Automating Network Management With Artificial Intelligence

2018 ◽  
pp. 113-145
Author(s):  
Imen Grida Ben Yahia ◽  
Jaafar Bendriss ◽  
Teodora Sandra Buda ◽  
Haytham Assem
Keyword(s):  
Artificial Intelligence ◽  
Network Management ◽  
Mobile Networks ◽  
Service Providers ◽  
Service Level Agreement ◽  
Service Level ◽  
Management Framework ◽  
Policy Based Management ◽  
Detailed Specification ◽  
Fast Adaptation

Artificial intelligence (AI) and in particular machine learning are seen as cornerstones to automate and rethink network management operations in the context of network softwarization (i.e., SDN, NFV, and Cloud). In this regard, operators and service providers target the creation of service offerings, the customization of network solutions, and the fast adaptation to rapidly changing market demands. This translates into requirements for increased flexibility, modularity, and scalability in network management operations. This chapter presents a detailed specification of a cognitive (AI-based) network management framework applicable for existing and future (software-defined) networks. The framework is built upon the combined state-of-the-art on autonomic, policy-based management and big data. It is exemplified with two detailed use cases: the urban mobility awareness for today's mobile networks and SLA (service level agreement) enforcement in the context of NFV and cloud.

scholarly journals An integrated three-tier trust management framework in mobile edge computing using fuzzy logic

2021 ◽  
Vol 7 ◽  
pp. e700
Author(s):  
Merrihan B.M. Mansour ◽  
Tamer Abdelkader ◽  
Mohamed Hashem ◽  
El-Sayed M. El-Horbaty
Keyword(s):  
Service Provider ◽  
Trust Management ◽  
Service Providers ◽  
Service Level Agreement ◽  
Cloud Service ◽  
Service Level ◽  
Edge Computing ◽  
Trust Value ◽  
Management Framework ◽  
Cloud Service Providers

Mobile edge computing (MEC) is introduced as part of edge computing paradigm, that exploit cloud computing resources, at a nearer premises to service users. Cloud service users often search for cloud service providers to meet their computational demands. Due to the lack of previous experience between cloud service providers and users, users hold several doubts related to their data security and privacy, job completion and processing performance efficiency of service providers. This paper presents an integrated three-tier trust management framework that evaluates cloud service providers in three main domains: Tier I, which evaluates service provider compliance to the agreed upon service level agreement; Tier II, which computes the processing performance of a service provider based on its number of successful processes; and Tier III, which measures the violations committed by a service provider, per computational interval, during its processing in the MEC network. The three-tier evaluation is performed during Phase I computation. In Phase II, a service provider total trust value and status are gained through the integration of the three tiers using the developed overall trust fuzzy inference system (FIS). The simulation results of Phase I show the service provider trust value in terms of service level agreement compliance, processing performance and measurement of violations independently. This disseminates service provider’s points of failure, which enables a service provider to enhance its future performance for the evaluated domains. The Phase II results show the overall trust value and status per service provider after integrating the three tiers using overall trust FIS. The proposed model is distinguished among other models by evaluating different parameters for a service provider.

Service level agreement management framework for utility-oriented computing platforms

2015 ◽  
Vol 71 (11) ◽  
pp. 4287-4303 ◽  
Author(s):  
Jemal Abawajy ◽  
Mohd Farhan Fudzee ◽  
Mohammad Mehedi Hassan ◽  
Majed Alrubaian
Keyword(s):  
Service Level Agreement ◽  
Service Level ◽  
Management Framework ◽  
Computing Platforms

A Novel QoS Aware Shortest Path Algorithm for VSDN

2017 ◽  
Vol 6 (1) ◽  
pp. 1-14
Author(s):  
Amandeep Kaur Sandhu ◽  
Jyoteesh Malhotra
Keyword(s):  
Energy Consumption ◽  
Shortest Path ◽  
Service Providers ◽  
Service Level Agreement ◽  
Service Level ◽  
Software Defined Networks ◽  
Shortest Path Algorithm ◽  
Internet Service ◽  
Decrease Energy Consumption

This article describes how a rapid increase in usage of internet has emerged from last few years. This high usage of internet has occurred due to increase in popularity of multimedia applications. However, there is no guarantee of Quality of Service to the users. To fulfill the desired requirements, Internet Service Providers (ISPs) establish a service level agreement (SLA) with clients including specific parameters like bandwidth, reliability, cost, power consumption, etc. ISPs make maximum SLAs and decrease energy consumption to raise their profit. As a result, users do not get the desired services for which they pay. Virtual Software Defined Networks are flexible and manageable networks which can be used to achieve these goals. This article presents shortest path algorithm which improves the matrices like energy consumption, bandwidth usage, successful allocation of nodes in the network using VSDN approach. The results show a 40% increase in the performance of proposed algorithms with a respect to existing algorithms.

