To improve the performance and robustness in service discovery, a self-organizing mechanism for service alliances of Service Providers (SPs) is proposed in this paper. According to the similarity of service content, a...To improve the performance and robustness in service discovery, a self-organizing mechanism for service alliances of Service Providers (SPs) is proposed in this paper. According to the similarity of service content, an SP publishes its services in a partition of SPs to construct connections between highly similar SPs. These SPs constitute a self-organized distributed environment. A self-organizing protocol is designed to ensure the correctness of the construction of the alliances. The protocol consists of four stages - initiating stage, developing stage, developed stage and degradation stage. The experimental results demonstrate that this protocol ensures the self-property. The visualization of alliance developing stages illustrates that sub-alliances are sp lit in balance and self-connected. Compared with the Random Walker algorithm, the time cost and the number of forwarded messages in alliance-based mechanism is lower in service discovery. On three typical topologies (Grid, Random-Graph, Power-Law), the success rate of service discovery is much higher, which shows that self-organized alliances are helpful to enhance the discovery performance.展开更多
基金This paper was supported by the Natural Science Foundation of China under Grants No. 61170053, No. 61100205 the Nat- ural Science Foundation of Beijing under Grant No. 4112027 the Natural Science Foundation of Hebei under Grant No. F2009000929. The authors would like to thank the anony- mous reviewers for their helpful comments from which the preparation for this version of the paper has benefited.
文摘To improve the performance and robustness in service discovery, a self-organizing mechanism for service alliances of Service Providers (SPs) is proposed in this paper. According to the similarity of service content, an SP publishes its services in a partition of SPs to construct connections between highly similar SPs. These SPs constitute a self-organized distributed environment. A self-organizing protocol is designed to ensure the correctness of the construction of the alliances. The protocol consists of four stages - initiating stage, developing stage, developed stage and degradation stage. The experimental results demonstrate that this protocol ensures the self-property. The visualization of alliance developing stages illustrates that sub-alliances are sp lit in balance and self-connected. Compared with the Random Walker algorithm, the time cost and the number of forwarded messages in alliance-based mechanism is lower in service discovery. On three typical topologies (Grid, Random-Graph, Power-Law), the success rate of service discovery is much higher, which shows that self-organized alliances are helpful to enhance the discovery performance.
