this analysis, we outline three key research directions: (i) the development of cost-\naware autoscaling algorithms for reliable and energy-efficient vRAN server farms; (ii) the design of privacy-preserving generative models for mobility-driven resource planning; and (iii) the evaluation of throughput gains achievable through dynamic spatial and temporal vRAN reconfiguration. Together, these directions provide a foundation for advancing intelligent, adaptive, and energy-efficient vRAN solutions that integrate algorithmic innovation, privacy-aware modeling, and performance evaluation.<\/p>\n<\/td>\n<\/tr>\n SORUS-RAN-A2.3-E2 (E12)<\/span><\/td>\n | Algorithms for network optimization:\nfinal design and implementation<\/a><\/td>\n | This deliverable presents the design and evaluation of a set of original algorithms for cost-aware and reliable autoscaling in vRAN infrastructures. Based on queueing models and a detailed characterization of both operational and capital expenditures, an optimization\nframework is developed to meet strict reliability targets while minimizing total cost.\nSimulations using real server profiles show that the proposed solution achieves up to 22%\ncost savings compared to classical methods, reaching near-optimal results with low computational complexity. This work provides a solid foundation for the development of self-\noptimizing and energy-efficient B5G\/6G networks.<\/td>\n<\/tr>\n | SORUS-RAN-A3.1-E1<\/span><\/td>\n | First version of the prototype to validate vRAN orchestration<\/span><\/a><\/td>\n | Este documento conforma el entregable SORUS-RAN-A3.1-E1, en el que se plantean diferentes algoritmos para dar soluci\u00f3n a los tres casos de uso planteados en el entregable SORUS-RAN-A1.2. La finalidad de los mismos es la de explorar distintos escenarios para optimizar el consumo energ\u00e9tico de las estaciones base virtualizadas, manteniendo los requerimientos de calidad de servicio. El objetivo es dise\u00f1ar un sistema de pol\u00edticas de energ\u00eda capaz de adaptarse a las necesidades del usuario y a las condiciones de la red maximizando el rendimiento del sistema. Se han hecho experimentos tanto en escenarios est\u00e1ticos como din\u00e1micos para calcular el rendimiento de la propuesta en presencia de r\u00e1pida variabilidad y cambios de repentinos de restricci\u00f3n.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A3.1-E2<\/td>\n | Second version of the prototype to validate vRAN orchestration<\/span><\/a><\/td>\n | Este documento se corresponde con el entregable SORUS-RAN-A3.1-E2. Este trabajo presenta soluciones a dos problemas detectados en vRANs generados por la compartici\u00f3n de recursos. En la primera parte se presenta AIRIC, un sistema para proporcionar reconfiguraci\u00f3n din\u00e1mica basada en Reinforcement Learning teniendo en cuenta el problema de los noisy neighbours. Se ha conseguido reducir la utilizaci\u00f3n de recursos en un 17% dimensionando correctamente el conjunto de n\u00facleos de computaci\u00f3n a lo largo del tiempo. La segunda parte est\u00e1 destinada a describir el framework implementado para solucionar la asignaci\u00f3n \u00f3ptima de memoria cach\u00e9 LLC (L3). Para ello se presenta MemorAI, que, mediante un Digital Twin y un clasificador basado en redes neuronales, permite una asignaci\u00f3n de LLC \u00f3ptima con un ahorro energ\u00e9tico entre 0,35kJ y 1 kJ seg\u00fan la estrategia de asignaci\u00f3n de v\u00edas de cach\u00e9.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A3.1-E3<\/td>\n | Final version of the prototype to validate vRAN orchestration<\/a><\/td>\n | Este documento se corresponde con el entregable SORUS-RAN-A3.1-E3. El trabajo reportado en este entregable aborda el problema del consumo energ\u00e9tico en redes de acceso radio (RAN) virtualizadas. En particular, el uso de aceleradores hardware (HA) implica un gran incremento en el consumo de energ\u00eda, lo que aumenta los costes y tiene graves consecuencias para el medio ambiente. Para resolver este problema, recopilamos datos de nuestra plataforma experimental y comparamos el rendimiento y el consumo energ\u00e9tico de una HA (GPU NVIDIA V100) frente a una CPU (Intel Xeon Gold 6240R, 16 n\u00facleos) para el procesamiento de software de bajo consumo energ\u00e9tico. A partir de los datos obtenidos, dise\u00f1amos una estrategia para descargar tr\u00e1fico en los HA de forma oportunista con el fin de ahorrar energ\u00eda y mantener la fiabilidad. Sin embargo, esta estrategia de descarga debe configurarse casi en tiempo real para cada estaci\u00f3n base (BS) que comparte recursos de computaci\u00f3n comunes. Esto plantea un problema colaborativo multi-agente en el que el n\u00famero de agentes implicados (BS) puede ser arbitrariamente grande y cambiar con el tiempo. Por lo tanto, proponemos un algoritmo llamado ECORAN, que resuelve un problema formulado como un contextual bandit multi-agente de forma eficiente. Nuestra soluci\u00f3n aplica conceptos de la teor\u00eda del campo medio para ser totalmente escalable. Utilizando una plataforma real y trazas de una red m\u00f3vil de producci\u00f3n, demostramos que ECORAN puede proporcionar hasta un 40% de ahorro de energ\u00eda con respecto al enfoque utilizado actualmente por la industria.