Broker-based optimization of SLA negotiations in cloud computing

2021 ◽  
Vol 17 (2) ◽  
pp. 179-195
Author(s):  
Priyanka Bharti ◽  
Rajeev Ranjan ◽  
Bhanu Prasad
Keyword(s):  
Cloud Computing ◽  
Service Providers ◽  
Service Level Agreement ◽  
Cloud Service ◽  
Service Level ◽  
Cloud Environment ◽  
Negotiation Strategies ◽  
Sla Negotiation ◽  
Conflicting Interests ◽  
The Impact

Cloud computing provisions and allocates resources, in advance or real-time, to dynamic applications planned for execution. This is a challenging task as the Cloud-Service-Providers (CSPs) may not have sufficient resources at all times to satisfy the resource requests of the Cloud-Service-Users (CSUs). Further, the CSPs and CSUs have conflicting interests and may have different utilities. Service-Level-Agreement (SLA) negotiations among CSPs and CSUs can address these limitations. User Agents (UAs) negotiate for resources on behalf of the CSUs and help reduce the overall costs for the CSUs and enhance the resource utilization for the CSPs. This research proposes a broker-based mediation framework to optimize the SLA negotiation strategies between UAs and CSPs in Cloud environment. The impact of the proposed framework on utility, negotiation time, and request satisfaction are evaluated. The empirical results show that these strategies favor cooperative negotiation and achieve significantly higher utilities, higher satisfaction, and faster negotiation speed for all the entities involved in the negotiation.

A Service Oriented SLA Management Framework for Grid Environments

2012 ◽  
pp. 45-61
Author(s):  
V. Pouli ◽  
C. Marinos ◽  
M. Grammatikou ◽  
S. Papavassiliou ◽  
V. Maglaris
Keyword(s):  
Web Service ◽  
Service Providers ◽  
Service Level ◽  
Service Availability ◽  
Management Framework ◽  
Qos Guarantees ◽  
Grid Environments ◽  
Monitoring Procedure ◽  
Service Oriented ◽  
And Performance

Traditionally, network Service Providers specify Service Level Agreements (SLAs) to guarantee service availability and performance to their customers. However, these SLAs are rather static and span a single provider domain. Thus, they are not applicable to a multi–domain environment. In this paper, the authors present a framework for automatic creation and management of SLAs in a multi-domain environment. The framework is based on Service Oriented Computing (SOC) and contains a collection of web service calls and modules that allow for the automatic creation, configuration, and delivery of an end-to-end SLA, created from the merging of the per-domain SLAs. This paper also presents a monitoring procedure to monitor the QoS guarantees stipulated in the SLA. The SLA establishment and monitoring procedures are tested through a Grid application scenario targeted to perform remote control and monitoring of instrument elements distributed across the Grid.

ODACE SLA

2010 ◽  
Vol 1 (3) ◽  
pp. 1-20 ◽  
Author(s):  
Kaouthar Fakhfakh ◽  
Tarak Chaari ◽  
Said Tazi ◽  
Mohamed Jmaiel ◽  
Khalil Drira
Keyword(s):  
Service Providers ◽  
Service Level Agreement ◽  
Service Level ◽  
Second Step ◽  
Technical Knowledge ◽  
Complex Task ◽  
Semantic Matching ◽  
The Third ◽  
Draft Version ◽  
Fourth Step

The establishment of Service Level Agreements between service providers and clients remains a complex task regarding the uninterrupted growth of the IT market. In fact, it is important to ensure a clear and fair establishment of these SLAs especially when providers and clients do not share the same technical knowledge. To address this problem, the authors started modeling client intentions and provider offers using ontologies. These models helped them in establishing and implementing a complete semantic matching approach containing four main steps. The first step consists of generating correspondences between the client and the provider terms by assigning certainties for their equivalence. The second step corrects and refines these certainties. In the third step, the authors evaluate the matching results using inference rules, and in the fourth step, a draft version of a Service Level Agreement is automatically generated in case of compatibility.

SLA Monitoring of Presence-Enabled Services

2011 ◽  
pp. 307-322
Author(s):  
Tapati Bandopadhyay ◽  
Pradeep Kumar
Keyword(s):  
Service Providers ◽  
Instant Messaging ◽  
Service Level Agreement ◽  
Service Level ◽  
Application Framework ◽  
End User ◽  
New Approach ◽  
Clear Guideline ◽  
Evaluation Measurement ◽  
Monitoring Service

