Network Management Solutions Research Articles

Channel Allocation in mobile multimedia network using artificial neural networks

Capital asset control systems may enhance network performance, reduce congestion, and optimise resource allocation with the use of artificial intelligence. Using machine learning models like decision trees and neural networks allows for more informed and adaptive admission control options. These models can precisely predict how the network's quality of service (QoS) will be affected by accepting a new call. Exploring AI-enhanced CAC schemes requires a thorough analysis of various machine learning methods and their potential applications to real-time network management. To ensure that AI-based CAC implementations are actually possible in resource-limited mobile situations, it is crucial to consider their computational complexity and resource requirements. Accuracy and computational efficiency are two competing goals, and this study examines both. Finding a happy medium that can meet the stringent requirements of mobile multimedia networks is the driving force behind this research. Also covered in this study is the possibility of mixing AI-powered CAC with cutting-edge tech like 5G networks and cloud computing. Collectively, these technology and artificial intelligence (AI) have to open up new opportunities for situationally-conscious, dynamic admission manipulate. As a result, mobile multimedia networks might be a lot more efficient and adaptable. An exploration of CAC schemes is provided in this article, which draws attention to the potential game-changing impact of AI-based methods for mobile multimedia network optimisation. The increasing demand for multimedia services is creating new challenges, yet these challenges may be amenable to artificial intelligence integration into CAC systems. More adaptive and intelligent network management solutions would be possible as a result.

Accelerator: an intent-based intelligent resource-slicing scheme for SFC-based 6G application execution over SDN- and NFV-empowered zero-touch network

Zero-touch networks (ZTNs) can provide autonomous network solutions by integrating software-based solutions for various emerging 5G and 6G applications. The current literature does not provide any suitable end-to-end network management and resource-slicing solutions for service function chaining (SFC) and user intent–based (time and cost preference) 6G/non-6G application execution over ZTNs enabled by mobile edge computing, network function virtualization, and software-defined networking. To tackle these challenges, this work initiates an end-to-end network management and user intent–aware intelligent network resource–slicing scheme for SFC-based 6G/non-6G application execution over ZTNs, taking into account various virtual and physical resources, task workloads, service requirements, and task numbers. The results depicted that at least 25.27% average task implementation delay gain, 6.15% energy gain, and 11.52% service monetary gain are realized in the proposed scheme over the compared schemes.

Gradient-Based Optimization for Intent Conflict Resolution

The evolving landscape of network systems necessitates automated tools for streamlined management and configuration. Intent-driven networking (IDN) has emerged as a promising solution for autonomous network management by prioritizing declaratively defined desired outcomes over traditional manual configurations without specifying the implementation details. This paradigm shift towards flexibility, agility, and simplification in network management is particularly crucial in addressing inefficiencies and high costs linked to manual management, notably in the radio access part. This paper explores the concurrent operation of multiple intents, acknowledging the potential for conflicts, and proposes an innovative reformulation of these conflicts to enhance network administration effectiveness. Following the initial detection of conflicts among intents using a gradient-based approach, our work employs the Multiple Gradient Descent Algorithm (MGDA) to minimize all loss functions assigned to each intent simultaneously. In response to the challenge posed by the absence of a closed-form representation for each key performance indicator in a dynamic environment for computing gradient descent, the Stochastic Perturbation Stochastic Approximation (SPSA) is integrated into the MGDA algorithm. The proposed method undergoes initial testing using a commonly employed toy example in the literature before being simulated for conflict scenarios within a mobile network using the ns3 network simulator.

Impact of EV charging on electrical distribution network and mitigating solutions – A review

AbstractRapidly increasing uptake of Electric Vehicles (EVs) is expected to have a significant impact on electrical power distribution networks. Considerable work has been carried out to understand this impact and quantify the distribution networks hosting capacity, with and without network management solutions. However, the current body of knowledge does not have a comprehensive review of the research done to‐date on this topic which is vital to understand the scope of the existing studies, the data used in analysing the impact, and, most importantly, the findings. A comprehensive yet focused review of impact of EV charging on distribution networks is presented by delving into the main factors restricting EV hosting capacity and the strategies used to maximise EV hosting capacity by managing the aforementioned impacts. The authors comprehensively summarise the approaches used to quantify the impact, network and data types, and the proposed solutions to increase network hosting capacity. Moreover, the shortcomings in the existing work are identified and recommendations for future research are provided to help stakeholders understand the current state‐of‐the‐art, make informed decisions, and to be considered by future researchers.