<\/span><\/td>\n<\/tr>\n | SORUS-RAN-A3.2-E1 (E16)<\/td>\n | Initial Performance Evaluation<\/a><\/td>\n | This work addresses the challenge of understanding user mobility in wireless networks, which is crucial for optimizing space usage, managing smart infrastructures, and improving network efficiency. Given the privacy risks associated with real mobility data, we propose DiWi, a Transformer-based model that generates realistic spatiotemporal mobility traces while preserving user privacy. We evaluate the quality and privacy guarantees of the synthetic data and show that it retains the key mobility patterns of real traces. These insights not only enable privacy-preserving mobility analysis but also provide a foundation for developing more efficient resource allocation and reconfiguration strategies in future vRAN systems.<\/td>\n<\/tr>\n | SORUS-RAN-A3.2-E2 (E17)<\/td>\n | Final performance evaluation<\/a><\/td>\n | This deliverable explores the algorithmic challenges and performance limits of dynamic\nreconfiguration in virtualized Radio Access Networks (vRAN) for B5G systems. By integrating realistic, mobility-driven traffic profiles into the analysis, it evaluates how spatial and temporal reconfiguration\nstrategies can optimize throughput and energy efficiency under varying user demands. The study also considers the interplay between vRAN, UAV-assisted access, and Reconfigurable Intelligent Surfaces (RIS), highlighting the benefits of coordinated, mobility-aware orchestration. The results\nprovide key insights into the potential of predictive and adaptive network management, laying the groundwork for intelligent, flexible, and energy-efficient B5G infrastructures.<\/td>\n<\/tr>\n | SORUS-RIS-A1.1-E1<\/span><\/td>\n | First version of the architecture<\/span><\/a><\/td>\n | The main objective of the three 6G-SORUS projects to study the integration of UAVs with RIS and vRAN. This integration can provide several benefits, including increased coverage and capacity, improved spectral and energy efficiency, and enhanced security and privacy. UAVs can be used as flying base stations to provide wireless coverage to areas where it is difficult or impossible to deploy traditional base stations. By using RIS, the UAVs can enhance the signal quality and coverage, while vRAN can provide dynamic resource allocation and efficient management of the wireless resources. This document describes the architectural elements for the integration of\nRIS in the operation of the network.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A1.1-E2 (E5) | \n<\/span><\/td>\n Final version of the architecture<\/span><\/a><\/td>\n | This Deliverable presents an integrated architecture for Reconfigurable Intelligent Surfaces (RIS) in Beyond 5G (B5G) systems, detailing its controller design and interaction with real-time (RT) controllers for coordinated operation with Unmanned Aerial Vehicles (UAVs) and virtualized Radio Access Networks (vRAN). We first conduct a comprehensive review of related work on RIS-enabled networks, UAV-assisted communications, and vRAN integration, identifying the gaps in existing control and coordination mechanisms. Building on this analysis, we propose an architecture where the RIS controller interfaces seamlessly with RT controllers to dynamically manage RIS configurations, enable UAV-assisted coverage enhancement, and optimize communication with vRAN controllers. This design facilitates flexible, low-latency control and efficient orchestration of RIS and UAV resources, contributing to improved adaptability and performance in B5G networks.