数据库高负载下的数据均衡策略研究与仿真  

Research and Simulation of Data Equilibrium Strategy under High Database Loading

作　　者：王爱新[1] 李强[1] 王春山[1] 

机构地区：[1]河北农业大学信息科学与技术学院,河北保定071001

出　　处：《计算机仿真》2016年第3期327-330,共4页Computer Simulation

摘　　要：在对数据库高负载下的数据均衡策略优化的研究中,由于高负荷数据库中的数据流存在负载不均的问题,数据传输速度慢。传统的调度方法都是采用溢出的思维,将过高数据均衡到临近信道,选择过程不是最优,效果不好。提出改进多蚁群算法的数据库高负载下的数据均衡方法,先利用ALAD算法在数据库中服务器上计算出服务器的总体响应延迟数据,并将其作为数据库高负载的主要依据,同时计算出服务器请求处理成功率和连续运行时间的最大值,将其作为数据库高负载的次要原因,计算出数据库中各服务器的综合权重,并融合于多蚁群算法,利用多蚁群间信息素的相互作用和动态更新,将代表高负载的蚂蚁均衡分配到负载较轻的服务器上,有效的实现了数据库高负载下的数据均衡策略。实验结果证明,改进多蚁群算法的数据库高负载下的数据均衡方法均衡效果好,并适应性强。In the paper, a data equilibrium approach was proposed based on improved ant colony algorithm under high database loading. In this method, ALAD algorithm was used to calculate the overall response delay data of the server in the database, which was taken as the main basis of high database loading. At the same time, the request processing success rate of server and the maximum value of continuous running time were calculated, which was taken as the secondary causes of high database loading. The comprehensive weight of each server in the database was calcu- lated and fused to multiple ant colony algorithm. Using the interaction and dynamic update of pheromone among mul- tiple ant colony, the ants representing high loading were assigned evenly to the server with lighter loading, so as to effectively implement the data equilibrium strategy under high database loading. Experimental results prove that the equilibrium effect of the data equilibrium approach is good, and the adaptability is strong.

关 键 词：负载均衡 蚁群算法 数据库高负载 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]