Infrastructure-Wide and Intent-Based Networking Dataset for 5G-and-beyond AI-Driven Autonomous Networks

In the era of Autonomous Networks (ANs), artificial intelligence (AI) plays a crucial role for their development in cellular networks, especially in 5G-and-beyond networks. The availability of high-quality networking datasets is one of the essential aspects for creating data-driven algorithms in network management and optimisation tasks. These datasets serve as the foundation for empowering AI algorithms to make informed decisions and optimise network resources efficiently. In this research work, we propose the IW-IB-5GNET networking dataset: an infrastructure-wide and intent-based dataset that is intended to be of use in research and development of network management and optimisation solutions in 5G-and-beyond networks. It is infrastructure wide due to the fact that the dataset includes information from all layers of the 5G network. It is also intent based as it is initiated based on predefined user intents. The proposed dataset has been generated in an emulated 5G network, with a wide deployment of network sensors for its creation. The IW-IB-5GNET dataset is promising to facilitate the development of autonomous and intelligent network management solutions that enhance network performance and optimisation.

A Network Management Solution for Pre-Alarm Detection in EPU Telecommunications Network

A Network Management Solution for Pre-Alarm Detection in EPU Telecommunications Network

Let model keep evolving: Incremental learning for encrypted traffic classification

Encrypted Traffic Classification (ETC) is valuable for many network management and security solutions as it provides insights into applications active on the network. However, the network environment constantly evolves, and new applications emerge in an endless stream daily, which gradually makes well-trained ETC models ineffective. The conventional approach to adapting new applications is to re-train the models on a re-formed dataset with both pre-existing and new application samples. The major limitation is that requiring redundant computing resources and sufficient storage spaces. In this work, we propose an Incremental Learning (IL) framework based on multi-view sequences fusion, MISS, to keep ETC models evolving with new applications. The key novelty of MISS is three-fold: extract cross-view information from multi-view sequences to capture sufficient knowledge; propose an exemplar selection algorithm from communication patterns to reduce redundant consumption; design a pair of branches from the learnability of parameters to mitigate accuracy loss during evolution. MISS outperforms the existing IL methods of ETC, and the state-of-the-art ETC models using the classic IL framework, on the real-world network traffic datasets, which achieves satisfactory improvements of 11.37%↑ and 1.58%↑. Furthermore, we comprehensively perform incremental experiments to evaluate the evolution ability of MISS, which is able to select representative exemplars of old applications, counteract the adverse effects of homogeneous applications, and keep evolving with unknown applications.

PBCLR: Prediction-based control-plane load reduction in a software-defined IoT network

The exponential growth of devices and applications in Internet of Things (IoT) networks has caused control-plane traffic to escalate. Experts have suggested Software-Defined Networking (SDN) as a solution for complicated IoT network management. Nevertheless, SDN encounters obstacles in managing the substantial control-plane traffic many IoT devices produce. Prior findings have identified the dynamic switch migration technique as a viable solution for control plane load oscillation. However, their tendency to migrate switches during instances of controller overload restricts the efficiency of traditional migration strategies. As a result, these approaches lead to inefficiencies in the switch migration process, resulting in elevated latency. The present study introduces a prediction-based novel approach for mitigating the control-plane workload by leveraging the dynamic switch migration technique. The proposed method proactively and predictively migrates the switches anticipated to generate excessive control-plane traffic to an alternative controller. We use the learning technique along with time-series analysis to predict the future workload based on the historical control-plane traffic data. The proposed methodology is evaluated through simulation and the results demonstrate that the proposed method outperforms conventional techniques in enhancing load balancing efficacy on a distributed control plane and decreasing migration cost and controller response time by 30.6% on average.