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A1.2-E1<\/span><\/td>\n | RIS Use Cases<\/span><\/a><\/td>\n | This document corresponds to deliverable A1.2 - Use Cases of RIS - which is in the initial phase of the tasks described in the technical specifications. This document presents a preliminary study of the technology and technical feasibility necessary to address the challenge of improving wireless networks through the use of reconfigurable smart surfaces. Three main areas of improvement have been defined: connectivity and reliability, localization and detection, and sustainability and security. It theoretically describes how this technology can be useful to overcome problems in urban environments with high density of obstacles or without direct line of sight from the base stations (BSs). In indoor and outdoor environments, it could be used for people detection as a passive radar or environment mapping. Regarding security, it can enable highly directional communications, resulting in greater energy efficiency and preventing signal interception by other agents.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A2.1-E1<\/span><\/td>\n | Measurement Platform<\/span><\/a><\/td>\n | This report introduces the environment used to measure the energy consumption of smartphones, based on the architecture of Battery Labs<\/a> (Varvello, 2022). After describing the environment, our focus will shift to analyzing radio access technologies (3G, 4G, 5G, and Wi-Fi) and their impact on energy consumption. Subsequently, we will outline the planned experiments for the upcoming Deliverable 2. Finally, from Telef\u00f3nica's perspective as a connectivity provider, we will explore the energy-saving mechanisms of base stations when entering different suspension patterns. These results will be presented in Deliverable 3.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A2.1-E2<\/span><\/td>\n | Experiment Design and Development<\/span><\/a><\/p>\n | In the field of telecommunications, understanding the energy consumption of smartphones is a critical area of focus. With approximately 8 billion smartphones in use worldwide, examining how these devices consume energy during internet use can highlight opportunities for significant improvements and optimizations. Despite its importance, this area remains relatively unexplored by researchers. Our goal is to identify the main factors contributing to the increased energy consumption in smartphones during internet use. To achieve this, we have concentrated on key elements such as content size, radio access technologies (3G, 4G, 5G, WiFi), device age (newer vs. older models), mobile network operators (e.g., Vodafone, Movistar), and types of applications (web browsers, social networks, video streaming). By identifying these factors, we aim to uncover insights that can drive more efficient energy use in smartphones.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A2.1-E3 | \n<\/span><\/td>\n Final Energy Measurements<\/span><\/a><\/p>\n | This deliverable updates the analysis of energy consumption across the entire mobile network stack, covering both user devices and infrastructure. It begins by examining how different Radio Access Technologies (RATs) affect smartphone energy usage during video streaming scenarios. Building on this, the focus shifts to the mobile network infrastructure, specifically the Radio Access Network (RAN), where energy-saving policies are evaluated in a real production environment. In this deliverable, we analyze five fixed-threshold-based cell switch-off policies deployed in a commercial network. The results provide novel insights into actual energy savings and user impact, showing that while user experience remains unaffected, energy savings reach a clear limit. This supports the need for more flexible approaches to improve RAN sustainability.\u00a0<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A2.2-E1<\/span><\/td>\n | Capture methodologies and initial classification of UEs according to the behavioral model<\/span><\/a><\/td>\n | Este entregable describe las actividades realizadas durante el primer per\u00edodo de SORUS-RIS-A2.2. \u00c9stas incluyen la identificaci\u00f3n de los conceptos psicol\u00f3gicos y conductuales relevantes para la caracterizaci\u00f3n de la respuesta de los usuarios a la latencia del sistema, as\u00ed como la identificaci\u00f3n de la metodolog\u00eda a utilizar para su medici\u00f3n. Adem\u00e1s, este Entregable presenta la primera versi\u00f3n del algoritmo de clasificaci\u00f3n de usuarios, aplicado a tres conjuntos de datos diferentes, as\u00ed como los resultados del estudio piloto basado en el uso de se\u00f1ales psicofisiol\u00f3gicas, como un primer paso para la integraci\u00f3n de estas en el algoritmo de clasificaci\u00f3n.