Business Process Execution Based on Map Reduce Architecture

Abstract

Map Reduce is a programming model and software framework for writing applications that rapidly process vast amounts of data in parallel on large clusters of compute nodes. Users define a map function with key/value parameters to generate a set of intermediate key/value pairs and a reduce function that merges all intermediate values associated with the same intermediate key. At the same time, the business process execution of web services has the same context with map reduce. It can be integrated with map reduce which will be the basic infrastructure. Business process is automatically parallelized and executed on a large cluster of web services. This paper takes care of the details of partitioning the input data, definite map function, compare function, reduce function and analysis functions. On the other hand, map reduce functions are also responsible to realize statistical analysis to provide services’ QoS data. We can finally know that this model can improve efficiency and is easy to realize the dynamic replacement of web services based on the generated QoS data.