Accelerating network softwarization in the cognitive age

This special issue contains extended versions of three best papers from the IEEE International Conference on Network Softwarization (NetSoft 2021, https://netsoft2021.ieee-netsoft.org/). The theme of NetSoft 2021 was “Accelerating Network Softwarization in the Cognitive Age.” The General Co-Chairs were Kohei Shiomoto, Tokyo City University, Japan and Young-Tak Kim, Yeungnam University, Korea. The TPC-Co-Chairs were Christian Esteve Rothenberg, University of Campinas, Brazil; Barbara Martini, CNIT, Italy; and Eiji Oki, Kyoto University, Japan. The first paper, titled “RNN-EdgeQL: An Auto-Scaling and Placement Approach for SFC,” proposes an innovative prediction-based scaling and placement algorithm for service function chains (SFCs) that improves service level agreements (SLAs) and reduces operational costs. The authors use a variant of recurrent neural networks (RNNs) called gated recurrent unit (GRU) for resource demand prediction and an algorithm that applies Q-Learning on Edge computing environment (EdgeQL) to place scaled-out virtual network functions (VNFs) in appropriate locations. The proposed algorithm is tested on realistic temporal dynamic load models and achieves the lowest overall latency, lowest SLA violations, and lowest VNFs requirement compared with existing algorithms. The second paper, titled “SRv6-based Time-Sensitive Networks (TSN) with Low Overhead Rerouting,” proposes a software-defined network (SDN)-based approach for low-overhead TSN network updates using segment routing over IPv6 (SRv6) for path control. The authors introduce the concept of TSN subgraphs to quickly reschedule flows traversing problematic areas and propose a TSN-aware routing heuristic to minimize convergence time. The proposed approach yields faster recovery and significantly reduces the number of required reconfigurations upon failures, at the expense of a small SRv6 encoding/decoding overhead. The third paper, titled “Analysis of Network Function Sharing in Content Delivery Network-as-a-Service Slicing Scenarios,” investigates the potential efficiencies that can be achieved when sharing a virtual cache function among Internet service providers (ISPs) that are sharing a common physical infrastructure. The authors simulate the sharing of virtualized cache functions and analyze the implications of limiting the storage capacity of the caches at the edge. The paper provides insights into the potential cost savings that can be achieved by sharing network infrastructures and virtualized cache functions among ISPs. We believe that these three papers make significant contributions and offer valuable insights into the challenges and opportunities of managing softwarized networks. We hope that this special issue will inspire further research in this area and lead to the development of more efficient and effective network management solutions. We would like to thank the authors for their excellent contributions and the reviewers for their insightful comments and suggestions. We would also like to acknowledge the editorial team for their hard work in putting together this special issue. We hope that readers find these papers informative and thought-provoking, and we look forward to further advancements in the field of network management. Sincerely,

LwHBench: A low-level hardware component benchmark and dataset for Single Board Computers

In today’s computing environment, where Artificial Intelligence (AI) and data processing are moving toward the Internet of Things (IoT) and Edge computing paradigms, benchmarking resource-constrained devices is a critical task to evaluate their suitability and performance. Between the employed devices, Single-Board Computers arise as multi-purpose and affordable systems. The literature has explored Single-Board Computers performance when running high-level benchmarks specialized in particular application scenarios, such as AI or medical applications. However, lower-level benchmarking applications and datasets are needed to enable new Edge-based AI solutions for network, system and service management based on device and component performance, such as individual device identification. Thus, this paper presents LwHBench, a low-level hardware benchmarking application for Single-Board Computers that measures the performance of CPU, GPU, Memory and Storage taking into account the component constraints in these types of devices. LwHBench has been implemented for Raspberry Pi devices and run for 100 days on a set of 45 devices to generate an extensive dataset that allows the usage of AI techniques in scenarios where performance data can help in the device management process. Besides, to demonstrate the inter-scenario capability of the dataset, a series of AI-enabled use cases about device identification and context impact on performance are presented as exploration of the published data. Finally, the benchmark application has been adapted and applied to an agriculture-focused scenario where three RockPro64 devices are present.

