【作者】 张雪君；

【导师】 陈刚；

【作者基本信息】 重庆大学 ， 电气工程， 2009， 硕士

【摘要】 电力系统中长期负荷预测主要是以年为时间单位进行年最大负荷、电量的预测,它是电力规划、生产和运行等工作的重要基础。其特点是历史数据少,负荷受经济、社会等不确定因素影响较大。准确的负荷预测有利于提高电网运行的安全稳定性,有效地降低发电成本,保证用电需求,增强供电可靠性,从而提高电力系统的经济效益和社会效益。本文介绍了电力系统中长期负荷预测的目的和意义,对国内外中长期负荷预测的现状进行综述。介绍了中长期负荷预测的基本原理,分析了各种方法的优缺点以及负荷预测的误差分析等情况。本文在分析了中长期负荷预测的特点的基础上,采用支持向量回归机算法对中长期负荷进行预测。介绍了支持向量机算法的基本原理,建立基于该方法的负荷预测模型,给出基本算法流程图,利用Matlab6.5进行程序设计,实现上述算法过程。通过实际算例分析并与其他方法的预测结果进行比较,表明该预测模型符合中长期负荷预测的特点,验证了该方法的可行性。然后本文进一步提出了利用粗糙集属性约简理论对支持向量回归机中长期负荷预测模型初始数据进行简化预处理,对支持向量机的输入进行特征提取会取得更好的效果。给出对影响中长期负荷预测的各因素根据影响程度进行筛选的方法和流程图,改进负荷预测模型,然后,通过算例分析,与标准支持向量回归机方法的预测结果进行比较分析,验证属性约简的有效性。最后在分析了支持向量回归机的各参数对其性能有很大影响的基础上,本文提出了在利用粗糙集理论对影响中长期负荷预测的各因素进行筛选的基础上,利用粒子群优化算法对支持向量回归机的各参数进行优化的方法。给出对各参数优化的算法原理及流程图,进一步修正负荷预测模型。通过实际算例分析,验证改进后的支持向量回归机中长期负荷预测模型具有预测精度高、计算量小等优势,该方法是可行和有效的。更多还原

【Abstract】 Medium and long-term power system load forecasting is mainly the largest load and power forecasting. It is an important basic job for electricity supply planning, production and operation . Its characteristics are less historical data, the load being affected by the economic and social impact of large uncertainties. Accurate load forecasting is conducive to improve the security and stability of the power system operation, effectively reduces the cost of power generation, ensures the electricity demand, and enhances supply reliability, thereby enhances the economic and social benefits for power system.The purpose and significance of medium and long-term load forecasting,the developments at home and abroad, a variety of methods used in load forecasting as well as the basic principles, analysis of load forecasting error and so on are presented.Based on analysis the characteristics of medium and long-term load forecasting, a medium and long-term load forecasting method based on support vector regression algorithm is presented. The basic principles of support vector machine is introduced.The model and algorithm flow chart based on this method are presented.The realization of this algorithm is based on Matlab 6.5 program design.Comparing with other methods,the actual example shows that the forecasting model is in line with the characteristics of medium and long-term load forecasting,it is feasible.Then the method of making use of rough set attribute reduction theory to simplify the initial data for support vector regression is presented. The feature extraction for support vector machines can produce better results. The flow chart and improved model of this method are presented.And then comparing with standard support vector regression model the validity of attribute reduction is verified by the actual example.At last, based on analysis that the parameters of support vector regression have great impact on its performance, the method of making use of particle swarm optimization algorithm to optimize the selection of parameters for support vector regression model is presented. The optimization principles and flow chart of the modified model are presented.The actual example shows that the improved support vector regression forecasting model is provided with advantages such as high accuracy to calculate,the small volume and so on.This method is feasible and effective.更多还原