The success of a service oriented computing significantly depends on its reliability and availability. To achieve better reliability and availability, any fault of the service oriented computing has to be properly handled. Low performance on handling the service fault becomes the most proliferated challenge on fault handling approaches. In this paper, a priority based fault handling strategy selection approach for fault recovery of SOA (Service Oriented Architecture) is proposed using priority selector and fault handler. This approach starts from fault detection method and select the first priority level strategies promptly and if fault could not be handled by first highest level then fault handler selects the second level or intermediate priority level for average performance. As a final in the worst case, least level strategies are applied to resolve the faulty situation. Through experiment, the correctness of the proposed algorithm and the efficiency of the approach are proved. This approach results better performance and high rate of fault repairing.

Congestion control approaches, source based approach and router based approach have their own limitations. In source based approach, it is difficult to get correct location of congestion and without proper admission control; we cannot effectively manage the congestion problem. Thus both the approaches have to work in coordination for effective congestion control. In this context, an interaction study plays an important role to verify how a TCP implemented at source end works with Active Queue Management at router end. In this paper, we analyzed the performance of different high speed TCP variants at the source end with some recent AQM approaches: CoDel and sfqCoDel. The main objective of this work is to obtain the interaction patterns of different high speed TCP variants like: HTCP, Compound, HSTCP, Scalable and Cubic with recently proposed AQMs: CoDel and sfqCoDel. Simulation results show that that if we want to achieve a better throughput, minimum delay and improved fairness simultaneously, Cubic-sfqCoDel may be a good choice of TCP-AQM combinations for high speed networks.

This paper presents some observations on Dependency Analysis of Service Oriented Architecture (SOA) based systems. In general, dependency analysis is based on the internal properties of artifacts (objects/components/services) and inter-relationship between the artifacts in the system. In order to make a dependency analysis for SOA based systems, one have to consider the special features of SOA that make them different with other approaches. This paper surveys the previous works taken on dependency analysis of service oriented systems. The present work provides insights about definitions related to service dependency, the modeling and analysis techniques of service dependency analysis, failure results to service dependence and some research challenges of the topic.The contribution of this paper is for novice researchers working on this topic as they can get an overview of dependency analysis of SOA based systems for their further research.

This paper presents a study of Router based Congestion control approaches in wired network. As network is considered as a distributed system, any problem arises in such a system requires a distributed solution. Thus for good congestion control in the network we also need a solution distributed at source as well as router ends. The purpose of this study is to review the router based Congestion control research for wired network and characterize the different approaches to Congestion control design, by considering their advantages and limitations.