Search for: All records

Network measurement and monitoring are instrumental to network operations, planning and troubleshooting. However, increasing line rates (100+Gbps), changing measurement targets and metrics, privacy concerns, and policy differences across multiple R&E network domains have introduced tremendous challenges in operating such high-speed heterogeneous networks, understanding the traffic patterns, providing for resource optimization, and locating and resolving network issues. There is strong demand for a flexible, high-performance measurement instrument that can empower network operators to achieve the versatile objectives of effective network management and resource provisioning. In this demonstration, we present AMIS: Advanced Measurement Instrument and Services to achieve programmable, flow-granularity and event-driven network measurement, sustain scalable line rates, to meet evolving measurement objectives and to derive knowledge for network advancement. 

This paper presents techniques for the description and management of distributed streaming data applications. The proposed solution provides an abstract description language and operational graph model for supporting collections of autonomous components functioning as distributed systems. Using our approach, applications supporting millions of devices can be easily modeled using abstract configurations. Through our models applications can implemented and managed through socalled server-less application orchestration. 

In the area of network monitoring and measurement a number of good tools are already available. However, most mature tools do not account for changes in network management brought about through Software Defined Networking (SDN). New tools developed to address the SDN paradigm often lack both observation scope and performance scale to support distributed management of accelerated measurement devices, high-throughput network processing, and distributed network function monitoring. In this paper we present an approach to distributed network monitoring and management using an agent-based edge computing framework. In addition, we provide a number of real-world examples where this system has been put into practice. 

The Cresco distributed agent-based framework is designed to address the challenges of edge computing. We present an actor-model implementation for the management of large numbers of geographically distributed services, comprised from heterogeneous resources and communication protocols, in support of low-latency realtime streaming applications. We present the purpose of our work, the basic methodology, the initial results already obtained, the relationship to the existing software, and the potential of the presently implemented framework to a number of potential further projects that could be developed on the basis of the existing implementation.