Design of biologically inspired distributed adaptive routing system

SPF(Shortest Path First)路由算法广泛分布于Internet等大规模网络中。由于该路由算法是为了提高在节点顺序生成的每个分组的吞吐量而设计的，因此不适合在网络中平均负载平衡。细胞内的酶反馈是实现代谢途径中各反应物的价值动态平衡的典型的、基本的调控机制。该研究的目的是设计一种自适应路由，在避免网络中的局部拥塞和时变拥塞的情况下，将节点产生的分组发送到最终目的地，并对网络中的负载均衡进行平均。通过在细胞内引入酶反馈控制机制，提出了一种新的受生物启发的自适应路由算法。通过对测试数据的仿真，对提出的算法与SPF和ECMP算法进行了评估和比较。仿真结果表明，该算法能够实现时延、负载均衡和容错性能的改善，同时也表明在无标度网络中，只有连接度较高的SPF节点才能被替换为自适应节点来改善时延和负载均衡。

The routing algorithm of SPF (Shortest Path First) is widely distributed in large scale network such as internet. Since this routing algorithm is designed in order to improve throughput of each packet which is sequentially generated at the nodes, it is not suitable for averaging load balance in the network. The enzymic feedback in the cell is the typical and basic control mechanism which can realize homeostasis of the value of every reactant in the metabolic pathway. The purpose of this study is to design an adaptive routing in which the packets generated at the nodes can be sent to the final destinations with avoiding the partial and time-variant congestions in the network, and the load balance in the network can be averaged. We have proposed here a new biologically inspired adaptive routing algorithm by introducing an enzymic feedback control mechanism in the cell. We evaluated and compared the proposed algorithm with SPF and ECMP by using the simulation of test data. The simulation results show that the proposed algorithm can realize improvement of both latency, load balance and fault tolerance, and it also indicates that only SPF nodes with high degree of connection in a scale-free network are replaced to the adaptive nodes for improvement of latency and load balance.