【摘要】：近年來，，集群系統(tǒng)成為高性能計(jì)算的主流平臺(tái)，在此系統(tǒng)上進(jìn)行并行計(jì)算蘊(yùn)涵著巨大的計(jì)算潛力，調(diào)度是挖掘這些計(jì)算能力的關(guān)鍵技術(shù)。在并行系統(tǒng)中，應(yīng)用任務(wù)被劃分為多個(gè)子任務(wù)，有向無環(huán)圖（DAG）因能反映并行系統(tǒng)中各子任務(wù)以及這些任務(wù)間的依賴關(guān)系而被廣泛采用，本文研究基于DAG圖的集群系統(tǒng)任務(wù)調(diào)度問題，具體如下： （1）對(duì)于同構(gòu)集群下的調(diào)度問題，采用表調(diào)度技術(shù)解決。分析現(xiàn)有表調(diào)度算法的不足，在此基礎(chǔ)上提出基于動(dòng)態(tài)關(guān)鍵路徑的全局調(diào)度算法GDCP。該算法在調(diào)度任務(wù)選擇階段準(zhǔn)確地賦予任務(wù)優(yōu)先級(jí)，并結(jié)合全局搜索策略選擇處理機(jī)。實(shí)驗(yàn)及數(shù)據(jù)分析表明，該算法有效地提高了調(diào)度性能。 （2）對(duì)于異構(gòu)集群下的調(diào)度問題，采用遺傳調(diào)度算法解決。針對(duì)傳統(tǒng)遺傳調(diào)度算法在種群初始化方式上的缺陷，提出異構(gòu)系統(tǒng)中改進(jìn)的遺傳調(diào)度算法ISGA。該算法利用任務(wù)的屬性值來構(gòu)造染色體，得到優(yōu)質(zhì)的初始種群。實(shí)驗(yàn)及數(shù)據(jù)分析表明，該算法可以獲得較好的調(diào)度質(zhì)量。 （3）將本文研究成果應(yīng)用于與國家電網(wǎng)電力科學(xué)研究院合作的項(xiàng)目“實(shí)時(shí)監(jiān)控系統(tǒng)的并行處理”中，以驗(yàn)證它們?cè)趯?shí)際計(jì)算環(huán)境中是有效的。
[Abstract]:In recent years, cluster system has become the mainstream platform of high performance computing. Parallel computing on this system has great computing potential. Scheduling is the key technology to mine these computing capabilities. In parallel systems, application tasks are divided into subtasks, and directed acyclic graphs (DAG) are widely used because they can reflect subtasks and their dependencies in parallel systems. In this paper, the task scheduling problem of cluster system based on DAG graph is studied. The details are as follows: (1) Table scheduling technology is used to solve the scheduling problem in isomorphic cluster. Based on the analysis of the shortcomings of the existing table scheduling algorithms, a global scheduling algorithm based on dynamic critical paths (GDCPs) is proposed. The algorithm accurately assigns priority to the task in the scheduling task selection phase and combines with the global search strategy selection processor. Experimental results and data analysis show that the proposed algorithm can effectively improve the scheduling performance. (2) genetic algorithm is used to solve the scheduling problem in heterogeneous clusters. Aiming at the defects of the traditional genetic scheduling algorithm in population initialization, an improved genetic scheduling algorithm ISGA in heterogeneous systems is proposed. The algorithm uses the attribute value of the task to construct the chromosome, and obtains the high quality initial population. Experiments and data analysis show that the algorithm can achieve better dispatching quality. (3) the research results of this paper are applied to the parallel processing of real-time monitoring system, which is a cooperative project with the State Research Institute of Electric Power Sciences of State Grid. To verify that they are valid in a real computing environment.
【學(xué)位授予單位】：南京航空航天大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TP338

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 舒昌奇,蘆偉;電力系統(tǒng)監(jiān)控的幾種類型對(duì)比[J];甘肅科技;2004年08期

2 鐘求喜,謝濤,陳火旺;任務(wù)分配與調(diào)度的共同進(jìn)化方法[J];計(jì)算機(jī)學(xué)報(bào);2001年03期

3 石威,鄭緯民;相關(guān)任務(wù)圖的均衡動(dòng)態(tài)關(guān)鍵路徑調(diào)度算法[J];計(jì)算機(jī)學(xué)報(bào);2001年09期

4 周雙娥,袁由光,熊兵周,歐中紅;基于任務(wù)復(fù)制的處理器預(yù)分配算法[J];計(jì)算機(jī)學(xué)報(bào);2004年02期

5 陸鑫達(dá),鄭飛,陳楚詢;異構(gòu)計(jì)算系統(tǒng)的任務(wù)調(diào)度算法SMT-GA[J];小型微型計(jì)算機(jī)系統(tǒng);1999年04期

本文編號(hào)：2198893