scholarly journals Deep Reinforcement Learning for the Management of Software-Defined Networks and Network Function Virtualization in an Edge-IoT Architecture

2020 ◽  
Vol 12 (14) ◽  
pp. 5706 ◽  
Author(s):  
Ricardo S. Alonso ◽  
Inés Sittón-Candanedo ◽  
Roberto Casado-Vara ◽  
Javier Prieto ◽  
Juan M. Corchado
Keyword(s):  
Reinforcement Learning ◽  
Service Providers ◽  
Response Times ◽  
Cloud Service ◽  
Edge Computing ◽  
Network Function Virtualization ◽  
Software Defined Networks ◽  
Learning Mechanisms ◽  
Network Function ◽  
Learning Techniques

The Internet of Things (IoT) paradigm allows the interconnection of millions of sensor devices gathering information and forwarding to the Cloud, where data is stored and processed to infer knowledge and perform analysis and predictions. Cloud service providers charge users based on the computing and storage resources used in the Cloud. In this regard, Edge Computing can be used to reduce these costs. In Edge Computing scenarios, data is pre-processed and filtered in network edge before being sent to the Cloud, resulting in shorter response times and providing a certain service level even if the link between IoT devices and Cloud is interrupted. Moreover, there is a growing trend to share physical network resources and costs through Network Function Virtualization (NFV) architectures. In this sense, and related to NFV, Software-Defined Networks (SDNs) are used to reconfigure the network dynamically according to the necessities during time. For this purpose, Machine Learning mechanisms, such as Deep Reinforcement Learning techniques, can be employed to manage virtual data flows in networks. In this work, we propose the evolution of an existing Edge-IoT architecture to a new improved version in which SDN/NFV are used over the Edge-IoT capabilities. The proposed new architecture contemplates the use of Deep Reinforcement Learning techniques for the implementation of the SDN controller.

scholarly journals VNF Placement Optimization at the Edge and Cloud †

2019 ◽  
Vol 11 (3) ◽  
pp. 69 ◽  
Author(s):  
Aris Leivadeas ◽  
George Kesidis ◽  
Mohamed Ibnkahla ◽  
Ioannis Lambadaris
Keyword(s):  
Cloud Computing ◽  
Service Providers ◽  
Research Area ◽  
End Users ◽  
Network Function Virtualization ◽  
Future Research ◽  
Cloud Infrastructure ◽  
Network Function ◽  
Computing Paradigm ◽  
Network Functions

Network Function Virtualization (NFV) has revolutionized the way network services are offered to end users. Individual network functions are decoupled from expensive and dedicated middleboxes and are now provided as software-based virtualized entities called Virtualized Network Functions (VNFs). NFV is often complemented with the Cloud Computing paradigm to provide networking functions to enterprise customers and end-users remote from their premises. NFV along with Cloud Computing has also started to be seen in Internet of Things (IoT) platforms as a means to provide networking functions to the IoT traffic. The intermix of IoT, NFV, and Cloud technologies, however, is still in its infancy creating a rich and open future research area. To this end, in this paper, we propose a novel approach to facilitate the placement and deployment of service chained VNFs in a network cloud infrastructure that can be extended using the Mobile Edge Computing (MEC) infrastructure for accommodating mission critical and delay sensitive traffic. Our aim is to minimize the end-to-end communication delay while keeping the overall deployment cost to minimum. Results reveal that the proposed approach can significantly reduce the delay experienced, while satisfying the Service Providers’ goal of low deployment costs.

scholarly journals Software Defined Networking and Network Function Virtualization for Service Providers using Network Slice AS a Service

2019 ◽  
Vol 9 (2) ◽  
pp. 733-737
Keyword(s):  
Service Providers ◽  
Software Defined Networking ◽  
Network Services ◽  
Network Function Virtualization ◽  
Use Case ◽  
Service Networks ◽  
Service Network ◽  
Network Slicing ◽  
Network Function ◽  
Shared Network

