研究目的
Investigating the development of a novel SDN-based QoS control framework for industrial networks that achieves hard real-time QoS guarantees with high bandwidth utilization.
研究成果
The proposed function split framework for SDN-based QoS control in industrial networks achieves hard real-time QoS guarantees with high bandwidth utilization. The framework allows for quick runtime admission decisions and comes close to the performance of a monolithic MIP approach in terms of connection carrying capacity and bandwidth utilization for short-hop distances. Future research directions include exploring more routing cost functions, scheduling policies, and refinements in resource allocation.
研究不足
The study focuses on a specific network topology (unidirectional ring) and a limited set of traffic mixes. The resource allocation algorithm's performance varies across different traffic mixes, indicating potential areas for optimization. The approach's applicability to more complex network structures and scheduling policies requires further investigation.
1:Experimental Design and Method Selection:
The study employs a novel SDN-based QoS control framework that utilizes network calculus for deterministic modeling of resource allocation and QoS parameter allocation. The framework introduces a function split between delay-constrained least-cost routing and resource allocation to queue links.
2:Sample Selection and Data Sources:
The evaluation is based on simulations of a unidirectional ring physical link topology, representing a typical elementary industrial network structure.
3:List of Experimental Equipment and Materials:
The simulations consider switching nodes with output ports having four output queues operating with strict priority scheduling, each with 90,000 Byte buffer.
4:Experimental Procedures and Operational Workflow:
The study involves online routing and admission control evaluations, offline resource allocation simulations, and comparisons with a monolithic mixed-integer programming (MIP)-based approach.
5:Data Analysis Methods:
The performance is evaluated based on average link utilization, average buffer utilization, and average delay deviation across different traffic mixes and hop distance scenarios.
独家科研数据包,助您复现前沿成果,加速创新突破
获取完整内容