【作者】 于海燕；

【导师】 张凤玲；

【作者基本信息】 天津大学 ， 运筹学与控制论， 2007， 硕士

【摘要】 电力负荷预测水平己成为衡量电力系统运行管理现代化的标志之一,电力系统的正确调度、规划和运行都离不开电力负荷预测,准确的负荷预测不仅对电力系统的安全、可靠、经济运行起着重要作用,同时也是潜在节约能源的方法。尤其是准确的短期负荷预测更具有重要的意义。负荷预测的影响因素较多,不只由负荷本身的历史数据决定,还要受众多非负荷因素的影响。本文分析了电力系统负荷预测的意义和方法,介绍了电力短期负荷预测的特点及研究现状。阐述了人工神经网络和模糊理论的相关概念和原理,分析了它们各自的优缺点以及它们之间的互补性。介绍了模糊神经网络的类型和训练算法。最后,本文针对电力负荷的特点,综合考虑温度、日期类型等对日最大负荷的影响,将模糊神经网络模型应用于电力系统的短期负荷预测中,详细介绍了预测模型建立的全过程。通过对EUNITE网络提供的实际数据进行详细分析,确定了影响日最大负荷的相关因素,进而选择了合适的模糊输入建立相应的模糊神经网络预测模型,取得了较为理想的预测结果。结论充分证明了模糊神经网络在短期电力负荷预测方面的巨大潜力。同时也表明,对电力负荷的影响因素的研究仍具有重要的现实意义。更多还原

【Abstract】 The level of load forecasting is one of the measures of modernization of power system management. It is important for making plans, distributing electricity. It can help saving the energy source. So load forecasting, especially accurate short-term load forecasting is of great importance to power system. There are many factors that affect system load, such as history data of load, many non-load factors.The dissertation analyzes the meaning and methods of power system load forecasting, explains the general theory and meaning of artificial neural network. Introduces fuzzy theory and studies of fuzzy neural network.Finally, according to the features of power load and considering the combined influence of temperature and day type, an approach based on fuzzy neural network is proposed for short-term load forecasting. After analyzing the original data provided by EUNITE network, and discussing the influencing factors of daily peak load, we chose the appropriate inputs for our network and build a fuzzy neural network forecasting model. Results show that fuzzy neural network is very effective in the short-term load forecasting. The study of influencing factors of short-term load forecasting is also significative.更多还原