Jungang Liu

Using Fuzzy Logic Control to Provide Intelligent Traffic Management Service for High-Speed Networks

In view of the fast-growing Internet traffic, this paper propose a distributed traffic management framework, in which routers are deployed with intelligent data rate controllers to tackle the traffic mass. Unlike other explicit traffic control protocols that have to estimate network parameters (e.g., link latency, bottleneck bandwidth, packet loss rate, or the number of flows) in order to compute the allowed source sending rate, our fuzzy-logic-based controller can measure the router queue size directly; hence it avoids various potential performance problems arising from parameter estimations while reducing much consumption of computation and memory resources in routers. As a network parameter, the queue size can be accurately monitored and used to proactively decide if action should be taken to regulate the source sending rate, thus increasing the resilience of the network to traffic congestion. The communication QoS (Quality of Service) is assured by the good performances of our scheme such as max-min fairness, low queueing delay and good robustness to network dynamics. Simulation results and comparisons have verified the effectiveness and showed that our new traffic management scheme can achieve better performances than the existing protocols that rely on the estimation of network parameters.

Design and Evaluation of an Intelligent Rate Controller for Heterogeneous Networks

This paper proposes an intelligent rate controller for the Internet traffic. Called the IntelRate (Intelligent Rate), it is a router-based controller and uses the fuzzy logic control approach to adjust the source sending rate based on the instantaneous queue size of the router. Unlike other explicit congestion control protocols, the IntelRate controller need not evaluate the link states (such as bottleneck bandwidth or the number of flows in the link) while performing well to the sudden changes in traffic load or bandwidth. Simulation results and comparisons have verified the effectiveness of our scheme, and showed the IntelRate controller is more stable and robust upon large network changes than other existing protocols that rely on the estimation of available bandwidth in order to compute the admissible source sending rate.

Stability Analysis and Evaluation of the IntelRate Controller for High-Speed Heterogeneous Networks

The IntelRate controller does not require to evaluate some critical network parameters (such as the bottleneck bandwidth and the number of flows in the link) while performing well to the sudden changes in traffic load or bandwidth. This paper demonstrates theoretically that the IntelRate control system is globally asymptotically stable. Opnet simulations verify that the IntelRate controller can maintain stable operations regardless of the traffic conditions. Finally, comparison demonstrates that the IntelRate controller can have more stable performance than other exiting controllers upon network changes.

Characterization of the IntelRate Controller for High-Speed Networks

Unlike other explicit congestion controllers that depend on the estimation of network parameters (such as link latency, bottleneck bandwidth, packet loss, or the number of flows) to compute the allowed source sending rate, the IntelRate controller can avoid this while maintaining good stability and robustness. Simulation results have verified these performances. In this paper, we theoretically investigate the rationale that gives the IntelRate controller such an advantage. Our study shows that the IntelRate controller can be approximated by a PI (Proportional-Integral) controller but with time-varying gains, which allows the controller to outperform its counterparts. Finally, by comparing with the API-RCP (Adaptive PI Rate Control Protocol) using Opnet simulation, we experimentally illustrate our conclusion.

An optimal and fully explicit rate controller for high-speed networks

We have designed and investigated a new congestion control scheme, called the OFEX (Optimal and Fully EXplicit) controller. Different from the existing relatively explicit controllers, this new scheme is able to provide not only optimal bandwidth allocation but also fully explicit congestion signal to sources. It overcomes the drawback of the relatively explicit controllers that “bias” the multi-bottlenecked users, and improves their convergence speed and source throughput performance. Furthermore, the OFEX controller design considers a dynamic model by proposing a remedial measure against the unpredictable bandwidth changes in contention-based networks (such as shared Ethernet and IEEE 802.11). Compared with the former works/controllers, such a remedy also effectively reduces the instantaneous queue size in a link, and thus significantly improving the queueing delay and system stability performance. We have evaluated the effectiveness of the OFEX controller in OPNET. The experimental comparison verifies the superiority of the OFEX controller.

Convergence performance of the OFEX controller for high-speed networks

The OFEX (Optimal and Fully EXplicit) rate controller is able to provide not only the optimal bandwidth allocation but also the fully explicit congestion signal to sources. It feeds back the congestion signal from the most congested link along a flow path, instead of the summation of congestion signals. The OFEX controller overcomes the drawbacks of the relatively explicit controllers that (1) bias the multi-bottlenecked users in terms of the source sending rate and convergence speed, (2) are not adaptable to varying link bandwidth and (3) can potentially incur large queue sizes upon congestion. In this paper, we would like to investigate the convergence property of the OFEX controller which is of particular concern and interests to researchers, and point out how the OFEX controller can quickly converge to equilibrium even under bandwidth variations. Furthermore, our OPNET simulation experimentally demonstrates the superior convergence capability of the OFEX controller when compared with other schemes.

Using the IntelRate Controller to Improve Throughput and Queue Size of High-Speed WLANs

The IntelRate controller does not need to evaluate some critical network parameters (such as link bandwidth) as required in the existing explicit congestion controllers while performing better upon network parameter changes. In this paper, we will further experimentally investigate the IntelRate controller under dynamic bandwidth situations in WLANs (Wireless Local Networks) via OPNET simulation. Comparison with other recent controllers that need to estimate bandwidth shows that the IntelRate controller has greatly improved the adaptation capability and stability of the system. In the meanwhile, we also point out some response limitations under fast bandwidth variations that a designer should pay attention to.