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A2.2-E2<\/span> | \n<\/span><\/td>\n Final classification of UEs according to the behavior model<\/span><\/a><\/td>\n | This document presents the research activities carried out in the second period of SORUS-RIS-A2.2. These activities include the mapping of users' cognitive and emotional variables to multimodal psychophysiological signals, the analysis of the reliability and robustness of these signals, and, finally, the definition of the final version of the user clustering algorithm based on their response to latency, in the context of using existing services in the real world. The results demonstrate the usefulness of this approach and provide user profiling that can be considered in future applications to provide users with more personalized telecommunication services.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A2.3-E1 (E12)<\/span><\/td>\n | Algorithms for RIS operation: selection and design<\/span><\/a><\/td>\n | This document introduces an autonomous and energy self-sufficient Reconfigurable\nIntelligent Surface (RIS) solution. The system is designed to overcome the limitations of\nconventional deployments, such as the need for a continuous external power supply and a\ndedicated control channel. The core of this solution is a Hybrid RIS (HRIS) capable of both\nreflecting and absorbing signals. The absorption capability is leveraged for radio frequency (RF) energy harvesting, enabling the HRIS to operate off-the-grid. The document details the system's design, including a battery charging and discharging model based on a Markov chain, and a battery dimensioning strategy.<\/td>\n<\/tr>\n | SORUS-RIS-A2.3-E2 (E13)<\/span><\/td>\n | Algorithms for RIS operation: results<\/a><\/td>\n | This Deliverable explores the integration of Reconfigurable Intelligent Surfaces (RIS) into campus-wide virtualized Radio Access Networks (vRAN), emphasizing the need for scalable control, latency-aware signalling, and resource-efficient architectures to meet the demands of emerging 6G services. We analyze the scalability of mechanically reconfigurable RIS, identifying computational and signalling strategies for real-time management of large-scale deployments. Additionally, we formulate an energy-aware AP ON\/OFF optimization problem that leverages demand forecasting\nand pre-configured RIS steering to achieve significant energy savings without compromising coverage. By combining predictive intelligence in vRAN with RIS control, this work provides a blueprint for intelligent, context-aware resource management. The findings underscore the transformative potential of coordinated RIS and vRAN operation, paving the way for sustainable,\nflexible, and service-oriented next-generation wireless networks.<\/td>\n<\/tr>\n | SORUS-RIS-A2.3-E3<\/span><\/td>\n | Final version of the RIS Simulator<\/span><\/a><\/p>\n | \n | This final SORUS-RIS-A2.3-E3 deliverable presents our results in terms of simulators for RIS placement. On the one hand, we rely on Sionna (which we confirmed in SORUS-RIS-A2.3-E2 as the state-of-the-art for this effort), and present our comprehensive, data-driven framework for the automated deployment of Reconfigurable Intelligent Surfaces (RIS) in cellular networks, considering real-world network deployment as simulation scenarios. Our framework integrates site-specific ray\ntracing (via the Sionna engine), user clustering, and ray-based heuristics to optimize RIS placement, orientation, phase configuration, and base station beamforming. In this context, we validate two complementary deployment strategies\u2014reflection-based and scattering-based\u2014across realistic multi-cell 4G, 5G, and 6G urban networks. Our results demonstrate that RIS deployment can significantly enhance coverage in high-density outage regions, though large-scale improvements require deploying many RIS units, highlighting a trade-off between performance and cost. In parallel, this deliverable introduces GraphWave, our very own neural graph-based radio propagation model inspired by ray tracing, capable of accurately inferring received signal strength (RSS) in complex 3D environments. With this effort, we formulate ray tracing as a learning problem, and leverage the power of deep learning to build ouw very own Sionna-like simulator. GraphWave outperforms conventional models in both synthetic and real-world settings, offering improved accuracy and computational efficiency. We validate both the RIS deployment framework and GraphWave with synthetic and real-world data; we will release the RIS deployment framework as open-source tools to foster reproducibility and further research in next-generation wireless network planning and optimization.<\/p>\n<\/td>\n<\/tr>\n SORUS-RIS-A3.1-E1<\/span><\/td>\n | RIS Simulator Design<\/span><\/a><\/td>\n | \n | This report represents a preliminary investigation into the benefits of incorporating RIS (Reconfigurable Intelligent Surface) equipment into Radio Access networks (RAN) to enhance cellular services. To conduct this evaluation, it is necessary to design a system-level simulator capable of capturing both realistic propagation environments and the behavior of RIS.