arXiv subjects

Ferran Adelantado

Publications and source records attributed to Ferran Adelantado.

12 recordsLinked to original sources

arXiv2025

Enhancing AI Transparency: XRL-Based Resource Management and RAN Slicing for 6G ORAN Architecture

This research introduces an advanced Explainable Artificial Intelligence (XAI) framework designed to elucidate the decision-making processes of Deep Reinforcement Learning (DRL) agents in ORAN architectures. By offering network-oriented explanations, the proposed scheme addresses the critical challenge of understanding and optimizing the control actions of DRL agents for resource management and allocation. Traditional methods, both model-agnostic and model-specific approaches, fail to address the unique challenges presented by XAI in the dynamic and complex environment of RAN slicing. This paper transcends these limitations by incorporating intent-based action steering, allowing for precise embedding and configuration across various operational timescales. This is particularly evident in its integration with xAPP and rAPP sitting at near-real-time and non-real-time RIC, respectively, enhancing the system's adaptability and performance. Our findings demonstrate the framework's significant impact on improving Key Performance Indicator (KPI)-based rewards, facilitated by the ability to make informed multimodal decisions involving multiple control parameters by a DRL agent. Thus, our work marks a significant step forward in the practical application and effectiveness of XAI in optimizing ORAN resource management strategies.

eess.SP↗

arXiv2025

AIaaS for ORAN-based 6G Networks: Multi-time Scale Slice Resource Management with DRL

This paper addresses how to handle slice resources for 6G networks at different time scales in an architecture based on an open radio access network (ORAN). The proposed solution includes artificial intelligence (AI) at the edge of the network and applies two control-level loops to obtain optimal performance compared to other techniques. The ORAN facilitates programmable network architectures to support such multi-time scale management using AI approaches. The proposed algorithms analyze the maximum utilization of resources from slice performance to take decisions at the inter-slice level. Inter-slice intelligent agents work at a non-real-time level to reconfigure resources within various slices. Further than meeting the slice requirements, the intra-slice objective must also include the minimization of maximum resource utilization. This enables smart utilization of the resources within each slice without affecting slice performance. Here, each xApp that is an intra-slice agent aims at meeting the optimal quality of service (QoS) of the users, but at the same time, some inter-slice objectives should be included to coordinate intra- and inter-slice agents. This is done without penalizing the main intra-slice objective. All intelligent agents use deep reinforcement learning (DRL) algorithms to meet their objectives. We have presented results for enhanced mobile broadband (eMBB), ultra-reliable low latency (URLLC), and massive machine type communication (mMTC) slice categories.

eess.SP↗

arXiv2023

Intelligent QoS aware slice resource allocation with user association parameterization for beyond 5G ORAN based architecture using DRL

The diverse requirements of beyond 5G services increase design complexity and demand dynamic adjustments to the network parameters. This can be achieved with slicing and programmable network architectures such as the open radio access network (ORAN). It facilitates the tuning of the network components exactly to the demands of future-envisioned applications as well as intelligence at the edge of the network. Artificial intelligence (AI) has recently drawn a lot of interest for its potential to solve challenging issues in wireless communication. Due to the non-deterministic, random, and complex behavior of models and parameters involved in the process, radio resource management is one of the topics that needs to be addressed with such techniques. The study presented in this paper proposes quality of service (QoS)-aware intra-slice resource allocation that provides superior performance compared to baseline and state of the art strategies. The slice-dedicated intelligent agents learn how to handle resources at near-RT RIC level time granularities while optimizing various key performance indicators (KPIs) and meeting QoS requirements for each end user. In order to improve KPIs and system performance with various reward functions, the study discusses Markov's decision process (MDP) and deep reinforcement learning (DRL) techniques, notably the deep Q network (DQN). The simulation evaluates the efficacy of the algorithm under dynamic conditions and various network characteristics. Results and analysis demonstrate the improvement in the performance of the network for enhanced mobile broadband (eMBB) and ultra-reliable low latency (URLLC) slice categories.

eess.SP↗

arXiv2022

Challenges and Opportunities for Simultaneous Multi-functional Networks in the UHF Bands

