基于改进权重的D-S证据理论的动态负载平衡算法
|
摘要
针对大型网络游戏中易出现的服务器集群负载不均衡的问题,提出基于改进权重的D-S(Dempster和Shafer)证据理论的负载平衡判别策略。首先,根据D-S证据理论,将影响服务器性能的多因素作为判据,利用历史数据与阈值大小的比较规则计算动态权重,再依据动态权重与原始信度的关系建立基本信任函数;然后,计算不同判据对应结果的信任函数,使用证据合成规则作深层融合;最后分析合成结果,最终推断服务器是否超载。模拟实验结果表明,与基于负反馈机制的动态均衡算法相比,所提算法的准确率更高,更符合真实情况;且所提算法的运行时间明显少于基于负反馈机制的动态均衡算法以及加权循环算法。实验结果表明,新算法有效缩短了运行判断的延迟,能够根据历史参数对当前服务器负载情况快速作出推断,且决策结果可信度高,更符合实际情况。
To solve the problem of load unbalance among servers in large network games, a load balancing strategy based on Dempster/Shafer( D-S) evidence theory was proposed. The multiple factors which influenced the servers were taken as parameters. Firstly, according to D-S evidence theory, the multiple factors affecting the performance of the server were used as the criteria, the dynamic weight was computed by comparing the historic data with the threshold, and then the basic belief function was set up according to the relationship between the dynamic weight and original reliability. After that, the belief functions corresponding to different criteria was calculated, and the calculation results were merged by the rules of evidence synthesis. Lastly, whether the server was overloaded or not was evaluated by the analysis of aforementioned results. Simulation results show that compared with the dynamic load balancing algorithm based on negative feedback, the proposed algorithm is more accurate and more realistic; the running time of the proposed algorithm is obviously less than that of the dynamic load balancing algorithm based on negative feedback and the weighted loop algorithm. Analysis indicates that the proposed algorithm can effectively reduce the delay of running judgement and make a quick deduction for the server load according to the historical parameters, and the dicision results are more reliable and more consistent with the actual situation.
To solve the problem of load unbalance among servers in large network games, a load balancing strategy based on Dempster/Shafer( D-S) evidence theory was proposed. The multiple factors which influenced the servers were taken as parameters. Firstly, according to D-S evidence theory, the multiple factors affecting the performance of the server were used as the criteria, the dynamic weight was computed by comparing the historic data with the threshold, and then the basic belief function was set up according to the relationship between the dynamic weight and original reliability. After that, the belief functions corresponding to different criteria was calculated, and the calculation results were merged by the rules of evidence synthesis. Lastly, whether the server was overloaded or not was evaluated by the analysis of aforementioned results. Simulation results show that compared with the dynamic load balancing algorithm based on negative feedback, the proposed algorithm is more accurate and more realistic; the running time of the proposed algorithm is obviously less than that of the dynamic load balancing algorithm based on negative feedback and the weighted loop algorithm. Analysis indicates that the proposed algorithm can effectively reduce the delay of running judgement and make a quick deduction for the server load according to the historical parameters, and the dicision results are more reliable and more consistent with the actual situation.
引文
[1]罗拥军,李晓乐,孙如祥.负载均衡算法综述[J].科技情报开发与经济,2008,18(23):134-136.(LUO Y J,LI X L,SUN RX.A review of load balancing algorithm[J].Sci-Tech Information Development&Economy,2008,18(23):134-136.)
[2]刘玉艳,沈明玉.LVS负载均衡技术在网络服务中的应用[J].合肥工业大学学报(自然科学版),2007,30(12):1592-1595.(LIU Y Y,SHEN M Y.Research on the LVS load balance in Web services[J].Journal of Hefei University of Technology(Natural Science Edition),2007,30(12):1592-1595.)
[3]朱辉,蔡洪斌,何明耘,等.MMOG中的一种动态负载共享算法[J].计算机应用研究,2007,27(7):249-251.(ZHU H,CAIH B,HE M Y,et,al.Dynamic load sharing algorithm in MMOG[J].Application Research of Computers,2007,27(7):249-251.)
[4]WANG T T,LIU Z B,CHEN Y,et al.Load balancing task scheduling based on genetic algorithm in cloud computing[C]//Proceedings of the 2014 IEEE 12th International Conference on Dependable,Autonomic and Secure Computing.Piscataway,NJ:IEEE,2014:146-152.
[5]ZHANG X Y,YU Y Q,CHEN B X.An entension-based dynamic load balancing model of heterogeneous sever cluster[C]//GRC2007:Proceedings of the 2007 IEEE International Conference on Granular Computing.Piscataway,NJ:IEEE,2007:675-679.
