The transition from LTE to 5G, and therefore from a monolithic network architecture to a service based architecture, introduces a myriad of new challenges. Most significantly, the decomposition of core components into individual services introduces an extensive signalling traffic overhead within the 5G core network. Additionally, there is a general lack of observability for the 5G core, hindering advancements in modelling and optimization for the system as a whole as well as the individual network functions. To address this, we present a measurement methodology to increase observability within the 5G core system and extract crucial information for the signalling traffic for specific user equipments within the individual network functions. Furthermore, we use our proposed methodology to conduct a case study on the performance of the attachment procedure in Open5GS, a commonly used open source implementation, under different loads. Lastly, we investigate the stability of the Access and Mobility Management Function under heavy load.

Beyond 5G(B5G) and 6 G networks must support diverse applications with widely varying Quality of Service (QoS) requirements, ranging from ultra-low latency to extremely high throughput. Effectively meeting these demands calls for efficient resource management across applications. However, static resource allocation often struggles to adapt to rapid traffic fluctuations and volatile radio channel conditions, resulting in inefficiencies and performance degradation. This requires adaptive, application-aware control that can respond in real time at fine granularity. In this work, we propose a runtime resource control mechanism that enables application-aware resource allocation based on specific QoS requirements. We focus on dynamic Physical Resource Block (PRB) allocation and evaluate its impact on application-level throughput and latency through experimental validation on a B5G testbed, built using open-source RAN (srsRAN) and core network (Open5GS) implementation. Our results show that dynamic PRB allocation has a significant impact on overall performance. We also evaluate the control loop latency to understand the responsiveness and effectiveness of real-time adaptive resource allocation. This study contributes to the open-source community by advancing autonomous resource management, with the implementation released as open-source to support reproducibility.

Autoscaling is a core capability in cloud computing with significant impact on service quality and cost. Modern applications, like microservices and serverless functions, consist of many containers that enable fine-grained, component-wise scaling. Effective autoscaling across large, heterogeneous service landscapes remains challenging. As cloud adoption increases, workloads have become more diverse, exhibiting highly variable request patterns, payload characteristics, and response time requirements. This limits the effectiveness of conventional autoscalers, whose fixed intervals and cooldown periods restrict responsiveness. At the same time, the growing number of services and frequent updates strain approaches based on predefined models, motivating more adaptive solutions.

5G New Radio (NR) is designed to support diverse services, shifting from a fixed smartphone-centric infrastructure to flexible deployment options tailored for verticals like Ultra-Reliable Low-Latency Communications (URLLC) and Machine-Type Communications (MTC). To optimize the QoS of 5G NR to the service needs, understanding the impact of the introduced configuration parameters is critical. This paper investigates the configuration space of 5G NR using open-source 5G standalone deployments based on OpenAirInterface (OAI) and srsRAN (SRS). We conduct a detailed study on the impact of Next Generation NodeB (gNB) configurations on uplink and downlink throughput and latency, we compare the 5G NR implementations of OAI and SRS, and we investigate reproducibility across different testbeds at the University of Wuerzburg and NTNU. Our datasets are made publicly available.

Driven by the development of programmable networking hardware, In-network Computing (INC) has gained a considerable amount of attention in recent years. However, INC has so far barely been studied in the context of mobile networks, despite the vast advantages shown for fixed networks, such as latency or traffic reduction. Motivated by an Augmented Reality (AR) use-case, our work envisions an INC-enabled Intelligent User Plane (IUP) for 6G networks, which allows offloading computational tasks to UP entities having enhanced computational capabilities. The 6G IUP thus helps to keep mobile end-devices lighter and supports meeting the stringent delay requirements of novel applications, such as AR. Besides elaborating on the involved prospects and challenges, we identify key enablers for realizing the INC-enabled IUP. We show that embedding INC into the 6G system entails major changes in the architecture, as compared to the current 5G design.

Scenarios related to 5G and beyond give rise to a high degree of heterogeneity in terms of applications, services, and user expectations as well as more demanding QoS requirements with an end-to-end scope that can cover multiple operator domains. In this work, we design an inter-domain component that addresses the control plane challenges of establishing such end-to-end connectivity in a scalable, efficient, and automated way. Furthermore, we provide insights into operational aspects by investigating to which extent different traffic aggregation mechanisms can be used to benefit from economies of scale while meeting QoS constraints.

Network operators generally aim at providing a good level of satisfaction to their customers. Diverse application demands require the usage of beyond best-effort resource allocation mechanisms, particularly in resource-constrained environments. Such mechanisms introduce additional complexity in the control plane and need to be configured appropriately. Within 5G mobile networks, two new mechanisms for QoS-aware resource allocation are introduced. While QoS Flows enable specifying various QoS profiles on a per flow granularity, slices are dedicated virtual networks, strongly isolated against each other, with aggregated QoS guarantees. It is, however, unclear how QoS Flows and network slicing can optimally be exploited to ensure a high customer QoE while efficiently utilizing the available network resources. We address this research question and evaluate the outlined interplay using the OMNeT++ simulation environment in a multi-application scenario. We show that resource isolation induced by slicing may negatively affect application quality or system utilization, and that this impact can be overcome by finetuning the system parameters.

