Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
925,972
result(s) for
"NETWORK SERVICES"
Sort by:
Machine Learning-Assisted Closed-Control Loops for Beyond 5G Multi-Domain Zero-Touch Networks
End-to-End (E2E) services in beyond 5G (B5G) networks are expected to be built upon resources and services distributed in multi-domain, multi-technology environments. In such scenarios, key challenges around multi-domain management and collaboration need to be tackled. ETSI Zero-touch network and Service Management (ZSM) architectural framework provides the structure and methods for effectively delivering E2E network services. ZSM pursues cross-domain automation with minimum human intervention through two main enablers: Closed Control Loop (CCL) and Artificial Intelligence (AI). In this work, we propose a multi-domain ZSM-based architecture aiming at B5G scenarios where several per-domain CCLs leverage Machine Learning (ML) methods to collaborate in E2E service management tasks. We instantiate the architecture in the use case scenario of multi-domain automated healing of Dynamic Adaptive Streaming over HTTP (DASH) video services. We present two ML-assisted techniques, first to estimate a Service Level Agreement (SLA) violation through a Edge-based Quality of Experience (QoE) Probe, and second to identify the root cause at the core transport network. Results from the experimental evaluation in an emulation environment using real mobile network traces point to the potential benefits of applying ML techniques for QoS-to-QoE estimation at Multi-Access Edge Computing facilities and correlation to faulty transport network links. Altogether, the work contributes towards a vision of ML-based sandbox environments in the spirit of E2E service and network digital twins towards the realization of automated, multi-domain CCLs for B5G.
Journal Article
Information systems for global financial markets : emerging developments and effects
\"This book offers focused research on the systems and technologies that provide intelligence and expertise to traders and investors and facilitate the agile ordering processes, networking, and regulation of global financial electronic markets\"--Provided by publisher.
Book
Deep Learning-Based Multi-Domain Framework for End-to-End Services in 5G Networks
Over the past few years, network slicing has emerged as a pivotal component within the realm of 5G technology. It plays a critical role in effectively delineating network services based on a myriad of performance and operational requirements, all of which draw from a shared pool of common resources. The core objective of 5G technology is to facilitate simultaneous network slicing, thereby enabling the creation of multiple distinct end-to-end networks. This multiplicity of networks serves the paramount purpose of ensuring that the traffic within one network slice does not impede or adversely affect the traffic within another. Therefore, this paper proposes a Deep learning-based Multi Domain framework for end-to-end network slicing in traffic-aware prediction. The proposed method uses Deep Reinforcement Learning (DRL) for in-depth resource allocation analysis and improves the Quality of Service (QOS). The DRL-based Multi-domain framework provides traffic-aware prediction and enhances flexibility. The study results demonstrate that the suggested approach outperforms conventional, heuristic, and randomized methods and enhances resource use while maintaining QoS.
Journal Article
A service network perspective to evaluate service matching in early design
Purpose
Service matching is defined in this paper as the process of combining a new service with one or more existing services. A recurring problem for service designer is to match new services with existing ones. This process may be seen as the fundamental action for the development of a service network. The purpose of this paper is to evaluate the consequences that may follow from service matching.
Design/methodology/approach
Through an analogy with living organisms in natural ecosystems, the service relationship deployment (SRD) allows the investigation of the possible relationships between matched services.
Findings
This paper presents a new method, named SRD, developed to support the process of service matching in the early design phases of a new service. The description of the method is supported by some practical examples.
Originality/value
The focus of the scientific community on the problem of matching new services with existing ones, is very limited. This paper proposes a new methodology to address this issue.
Journal Article
Adaptive Machine Learning Based Distributed Denial-of-Services Attacks Detection and Mitigation System for SDN-Enabled IoT
The development of smart network infrastructure of the Internet of Things (IoT) faces the immense threat of sophisticated Distributed Denial-of-Services (DDoS) security attacks. The existing network security solutions of enterprise networks are significantly expensive and unscalable for IoT. The integration of recently developed Software Defined Networking (SDN) reduces a significant amount of computational overhead for IoT network devices and enables additional security measurements. At the prelude stage of SDN-enabled IoT network infrastructure, the sampling based security approach currently results in low accuracy and low DDoS attack detection. In this paper, we propose an Adaptive Machine Learning based SDN-enabled Distributed Denial-of-Services attacks Detection and Mitigation (AMLSDM) framework. The proposed AMLSDM framework develops an SDN-enabled security mechanism for IoT devices with the support of an adaptive machine learning classification model to achieve the successful detection and mitigation of DDoS attacks. The proposed framework utilizes machine learning algorithms in an adaptive multilayered feed-forwarding scheme to successfully detect the DDoS attacks by examining the static features of the inspected network traffic. In the proposed adaptive multilayered feed-forwarding framework, the first layer utilizes Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), k-Nearest Neighbor (kNN), and Logistic Regression (LR) classifiers to build a model for detecting DDoS attacks from the training and testing environment-specific datasets. The output of the first layer passes to an Ensemble Voting (EV) algorithm, which accumulates the performance of the first layer classifiers. In the third layer, the adaptive frameworks measures the real-time live network traffic to detect the DDoS attacks in the network traffic. The proposed framework utilizes a remote SDN controller to mitigate the detected DDoS attacks over Open Flow (OF) switches and reconfigures the network resources for legitimate network hosts. The experimental results show the better performance of the proposed framework as compared to existing state-of-the art solutions in terms of higher accuracy of DDoS detection and low false alarm rate.
