摘要
为解决中央处理器(Central Processing Unit, CPU)性能分析所面临的分析指标复杂、分析过程不具有可解释性、分析结果不可追溯的问题,提出了一种融合ER(Evidence Reasoning)和分层BRB(Belief Rule Base)的CPU性能分析模型.首先,利用ER算法从不同层面对处理器影响因素进行指标评估,其次,通过分层BRB实现对CPU性能的综合分析,最后,采用鲸鱼优化算法(Whale Optimization Algorithm, WOA)对模型参数优化.通过UCI数据库(University of California Irvine, UCI)计算机硬件数据集验证了模型的有效性.整个分析模型建立在ER算法上,保证了模型推理的可解释性,而分层BRB方法解决了传统BRB的组合规则爆炸问题,同时结合优化算法有效的提高模型的准确度.
In order to solve the problems of complex analysis indicators,uninterpretable analysis process,and untraceable analysis results faced by the performance analysis of the Central Processing Unit(CPU),a fusion ER(Evidence Reasoning)and hierarchical BRB(Belief Rule Base)CPU performance analysis model is proposed.First,the ER algorithm is used to evaluate the factors affecting the processor from different levels.Second,the comprehensive analysis of the CPU performance is realized through the hierarchical BRB.Finally,the Whale Optimization Algorithm(WOA)is used to optimize the model parameters.The validity of the model is verified by the UCI database(University of California Irvine,UCI)computer hardware dataset.The whole analysis model is built on the ER algorithm,which ensures the interpretability of the model reasoning,while the hierarchical BRB method solves the problem of the combination rule explosion of the traditional BRB,and at the same time combines the optimization algorithm to effectively improve the accuracy of the model.
作者
陈伟伟
曲媛媛
贺维
朱海龙
张广玲
魏洪伟
CHEN Wei-wei;QU Yuan-yuan;HE Wei;ZHU Hai-long;ZHANG Guang-ling;WEI Hong-wei(College of Computer Science and Information Engineering,Harbin Normal University,Harbin 150500,China;Heilongjiang Agricultural Engineering Vocational College,Harbin 150503,China;Rocket Force University of Engineering,Xi′an 710025,China)
出处
《小型微型计算机系统》
CSCD
北大核心
2023年第12期2872-2880,共9页
Journal of Chinese Computer Systems
基金
中国博士后科学基金项目(2020M683736)资助
黑龙江省自然科学基金项目(LH2021F038)资助
哈尔滨师范大学研究生学术创新项目(HSDSSCX2022-17,HSDSSCX2022-18,HSDSSCX2022-19)资助
关键词
性能分析
ER
指标评估
BRB
鲸鱼优化算法
performance analysis
evidence reasoning
indicator evaluation
confidence rule base
whale optimization algorithm