Network softwarization paradigms such as SDN and NFV provide network operators with advantages in terms of scalability, cost and resource efficiency, as well as flexibility. However, in order to fully reap these benefits and cope with new challenges regarding the heterogeneity of user demands and an ever-growing service landscape, management and operation of such networks requires a high degree of automation that ensures fast and proactive decision making. With the recent success of machine learning (ML) across numerous domains, a shift from traditional rule-based policies towards ML-based approaches in the context of network management is taking place. Although many individual contributions cover use cases such as predicting various network characteristics or optimizing the configuration of components, a fully integrated architecture for achievingNetwork Intelligenceis still missing. Hence, in this work, we propose such an architecture that combines the capabilities of softwarized networks with ML-based management. The contribution of this article is threefold: first, we present the proposed architecture alongside its components. Second, we implement a proof-of-concept version of all components in our OpenStack-based testbed. Finally, we demonstrate in a case study regarding VNF resource prediction how the proposed architecture can be used to generate realistic data sets to train and evaluate ML-based models for this task.

Software-defined networking (SDN) and the network function virtualization (NFV) led to great developments in software based control technology by decreasing expenditures. Service function chaining (SFC) is an important technology to find efficient paths in network servers to process all of the requested virtualized network functions (VNF). However, SFC is challenging since it has to maintain high Quality of Service (QoS) even for complicated situations. Although some works have been conducted for such tasks with high-level intelligent models like deep neural networks (DNNs), those approaches are not efficient in utilizing the topology information of networks and cannot be applied to networks with dynamically changing topology since their models assume that the topology is fixed. In this paper, we propose a new neural network architecture for SFC, which is based on graph neural network (GNN) considering the graph-structured properties of network topology. The proposed SFC model consists of an encoder and a decoder, where the encoder finds the representation of the network topology, and then the decoder estimates probabilities of neighborhood nodes and their probabilities to process a VNF. In the experiments, our proposed architecture outperformed previous performances of DNN based baseline model. Moreover, the GNN based model can be applied to a new network topology without re-designing and re-training.

Software-Defined Networking (SDN) and Network Function Virtualization (NFV) help reduce OPEX and CAPEX as well as increase network flexibility and agility. But at the same time, operators have to cope with the increased complexity of managing virtual networks and machines, which are more dynamic and heterogeneous than before. Since this complexity is paired with strict time requirements for making management decisions, traditional mechanisms that rely on, e.g., Integer Linear Programming (ILP) models are no longer feasible. Machine learning has emerged as a possible solution to address network management problems to get near-optimal solutions in a short time. In this paper, we propose a Graph Neural Network (GNN) based algorithm to manage VNFs. The proposed model solves the complex VNF management problem in a short time and gets near-optimal solutions.

Network Function Virtualization (NFV) environment can deal with dynamic changes in traffic status with appropriate deployment and scaling of Virtualized Network Function (VNF). However, determining and applying the optimal VNF deployment in consideration of the cost and Quality of Service (QoS) is a complicated and difficult task. In particular, it is necessary to predict the situation at a future point when the deployment decision is applied because it takes processing time to apply the deployment decision to the actual NFV environment. In this paper, we randomly generate service requests in Multiaccess Edge Computing (MEC) topology, then obtain optimal VNF deployment and Service Function Chaining (SFC) result from an Integer Linear Programming (ILP) solution. We use the simulation data to train a machine learning model which predicts the optimal VNF deployment at a predefined future point. The prediction model shows the accuracy over 90% compared to the ILP solution for the 5-minute future time point.

Software-Defined Networking (SDN) and Network Function Virtualization (NFV) help reduce OPEX and CAPEX as well as increase network flexibility and agility. But at the same time, operators have to cope with the increased complexity of managing virtual networks and machines, which are more dynamic and heterogeneous than before. Since this complexity is paired with strict time requirements for making management decisions, traditional mechanisms that rely on, e.g., Integer Linear Programming (ILP) models are no longer feasible. Machine learning has emerged as a possible solution to address network management problems to get near-optimal solutions in a short time. In this paper, we propose a Graph Neural Network (GNN) based algorithm to manage Virtual Network Functions (VNFs). The proposed model solves the complex VNF management prob-lem in a short time and gets near-optimal solutions.

