A bio-inspired method of e-service emergence based on the bio-network

An emergence modeling approach is proposed to the study of e-service composition, which is inspired by the characteristics of emergence and self-evolution in biological neuroendocrine and immune system. E-services are represented by autonomous bio-entities (mobile agents with biological operation), each bio-entity is described as a Mealy state machine. The e-service composition was achieved by the evolution of the bioentities. The characteristic coding, which included relation matrix coding and QoS matrix coding, was applied to the negotiation of the bio-entities, the optimization of the e-service composition is translated into constraints optimization problem. The simulation results show that the approach can significantly improve the e-service composition performance. It adapts well to the changes of dynamic environments.