اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدThe Need for Advanced Intelligence in NFV Management and Orchestration
408
0
0.0
(
0
)
نشر من قبل
Dimitrios Michael Manias
تاريخ النشر
2020
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
With the constant demand for connectivity at an all-time high, Network Service Providers (NSPs) are required to optimize their networks to cope with rising capital and operational expenditures required to meet the growing connectivity demand. A solution to this challenge was presented through Network Function Virtualization (NFV). As network complexity increases and futuristic networks take shape, NSPs are required to incorporate an increasing amount of operational efficiency into their NFV-enabled networks. One such technique is Machine Learning (ML), which has been applied to various entities in NFV-enabled networks, most notably in the NFV Orchestrator. While traditional ML provides tremendous operational efficiencies, including real-time and high-volume data processing, challenges such as privacy, security, scalability, transferability, and concept drift hinder its widespread implementation. Through the adoption of Advanced Intelligence techniques such as Reinforcement Learning and Federated Learning, NSPs can leverage the benefits of traditional ML while simultaneously addressing the major challenges traditionally associated with it. This work presents the benefits of adopting these advanced techniques, provides a list of potential use cases and research topics, and proposes a bottom-up micro-functionality approach to applying these methods of Advanced Intelligence to NFV Management and Orchestration.
قيم البحث
اقرأ أيضاً
Autonomous management and orchestration (MANO) of virtualized resources and services, especially in large-scale Network Function Virtualization (NFV) environments, is a big challenge owing to the stringent delay and performance requirements expected
of a variety of network services. The Quality-of-Decisions (QoD) of a Management and Orchestration (MANO) system depends on the quality and timeliness of the information received from the underlying monitoring system. The data generated by monitoring systems is a significant contributor to the network and processing load of MANO systems, impacting thus their performance. This raises a unique challenge: how to jointly optimize the QoD of MANO systems while at the same minimizing their monitoring loads at runtime? This is the main focus of this paper. In this context, we propose a novel automated NFV orchestration solution, namely z-TORCH (zero Touch Orchestration) that jointly optimizes the orchestration and monitoring processes by exploiting machine-learning-based techniques. The objective is to enhance the QoD of MANO systems achieving a near-optimal placement of Virtualized Network Functions (VNFs) at minimum monitoring costs.
Cyber-Physical Systems (CPSs) are increasingly important in critical areas of our society such as intelligent power grids, next generation mobile devices, and smart buildings. CPS operation has characteristics including considerable heterogeneity, va
riable dynamics, and high complexity. These systems have also scarce resources in order to satisfy their entire load demand, which can be divided into data processing and service execution. These new characteristics of CPSs need to be managed with novel strategies to ensure their resilient operation. Towards this goal, we propose an SDN-based solution enhanced by distributed Network Function Virtualization (NFV) modules located at the top-most level of our solution architecture. These NFV agents will take orchestrated management decisions among themselves to ensure a resilient CPS configuration against threats, and an optimum operation of the CPS. For this, we study and compare two distinct incentive mechanisms to enforce cooperation among NFVs. Thus, we aim to offer novel perspectives into the management of resilient CPSs, embedding IoT devices, modeled by Game Theory (GT), using the latest software and virtualization platforms.
Next generation wireless networks are expected to support diverse vertical industries and offer countless emerging use cases. To satisfy stringent requirements of diversified services, network slicing is developed, which enables service-oriented reso
urce allocation by tailoring the infrastructure network into multiple logical networks. However, there are still some challenges in cross-domain multi-dimensional resource management for end-to-end (E2E) slices under the dynamic and uncertain environment. Trading off the revenue and cost of resource allocation while guaranteeing service quality is significant to tenants. Therefore, this article introduces a hierarchical resource management framework, utilizing deep reinforcement learning in admission control of resource requests from different tenants and resource adjustment within admitted slices for each tenant. Particularly, we first discuss the challenges in customized resource management of 6G. Second, the motivation and background are presented to explain why artificial intelligence (AI) is applied in resource customization of multi-tenant slicing. Third, E2E resource management is decomposed into two problems, multi-dimensional resource allocation decision based on slice-level feedback and real-time slice adaption aimed at avoiding service quality degradation. Simulation results demonstrate the effectiveness of AI-based customized slicing. Finally, several significant challenges that need to be addressed in practical implementation are investigated.
In this paper, we propose fairness-oriented packet scheduling (PS) schemes with power-efficient control mechanism for future packet radio systems. In general, the radio resource management functionality plays an important role in new OFDMA based netw
orks. The control of the network resource division among the users is performed by packet scheduling functionality based on maximizing cell coverage and capacity satisfying, and certain quality of service requirements. Moreover, multiantenna transmit-receive schemes provide additional flexibility to packet scheduler functionality. In order to mitigate inter-cell and co-channel interference problems in OFDMA cellular networks soft frequency reuse with different power masks patterns is used. Stemming from the earlier enhanced proportional fair scheduler studies for single-input multiple-output (SIMO) and multiple-input multipleoutput (MIMO) systems, we extend the development of efficient packet scheduling algorithms by adding transmit power considerations in the overall priority metrics calculations and scheduling decisions. Furthermore, we evaluate the proposed scheduling schemes by simulating practical orthogonal frequency division multiple access (OFDMA) based packet radio system in terms of throughput, coverage and fairness distribution among users. As a concrete example, under reduced overall transmit power constraint and unequal power distribution for different sub-bands, we demonstrate that by using the proposed power-aware multi-user scheduling schemes, significant coverage and fairness improvements in the order of 70% and 20%, respectively, can be obtained, at the expense of average throughput loss of only 15%.
This paper proposes a novel QoE-aware SDN enabled NFV architecture for controlling and managing Future Multimedia Applications on 5G systems. The aim is to improve the QoE of the delivered multimedia services through the fulfilment of personalized Qo
E application requirements. This novel approach provides some new features, functionalities, concepts and opportunities for overcoming the key QoE provisioning limitations in current 4G systems such as increased network management complexity and inability to adapt dynamically to changing application, network transmission or traffic or end-users demand.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