\nIn this work, we have designed such a simulator using the Remcom Wireless InSite ray-tracing tool, an advanced commercial software for radio-level analysis. Our goal is to augment the capabilities of this tool to aid in the deployment and simulation of RIS, featuring specific radiation patterns derived from laboratory test bench environments. We aim to assess the impact of RIS repeaters on radio coverage improvement, taking into account key system parameters such as size, location, and orientation.<\/span><\/div>\n<\/td>\n<\/tr>\n SORUS-RIS-A3.1-E2<\/td>\n | Initial version of the RIS Simulator<\/span><\/a><\/td>\n | This report represents an investigation into the benefits of incorporating RIS (Reconfigurable\nIntelligent Surface) equipment into Radio Access Networks (RAN) to enhance cellular services. In the first part of this study, we gauge the benefits of including RIS elements towards radio coverage improvement in real-world scenarios. Specifically, we select a crowded city location with a dense topography and an environment that might account for diversity in the propagation radio models. For this setup, we collect the real-world radio network deployment of a commercial network and derive the theoretical radio coverage based on the network deployment. We then feed this to the RIS-augmented Wireless InSite ray-tracing simulator to account for the strategical deployment of RIS within each specific scenario. Our goal is to demonstrate the impact of RIS deployments in different environments and RIS configurations. Our findings advocate for RIS as a cost-effective\nsolution for expanding coverage in real-world urban mobile networks.<\/span><\/p>\n | In the second part of this study, we employ a different ray-tracing tool, namely Sionna RT (by Nvidia). To this end, we develop a modular system-level simulator to analyze and optimize wireless network environments. The simulator includes blocks for BS\/user deployment, channel computation, and KPI calculation, and captures key performance indicators such as coverage, SNR, SINR, and data rates. By utilizing datasets from Telef\u00f3nica\u2019s cellular network, we enhance the simulator to accurately model real-world deployments and integrated Nvidia's Sionna RT for advanced channel modeling, allowing us to assess propagation scenarios with high precision. Key features of Sionna RT, such as RIS placement and reradiation mode optimization, enable us to evaluate the impact of Reconfigurable Intelligent Surfaces on network performance.<\/span><\/div>\n<\/td>\n<\/tr>\n SORUS-RIS-A3.2-E1<\/span><\/td>\n | Platform design<\/span><\/a><\/td>\n | This document includes the requirements imposed to achieve a passive, scalable and sustainable RIS. In contrast to other works, a RIS design is proposed with modularity features and capable of offering 3-bit resolution, which enables high spatial resolution codebooks. A RIS design is proposed using an RF switch, which reduces the cost of controlling the reflector cells with respect to PIN diode-based solutions, and the use of two buses called cell selection and phase selection buses, which enable scalability.<\/span><\/td>\n<\/tr>\n | SORUS-RIS-A3.2-E2<\/span><\/td>\n | Operational RIS platform<\/span><\/a><\/td>\n | This document corresponds to the deliverable SORUS-RIS A3.2-E2, which is in the initial phase of the tasks described in the technical specifications. This document explains the practical implementation and empirical characterization of a RIS prototype based on the design presented in the SORUS-RIS A3.2-E1 document, where a system based on reconfigurable intelligent surfaces capable of adjusting the phase of incident radio frequency signals for passive 3D beamforming was introduced. The construction on a printed circuit board and all the design decisions involved in the process are detailed. The prototype is validated through various experiments, including beam patterns, received power measurement, and scalability analysis, as well as a cost study associated with the production of each cell.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>","protected":false},"excerpt":{"rendered":" | Nombre corto Entregable Descripci\u00f3n SORUS-DRONE-A1.1-E1 Primera versi\u00f3n de la arquitectura El principal objetivo de los tres proyectos 6G-SORUS es estudiar la integraci\u00f3n de los UAVs con RIS y vRAN. Esta integraci\u00f3n puede proporcionar varios beneficios, incluyendo mayor cobertura y capacidad, eficiencia energ\u00e9tica y espectral mejorada, y una mayor seguridad y privacidad. Los UAVs pueden… |
|---|