采用语言信息决策理论的电力负荷密度预测法

发布时间：2018-05-06 20:28

  本文选题：城市小区负荷密度预测 + 语言信息决策理论　； 参考：《长沙理工大学》2014年硕士论文

【摘要】：随着我国城镇化事业的不断发展,对城市配电网的要求也越来越高,如何建设出智能、可靠的城市供电系统,正日益成为电力系统规划关注的焦点之一。作为城市配网规划的基础领域,城市小区负荷密度预测在智能电网的建设中扮演着极其重要的角色,是配电网发展的基础和前提。当前已有大量的城市小区负荷密度预测方法,每种方法都有各自的优势和特点,然而不论哪种方法其所依赖的基础都是需要收集大量的样本数据。目前由于我国正处于发展阶段,许多地区的信息系统还不完善,因此在实际应用中有时难以收集到完整的样本数据以满足预测的需求。针对这一问题,依据城市自身特点和原始数据采集的结果,提出一种采用语言信息决策理论的电力负荷密度预测法。样本数量的完整性将决定最终的预测精度,因此在无法收集实际数据的前提下通过运用专家的知识与经验合理地对城市小区的各类指标进行语言评判能够有效的弥补数据收集残缺的问题。在预测过程中,为使预测结果更加可信,探究了在专家对城市小区的语言评判过程中,建立城市小区负荷密度评判体系、消除专家语言信息的混合性、集成专家语言信息以及如何协调专家评价冲突的问题,并从考虑城市小区综合评分、专家语言信息同典型预测模型相结合、采用比较冲突度交互式协调专家信息这三个方面讨论了语言信息决策理论在城市小区负荷密度预测中的应用。以若干城市小区为样本实例,检验在不同预测方法下,语言信息决策理论在城市小区负荷密度预测中的应用效果,结果表明由于采用比较冲突度交互式协调专家信息的预测方法,能够使专家达成更为统一的评价结果,因此利用该方法进行的城市小区负荷密度预测其预测精度最佳。采用语言信息决策理论的城市小区负荷密度预测法,能够在实际数据收集困难的前提下,作为一种有效的辅助补充手段引入至小区负荷密度的预测中,具有很强的工程实际意义,其预测结果可为城市配电网规划提供重要的辅助依据。
[Abstract]:With the continuous development of urbanization in China, the demand for urban distribution network is becoming higher and higher. How to build an intelligent and reliable urban power supply system is becoming one of the focus of power system planning. As the basic field of urban distribution network planning, urban residential area load density forecasting plays an extremely important role in the construction of smart grid, is the basis and premise of distribution network development. At present, there are a large number of load density forecasting methods for urban residential areas, each method has its own advantages and characteristics. However, no matter which method is based on the need to collect a large number of sample data. At present, because our country is in the stage of development and the information system in many areas is not perfect, it is sometimes difficult to collect complete sample data in practical application to meet the demand of forecast. In order to solve this problem, according to the characteristics of the city and the results of the original data collection, a power load density forecasting method based on the linguistic information decision theory is proposed. The completeness of the sample size will determine the final prediction accuracy, Therefore, under the premise that the actual data can not be collected, the problem of incomplete data collection can be effectively remedied by using the knowledge and experience of experts to reasonably judge all kinds of indexes in urban residential areas. In the process of forecasting, in order to make the prediction result more credible, this paper probes into the establishment of the evaluation system of load density of urban residential area in the process of expert language evaluation to eliminate the mixture of expert language information. Integrating expert language information and how to coordinate expert evaluation conflict, and considering the comprehensive score of urban residential area, the expert language information is combined with typical prediction model. This paper discusses the application of language information decision theory in urban residential area load density forecasting by using the three aspects of comparative conflict degree interactive coordinated expert information. Taking several urban districts as sample examples, this paper tests the application effect of language information decision theory in forecasting load density of urban residential areas under different forecasting methods. The results show that the prediction method of comparative conflict degree and interactive coordination of expert information can make the experts reach a more unified evaluation result, so the forecasting accuracy of load density prediction of urban residential area is the best. The load density forecasting method based on linguistic information decision theory can be introduced into the prediction of cell load density as an effective supplementary means on the premise of difficult data collection. It is of great practical significance, and the prediction results can provide an important auxiliary basis for urban distribution network planning.
【学位授予单位】：长沙理工大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：TM715
，

本文编号：1853756