The exponential growth in connectivity and computing demand has made Network Function Virtualization Infrastructure (NFVI) a major contributor to global energy consumption. Conventional network and service deployments, whether based on legacy hardware appliances or NFVI stacks, struggle to dynamically provision resources for peak data traffic demand. This results in nearly constant energy consumption, even during low-traffic periods, leading to inefficient resource use. Network softwarization and virtualization have enabled flexible and programmable service deployments, which are beneficial for the rapid and dynamic scaling of network functions. This paper validates energy-aware service and network orchestration with a Zero-touch Network and Service Management (ZSM) framework for the autonomous optimization of computing, network, and power resources from NFVI in a use case focused on connected mobility, and in particular, smart traffic management. By modeling road traffic based on vehicle count and type and 3rd Generation Partnership Project (3GPP) profiles for data formats in vehicular communication scenarios, the ZSM framework adjusts services and resources to service requirements and to actual demand. Experimental validation on the real-life Smart Highway testbed in Antwerp, Belgium, demonstrates a strong correlation between vehicular traffic and power consumption, supporting the hypothesis that adaptive compute and network resource management reduces unnecessary energy use and advances the vision of sustainable and self-optimizing Sixth-Generation (6G) networks.

Despite major advances in Connected and Autonomous Vehicles (CAVs), edge cases such as unmapped construction zones or dense urban areas still require human intervention. Teleoperation, often combined with Level 4 automation, addresses these situations but demands strict network performance i.e., latency below 5 ms, uplink throughput above 25 Mbps, and 99.999% reliability, to ensure safe, responsive control under heavy load. This paper presents a Proof-of-Concept (PoC) 5G Standalone (SA) network supporting end-to-end Network Slicing for teleoperation. The PoC achieves seamless slice isolation across the 5G Core (5GC), Transport Network (TN), and Radio Access Network (RAN), enabling dynamic and cross-domain Network Slicing to meet teleoperation requirements.

This paper presents a comprehensive benchmark study of a real-life 5G Standalone (SA) deployment with different Multiple Input Multiple Output (MIMO) configurations (1x1, 2x2, and 4x4) in an indoor office environment. We evaluate the impact of distance, obstacles, and material composition on key performance metrics, including throughput, Reference Signal Received Power (RSRP), Signal-to-Interference-plus-Noise Ratio (SINR), and Rank Indicator (RI). The results demonstrate that while higher-order MIMO configurations can deliver substantial throughput gains under favorable conditions, their effectiveness is fundamentally constrained by environmental factors such as signal attenuation, multipath propagation, and material-induced losses. Our results provide practical guidelines for indoor network planning and optimization, establishing concrete performance baseline for open-source 5G systems in typical office scenarios highlighting the critical importance of site selection.

This paper presents a novel stream allocation algorithm for semi-coherent Cell-Free Multi-User Multiple-Input Multiple-Output (CF-MU-MIMO) networks. In such networks, groups of phase-coherent Access Points (APs) are organized into clusters that operate coherently inside the clusters, while inter-cluster phase coherence is not maintained, reflecting practical limitations in achieving network-wide synchronization. The proposed algorithm is tailored for multi-cluster service, where multiple clusters can simultaneously serve each User Equipment (UE). To support this flexibility, different stream sequences are constructed for each UE, and each of the sequences is initialized and dynamically constructed based on the strongest links across all serving clusters and the UEs. During the allocation process, both inter-cluster and inter-stream interference are mitigated using projection-based techniques, thereby improving spatial multiplexing efficiency. Compared to the greedy stream allocation which is commonly adopted in the literature as a low-complexity benchmark due to its near-optimal performance in downlink MIMO systems, the proposed method achieves higher performance with only a modest increase in complexity. Furthermore, a significant enhancement in the achievable sum rate is demonstrated relative to single-user-single-cluster allocation strategies in distributed cell-free systems.

The real-world deployments of 5G SA networks have highlighted significant challenges, particularly related to signal coverage, leading to performance degradation for enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and massive Machine-Type Communications (mMTC). To address these challenges and minimize the costs of new infrastructure deployment, Network Sharing among multiple operators has become a viable, cost-effective solution. The 3rd Generation Partnership Project (3GPP) began exploring network sharing in 5G with Release 15, expanding it with an Indirect Network Sharing configuration in Release 19. In this work, we present an Indirect Network Sharing approach that utilizes Network Slicing to create multiple isolated virtual networks on a single physical infrastructure, ensuring resource isolation and efficient management in a multi-operator environment. Our demonstration illustrates how a third-party entity can effectively manage network resources, maintaining isolation and performance quality across different network domains operated by various providers.

