Site maintenance: Ilka Miloucheva

• Integrated inter-domain QoS monitoring and analysis architecture with different components for automated Internet inter-domain structure analysis, QoS and traffic monitoring, measurement based modelling, simulation and visual data mining using data base with policy control
  

• Inter-domain framework for policy controlled data collection and monitoring
  - Spatial composition of inter-domain QoS parameters to end-to-end QoS allowing to study and verify SLAs and QoS of application classes in large interconnected domain infrastructures
  - Integrated data collection at domain’s ingress / egress border and edge router for the purpose of inter-domain QoS analysis (including modelling, simulation and visual data mining)
  - Considering the domains as “black boxes” and measuring the QoS at the border ingress/egress routers of interconnected domains. Study interconnections of domains based on different QoS technology (DiffServ, IntServ, MPLS).
  - Distributed inter-domain QoS database with automated information processing
  

• Inter-domain modelling toolkit
  - Modelling toolkit for application classes and aggregated traffic focussed on long range and short term modelling of inter-domain traffic and QoS based on monitoring data
  - Integration of new algorithms for detecting anomalies in inter-connected domain infrastructure, normal and abnormal behaviour (“QoS outliers”) , event pattern study, automated detection and localisation of specific inter-domain problems (e.g. DoS attacks, bottleneck and excess capacity)
  - Mathematical, operative and predictive models (inter-domain QoS and traffic models of application classes, border domain’s resources, spatial composition of QoS in inter-domain environment) based on measurements:
  - Models for QoS predictions (ARIMA forecasting, neural networks)
  

• Scalable and efficient inter-domain measurement based simulation environment
  - Model validation by simulations and monitoring considering different kind of network
  connectivity, inter-domain routing policies, costs, resource and QoS parameter restrictions

  | Integration of new inter-domain modelling and simulation techniques
  - Hybrid simulation (packet based analytical hybrid simulation with ns-2)
  - Continuous fluid flow simulation based on differential equations (RTC-FSIM)
  - Time series data simulation
  | Measurement based input models used in simulation environments
  - aggregate and application traffic models
  - inter-domain link model
  - domain cloud model
  

• Innovative visual data mining concepts for QoS and traffic analysis
  - Flexible configurable filters
  - Spatio-temporal QoS analysis (QoS patterns, outliers)
  - Traffic analysis (traffic matrix)
  - Data mining functions for filtering and statistical modelling of QoS and traffic data, QoS pattern detection and analysis
  - Policy collection and mapping of large sets of inter-domain information, i.e. passive and active monitoring/measurement information (considering inter-domain QoS, traffic and event behaviour),modelling, and simulation data, structure discovery