Abstract-In this paper, we propose a novel algorithm for mapping of service classes among multiple Internet providers on an end-to-end (E2E) path. The third-party (3P) approach is assumed for E2E service negotiation, whereas the foundation for class mapping is laid on the integer programming mathematical model. The algorithm selects service classes in domains on the path so that requirements for E2E quality of service (QoS) are fulfilled. This selection is based on multiple constraints, referring to performance fulfillment and at the same time aiming to achieve minimal E2E interconnection cost through definition of a single objective function. Performance evaluation has clearly indicated benefits of the proposed algorithm in terms of QoS achievement and decreasing costs, as well as its suitability for services that require stringent QoS guarantees.
The third party (3P) model has been recognized as a perspective approach for different interprovider quality of service (QoS) solutions. In this paper, we address 3P-based mapping of services classes among heterogeneous providers' networks, which constitute an end-to-end (E2E) path. We propose and investigate a novel, highly flexible mapping scheme, which enables fulfillment of E2E network performance objectives, whereas minimizing interconnection costs. Starting from E2E service requirements, the proposed scheme uses goal programming technique to select the most appropriate service class in each domain on the path. Results of the comparative analysis of the proposed scheme and the two existing 3P-based schemes have clearly demonstrated superiority of our proposal in terms of accuracy, flexibility, and capability to support deployment of various business objectives. IndexTerms-Goal programming, interprovider negotiation, third party, quality of service. I. INTRODUCTIONRecent trends in Internet development including cloud computing, mobility, content distribution, Internet of things, and the big data paradigm pose new architectural challenges for network interconnection in the future Internet [1]. Enhanced solutions for quality of service (QoS) provisioning are still needed, particularly regarding end-to-end (E2E) service negotiation, performance monitoring and measurements for inter-domain performance assessment. The basic bilateral approach [2], which assumes service negotiation only between the adjacent providers, fails to meet E2E requirements. On the other side, heterogeneity of the existing providers' networks, including different intradomain QoS architectures, complicates the problem of establishing QoS-enabled E2E paths.The third-party (3P) approach has been recognized as a promising solution for the interprovider QoS delivery [3]. It assumes that a trusted, authorized intermediary (3P agent) Manuscript
In this paper, we propose a novel algorithm for mapping of service classes among multiple Internet providers on an end-to-end (E2E) path. The third-party (3P) approach is assumed for E2E service negotiation, whereas the foundation for class mapping is laid on the integer programming mathematical model. The algorithm selects service classes in domains on the path so that requirements for E2E quality of service (QoS) are fulfilled. This selection is based on multiple constraints, referring to performance fulfillment and at the same time aiming to achieve minimal E2E interconnection cost through definition of a single objective function. Performance evaluation has clearly indicated benefits of the proposed algorithm in terms of QoS achievement and decreasing costs, as well as its suitability for services that require stringent QoS guarantees.
Packet burst losses are proven to be detrimental to multimedia applications. Most of the burst losses in the Internet are the result of tail drop discipline, which drops packets when queues in routers are filled to their maximum capacity. A potential way of addressing the burst losses is to use packet dispersion over multiple and disjoint paths to destination. However, packet dispersion requires packet reordering and addressing the problems concerning packet latency and jitter. We are proposing a model that dynamically triggers packet dispersion depending on the high priority queue occupancy containing high priority traffic, whereas the need for packet dispersion and the number of dispersion paths is inferred from traffic load in other queues. Proposed mechanism reduces tail drops in queues containing high priority traffic by performing packet shifting to high priority queues that belong to other output interfaces designated for packet dispersion. It delivers significant benefits regarding packet loss and packet loss distance, which are considered imperative parameters for describing the quality of multimedia and real-time traffic.
The appearance of burst packet losses and its devastating effect on Voice over IP (VoIP) service have imposed a requirement for the implementation of loss recovery mechanisms to address VoIP quality during periods when high packet loss is exhibited. Existing loss recovery mechanisms are dependent on end point capabilities, whereas Quality of service (QoS) routing protocols suffer from complexity and scalability issues. In this paper, we examine packet dispersion's ability to address burst losses and provide a computational model, which is verified using real network testing. A study has been carried out to investigate the effect of different packet dispersion strategies on burst losses, which clearly shows dispersion's qualitative superiority over single path routing. Furthermore, an analytical approach is proposed resulting in quality estimation obtained by individual strategies. Practical evaluation has shown that each strategy copes differently with various burst scenarios in order to maximize VoIP quality.Keywords: burst loss, Markov model, packet dispersion, voice over IP, quality of service.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.