The traditional network is configured based on the prescribed network requirements. Sometimes the resources of the network are underutilized and at sometimes there may resource starvation because of the static configuration of the network. As against traditional network, which is operated either as dedicated network or as an overlay network, network services can be operated over a shared network infrastructure. Thus maximum resource utilization under minimal infrastructure cost can be achieved. The on-demand network requirement can be configured dynamically using network slice. The backbone of the rapidly evolving 5G technology is network slice and service networks can be benefited from it. Different network function for multiple tenants can be enabled customized using network slice with each slice operating independently. Network slice can be offered as a service to meet various requirements from the network slice tenant with different granularities. The Software Defined Networking and Network Function Virtualization are the enabling technologies for network slice. This paper discusses various network slicing use case requirements. And also OpenFlow based software defined network environment is simulated to validate the discussions. Experimental results show that the efficiency of the service network is maximized with improved reliability of service

scholarly journals Τεχνοοικονομική διαχείριση κινητών δικτύων πέμπτης γεννιάς (5G) και εξής

2021 ◽  
Author(s):  
Anastasia Κόλλια. Αναστασία
Keyword(s):  
Cloud Computing ◽  
Cognitive Radio ◽  
Massive Mimo ◽  
Multiple Input Multiple Output ◽  
Network Function Virtualization ◽  
Software Defined Networks ◽  
Network Function ◽  
Multiple Input ◽  
Input Multiple Output ◽  
Antenna Systems

Σήμερα, η χρήση κινητών δικτύων αποτελεί αναπόσπαστο κομμάτι της καθημερινότητας. Οι χρήστες χρησιμοποιούν το κινητό τόσο για κλήσεις και μηνύματα όσο και για κοινωνικά δίκτυα, βίντεο, ταινίες, εφαρμογές ασκήσεις και φυσικής κατάστασης, παιχνίδια, εφαρμογές γραφείου, ημερολόγια κλπ. Η χρηστικότητα των συσκευών όχι μόνο έχει αλλάξει άρδην τα τελευταία χρόνια, αλλά αναμένεται να μεταβληθεί ακόμα περισσότερο ιδίως όταν εφαρμογές Internet of Things (IoT) προστεθούν στην ήδη διευρυμένη χρήση των κινητών συσκευών. Ακόμα, εμφανίζεται η τάση προσθήκης στο δίκτυο άλλων απλών οικιακών συσκευών και άλλου επιπρόσθετου εξοπλισμού π.χ. ιατρικών μικροσυσκευών, συσκευών παρακολούθησης, καμερών ασφαλείας κλπ. Η διδακτορική αυτή διατριβή αποτελεί μία συνολική μελέτη και περιλαμβάνει ένα πλαίσιο σχετικά με την πέμπτη γενιά κινητής τηλεπικοινωνίας. Αναλύεται η κατάσταση των Τηλεπικοινωνιών στην Ελλάδα σε βάθος. Ακόμα, περιγράφονται οι σημαντικότερες έννοιες και τα πιο βασικά βήματα και οι σημαντικότερες εξελίξεις των υπαρχουσών γενεών κινητών δικτύων επικοινωνίας. Επιπρόσθετα, περιγράφεται το θεωρητικό πλαίσιο για τα κινητά δίκτυα επικοινωνίας, καθώς και διάφοροι όροι, που είναι απαραίτητοι για την κατανόηση της παρούσας διατριβής. Αναλύονται διεξοδικά οι σημαντικότερες τεχνολογίες, που αποτελούν δομικούς λίθους για την ανάπτυξη, αλλά και την εξέλιξη στη δόμηση και ύπαρξη της 5G γενιάς κινητής τηλεπικοινωνίας, όπως έχει ήδη περιγραφεί από πλήθος ερευνητικών δράσεων και περιλαμβάνουν τις τεχνολογίες: Υπέρπυκνες Αρχιτεκτονικές (Ultra-dense), Distributed Antenna Systems (DAS), Network Function Virtualization (NFV), Software Defined Networks (SDN), Massive Multiple Input Multiple Output (MIMO), Cognitive Radio (CR), Milimeter Wave (mmWave), Cloud Computing και IoT και σύγκριση με τις σημερινές τεχνολογίες. Παρατίθενται τεχνο-οικονομικά μοντέλα, με βάση τις πιο σημαντικές τεχνολογίες, που συντελούν στην ανάπτυξη και προώθηση της 5G. Τα μοντέλα αυτά αποτελούν σημαντικό όπλο, ώστε οι πάροχοι να επενδύσουν σε νέες τεχνολογίες, να έχουν κέρδη και να καινοτομούν. Για το σκοπό αυτό επεξηγούνται τα αρχιτεκτονικά μοντέλα, τα μαθηματικά μοντέλα, οι παράμετροι, που επιλέγονται αλλά και τα αντίστοιχα πειράματα, που διεξάγονται για τις τεχνολογίες Ultra-density, DAS, NFV, SDN, Massive MIMO, CR, mmWave. Συνοψίζονται τα κυριότερα συμπεράσματα βάση των επιμέρους μελετών, που πραγματοποιήθηκαν στα πλαίσια της παρούσας διατριβής και προτείνονται ιδέες για μελλοντική έρευνα στον τομέα. Στα πλαίσια αυτά φιλοδοξείται ότι η συγκεκριμένη εργασία θα αποτελέσει ένα βασικό εργαλείο πληροφόρησης και ενημέρωσης για την επιστημονική και τηλεπικοινωνιακή κοινότητα σε ό,τι αναφορά στην τεχνο-οικονομική ανάλυση των τεχνολογιών, που αποτελούν τους θεμέλιους λίθους για τα δίκτυα Πέμπτης γενιάς.

