本文選題：Web緩存 + 緩存替換��； 參考：《高技術(shù)通訊》2013年07期

【摘要】：研究了Web內(nèi)容分發(fā)和對(duì)Web服務(wù)性能有重要影響的緩存替換機(jī)制�？紤]到當(dāng)前的緩存替換策略主要采用基于頻度與本地局部性的替換基準(zhǔn),而且通過(guò)對(duì)實(shí)際Web數(shù)據(jù)訪問(wèn)情況的分析發(fā)現(xiàn)訪問(wèn)間隔的變化率對(duì)命中率的影響具有更高的準(zhǔn)確性,提出了一種基于訪問(wèn)密度與大小混合的緩存替換策略。該策略通過(guò)統(tǒng)計(jì)近期緩存對(duì)象的平均訪問(wèn)間隔,結(jié)合該對(duì)象的字節(jié)大小進(jìn)行緩存替換,并分別在固定對(duì)象數(shù)目空間與對(duì)象字節(jié)空間上進(jìn)行對(duì)比實(shí)驗(yàn),實(shí)驗(yàn)結(jié)果表明,該策略比最近最少使用(LRU)和最近頻繁使用(LFU)算法提升3%~5%的命中率,比空間與頻度混合貪心(GDSF)算法提升5%~8%的字節(jié)命中率。
[Abstract]:This paper studies the Web content distribution and cache replacement mechanism which has an important impact on the performance of Web services. Considering that the current cache replacement strategy mainly adopts the replacement benchmark based on frequency and local characteristics, and through the analysis of the actual Web data access, it is found that the impact of the rate of access interval on the hit rate is more accurate. A cache replacement strategy based on the mixing of access density and size is proposed. By counting the average access interval of the recently cached object and combining the byte size of the object, the strategy performs cache replacement, and compares the number of objects with the object byte space. The experimental results show that, Compared with the least recently used LRUs algorithm and the recently frequently used LFU algorithm, the strategy increases the hit ratio by 3% and 8% compared with the space and frequency mixed greedy GDSFs algorithm.
【作者單位】： 哈爾濱工業(yè)大學(xué)網(wǎng)絡(luò)與信息安全研究中心;
【基金】：863計(jì)劃(2011AA010705) 973計(jì)劃(2011CB302605) 國(guó)家自然科學(xué)基金(61173145,60203021)資助項(xiàng)目
【分類號(hào)】：TP393.09

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 石磊;葉海琴;衛(wèi)琳;連衛(wèi)民;;Web緩存命中率與字節(jié)命中率關(guān)系[J];計(jì)算機(jī)工程;2007年13期

相關(guān)碩士學(xué)位論文 前1條

1 唐宗偉;一種基于字節(jié)命中率的緩存替換算法[D];暨南大學(xué);2012年

，

本文編號(hào)：1807970