Composite service provision in mobile ad hoc networks encounters great challenges and its success rate is not satisfactory because the nodes’ locations are dynamic and the nodes maybe unavailable at any time.Composite service is built through the service composition.In mobile ad hoc networks,the factors influencing the success rate of service composition are mainly the number of nodes and the time spent for the composition.The node’s failure probability is proportional to the length of time the node exist in the networks.In order to improve the success rate of service composition,we take several measures.First,we split the service requirement into several segments and cluster the nodes,so that the nodes’ waiting time for service composition can be reduced.Second,we propose a new node model of “one node contains multiple services” in mobile ad hoc networks.Using this type of nodes model,the number of nodes required for service composition can be reduced.These means can increase the success rate of service composition. Composite service provision in mobile ad hoc networks encounters great challenges and its success rate is not satisfactory because the nodes’ locations are dynamic and the nodes maybe unavailable at any time .Composite service is built through the service composition. Mobile ad hoc networks, the factors influencing the success rate of service composition are mainly the number of nodes and the time spent for the composition.The node’s failure probability is proportional to the length of time the node exist in the networks.In order to improve the success rate of service composition , we take several requirements measures. First, we split the service requirement into several segments and cluster the nodes, so that the nodes’ waiting time for service composition can be reduced. Second, we propose a new node model of “one node contains multiple services ”in mobile ad hoc networks. Using this type of nodes model, the number of nodes required for service composition can be reduced. the means can increase the su ccess rate of service composition.