【摘要】：為提高云存儲(chǔ)環(huán)境下內(nèi)容分發(fā)網(wǎng)絡(luò)(CDN)的分發(fā)效率,提出一種基于Stackelberg博弈的緩存資源分配與定價(jià)算法。將Web服務(wù)器和云CDN代理商建模成一個(gè)多主多從的Stackelberg博弈模型,并構(gòu)建其各自的效用函數(shù)。證明在代理商價(jià)格確定的情況下存在Web服務(wù)器納什均衡點(diǎn),利用一種分布式迭代算法求解博弈模型,得到最優(yōu)定價(jià)與該定價(jià)下的最優(yōu)緩存分配結(jié)果。仿真結(jié)果表明,該算法可保證Web服務(wù)器緩存需求在代理商之間的高效分配,與用戶服務(wù)質(zhì)量優(yōu)先算法相比,可使Web服務(wù)器獲得更高的單位成本效益。
[Abstract]:In order to improve the efficiency of content distribution network (CDN) in cloud storage environment, a buffer resource allocation and pricing algorithm based on Stackelberg game is proposed. Web servers and cloud CDN agents are modeled as a multi-principal multi-slave Stackelberg game model and their respective utility functions are constructed. It is proved that there exists a Web server Nash equilibrium point when the agent price is determined. A distributed iterative algorithm is used to solve the game model, and the optimal pricing and the optimal cache allocation under this pricing are obtained. The simulation results show that the proposed algorithm can ensure the efficient allocation of cache requirements among agents, and it can achieve higher unit cost benefit than the QoS priority algorithm.
【作者單位】： 北京信息科技大學(xué)信息與通信工程學(xué)院;
【基金】：國家自然科學(xué)基金“基于資源標(biāo)簽交換的無線網(wǎng)絡(luò)端到端能效管理策略研究”(61271198) 北京市教委科技計(jì)劃重點(diǎn)項(xiàng)目“分層合作博弈的端到端綠色網(wǎng)絡(luò)體系與關(guān)鍵技術(shù)研究”(KZ201511232036)
【分類號(hào)】：TP393.0
，

本文編號(hào)：2137897