In addition to providing network operators with benefits in terms of flexibility and cost efficiency, softwarization paradigms like SDN and NFV are key enablers for the concept of Service Function Chaining (SFC). The corresponding networks need to support a wide range of services and applications with highly dynamic temporal profiles and heterogeneous demands. Hence, efficient management and operation of such networks requires a high degree of automation that is paired with fast and proactive decisions in order to cope with these phenomena. In particular, determining the optimal number of VNF instances that is required for accommodating current and upcoming demands is a crucial task that also affects subsequent management decisions. To enable fast and proactive decisions in this context, we propose a machine learning-based approach that uses recent monitoring data to predict whether to adapt the current number of VNF instances of a given type. Furthermore, we present a work flow for generating labeled training data that reflects temporal dynamics and heterogeneous demands of real world networks. In addition to demonstrating the feasibility of the approach in a case study, we provide guidelines regarding the choice of monitoring data that should be collected for reliable prediction as well as the amount of data that is required to train such a predictor.

In addition to providing network operators with benefits in terms of flexibility and cost efficiency, softwarization paradigms like SDN and NFV are key enablers for the concept of Service Function Chaining (SFC). The corresponding networks need to support a wide range of services and applications with highly heterogeneous requirements that change dynamically during the network's lifetime. Hence, efficient management and operation of such networks requires a high degree of automation that is paired with fast and proactive decisions in order to cope with these phenomena. In particular, determining the optimal number of VNF instances that is required for accommodating current and upcoming demands is a crucial task that also affects subsequent management decisions. To enable fast and proactive decisions in this context, we propose a machine learning-based approach that uses recent monitoring data to predict whether to adapt the current number of VNF instances of a given type. Furthermore, we present a methodology for generating labeled training data that reflects temporal dynamics and heterogeneous demands of real world networks. We demonstrate the feasibility of the approach using two different network topologies that represent WAN and mobile edge computing use cases, respectively. Additionally, we investigate how well the models generalize among networks and provide guidelines regarding the prediction horizon, i.e., how far ahead predictions can be performed in a reliable manner.

Network Functions Virtualization (NFV) is among the latest network revolutions, bringing flexibility and avoiding network ossification. At the same time, all-software NFV implementations on commodity hardware raise performance issues with respect to ASIC solutions. To address these issues, numerous software acceleration frameworks for packet processing have appeared in the last few years. Common among these frameworks is the use of batching techniques. In this context, packets are processed in groups as opposed to individually, which is required at high-speed to minimize the framework overhead, reduce interrupt pressure, and leverage instruction-level cache hits. Whereas several system implementations have been proposed and experimentally benchmarked, the scientific community has so far only to a limited extent attempted to model the system dynamics of modern NFV routers exploiting batching acceleration. In this paper, we fill this gap by proposing a simple generic model for such batching-based mechanisms, which allows a very detailed prediction of highly relevant performance indicators. These include the distribution of the processed batch size as well as queue size, which can be used to identify loss-less operational regimes or quantify the packet loss probability in high-load scenarios. We contrast the model prediction with experimental results gathered in a high-speed testbed including an NFV router, showing that the model not only correctly captures system performance under simple conditions, but also in more realistic scenarios in which traffic is processed by a mixture of functions.

The ongoing network softwarization trend holds the promise to revolutionize network infrastructures by making them more flexible, reconfigurable, portable, and more adaptive than ever. Still, the migration from hard-coded/hard-wired network functions toward their software-programmable counterparts comes along with the need for tailored optimizations and acceleration techniques so as to avoid or at least mitigate the throughput/latency performance degradation with respect to fixed function network elements. The contribution of this paper is twofold. First, we provide a comprehensive overview of the host-based network function virtualization (NFV) ecosystem, covering a broad range of techniques, from low-level hardware acceleration and bump-in-the-wire offloading approaches to high-level software acceleration solutions, including the virtualization technique itself. Second, we derive guidelines regarding the design, development, and operation of NFV-based deployments that meet the flexibility and scalability requirements of modern communication networks.

With software defined networking (SDN), operators benefit from a higher flexibility, cost efficiency, as well as programmability of their networks. Since modern networks are comprised of a multitude of heterogeneous devices and also include non-SDN legacy devices, network management systems (NMSs) are often used in order to monitor and configure the network. Although both, the SDN controller and the NMS, have a centralized view of the network, they operate at different time scales and deal with information at different levels of granularity. In this work, we investigate the impact on the network performance when an NMS regularly provides information to an SDN controller. To this end, we design, implement, and compare three interaction mechanisms based on the ONOS controller. These represent different trade-offs regarding the complexity of the resulting system and its performance. In addition to the default ONOS controller, we develop two extended versions. One performs hash-based load balancing on equal cost paths while the other utilizes external NMS information via ONOS's intent and annotation framework to optimize control plane decisions. In addition to evaluations that show a significant performance improvement when using the optimized controllers, we present a parameter study that highlights the performance impact of network characteristics like the flow interarrival time, the flow duration, and the number of active flows.