5G NPN Performance Evaluation for I4.0 Environments

This paper aims to develop an open Asset Administration Shell (AAS) solution for 5G Non-Public Network (NPN) management, focusing on manufacturing digitization and complete Information and Operational Technology (IT/OT) convergence. The proposed 5G NPN framework is evaluated in a factory-like simulation scenario considering network slicing for I4.0, and demonstrates the outlook of 5G communication in the industrial domain, achieving an upload data rate of up to 86 Mbps, and a Round-Trip Time (RTT) for end-to-end communication as low as 11 ms. The proposed framework integrates OPC UA as an enabler and middleware across different protocols, equipment, and the manufacturing shop floor, with the target of aggregating different industrial data and creating insights on production optimization in a unified manner. The framework combines 5G NPNs with I4.0 environments, in the form of a complete FNMS and its corresponding AAS. In parallel, a set of I4.0 enablers are investigated within the framework of the project, covering a Time-Sensitive Network (TSN) on the shop floor. The main objective of this paper is to propose a method for the unified integration of various enablers in the I4.0 domain and their combination with 5G technology, and to evaluate the feasibility of hosting industrial applications and services over 5G channels through the implementation of different slicing schemas. The paper presents detailed experimental data regarding 5G downlink/uplink data rates and RTT delays.

Hierarchical pattern matching for anomaly detection in time series

As companies rely on an ever increasing number of connected devices for their day to day operations, a need arises for automated anomaly detectors to constantly observe crucial device metrics in real time to prevent downtime and data loss. As production environments tend to monitor a huge amount of these metrics, it prevents current state-of-the-art techniques to be deployed as the required computational resources is too high. This paper proposes a lightweight anomaly detection method that can be deployed in these environments without a reduction in accuracy. The approach works fully online, and does not require an extensive history set to be kept in memory. The method is benchmarked on the publicly available Numenta dataset, as well as a network monitoring dataset from different environments provided by a network management solution vendor. These benchmarks show the proposed technique to be very competitive with the current state-of-the-art and exceeding it in production applicability.

Flexible management and decarbonisation of rural networks using multi‐functional battery control

To support the electrification of heat and transport, distribution network operators are looking to adopt network management solutions which can exploit local flexibility to advance their decarbonisation efforts in line with the evolving management requirements of the network. This paper develops a multi-functional battery control strategy that integrates constraint management with carbon-intensity linked control dispatch – carbon control – to support decarbonisation of rural distribution networks in Scotland by displacing last resort backup diesel generation and facilitating low carbon network balancing in the drive towards self-sustaining local distribution networks. The interplay between the different functionalities is considered to understand the challenges, and opportunities, of adopting multi-functional battery storage as an alternative management solution based on an operational distribution network in Scotland. Case studies are presented which consider network constraints at different times of day and year for various generation, demand and carbon intensity profiles to support this investigation. The findings of this work provide for the near-term, realisation of self-sustaining carbon-neutral local distribution networks that are in keeping with both the operational objectives of incumbent network operators, smart local energy systems and also low carbon policy objectives.

Practical Intrusion Detection of Emerging Threats

The Internet of Things (IoT), in combination with advancements in Big Data, communications and networked systems, offers a positive impact across a range of sectors including health, energy, manufacturing and transport. By virtue of current business models adopted by manufacturers and ICT operators, IoT devices are deployed over various networked infrastructures with minimal security, opening up a range of new attack vectors. Conventional rule-based intrusion detection mechanisms used by network management solutions rely on pre-defined attack signatures and hence are unable to identify new attacks. In parallel, anomaly detection solutions tend to suffer from high false positive rates due to the limited statistical validation of ground truth data, which is used for profiling normal network behaviour. In this work we go beyond current solutions and leverage the coupling of anomaly detection and Cyber Threat Intelligence (CTI) with parallel processing for the profiling and detection of emerging cyber attacks. We demonstrate the design, implementation, and evaluation of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Citrus</i> : a novel intrusion detection framework which is adept at tackling emerging threats through the collection and labelling of live attack data by utilising diverse Internet vantage points in order to detect and classify malicious behaviour using graph-based metrics as well as a range of machine learning (ML) algorithms. Citrus considers the importance of ground truth data validation and its flexible software architecture enables both the real-time and offline profiling, detection and classification of emerging cyber-attacks under optimal computational costs. Thus, establishing it as a viable and practical solution for next generation network defence and resilience strategies.