Multi-functional wireless networks are rapidly evolving and aspire to become a promising attribute of the upcoming 6G networks. Enabling multiple simultaneous networking functions with a single radio fosters the development of more integrated and simpler equipment, overcoming design and technology barriers inherited from radio systems of the past. We are seeing numerous trends exploiting these features in newly designed radios, such as those operating on the mmWave band. In this article, however, we carefully analyze the challenges and opportunities for multi-functional wireless networks in UHF bands, advocating the reuse of existing infrastructures and technologies, and exploring the possibilities of expanding their functionality without requiring architectural changes. We believe that both modern and legacy technologies can be turned into multi-functional systems if the right scientific and technological challenges are properly addressed. This transformation can foster the development of new applications and extend the useful life of these systems, contributing to a more sustainable digitization by delaying equipment obsolescence.

cs.NI↗

arXiv2020

LR-FHSS: Overview and Performance Analysis

Long Range-Frequency Hopping Spread Spectrum (LR-FHSS) is the new physical layer designed to address extremely long-range and large-scale communication scenarios, such as satellite IoT. At its core is a fast frequency hopping technique designed to offer higher network capacity while offering the same radio link budget as LoRa. Additionally, LR-FHSS finely manages packet transmission thanks to its design principles, enabling QoS policies on a per-packet basis. Given the notorious adoption of LoRaWAN in the IoT application landscape, this article is a reference for understanding how exactly LR-FHSS works, the performance it can offer, and its limitations and research opportunities.

cs.NI↗

arXiv2019

Exploring the Performance Boundaries of NB-IoT

NarrowBand-IoT has just joined the LPWAN community. Unlike most of its competitors, NB-IoT did not emerge from a blank slate. Indeed, it is closely linked to LTE, from which it inherits many of the features that undoubtedly determine its behavior. In this paper, we empirically explore the boundaries of this technology, analyzing from a user's point of view critical characteristics such as energy consumption, reliability and delays. The results show that its performance in terms of energy is comparable and even outperforms, in some cases, an LPWAN reference technology like LoRa, with the added benefit of guaranteeing delivery. However, the high variability observed in both energy expenditure and network delays call into question its suitability for some applications, especially those subject to service-level agreements.

cs.NI↗

arXiv2019

Aggressive Fragmentation Strategy for Enhanced Network Performance in Dense LPWANs

Low Power Wide Area Networks (LPWANs) are gaining ground in the IoT landscape and, in particular, for Industrial IoT applications. However, given the strict duty cycle restrictions (e.g. 1% in SubGHz bands) and the limited power supply of devices, requirements of some applications can not always be met. This paper analyzes the potential of the combination of packet fragmentation -in the direction of the IETF LPWAN working group- and negative group acknowledgement (NACK) in LoRaWAN networks, a widespread LPWAN technology. Results show that the proposed strategy can lead to significant gains in terms of goodput and energy efficiency under congested situations.

cs.NI↗

arXiv2018

An Analysis of Packet Fragmentation Impact in LPWAN

Packet fragmentation has mostly been addressed in the literature when referring to splitting data that does not fit a frame. It has received attention in the IoT community after the 6LoWPAN working group of IETF started studying the fragmentation headers to allow IPv6 1280 B MTU to be sent over IEEE 802.15.4 networks supporting a 127 B MTU. In this paper, and following some of the recent directions taken by the IETF LPWAN WG, an analysis of packet fragmentation in LPWANs has been done. We aim to identify the impact of sending the data in smaller fragments considering the restrictions of industrial duty-cycled networks. The analyzed parameters were the energy consumption, throughput, goodput and end to end delay introduced by fragmentation. The results of our analysis show that packet fragmentation can increase the reliability of the communication in duty-cycle restricted networks. This is of especial relevance when densifying the network. We observed relevant impact in energy consumption and extra latency, and identified the need for acknowledgements from the gateway/sink to exploit some of the benefits raised by fragmentation.

