基因表达式编程在电力负荷预测中的应用

发布时间：2018-01-15 04:30

本文关键词：基因表达式编程在电力负荷预测中的应用　出处：《西安建筑科技大学》2017年硕士论文　论文类型：学位论文

【摘要】：基因表达式编程算法(Gene Expression Programming,GEP)是在继承并发展遗传算法和遗传编程优点的基础上,借鉴生物遗传的基因表达规律,所提出的搜索和知识发现的新技术。该算法因其更强的解决问题的能力、易于进行遗传操作以及独特的编码方式等优点备受国内外研究学者关注,现已广泛应用于函数挖掘、预测、关联规则和分类聚类等研究领域中的典型应用,如时间序列和数据流预测模型、灾情分析、多层关联规则挖掘、特征自动提取、挖掘递归函数等。本文主要的研究工作是改进了标准GEP算法,将改进后的算法应用于电力负荷预测领域,构建了基于GEP算法的电力负荷预测模型,在此基础上,设计了基于基因表达式编程的电力负荷预测的原型系统。本文的具体工作主要有以下几点:(1)依据小生境思想,本文对标准GEP算法进行改进得到一种基于远缘融合的小生境技术的基因表达式编程算法(OFN-GEP)。(2)本文将OFN-GEP算法应用于电力负荷预测中,对咸阳市居民用电负荷量进行建模预测,构建了基于OFN-GEP算法的电力负荷预测模型,将OFN-GEP算法与最新文献中的类似改进算法进行了比较,验证了基于OFN-GEP算法的电力负荷预测模型的优越性和较高的预测精度。(3)本文设计了电力负荷预测原型系统,为电厂调度人员提供科学有效的参考依据。本文所实现的基于基因表达式编程算法的电力负荷预测系统已经在咸阳市某电厂发挥了实际作用,为电厂的调度人员提供一定的参考价值。
[Abstract]:Gene expression programming algorithm (Gene Expression Programming, GEP) is based on the inheritance and development of the advantages of genetic algorithm and genetic programming, genetic reference gene expression pattern, the proposed new technology search and knowledge discovery. This algorithm because of its stronger ability to solve problems, easy operation and unique genetic encoding the way the advantages have attracted much attention of researchers at home and abroad, it has been widely applied in function mining, prediction, typical application of association rules and classification in the field of research, such as the prediction model of time series and data flow disaster analysis, association rule mining, automatic feature extraction, mining recursive function. The main work of this paper is to improve the standard GEP algorithm, the improved algorithm is applied to the field of power load forecasting, power load prediction model is built based on the GEP algorithm, on the basis of On the design of the prototype system of electric power load forecasting based on gene expression programming. The main work of this paper are as follows: (1) based on the niche theory, the standard GEP algorithm is improved by an expression programming algorithm and niche technique of distant fusion genes based on (OFN-GEP) (2). The OFN-GEP algorithm is applied to power load forecasting, the residents of Xianyang city electric load modeling and forecasting, construction of power load forecasting model based on OFN-GEP algorithm, improved OFN-GEP algorithm will be similar with the latest literature of the algorithm were compared to verify the prediction accuracy and superiority of high power load OFN-GEP algorithm based on the prediction model. (3) the design of electric power load forecasting system, to provide a scientific reference basis for power dispatch personnel. Gene expression programming algorithm based on the realization of the The power load forecasting system of the method has played a practical role in a power plant in Xianyang and provides a certain reference value for the dispatchers of the power plant.

【学位授予单位】：西安建筑科技大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP18;TM715

【参考文献】