Series Editorial: Network Softwarization and Management

The broad scope of the IEEE Communications Magazine Series on Network Softwarization and Management covers two aspects of communication networks that have become highly relevant nowadays. On one hand, network softwarization advocates for architectures where software and programmability aspects in the implementation of network functions, protocols, and services are decoupled from the underlying infrastructure, fostering unprecedented levels of flexibility, abstraction, automation, and intelligence. On the other hand, network management aims at integrating fault, configuration, accounting, performance, and security (FCAPS) capabilities in the network, and supporting advanced autonomic and self-management features, often taking advantage of the potential offered by network softwarization. The intent of this Series is to provide a timely source of in-depth, cutting-edge articles on state-of-the-art technologies and solutions for network softwarization and management.

Zero Touch Management: A Survey of Network Automation Solutions for 5G and 6G Networks

Mobile networks are facing an unprecedented demand for high-speed connectivity originating from novel mobile applications and services and, in general, from the adoption curve of mobile devices. However, coping with the service requirements imposed by current and future applications and services is very difficult since mobile networks are becoming progressively more heterogeneous and more complex. In this context, a promising approach is the adoption of novel network automation solutions and, in particular, of zero-touch management techniques. In this work, we refer to zero-touch management as a fully autonomous network management solution with human oversight. This survey sits at the crossroad between zero-touch management and mobile and wireless network research, effectively bridging a gap in terms of literature review between the two domains. In this paper, we first provide a taxonomy of network management solutions. We then discuss the relevant state-of-the-art on autonomous mobile networks. The concept of zero-touch management and the associated standardization efforts are then introduced. The survey continues with a review of the most important technological enablers for zero-touch management. The network automation solutions from the RAN to the core network, including end-toend aspects such as security, are then surveyed. Finally, we close this article with the current challenges and research directions.

Green Multistage Upgrade of Switches and Controllers for Bundled-Links SDNs

The switches in legacy networks perform both control and data forwarding operations. In contrast, in a software defined network (SDN), a controller is responsible for network control and each SDN-switch (<i>s</i>-switch) only forwards data packets. Advantageously, controllers can be upgraded easily to run state-of-the-art network configuration and management solutions. In this context, this paper addresses the novel problem of upgrading a legacy network into an SDN over multiple stages that span months or years. More specifically, it aims to minimize energy consumption by optimizing switch upgrades, controller placement, and traffic routing subject to an operator&#x2019;s budget, traffic delay tolerance, and controller capacity. We formulate the problem as a mixed integer program (MIP), and develop a heuristic solution that ensures a single path is used between switches and up to two link-disjoint paths are used between an s-switch and its controller. Our simulation results show that increasing an operator&#x2019;s budget and the number of upgrade stages reduce the energy consumption of tested networks by 68.42%. Further, our heuristic solution yields energy saving that is within 5% away from the optimal value. In addition, deploying controllers at strategic locations saves more energy than placing them at arbitrary locations. Lastly, our heuristic solution guarantees the delay requirement of traffic demands and runs up to 307 times faster than a prior solution.

