摘要
灰色GM(1,1)预测模型,在负荷预测中得到了广泛应用,但是也有其局限性。当数据灰度越大,预测精度越差,并且不太适合经济长期后推若干年的预测,在一定程度上是由模型中的参数a造成的,为此引入向量θ,建立蚁群灰色模型,然后与神经网络模型相组合,即建立蚁群灰色神经网络组合预测模型。实证分析表明,该预测方法是合理有效的,与传统的预测方法相比,提高了预测精度,具有较好的实用价值。
Although GM（1,1） forecasting model is extensively applied in the load forecasting, it has its localization. The greater the gray level of data is, the lower the prediction precision is. Besides, it is not suitable to long-term forecasting of economy to backstep for years, which, to a certain extent, is caused by parameter α in the model. To solve the problem, vector θ is introduced to set up Ant Colony Gray model, then combined with Neural Network model. Ant Colony Gray Neural Network combined forecasting model is set up. Case analysis shows that the forecast method is suitable and effective, improving prediction precision compared with traditional forecast methods, and has better utility value.
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2009年第2期48-52,共5页
Power System Protection and Control