The concept of presence was initially associated with an instant messaging service, allowing an end user to recognize the presence of a peer online to send or receive messages. Now the technology has grown up to include various services like monitoring performance of any type of end user device, and services are accessible from anywhere, any time. The need for enhanced value remains the driving force behind these services, for example, Voice over Internet Protocol (VoIP) services, which is drawing tremendous research interest in services performance evaluation, measurement, benchmarking, and monitoring. Monitoring service level parameters happens to be one of the most interesting application-oriented research issues because various service consumers at the customer companies/end users’ level are finding it very difficult to design and monitor an effective SLA (Service Level Agreement) with the presence-enabled service providers. This chapter focuses on to these specific issues and presents a new approach of SLA monitoring through Data Envelopment Analysis (DEA). This extreme point approach actually can work much better in the context of SLA monitoring than general central-tendency-based statistical tools, a fact which has been corroborated by similar application examples of DEA presented in this chapter and has therefore it acts as the primary motivation to propose this new approach. Towards this end, this chapter first builds up the context of presence-enabled services (Day, Rosenburg, & Sugano, 2000), its SLA and SLA parameters, and the monitoring requirements. Then it explains the basics of DEA and its application in various other engineering and services context. Ultimately, a DEA application framework for monitoring an SLA of presence-enabled services is proposed which can serve as a clear guideline for the customers of presence-enabled services, not only for SLA monitoring but also at various other stages of implementing presence-enabled services frameworks. This approach exploits the definitive suitability of the application of DEA methods to presence-enabled service monitoring problems, and can be easily implemented by the industry practitioners.

scholarly journals Distributed Meta-Brokering P2P Overlay for Scheduling in Cloud Federation

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 852 ◽  
Author(s):  
Sajid Latif ◽  
Syed Mushhad Gilani ◽  
Rana Liaqat Ali ◽  
Misbah Liaqat ◽  
Kwang-Man Ko
Keyword(s):  
Resource Management ◽  
Service Provision ◽  
Large Scale ◽  
Service Providers ◽  
Service Level Agreement ◽  
Service Level ◽  
Distributed Resources ◽  
Proposed Model ◽  
Geographically Distributed ◽  
Application Programming

The interconnected cloud (Intercloud) federation is an emerging paradigm that revolutionizes the scalable service provision of geographically distributed resources. Large-scale distributed resources require well-coordinated and automated frameworks to facilitate service provision in a seamless and systematic manner. Unquestionably, standalone service providers must communicate and federate their cloud sites with other vendors to enable the infinite pooling of resources. The pooling of these resources provides uninterpretable services to increasingly growing cloud users more efficiently, and ensures an improved Service Level Agreement (SLA). However, the research of Intercloud resource management is in its infancy. Therefore, standard interfaces, protocols, and uniform architectural components need to be developed for seamless interaction among federated clouds. In this study, we propose a distributed meta-brokering-enabled scheduling framework for provision of user application services in the federated cloud environment. Modularized architecture of the proposed system with uniform configuration in participating resource sites orchestrate the critical operations of resource management effectively, and form the federation schema. Overlaid meta-brokering instances are implemented on the top of local resource brokers to keep the global functionality isolated. These instances in overlay topology communicate in a P2P manner to maintain decentralization, high scalability, and load manageability. The proposed framework has been implemented and evaluated by extending the Java-based CloudSim 3.0.3 simulation application programming interfaces (APIs). The presented results validate the proposed model and its efficiency to facilitate user application execution with the desired QoS parameters.

SLA (Service Level Agreement) Driven Orchestration Based New Methodology for Cloud Computing Services

2013 ◽  
Vol 660 ◽  
pp. 196-201 ◽  
Author(s):  
Muhammad Irfan ◽  
Zhu Hong ◽  
Nueraimaiti Aimaier ◽  
Zhu Guo Li
Keyword(s):  
Cloud Computing ◽  
Computer Science ◽  
Service Providers ◽  
Service Level Agreement ◽  
Cloud Service ◽  
Service Level ◽  
Cloud Services ◽  
Computing Services ◽  
Cloud Service Providers ◽  
Cloud Computing Services

Cloud Computing is not a revolution; it’s an evolution of computer science and technology emerging by leaps and bounds, in order to merge all computer science tools and technologies. Cloud Computing technology is hottest to do research and explore new horizons of next generations of Computer Science. There are number of cloud services providers (Amazon EC2), Rackspace Cloud, Terremark and Google Compute Engine) but still enterprises and common users have a number of concerns over cloud service providers. Still there is lot of weakness, challenges and issues are barrier for cloud service providers in order to provide cloud services according to SLA (Service Level agreement). Especially, service provisioning according to SLAs is core objective of each cloud service provider with maximum performance as per SLA. We have identified those challenges issues, as well as proposed new methodology as “SLA (Service Level Agreement) Driven Orchestration Based New Methodology for Cloud Computing Services”. Currently, cloud service providers are using “orchestrations” fully or partially to automate service provisioning but we are trying to integrate and drive orchestration flows from SLAs. It would be new approach to provision cloud service and deliver cloud service as per SLA, satisfying QoS standards.

Sign in / Sign up

Export Citation Format

Share Document