scholarly journals Machine-Learning Defined Networking: Towards Intelligent Networks

2021 ◽  
pp. 3-12
Author(s):  
Sebastian Troia
Keyword(s):  
Machine Learning ◽  
Service Providers ◽  
Dynamic Network ◽  
Network Function Virtualization ◽  
Traffic Demand ◽  
Network Function ◽  
Network Utilization ◽  
Underlying Network ◽  
Network Operations ◽  
Network Technologies

AbstractWith the advent of 5G technology and an ever-increasing traffic demand, today Communication Service Providers (CSPs) experience a progressive congestion of their networks. The operational complexity, the use of manual configuration, the static nature of current technologies together with fast-changing traffic profiles lead to: inefficient network utilization, over-provisioning of resources and very high Capital Expenditures (CapEx) and Operational Expenses (OpEx). This situation is forcing the CSPs to change their underlying network technologies, and have started to look at new technological solutions that increase the level of programmability, control, and flexibility of configuration, while reducing the overall costs related to network operations. Software Define Networking (SDN), Network Function Virtualization (NFV) and Machine Learning (ML) are accepted as effective solutions to reduce CapEx and OpEx and to boost network innovation. This chapter summarizes the content of my Ph.D. thesis, by presenting new ML-based approaches in order to efficiently optimize resources in 5G metro-core SDN/NFV networks. The main goal is to provide the modern CSP with intelligent and dynamic network optimization tools in order to address the requirements of increasing traffic demand and 5G technology.

scholarly journals Blockchain-enabled real-time SLA monitoring for cloud-hosted services

2021 ◽  
Author(s):  
Kashif Mehboob Khan ◽  
Junaid Arshad ◽  
Waheed Iqbal ◽  
Sidrah Abdullah ◽  
Hassan Zaib
Keyword(s):  
Cloud Computing ◽  
Real Time ◽  
Service Providers ◽  
Response Times ◽  
Cloud Service ◽  
Service Level ◽  
Cloud Services ◽  
Blockchain Technology ◽  
Manual Processing ◽  
And Performance

AbstractCloud computing is an important technology for businesses and individual users to obtain computing resources over the Internet on-demand and flexibly. Although cloud computing has been adopted across diverse applications, the owners of time-and-performance critical applications require cloud service providers’ guarantees about their services, such as availability and response times. Service Level Agreements (SLAs) are a mechanism to communicate and enforce such guarantees typically represented as service level objectives (SLOs), and financial penalties are imposed on SLO violations. Due to delays and inaccuracies caused by manual processing, an automatic method to periodically verify SLA terms in a transparent and trustworthy manner is fundamental to effective SLA monitoring, leading to the acceptance and credibility of such service to the customers of cloud services. This paper presents a blockchain-based distributed infrastructure that leverages fundamental blockchain properties to achieve immutable and trustworthy SLA monitoring within cloud services. The paper carries out an in-depth empirical investigation for the scalability of the proposed system in order to address the challenge of transparently enforcing real-time monitoring of cloud-hosted services leveraging blockchain technology. This will enable all the stakeholders to enforce accurate execution of SLA without any imprecisions and delays by maintaining an immutable ledger publicly across blockchain network. The experimentation takes into consideration several attributes of blockchain which are critical in achieving optimum performance. The paper also investigates key characteristics of these factors and their impact to the behaviour of the system for further scaling it up under various cases for increased service utilization.

Sign in / Sign up

Export Citation Format

Share Document