5G Standalone (SA) networks introduce a concept of Network Slicing that enables a range of new applications, such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and massive Machine-Type Communications (mMTC). However, despite the promising potential of 5G SA networks, real-world deployments have revealed significant limitations, particularly in terms of signal coverage, resulting in performance degradation for eMBB, URLLC, and mMTC services. To mitigate these challenges and reduce the costs associated with deploying new infrastructure, Network Sharing among multiple operators has emerged as a cost-effective solution. While the 3rd Generation Partnership Project (3GPP) introduced Network Sharing in 5G Release 15 and added an Indirect Network Sharing configuration in Release 19, real-life implementation remains limited due to immature mechanisms and the lack of automated systems for neutral hosts providers to easily onboard new operators and dynamically allocate network resources to meet specific network requirements. In this paper, we explore the application of Network Slicing as a mechanism to deploy Network Sharing among multiple operators, presenting a 5G SA Indirect Network Sharing architecture as proof of concept (PoC). Through our experiment, performed in a real-world and open-source testbed based on O-RAN principles, we demonstrate how applying Network Slicing technology, Neutral Host providers can effectively deploy resource isolation and enable collaboration in a multi-operator environment while guaranteeing service quality to their users.

Nowadays, many services are offered via the cloud, i.e., they rely on interacting software components that can run on a set of connected Commercial Off-The-Shelf (COTS) servers sitting in data centers. As the demand for any particular service evolves over time, the computational resources associated with the service must be scaled accordingly while keeping the Key Performance Indicators (KPIs) associated with the service under control. Consequently, scaling always involves a delicate trade-off between using the cloud resources and complying with the KPIs. In this paper, we show that a (workload-dependent) Pareto front embodies this trade-off’s limits. We identify this Pareto front for various workloads and assess the ability of several scaling algorithms to approach that Pareto front.

Modern networks, characterized by their complexity and heterogeneity, are transitioning from manual to automated and intelligent management, according to the vision of Autonomous Networks (ANs). Leveraging data-driven techniques, ANs aim to provide the "Zero-X" and "Self-X" experience, where intelligent and adaptable network operations are key cornerstones. Such is the case of intelligent resource scaling, where the goal is to optimize resource orchestration to maximize efficiency, reduce latency, and maintain high-quality service, even amid fluctuating network loads and changing service requirements. Unfortunately, current approaches for auto-scaling are computationally expensive to deploy in resource-constrained devices such as those found at the edge or beyond. This paper introduces an innovative four-phase approach to train a compact, data-driven Deep Reinforcement Learning (DRL) scaler that can be deployed on low-power devices. Our results demonstrate the scalability and efficiency of this model, achieving state-of-the-art scaling with up to 1003x fewer parameters, enhancing interpretability and computational efficiency, making it a robust solution for intelligent resource scaling in network environments. The resulting 1487x runtime speed improvement and 28.5x reduction in memory requirements allow the scaler to be deployed on low-power devices and still operate in real-time, which is essential for mission-critical and latency-sensitive applications.

Enhancing communication between Vulnerable Road Users (VRUs) and Unmanned Automated Vehicles (UAVs) has significant potential to improve road safety. The need for this communication is due to the fact that VRUs will no longer be able to establish physical eye contact with UAVs, given the absence of a human driver behind the steering wheel. However, a challenge in the state-of-the-art technologies for Connected, Cooperative, and Automated Mobility (CCAM), i.e. ITS-G5 (IEEE 802.11p) and Cellular Vehicle-to-Everything (C-V2X), is the lack of a unified communication stack that connects all types of users. This is because the current generation of CCAM communication technologies requires dedicated hardware devices that cannot be easily installed on devices carried by VRUs (such as phones or wearables). This paper aims to address this challenge by providing a real-life, sophisticated solution that offers the CCAM communication stack as a Network-as-a-Service (NaaS) in the 5G and Beyond ecosystem. Integration is achieved by relying on the Service Enabler Architecture Layer (SEAL) principles standardised by the 3rd Generation Partnership Project (3GPP). These architectural principles are embedded in the design of Network-Aware Edge Applications (EdgeApps), which are the building blocks of vertical services in 5G and Beyond. This way, any device or user with the capability to connect to 5G will also be able to retrieve important CCAM services from the network by using EdgeApps. In addition, no dedicated CCAM hardware is needed. Furthermore, this paper provides key lessons learned from the challenges encountered in connecting VRUs and UAVs by integrating CCAM into the 5G and Beyond ecosystem. Moreover, we have conducted real-life experiments to evaluate the system-level latency characteristics of the proposed solution and compared them with those of ITS-G5 and C-V2X.

