A Differentiated Pricing Framework for Improving the Performance of the Elastic Traffics in Data Networks

Rate allocation has become a demanding task in data networks as diversity in users and traffics proliferate. Most commonly used algorithm in end hosts is TCP. This is a loss based scheme therefore it exhibits oscillatory behavior which reduces network performance. Moreover, since the price for all sessions is based on the aggregate throughput, losses that are caused by TCP affect other sessions as well and aggressively reduce their throughput and also have a drastic effect on the overall good put of the system. In this paper a new differentiated pricing method is proposed that not only reduces the loss phenomenon in the network, it improves the overall performance of the network and allows other sessions such as Proportional or Minimum Potential Delay schemes achieve more fair rates. Stability property of the algorithm is investigated and some numerical analysis is presented to verify the claims.