cs.NI↗

arXiv2018

The Wireless Technology Landscape in the Manufacturing Industry: A Reality Check

An upcoming industrial IoT revolution, supposedly led by the introduction of embedded sensing and computing, seamless communication and massive data analytics within industrial processes [1], seems unquestionable today. Multiple technologies are being developed, and huge marketing efforts are being made to position solutions in this industrial landscape. However, we have observed that industrial wireless technologies are hardly being adopted by the manufacturing industry. In this article, we try to understand the reasons behind this current lack of wireless technologies adoption by means of conducting visits to the manufacturing industry and interviews with the maintenance and engineering teams in these industries. The manufacturing industry is very diverse and specialized, so we have tried to cover some of the most representative cases: the automotive sector, the pharmaceutical sector (blistering), machine-tool industries (both consumer and aerospace sectors) and robotics. We have analyzed the technology of their machinery, their application requirements and restrictions, and identified a list of obstacles for wireless technology adoption. The most immediate obstacles we have found are the need to strictly follow standards and certifications processes, as well as their prudence. But the less obvious and perhaps even more limiting obstacles are their apparent lack of concern regarding low energy consumption or cost which, in contrast, are believed to be of utmost importance by wireless researchers and practitioners. In this reality-check article, we analyze the causes of this different perception, we identify these obstacles and devise complementary paths to make wireless adoption by the industrial manufacturing sector a reality in the coming years.

cs.CY↗

arXiv2017

Spectral Efficient and Energy Aware Clustering in Cellular Networks

The current and envisaged increase of cellular traffic poses new challenges to Mobile Network Operators (MNO), who must densify their Radio Access Networks (RAN) while maintaining low Capital Expenditure and Operational Expenditure to ensure long-term sustainability. In this context, this paper analyses optimal clustering solutions based on Device-to-Device (D2D) communications to mitigate partially or completely the need for MNOs to carry out extremely dense RAN deployments. Specifically, a low complexity algorithm that enables the creation of spectral efficient clusters among users from different cells, denoted as enhanced Clustering Optimization for Resources' Efficiency (eCORE) is presented. Due to the imbalance between uplink and downlink traffic, a complementary algorithm, known as Clustering algorithm for Load Balancing (CaLB), is also proposed to create non-spectral efficient clusters when they result in a capacity increase. Finally, in order to alleviate the energy overconsumption suffered by cluster heads, the Clustering Energy Efficient algorithm (CEEa) is also designed to manage the trade-off between the capacity enhancement and the early battery drain of some users. Results show that the proposed algorithms increase the network capacity and outperform existing solutions, while, at the same time, CEEa is able to handle the cluster heads energy overconsumption.

cs.NI↗

arXiv2017

Understanding the limits of LoRaWAN

The quick proliferation of LPWAN networks, being LoRaWAN one of the most adopted, raised the interest of the industry, network operators and facilitated the development of novel services based on large scale and simple network structures. LoRaWAN brings the desired ubiquitous connectivity to enable most of the outdoor IoT applications and its growth and quick adoption are real proofs of that. Yet the technology has some limitations that need to be understood in order to avoid over-use of the technology. In this article we aim to provide an impartial overview of what are the limitations of such technology, and in a comprehensive manner bring use case examples to show where the limits are.

cs.NI↗

arXiv2015

Scalable RAN Virtualization in Multi-Tenant LTE-A Heterogeneous Networks (Extended version)

Cellular communications are evolving to facilitate the current and expected increasing needs of Quality of Service (QoS), high data rates and diversity of offered services. Towards this direction, Radio Access Network (RAN) virtualization aims at providing solutions of mapping virtual network elements onto radio resources of the existing physical network. This paper proposes the Resources nEgotiation for NEtwork Virtualization (RENEV) algorithm, suitable for application in Heterogeneous Networks (HetNets) in Long Term Evolution-Advanced (LTE-A) environments, consisting of a macro evolved NodeB (eNB) overlaid with small cells. By exploiting Radio Resource Management (RRM) principles, RENEV achieves slicing and on demand delivery of resources. Leveraging the multi-tenancy approach, radio resources are transferred in terms of physical radio Resource Blocks (RBs) among multiple heterogeneous base stations, interconnected via the X2 interface. The main target is to deal with traffic variations in geographical dimension. All signaling design considerations under the current Third Generation Partnership Project (3GPP) LTE-A architecture are also investigated. Analytical studies and simulation experiments are conducted to evaluate RENEV in terms of network's throughput as well as its additional signaling overhead. Moreover we show that RENEV can be applied independently on top of already proposed schemes for RAN virtualization to improve their performance. The results indicate that significant merits are achieved both from network's and users' perspective as well as that it is a scalable solution for different number of small cells.

cs.NI↗