Connected and Automated Vehicles (CAVs) are revolutionizing the automotive industry by improving real-time situational awareness, and road safety. Connectivity and latency are critical for the secure and efficient operation of CAVs. The evolution of Cellular Vehicular-to-Everything (C-V2X) technology, particularly through Long Term Evolution V2X (LTE-V2X) and its successor New Radio-V2X (NR-V2X), is essential to address these challenges. LTE-V2X and NR-V2X are intended to coexist, complementing each other to cover a broad spectrum of vehicular communication needs. However, network overload is a critical issue, which risks severely degrading the performance of V2X applications and compromising road safety. This study delves into the practical implementation of Network Slicing within a real-world 5G environment, incorporating a modular Open Radio Access Network (O-RAN) architecture on the radio side, and Service-Based Architecture (SBA) principles on the core. We present a Network Slicing configuration that deploys a synergy between the 5G Core (5GC) and the Radio Access Network (RAN). Through strategic placement and policy application across multiple User Plane Functions (UPFs), our configuration enhances network performance and reliability for V2X applications. We validate our approach by demonstrating how this setup effectively manages the high demands of diverse and rigorous applications, ensuring the network requirements for enhanced V2X scenarios under various network conditions. Our results highlight the importance of synergy between 5GC and RAN for the application of an efficient network slicing mechanism in NR-V2X networks.

As 5G rollout keeps progressing, the need for experimentation platforms with different functionalities, like MEC deployments, flexible Core functions and multi-vendor compatibility, keeps growing. Existing testbeds have some commercial/closed source solutions integrated to a degree (in the Core, Radio Access Network (RAN) or both), limiting development of new and innovative functionalities, and experimentation that might require more fine grain control over the network. This paper provides valuable insights into the current 5G performance by using the 5GOpen@TheBeacon testbed, a flexible solution that utilizes multiple open-source solutions in both indoor and outdoor environments, working in real-world conditions. We leverage two architectures and combine the different software available which later can enable research across different use cases, such as eMBB, URLLC and V2X.

To properly orchestrate challenging services such as those deployed for Vehicle-to-Everything (V2X) use cases, MANO systems need to be intelligent and automated. Network Function Virtualization (NFV) and Machine Learning (ML) provide opportunities for automating MANO operations, and this paper presents our MI-enhAnced Edge Service orchesTRatiOn (MAESTRO) algorithm that makes proactive ML-driven decisions for edge service relocation to ensure Quality of Service (QoS) guarantees for V2X services. Moreover, to validate the effectiveness of our proposed solution, we have performed the experimentation using real-life testbeds for high computing and smart mobility i.e., Smart Highway and Virtual Wall, located in Antwerp and Gent, Belgium. The contribution of our paper is two-fold: i) we study the interrelation between the Key Performance Indicators (KPIs) measured at the vehicle client side, and the infrastructure metrics at the edge computing nodes and ii) we propose and evaluate an ML-based quality-aware algorithm that automates edge service orchestration to decrease average latency while guaranteeing high service availability and reliability.

Cloud and edge Data-center (DC) are designed to allocate computing resources dynamically to users based on the agreed Service Level Agreement (SLA). However, the ever-increasing demand for beyond 5G services necessitates an efficient workload management. A key challenge in this regard is auto-scaling, a dynamic process that adjusts computing resources to meet fluctuating system demands, optimizing resource utilization and cost efficiency. Traditional auto-scaling algorithms, which rely on fixed thresholds or control-theory, may face limitations in modern DC which are characterized by diverse, dynamic, and multi-user workloads. In this paper, we propose a Reinforcement Learning (RL)-based controller that extends the capacity of the state-of-the-art RL-based auto-scalers to the multi-user workload scenario. We compare the proposed RL agent against the well-known Proportional-Integral (PI) controller and a Threshold (THD)-based controller in a multi-user workload scenario in terms of created Cloud-native Network Functions (CNFs) and peak latency performed in a discrete event simulator.