Modern enterprise applications are often designed as distributed architectures, e.g., thin client computing and thus degradations in network related Quality of Service (QoS) parameters may also negatively impact the user-perceived Quality of Experience (QoE) of the application. In this work, we create a model to predict the perceived application quality based on measurements of objective technical parameters. For this, we gathered a data set in a cooperating enterprise over a timespan of nearly three months. As the obtained data set is subject to bias that originates from seasonal effects as well as a limited and predefined set of technical parameters, we further evaluate how to identify segments of the data that lead to misclassification. Last, we quantify the trade-off between the gain in the QoE prediction accuracy and the amount of filtered data.

One of the benefits when network operators adopt the Software Defined Networking (SDN) paradigm is the ability to monitor the traffic in the network without an additional network management system. Usually, SDN controllers utilize OpenFlow statistics messages in order to regularly gather information about all flows in the network. However, using the same polling interval for all flows does not take into account the heterogeneity of real world traffic and thus results in an imbalance between monitoring accuracy and control plane overhead. In particular, frequent querying results in a high resource consumption at the controller. This work proposes a Selective Flow Monitoring (SFM) mechanism that allows administrators to classify flows according to their individual requirements in terms of monitoring frequency, e.g., less frequent polling of elephant flows and frequent polling of QoS sensitive VoIP connections. We compare the performance of the SFM mechanism with the default monitoring scheme in a testbed featuring the Open Network Operating System (ONOS) controller. In this context, the CPU utilization of the controller is used as performance indicator. After identifying relevant influence factors like the number of flows and switches in the network, we investigate the viability of the approaches in different scenarios. Finally, we provide guidelines regarding their choice.

Network Functions Virtualization (NFV) is a concept that aims at providing network operators with benefits in terms of cost, flexibility, and vendor independence by utilizing virtualization techniques to run network functions as software on commercial off-the-shelf (COTS) hardware. In contrast, prior solutions rely on specialized hardware for each function. Performance evaluation of such systems usually requires a dedicated testbed for each individual component. Rather than analyzing these proprietary black-box components, Virtualized Network Functions (VNFs) are pieces of software that run on COTS hardware and whose properties can be investigated in a generic testbed. However, depending on the underlying hardware, operating system, and implementation, VNFs might behave differently. Therefore, mechanisms for the performance evaluation of VNFs should be similar to benchmarking of software, where different implementations are compared by applying them to predefined test cases and scenarios. This work presents a first step towards a benchmarking framework for VNFs. Given two different implementations of a VNF that acts as LTE Serving Gateway (SGW), influence factors and key performance indicators are identified and a comparison between the two mechanisms is drawn.

Software Defined Networking (SDN) introduces the concept of logically-centralized controllers in charge of managing the forwarding behavior of network elements. The new possibilities enabled through the centralization of control logic come with a certain risk: The controller might become a performance bottleneck. Therefore, ensuring sufficient controller performance is one of the crucial tasks prior to a successful SDN deployment. Furthermore, fine-grained traffic engineering, e.g., to achieve higher link utilization, results in a higher frequency of requests that are sent to the controller, which leads to an increased controller load. It is therefore important to analyze the capabilities of SDN controllers prior to deployment. This paper investigates two software implementations, the OpenDaylight and Ryu controllers. The control message throughput of different controllers has been studied several times already; however, it is not yet known what influence the number and topology of connected switches have. This paper investigates this influence in detail for a fat-tree data center topology and a WAN topology as well as 261 topologies with varying characteristics from the Internet Topology Zoo.

Software Defined Networking (SDN) marks a paradigm shift towards an externalized and logically centralized network control plane. A particularly important task in SDN architectures is that of controller placement, i.e., the positioning of a limited number of resources within a network to meet various requirements. These requirements range from latency constraints to failure tolerance and load balancing. In most scenarios, at least some of these objectives are competing, thus no single best placement is available and decision makers need to find a balanced trade-off. This work presents POCO, a framework for Pareto-based Optimal COntroller placement that provides operators with Pareto optimal placements with respect to different performance metrics. In its default configuration, POCO performs an exhaustive evaluation of all possible placements. While this is practically feasible for small and medium sized networks, realistic time and resource constraints call for an alternative in the context of large scale networks or dynamic networks whose properties change over time. For these scenarios, the POCO toolset is extended by a heuristic approach that is less accurate, but yields faster computation times. An evaluation of this heuristic is performed on a collection of real world network topologies from the Internet Topology Zoo. Utilizing a measure for quantifying the error introduced by the heuristic approach allows an analysis of the resulting trade-off between time and accuracy. Additionally, the proposed methods can be extended to solve similar virtual functions placement problems which appear in the context of Network Functions Virtualization (NFV).