ICE-T: RC: Multi-Domain Multi-Broker Elastic Optical Networks with Cognitive Functionalities

拟议的项目寻求一种创新的方法来设计，控制和管理下一代互联网核心网络。一个新的域间网络的范例被认为是，在代理代理之间自由竞争，以提供有吸引力的互联网络服务的自治系统（AS），而AS也选择代理服务适合自己的互联网络的需要。该项目开发了一个市场驱动的多代理辅助的多域框架，可以协调-在一个分布式，激励方式-同时为经纪人和AS提供完全的自主权和自由。通过市场驱动的激励和竞争，经纪人和AS将追求互利的服务，这反过来又会不断刺激创新的解决方案和服务。 具有多个代理的新的域间网络架构将促进自动化、服务质量感知和损伤响应服务。该项目利用基于机器学习的认知功能来优化端到端服务提供。该项目寻求架构、模拟、原型和实验，以提高系统的（a）可扩展性，（B）端到端性能，（c）健壮性和适应性，以及（d）可扩展性和协调性。 该项目将利用新的和新兴的认知技术进行动态流量预测和自适应配置，传输质量估计和跨多个域的故障检测。该项目扩展了加州大学大卫分校、西班牙加泰罗尼亚理工大学（UPC）和意大利国家大学联盟和国际大学间的研究合作。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

The proposed project seeks an innovative approach to the design, control and management of next generation Internet core networks. A new inter-domain networking paradigm is considered, where broker agents compete freely with each other to provide attractive inter-networking services to Autonomous Systems (ASes), while ASes also choose broker services suitable for their inter-networking needs.The project develops a market-driven multi-broker-assisted multi-domain framework that can coordinate -- in a distributed, incentivized manner - while providing complete autonomy and freedom to both brokers and ASes. Through market-driven incentives and competitions, the brokers and the ASes will pursue mutually beneficial services, which will in turn continuously spur innovative solutions and services. The new inter-domain networking architecture with multiple brokers will facilitate automated, Quality-of-Service aware, and impairment-responsive services. The project leverages cognitive functionalities based on machine learning to optimize end-to-end service provisioning. The project seeks to architect, simulate, prototype, and experiment to improve system (a) scalability, (b) end-to-end performance, (c) robustness and adaptability, and (d) manageability and coordination. The project will leverage novel and emerging cognitive techniques for dynamic traffic prediction and adaptive provisioning, quality of transmission estimation and fault detection across multiple domains. This project extends a research collaboration between the University of California, David, the Universitat Politecnica de Cataluna (UPC), Spain, and Consorzio Nazionale and Interuniversitario per le Telecomunicazioni (CNIT), Italy.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.