Next-generation mobile networks are expected to flaunt highly (if not fully) automated management. To achieve such a vision, Artificial Intelligence (AI) and Machine Learning (ML) techniques will be key enablers to craft the required intelligence for networking, i.e., Network Intelligence (NI), empowering myriad of orchestrators and controllers across network domains. In this paper, we elaborate on the DAEMON architectural model, which proposes introducing a NI Orchestration layer for the effective end-to-end coordination of NI instances deployed across the whole mobile network infrastructure. Specifically, we first outline requirements and specifications for NI design that stem from data management, control timescales, and network technology characteristics. Then, we build on such analysis to derive initial principles for the design of the NI Orchestration layer, focusing on (i) proposals for the interaction loop between NI instances and the NI Orchestrator, and (ii) a unified representation of NI algorithms based on an extended MAPE-K model. Our work contributes to the definition of the interfaces and operation of a NI Orchestration layer that foster a native integration of NI in mobile network architectures.

The plethora of heterogeneous and diversified services in 5G and beyond requires from networks to be flexible, adaptable, and programmable, i.e., to be able to correspondingly adapt to changes. As human intervention might significantly increase delays in MANagement and Orchestration (MANO) operations, automation and intelligence become imperative for orchestrating services and resources, especially the ones with stringent requirements for latency and capacity, such as Vehicle-to-Everything (V2X) services. As virtualization and Artificial Intelligence (AI) promise to mitigate those challenges towards enabling true automation in MANO operations, in this paper we present our effort towards building and fully utilizing the real-life testbeds, such as Smart Highway and Virtual Wall, located in Belgium, to conduct realistic experimentation and validation of distributed orchestration intelligence in a dynamic network such as V2X system.

As manual Management and Orchestration (MANO) of services and resources might delay the execution of MANO operations and negatively impact the performance of 5G and beyond Vehicle-to-Everything (V2X) services, applying AI in MANO to enable automation and intelligence is an imperative. The Network Function Virtualization (NFV), Software Defined Networking (SDN), and Artificial Intelligence (AI), could all together mitigate those challenges, and enable true automation in MANO operations. Thus, in this demo paper we will showcase the use of real-life testbed environments (Smart Highway and Virtual Wall, Belgium) and the Proof-of-Concept that we build to conduct realistic experimentation and validation of intelligent and distributed MANO in a dynamic network such as a V2X system.

Autonomous Fifth Generation (5G) and Beyond 5G (B5G) networks require modelling tools to predict the impact on the performance when new configurations and features are applied in the network. Modeling modern networks through traditional mathematical analysis can lead to low accuracy, while the execution time and resource usage are high in network simulators. Machine Learning (ML) algorithms, and specifically Graph Neural Networks (GNNs), are suggested as a promising alternative since they can capture complex relationships from graph-like data, predicting properties with high accuracy and low resource requirements. However, they cannot generalize to larger networks, as their prediction accuracy decreases when input data (e.g., network topologies) is significantly different (e.g., larger) than the training data. This paper addresses the GNNs scalability issue by following a step-by-step approach, exploiting networking concepts to improve a baseline model. This work is framed in the 2021 International Telecommunication Union (ITU) and Barcelona Neural Networking Center - Universitat Politècnica de Catalunya (BNN-UPC) challenge. Results show that by following the suggested steps, applied on the RouteNet baseline developed by the BNN-UPC, can lower the Mean Average Percentage Error (MAPE) from 187.28% to 1.838%, improving the generalization significantly over larger graphs. Our approach is more simple than other solutions that participated in the challenge, but obtained similar results.

Traffic Classification (TC) systems allow inferring the application that is generating the traffic being analyzed. State-of-the-art TC algorithms are based on Deep Learning (DL) and have outperformed traditional methods in complex and modern scenarios, even if traffic is encrypted. Most of the works on TC assume the traffic flows on a wired network under the same network management domain. This assumption limits the capabilities of TC systems in wireless networks since users’ traffic on one network domain can be negatively impacted by undetected users’ traffic from other network domains or detected ones but with no traffic context in a shared spectrum. To solve this problem, we introduce a novel framework to achieve TC at any layer on the radio network stack. We propose a spectrum-based procedure that uses a DL-based classifier to realize this framework. We design two DL-based classifiers, a novel Convolutional Neural Network (CNN) spectrum-based TC and a Recurrent Neural Networks (RNN) as baseline architecture, and benchmark their performance on three TC tasks at different radio stack layers. The datasets were generated by combining packet traces from real transmissions with an 802.11 standard-compliant waveform generator. Performance evaluations show that the best model can achieve an accuracy above 92% in the most demanding TC task, a drop of only 4.37% in accuracy compared to a byte-based DL approach, with micro-second per-packet prediction time, which is very promising for delivering real-time spectrum-based traffic analyzers.

