Gong Xiangyang

Autonomic QoS Management Mechanism in Software Defined Network

With the increase of network complexity, the flexibility of network control and management becomes a nontrivial problem. Both Software Defined Network (SDN) and Autonomic Network technologies are sophisticated technologies for the network control and management. These two technologies could be combined together to construct a software defined self-managing solution for the future network. An autonomic QoS management mechanism in Software Defined Network (AQSDN) is proposed in this paper. In AQSDN, the various QoS features can be configured autonomically in an OpenFlow switch through extending the OpenFlow and OF-Config protocols. Based on AQSDN, a novel packet context-aware QoS model (PCaQoS) is also introduced for improving the network QoS. PCaQoS takes packet context into account when packet is marked and managed into forwarding queues. The implementation of a video applications prototype which evaluates the self-configuration feature of the AQSDN and the enhancement ability of the PCaQoS is presented in order to validate this design.

Autonomicity design in OpenFlow based Software Defined Networking

Software Defined Networking (SDN) is a new area in network management. It is understood as using software to improve the network capabilities and intelligence. Autonomicity is one of proposed technologies, which also can improve network management capabilities. A scheme of the combination of OpenFlow based SDN and Autonomicity is proposed in this paper to introduce self-* attributes into OpenFlow Based SDN so that the network could be better controlled and operated efficiently.

Effective fairness queuing algorithms

In this paper we present two effective fair queuing algorithms (EFQs), which achieves fairness properties and delay properties similar to WFQ (which is currently the better scheduling algorithm among others), and uses a system potential function of O(l) complexity. In EFQs, computation of system potential function does not require any division or multiplication operations such as in minimum delay-self clocked fair queuing (MD-SCFQ). Compared to MD-SCFQ, EFQs have lower complexity and can be easily implemented on chips. We verify the effectiveness of the proposed EFQs through theoretical analysis and give some simulation results.

N3S-OLSR: Node-Status Self-Sensing Optimized Link-State Routing Protocols for MANET

In MANET, the severe instability feature produced by mobility and wireless nature leads to the frequent change of network topology and influences network performance. In this paper, we propose an improved routing protocol -- N3S-OLSR, which calculates MPR sets with combination of self-sensing information and hop count. Through self-sensing module, nodes obtain the network status information, and map them into two values - NS_COST and LINK_COST. N3S-OLSR exchanges network status information through extended Hello message, and calculates the MPR set with neighbors’ NS_COST and LINK_COST not only between node and its neighbors but also between its neighbors and its 2-hop neighbors. Simulation results show that, our protocol can provide better network performance than traditional OLSR.