摘要
电力系统短期负荷预测既是电力系统调度部门制定发电计划的依据,也是制定电力市场交易计划的基础,它对电力系统的运行、控制和计划都有着非常重要的影响。可由于负荷预测的复杂性、不确定性,难以获得精确的预测值。为提高预测精度,针对电力负荷的特点,综合考虑历史负荷、天气、日类型等因素的影响,将基于均匀设计(UD)和改进遗传算法(IGA)的网络构造法用于短期负荷预测。数据样本训练和实际预测结果表明,该模型不仅可避免陷入局部极小点,而且提高了预测精度和网络的训练速度。
Electric power system short term load forecasting is not only the basis for the scheduling of generating sets, but also the basis to work out the transaction schedule in electricity market. It has great influence on the operating, controlling and planning of electric power system. Due to the complicacy and uncertainty of load forecasting, electric power load is difficult to be forecasted precisely. In order to improve the precision of electric power system short term load forecasting, according tothe features of power load and considering the combined influence of historical load data, weather and day type, a neural network structure method which combines uniform design with improved genetic algorithm is used to short-term load forecasting in this paper, The training and testing results show that the model can not only avoid convergence to the local, minimum, but also improve the training speed for the neural network and accuracy for load forecasting,
出处
《继电器》
CSCD
北大核心
2007年第7期66-69,76,共5页
Relay
基金
湖南省教育厅资助科研项目(06C718)
关键词
均匀设计
改进遗传算法
短期负荷预测
uniform design
improved genetic algorithm
short-term load forecasting