Recently, the operation of LTE in unlicensed bands has been proposed to cope with the ever-increasing mobile traffic demand. However, the deployment of LTE in such bands implies sharing spectrum with mature technologies such as Wi-Fi. Several studies have discussed this coexistence problem by suggesting that LTE implements different adaptation mechanisms that allow transmission possibilities to Wi-Fi. While such adaptation mechanisms exist, they still negatively impact Wi-Fi performance, mainly due to the lack of collaboration/coordination mechanisms that inform about the co-located networks' activities. In this paper, we propose a distributed spectrum management framework that enhances the performance of Wi-Fi, as a particular case, by detecting harmful co-located wireless networks and changes the Wi-Fi's operating central frequency to avoid them. The framework is based on a Convolutional Neural Network (CNN) that can identify different wireless technologies and provides spectrum usage statistics. Experiments were carried out in a real-life testbed, and the results show that Wi-Fi maintains its performance when using our framework. This translates in an increase of at least 40% on the overall throughput compared to a non-managed operation of Wi-Fi.

Dynamic Spectrum Access allows using the spectrum opportunistically by identifying wireless technologies sharing the same medium. However, detecting a given technology is, most of the time, not enough to increase spectrum efficiency and mitigate coexistence problems due to radio interference. As a solution, recognizing traffic patterns may lead to select the best time to access the shared spectrum optimally. To this extent, we present a traffic recognition approach that, to the best of our knowledge, is the first non-intrusive method to detect traffic patterns directly from the radio spectrum, contrary to traditional packet-based analysis methods. In particular, we designed a Deep Learning (DL) architecture that differentiates between Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) traffic, burst traffic with different duty cycles, and traffic with varying rates of transmission. As input to these models, we explore the use of images representing the spectrum in time and time-frequency. Furthermore, we present a novel data randomization approach to generate realistic synthetic data that combines two state-of-the-art simulators. Finally, we show that after training and testing our models in the generated dataset, we achieve an accuracy of ≥ 96 % and outperform state-of-the-art methods based on IP-packets with DL.

Many Internet of Things (IoT) applications require a distributed architecture for decision making either because of a lack of a centralized system, failure-prone connectivity to a centralized system or because the imposed latency to contact such a system is too high for real-time applications. Often, these IoT applications fall in the domain of reinforcement learning (RL), e.g., autonomous robot navigation in smart factories and traffic signal control in smart cities. However, RL-based applications require a long learning time. To overcome this limitation and scale with the number of agents, parallel RL (PRL) algorithms run multiple RL agents in parallel and on distributed environments. However, deploying PRL algorithms in such environments entails a communication overhead that increases the (actual) execution time. The state-of-the-art PRL algorithms are designed for reducing the learning time while assuming no (or limited) communication overhead. In this article, we present a novel partitioning algorithm that minimizes the communication overhead in PRL running on IoT environments. To the best of our knowledge, this is the first work that focuses on solving the communication overhead of distributing PRL algorithms without requiring any a priori knowledge about the structure of the problem. The proposed algorithm intelligently combines a dynamic state partitioning strategy, which exploits the agent's exploration capabilities to build partition knowledge while learning, with an efficient mapping of agents to partitions, which reduces the communication among agents. Performance evaluations show that the proposed algorithm can achieve almost no communication among PRL agents at the converged state.

Wireless network technologies are becoming more and more popular. Because of this, important parts of the wireless spectrum become overloaded. Static spectrum allocation, which has been the norm for decades, is not suitable anymore. To maintain the high demand for spectrum and the continuous development of new wireless technologies, there is a need for an intelligent, dynamic spectrum allocation mechanism, where different network technologies collaboratively optimize the spectrum usage. New wireless network paradigms, such as Neutral Host Networks (NHNs) and private 5G, require a smart, spectrum-footprint-aware flow control algorithm to overcome the spectrum scarcity in collaborative way. This article presents a strategy, vision and flow control mechanism to implement collaboration in a Quality of Service (QoS)-driven way. The solution in this article is based on policies which may activate depending on its current and neighbor's network states. Through a flow ordering and selection strategy, these policies optimize the spectrum footprint, based on the performance and QoS-requirements of the own and surrounding networks. The proposed algorithm is tested extensively and validated on a large scale during the DARPA Spectrum Collaboration Challenge (SC2) competition. The results of the SC2 final event and intermediate scrimmages showed that the proposed approach increased the score, indicating increased inter-network collaboration was achieved.

