Research On Grid-based Railway Transport Price Calculation Task Scheduling And Its Application

Grid computing is a new generation of the Internet and a new kind of information infrastructure. It will cause the third information technology revolution after Internet and WEB. It is the first time to use grid computing technology in RFTS (Railway Freight Transport System) around the whole country. Building a railway grid platform can easily solve the problem of distributed, heterogeneous, large-scale resource sharing in RFTS, as well as collaborative computing.This dissertation is summarized from the implementation of the project named "Grid-based Railway Freight Information System". It analyzes the requirement of TPC (Transport Price Calculation) in current RFTS, discusses its development and the problem it faced in load balance and efficiency of task execution under railway grid platform. To solve these problems, we briefly state our researches as follows and summarize this dissertation:1) Put forward a distributed parallel computing model. This model makes full use of the advantage of railway grid to overcome the problem of overload in central computing node and large-scale data remotely transfer, which caused by the traditional method of TPC, distribute the calculation tasks to each bureau node and execute them parallel, minimize the calculation task finished time.2) According to the characteristics of TPC task, this dissertation puts forward a task decomposition method, which is decomposed by the combination of region and time period; furthermore, analyzes the TPC decomposition system architecture and brings in an idea of two level task-pool management mechanisms.3) Considering the aim of calculation task scheduling, the basic service of railway grid and the characteristics of decomposed calculation tasks, this dissertation puts forward a dynamic scheduling Load-Balance algorithm. This algorithm can dynamically adjust each node's load, according to the state information returned from grid and running job monitor service; at last make all the bureau nodes load balance.At last, we will use the research method and computing model in railway grid system project. Through decomposing the calculation task, scheduling and aggregating the results, we can solve the large-scale calculation problem by executing the distributed tasks parallel, and then enhance the efficiency of task execution, and minimize the task finished time. This dissertation is financially supported by National "863" High-Tech Development Plan (2006AA01Z121) Funding.