基于小脑模型关节控制器神经网络的短期电价预测

电价预测是电力市场决策的基础。文中介绍了采用小脑模型关节控制器(CMAC)神经网络建立预测提前1天不同时段的电力市场短期电价的预测模型。并以美国加州电力市场的数据作为计算实例，分别采用CMAC神经网络和反向传播算法(BP)神经网络进行短期电价预测。两种预测结果对比表明，CMAC神经网络具有所需训练样本少、输出稳定性好、计算速度快和预测精度高等优点，比较适用于短期电价预测。

SHORT-TERM ELECTRICITY PRICE FORCASTING USING CEREBELLAR MODEL ARTICULATION CONTROLLER NEURAL NETWORK

Electricity price forecasting is the basis of decision making for each participant in electricity market. Using the method based on cerebellar model articulation controller (CMAC) neural network a day-ahead electricity price short-term forecasting model is established and different models are designed for different time intervals respectively. Then taking the data of California electricity market for calculation example, the short-term electricity price forcasting is performed by CMAC and BP neural network. The comparison between two results shows that using CMAC neural network the short-term electricity price can be forecasted more quickly and steadily.