This paper presents a Convolutional Neural Network (CNN) approach for classification of low power wide area network (LPWAN) technologies such as Sigfox, LoRA and IEEE 802.15.4g. Since the technologies operate in unlicensed sub-GHz bands, their transmissions can interfere with each other and significantly degrade their performance. This situation further intensifies when the network density increases which will be the case of future LPWANs. In this regard, it becomes essential to classify coexisting technologies so that the impact of interference can be minimized by making optimal spectrum decisions. State-of-the-art technology classification approaches use signal processing approaches for solving the task. However, such techniques are not scalable and require domain-expertise knowledge for developing new rules for each new technology. On the contrary, we present a CNN approach for classification which requires limited domain-expertise knowledge, and it can be scalable to any number of wireless technologies. We present and compare two CNN based classifiers named CNN based on in-phase and quadrature (IQ) and CNN based on Fast Fourier Transform (FFT). The results illustrate that CNN based on IQ achieves classification accuracy close to 97% similar to CNN based on FFT and thus, avoiding the need for performing FFT.

In the unlicensed spectrum, many wireless technologies (e.g Wi-Fi, Bluetooth) use the same spectrum for wireless transmission. This often results in cross-technology interference effects, which are hard to address. Without new methods to manage this shared spectrum, wireless communication is increasingly challenging as too many nodes attempt at accessing the same spectrum. Collaboration between different wireless networks that use the same spectrum will be required to handle this massive amount of devices. In this paper, we present two algorithms based on Neural Networks (NNs) to demonstrate that a function approximation can accurately predict free slots in a Multiple Frequencies Time Division Multiple Access (MF-TDMA) network. By observing the spectrum, we are able to do online learning and let the corresponding NN predict the behavior of the spectrum a second in advance using our approach. We are able to reduce the number of collisions by half if the nodes from other networks are sending data following a Poisson distribution. When the nodes of the other network follow a more periodic traffic pattern, a collision reduction of factor 15 could be achieved.

In the last decade, several routing algorithms have been proposed in ad hoc wireless networks. However, most of them require either a high bandwidth, to maintain a full routing table, or suffer a high delay with packet flooding over the network, when the routes are discovered on-demand. As a solution, hybrid approaches, i.e. algorithms that combine on-demand route discovery with proactive updates of the available routes, have shown a good trade-off between low communication overhead and quality of the found routes. One of the approaches used in hybrid algorithms is Multi-Agent Reinforcement Learning (MARL), where the routing problem is addressed as a complex distributed control and learning problem. However, state-of-the-art MARL routing algorithms suffer from some limitations such as either lack of exploration or exploration at the cost of a high communication overhead, slow convergence under network dynamics, or no support for Quality of Service (QoS). In order to overcome such limitations, in this paper, we propose the Q2-Routing algorithm, which merges existing techniques in wireless routing and enhances them by using techniques from the MARL domain. Simulation results showed that the proposed algorithm is able to outperform well-known ad-hoc routing algorithms in dynamic environments under QoS constraints.

Data center networks (DCNs) connect hundreds and thousands of computers and, as a result of the exponential growth in their number of nodes, the design of scalable (compact) routing schemes plays a pivotal role in the optimal operation of the DCN. Traditional trends in the design of DCN architectures have led to solutions, where routing schemes and network topologies are interdependent, i.e., specialized routing schemes. Unlike these, we propose a routing scheme that is compact and generic, i.e., independent of the DCN topology, the word-metric-based greedy routing. In this scheme, each node is assigned to a coordinate (or label) in the word-metric space (WMS) of an algebraic group and then nodes forward packets to the closest neighbor to the destination in this WMS. We evaluate our scheme and compare it with other routing schemes in several topologies. We prove that the memory space requirements in nodes and the forwarding decision time grow sub-linearly (with respect to n, the number of nodes) in all of these topologies. The scheme finds the shortest paths in topologies based on Cayley graphs and trees (e.g. Fat tree), while in the rest of topologies, the length of any path is stretched by a factor that grows logarithmically (with respect to n). Moreover, the simulation results show that many of the paths remain far below this upper bound.