Inter-PLMN Mobility Management Challenges for Supporting Cross-Border Connected and Automated Mobility (CAM) Over 5G

As the first 5G networks are being deployed across the world, new services enabled by the superior performance of 5G in terms of throughput, latency and reliability are emerging. Connected and Automated Mobility (CAM) services are perhaps among the most demanding applications that 5G networks will have to support and their deployment, performance and potential for improvement has been well investigated over the past few years. However, CAM operation in multi-operator environments and the inevitable inter-PLMN handover caused by the inherent mobility of CAM services have not been studied in length. Moreover, the multiple domains, multi-vendor components and inherent high mobility of the cross-border vehicular environment, introduce multiple challenges in terms of network management and dynamic slicing, making Zero-touch network and Service Management (ZSM) solutions an attractive alternative for these environments. The work presented in this study attempts to analyse the requirements for cross-border CAM operation for the five main CAM use cases selected by 3GPP, based on input from key European stakeholders (Network Operators, vendors, Automotive Manufacturers etc.). A detailed analysis and categorization into four categories of the main challenges for cross-border CAM service provisioning is performed, namely Telecommunication, Application, Security/Privacy and Regulatory issues, while potential solutions based on existing and upcoming technological enablers are discussed for each of them. The role of standardization and relevant regulatory and administrative bodies is analysed, leading to insights regarding the most promising future research directions in the field of cross-border CAM services.

Implementation Scheme SLA and Network Availability Mechanism for Customer Service Provider

Increasingly complex network heterogeneity and network monitoring tasks become the management concentration of a large distributed production infrastructure with various business services requiring a centralized control monitoring system, with increasing network size, heterogeneity and complexity. The network monitoring and management solutions available are not only expensive but also difficult to use, configure and maintain. Manually routing pins to the wrong device on a large complex network is very complicated and time-consuming for Service Provider (SP). Thus, it is necessary to have an automatic system that immediately reports to the network Service Provider (SP) monitoring system regarding the type of error or alert, Network Availability and Service Level Agreement (SLA). This research presents the modeling design and implementation of Network Availability and SLA network systems for Service Provider (SP) organizations, by being based on open-source programming tools (Zabbix System) and intelligently integrating to monitor network devices, especially to get Network Availability and SLA parameters and values on a customer or customer. Monitoring Customers devices in the network in the form of a module alert parameter that will be applied so that it is seen and can be said to be a universal Plug &amp; Play technology concept (UPnP). Monitoring system developed will provide value and quality of service (qos) output parameters in the form of measuring and taking test value parameters Network Availability and SLA modeling, which will produce an accurate Service Level Agreement (SLA) value parameter test, and become a reference for an agreement between a service provider and a customer. As a guarantee or link availability for the services provided by Service Provide (SP) to customers. With the SLA value fulfilled at 99.9% with a 99.5% agreement, Network availability is met with a percentage of 98.89% and Down time with a percentage of only 1% of the agreement 2%, and the latency value of the terrestrial transmission media obtained is 2 ms, from the 8 ms agreement and the obtained VSAT transmission media is 500-600 ms from the agreement latency value is 700 ms.

Online reconfiguration scheme of self-sufficient distribution network based on a reinforcement learning approach

With increasing number of distributed renewable energy sources integrated in power distribution networks, network security issues such as line overloading or bus voltage violations are becoming increasingly common. Traditional capital-intensive system reinforcements could lead to overinvestment. Moreover, active network management solutions, which have emerged as important alternatives, may become a financial burden for distribution system operators or reduce profits for owners of distributed renewable energy sources, or both. To address these limitations, this paper proposes an online network reconfiguration scheme based on a deep reinforcement learning approach. In this scheme, the distribution network operator modifies the network topology to change the power flow when the reliability of network is threatened. Because the variability of distributed renewable energy is large in self-sufficient distribution networks, the reconfiguration process needs to be performed online within short time intervals, which involves the use of conventional algorithms. To solve this problem efficiently, a deep q-learning model is utilized to determine the optimal network topology. Performances of proposed and other algorithms were compared in modified CIGRE 14-bus and IEEE 123-bus test network, as well as varying penalties for frequent switching operation in consideration of physical characteristic of the network. Simulation results demonstrated that the proposed algorithm showed almost identical performances with brute-force search algorithm in both test networks, satisfying network constraints over almost all timespans. Further, the proposed method required very small computation times - under a second per each state and its scalability was verified by comparing the computation time between two test networks.