Journal Article
Principles of Broadband Switching and Networking
An authoritative introduction to the roles of switching and transmission in broadband integrated services networks Principles of Broadband Switching and Networking explains the design and analysis of switch architectures suitable for broadband integrated services networks, emphasizing packet-switched interconnection networks with distributed routing algorithms. The text examines the mathematical properties of these networks, rather than specific implementation technologies. Although the pedagogical explanations in this book are in the context of switches, many of the fundamental principles are relevant to other communication networks with regular topologies. After explaining the concept of the modern broadband integrated services network and why it is necessary in today’s society, the book moves on to basic switch design principles, discussing two types of circuit switch design—space domain and time domain—and packet switch design. Throughput improvements are illustrated by some switch design variations such as Speedup principle, Channel-Grouping principle, Knockout principle, and Dilation principle. Moving seamlessly into advanced switch design principles, the book covers switch scalability, switch design for multicasting, and path switching. Then the focus moves to broadband communications networks that make use of such switches. Readers receive a detailed introduction on how to allocate network resources and control traffic to satisfy the quality of service requirements of network users and to maximize network usage. As an epilogue, the text shows how transmission noise and packet contention have similar characteristics and can be tamed by comparable means to achieve reliable communication. Principles of Broadband Switching and Networking is written for senior undergraduate and first-year postgraduate students with a solid background in probability theory.
eBook
Community detection in social recommender systems: a survey
Information extracted from social network services promise to improve the accuracy of recommender systems in various domains. Against this background, community detection techniques help us understand more of users’ collective behavior by clustering similar users w.r.t. their interests, preferences and activities. The purpose of this paper is to bring the novice or practitioner quickly up to date with the main outcomes and research directions in the field of social recommendation based on community detection. The research synthesis consists of a narrative review which identifies what has been written on the topic of community-based recommender system. The comprehensive search of relevant literature aims at synthesizing prior study findings by identifying approaches that follow similar paradigms and techniques. The paper is of value to those involved with recommender systems and social media.
Journal Article
Examining Gifting Through Social Network Services: A Social Exchange Theory Perspective
The increasing popularity of social network services (SNS) presents an opportunity to offer gifting services through SNS. For givers, gifting can be an important means to enhance social relationships. On the other hand, for SNS providers, members’ gifting can serve as a major source of revenue. As SNS providers continue to face challenges in generating revenues, understanding how to stimulate gifting through SNS can allow them to profit from members’ relationships. However, there is little understanding of what drives members’ gifting through SNS, with limited prior research on online gifting. Thus motivated, we develop a research model of the antecedents of SNS gifting that builds on social exchange theory and prior gifting literature, and incorporates the unique aspects of such gifting (that we refer to as microgifting, with low-price digital voucher gifts). The theoretical model was validated through a field study, in which both subjective and objective data were collected from an SNS that has been successful in offering such gifting services. Our findings highlight the effects of perceived worth, SNS gifting experience, and the number of SNS friends on the frequency of SNS gifting. The results also show that expected benefits (i.e., reciprocity, pleasure, relationship support, convenience, and immediacy of gift sending) and costs (i.e., impersonality) indirectly impact SNS gifting frequency through the assessment of perceived worth. The study contributes to research by adding to our understanding of this new approach of gifting through SNS, i.e., microgifting. It also lends insights on how SNS providers can offer such services to tap this source of revenue.
Journal Article
The Continuous-Time Service Network Design Problem
Consolidation carriers transport shipments that are small relative to trailer capacity. To be cost effective, the carrier must consolidate shipments, which requires coordinating their paths in both space and time; i.e., the carrier must solve a
service network design
problem. Most service network design models rely on discretization of time—i.e., instead of determining the exact time at which a dispatch should occur, the model determines a time interval during which a dispatch should occur. While the use of time discretization is widespread in service network design models, a fundamental question related to its use has never been answered:
Is it possible to produce an optimal continuous-time solution without explicitly modeling each point in time
? We answer this question in the affirmative. We develop an iterative refinement algorithm using partially time-expanded networks that solves continuous-time service network design problems. An extensive computational study demonstrates that the algorithm not only is of theoretical interest but also performs well in practice.
Journal Article