【摘要】：隨著存儲(chǔ)系統(tǒng)的發(fā)展,為了滿足當(dāng)前高速增長(zhǎng)的信息數(shù)據(jù)量對(duì)存儲(chǔ)的需求,云存儲(chǔ)行業(yè)迅速興起。然而,單云存儲(chǔ)面臨著數(shù)據(jù)保密性、安全性、可用性和廠商鎖定的風(fēng)險(xiǎn)�；诋惢虻姆窍到y(tǒng)糾刪碼-隱私保護(hù)碼(PPC)可以用來(lái)構(gòu)造具有隱私保護(hù)能力的多云存儲(chǔ)系統(tǒng),從而在很大程度上解決上述問(wèn)題。主要針對(duì)PPC編碼算法進(jìn)行優(yōu)化,以提高編碼運(yùn)行性能。通過(guò)設(shè)計(jì)搜索PPC的最優(yōu)調(diào)度來(lái)減少編碼過(guò)程中的異或次數(shù)。由于PPC的編碼/解碼計(jì)算可以表示為生成矩陣(0/1矩陣)和數(shù)據(jù)向量的乘法,直觀上計(jì)算量與生成矩陣中1的數(shù)目成正比,因此通過(guò)對(duì)計(jì)算次序的優(yōu)化調(diào)度可以獲得更好的性能。首先,設(shè)計(jì)并實(shí)現(xiàn)搜索PPC最優(yōu)調(diào)度次序的算法,利用此算法尋找計(jì)算性能最優(yōu)者,可優(yōu)化具有隱私保護(hù)能力的多云存儲(chǔ)系統(tǒng)的性能。其次,在基于最優(yōu)調(diào)度次序的編碼算法的基礎(chǔ)上,利用AVX2技術(shù)的SIMD并行優(yōu)化來(lái)提高編碼過(guò)程中的每次異或的性能。實(shí)驗(yàn)表明,基于最優(yōu)調(diào)度的編碼性能提高了34.8%,進(jìn)行SIMD并行優(yōu)化后進(jìn)一步提高了107.1%。
[Abstract]:With the development of storage system, cloud storage industry is rising rapidly in order to meet the demand of high speed information data volume. However, single cloud storage faces risks of data confidentiality, security, availability, and vendor locking. Non-system erasure code based on XOR-privacy protection code (PPC) can be used to construct a multi-cloud storage system with privacy protection ability to solve the above problem to a large extent. The PPC coding algorithm is optimized to improve the performance of the coding. In order to reduce the number of XOR in the coding process, the optimal scheduling of searching PPC is designed. Because the encoding / decoding calculation of PPC can be expressed as the multiplication of the generating matrix (0 / 1 matrix) and the data vector, the computation amount is directly proportional to the number of 1 in the generated matrix. Therefore, better performance can be obtained by optimizing the order of calculation. Firstly, an algorithm to search for the optimal scheduling order of PPC is designed and implemented. The algorithm can be used to find the optimal computing performance, which can optimize the performance of the multi-cloud storage system with privacy protection. Secondly, on the basis of the coding algorithm based on the optimal scheduling order, SIMD parallel optimization based on AVX2 technology is used to improve the performance of each XOR in the coding process. Experiments show that the coding performance based on optimal scheduling is improved by 34.8. after parallel optimization of SIMD, it is further improved by 107.1.
【作者單位】： 南開(kāi)大學(xué)計(jì)算機(jī)與控制工程學(xué)院;
【分類號(hào)】：TP309;TP333

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 龔慶悅;;計(jì)算機(jī)和網(wǎng)絡(luò)之隱私問(wèn)題探析[J];醫(yī)學(xué)信息學(xué)雜志;2009年08期

2 康琳;李秀華;王衛(wèi)東;;參與感知世界的激勵(lì)機(jī)制研究[J];單片機(jī)與嵌入式系統(tǒng)應(yīng)用;2013年08期

3 ;[J];;年期

相關(guān)重要報(bào)紙文章 前3條

1 中國(guó)科學(xué)院信息安全國(guó)家重點(diǎn)實(shí)驗(yàn)室 左曉棟;P3P技術(shù)，網(wǎng)絡(luò)隱私的保護(hù)神[N];電腦報(bào);2001年

2 ;RFID蠢蠢欲動(dòng)[N];網(wǎng)絡(luò)世界;2003年

3 陳翔 吳鋒;誰(shuí)偷窺了你的隱私[N];中國(guó)計(jì)算機(jī)報(bào);2006年

相關(guān)碩士學(xué)位論文 前3條

1 姚川;基于分布式云存儲(chǔ)的隱私保護(hù)協(xié)議研究[D];福建師范大學(xué);2015年

2 楊亭亭;面向云存儲(chǔ)的訪問(wèn)控制方法研究[D];華北電力大學(xué)(北京);2016年

3 周靜嵐;云存儲(chǔ)數(shù)據(jù)隱私保護(hù)機(jī)制的研究[D];南京郵電大學(xué);2014年

，

本文編號(hào)：2375196