Profile-Based Adaptive DiffServ Policing with Learning Techniques

Abstract

IETF's Differentiated Services (DiffServ) is a scalable, distributed architecture aimed to provide a fair distribution of network resources according to expected levels of service. However, variable traffic and performance expectations may require an adjustment of management policies so that congestion situations are avoided and service parameters are met. Existing solutions that improve the standard DiffServ architecture do not cope well with this dynamics and network resources are not efficiently managed, preventing user expectations from being properly fulfilled. In this paper we show how a reinforcement learning approach can optimize the choice of adaptation profiles for the optimal adjustment of ingress policies when a precongestion state is detected. Numerical results from simulations showed improvements for priority traffic (video) without impacting excessively the other traffic.

Performance of new dynamic benefit-weighted scheduling scheme in DiffServ networks

“…DiffServ architecture [1] offers end to end QoS on the Internet. It also supports a number of mechanisms such as WRR, priority scheduling and class based queuing to offer QoS that can be implemented in DiffServ to achieve the desired packet rates and delays for EF, AF and BE services.…”

“…The user data packet (UDP) is the traffic type.. As shown in Fig. 3, AF sources (1,2) and BE traffic sources (1,2), generate data at a constant speed and at core routers AF and BE data of 1Mbps and 2Mbps respectively is examined. It is kept constant for all simulation results.…”

“…Over the years, the Internet engineering task force (IETF) has proposed and developed several novel architectures for QoS provisioning in the Internet. For example, Integrated Services (IntServ), Differentiated Services (DiffServ) [1] and Multi Protocol Label Switching (MPLS). Scalable network architecture, DiffServ network [2] was introduced to classify and manage network traffic to provide QoS for multi service networks.…”