[6]TEO Y M,AYANI R.Comparison of load balancing strategies on cluster-based Web servers[J].Simulation,2001,77(5/6):185-195.
[7]李坤,王百杰.服务器集群负载均衡技术研究及算法比较[J].计算机与现代化,2009(8):7-10,15.(LI K,WANG B J.Research on load balancing of web-server system and comparison of algorithms[J].Computer and Modernization,2009(8):7-10,15.)
[8]PILAVARE M S,DESAI A.A novel approach towards improving performance of load balancing using genetic algorithm in cloud computing[C]//Proceedings of the 2015 IEEE International Conference on Innovations in Information,Embedded and Communication Systems.Piscataway,NJ:IEEE,2015:1-4.
[9]SUN D H,ZHU Q.Comparison and improvement of load balance scheduling algorithm based on cluster technology[C]//Proceedings of the 2014 International Conference on Electrical and Electronics Engineering.Miami:[s.n.],2014,92:67-74.
[10]BOSQUE J L,TOHARIA P,ROBLES O D,et al.A load index and load balancing algorithm for heterogeneous clusters[J].The Journal of Supercomputing,2013,65(3):1104-1113.
[11]崔智军,王庆春.基于D-S证据理论的多传感器数据融合[J].现代电子技术,2011,34(12):201-204.(CUI Z J,WANG Q C.Multisensor data fusion based on D-S evidence theory[J].Modern Electronic Technology,2011,34(12):201-204.)
[12]郑祺.基于混合策略的集群负载均衡算法的研究[J].浙江科技学院学报,2013,25(5):361-365.(ZHENG Q.Research on combined load balancing algorithm in cluster[J].Journal of Zhejiang University of Science and Technology,2013,25(5):361-363.)
[2]刘玉艳,沈明玉.LVS负载均衡技术在网络服务中的应用[J].合肥工业大学学报(自然科学版),2007,30(12):1592-1595.(LIU Y Y,SHEN M Y.Research on the LVS load balance in Web services[J].Journal of Hefei University of Technology(Natural Science Edition),2007,30(12):1592-1595.)
[3]朱辉,蔡洪斌,何明耘,等.MMOG中的一种动态负载共享算法[J].计算机应用研究,2007,27(7):249-251.(ZHU H,CAIH B,HE M Y,et,al.Dynamic load sharing algorithm in MMOG[J].Application Research of Computers,2007,27(7):249-251.)
[4]WANG T T,LIU Z B,CHEN Y,et al.Load balancing task scheduling based on genetic algorithm in cloud computing[C]//Proceedings of the 2014 IEEE 12th International Conference on Dependable,Autonomic and Secure Computing.Piscataway,NJ:IEEE,2014:146-152.
[5]ZHANG X Y,YU Y Q,CHEN B X.An entension-based dynamic load balancing model of heterogeneous sever cluster[C]//GRC2007:Proceedings of the 2007 IEEE International Conference on Granular Computing.Piscataway,NJ:IEEE,2007:675-679.
[6]TEO Y M,AYANI R.Comparison of load balancing strategies on cluster-based Web servers[J].Simulation,2001,77(5/6):185-195.
[7]李坤,王百杰.服务器集群负载均衡技术研究及算法比较[J].计算机与现代化,2009(8):7-10,15.(LI K,WANG B J.Research on load balancing of web-server system and comparison of algorithms[J].Computer and Modernization,2009(8):7-10,15.)
[8]PILAVARE M S,DESAI A.A novel approach towards improving performance of load balancing using genetic algorithm in cloud computing[C]//Proceedings of the 2015 IEEE International Conference on Innovations in Information,Embedded and Communication Systems.Piscataway,NJ:IEEE,2015:1-4.
[9]SUN D H,ZHU Q.Comparison and improvement of load balance scheduling algorithm based on cluster technology[C]//Proceedings of the 2014 International Conference on Electrical and Electronics Engineering.Miami:[s.n.],2014,92:67-74.
[10]BOSQUE J L,TOHARIA P,ROBLES O D,et al.A load index and load balancing algorithm for heterogeneous clusters[J].The Journal of Supercomputing,2013,65(3):1104-1113.
[11]崔智军,王庆春.基于D-S证据理论的多传感器数据融合[J].现代电子技术,2011,34(12):201-204.(CUI Z J,WANG Q C.Multisensor data fusion based on D-S evidence theory[J].Modern Electronic Technology,2011,34(12):201-204.)
[12]郑祺.基于混合策略的集群负载均衡算法的研究[J].浙江科技学院学报,2013,25(5):361-365.(ZHENG Q.Research on combined load balancing algorithm in cluster[J].Journal of Zhejiang University of Science and Technology,2013,25(5):361-363.)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |