摘要
城市燃气小时负荷预测的研究对燃气调度系统的安全与稳定具有重要意义。为了提高城市燃气小时负荷预测精度,在分析讨论主成分分析特性和BP神经网络优缺点的基础上,建立了利用主成分分析法对BP神经网络进行优化的小时负荷预测模型。该模型综合了主成分分析的降维特性和BP神经网络具有强大的自学习和自适应能力等特点,首先通过主成分分析法对所有相关影响因子进行降维处理,再将处理后累计贡献率占比85%以上的几种主成分作为输入层神经元输入BP神经网络进行训练,最后运用该组合模型对某县的小时负荷进行预测。实例分析表明:与单一模型相比,提出的PCA-BPNN组合预测模型精度更高,是一种更为有效的城市燃气小时负荷预测方法。
The study of urban gas hourly load forecasting is of great significance to the safety and stability of gas dispatching system. In order to improve the prediction accuracy of urban gas hourly load prediction, based on the analysis and discussion of the characteristics of principal component analysis and the advantages and disadvantages of BP neural network, an hourly load prediction model is established by principal component analysis method. This model combines the dimension reduction characteristic of principal component analysis and the BP neural network strong ability of self-learning and self-adaptive. First, the principal component analysis method is used to reduce the dimension of all related factors, and then several principal components which account for more than 85% of the cumulative contribution rate are trained as input layer neurons to input BP neural network.Finally, the combined model is used to predict the hourly load in a county. The example analysis shows that compared with the single model, the PCA-BPNN combined forecasting model proposed in this paper is more accurate. It is a more effective method for urban gas hourly load forecasting.
作者
刘金源
LIU Jinyuan(Xi＇an Shiyou University,Xi＇an 710065,China)
出处
《工业加热》
CAS
2018年第5期49-53,共5页
Industrial Heating
