【摘要】 提出一种将混沌理论、关联度和神经网络相结合的短期负荷预测模型,首先利用混沌理论重构负荷时间序列的相空间吸引子,然后用BP神经网络来拟合空间吸引子的演化,由于使用空间欧氏距离和关联度联合来选取神经网络的训练样本,这样就提高了神经网络对负荷序列混沌特性的联想和泛化推理能力,能够更好的拟合吸引子的演化。实例预测结果表明,本文所提出的预报是有效的、可行的。更多还原

【Abstract】 A hybrid model of short-term load forecasting based on chaotic theory, correlation and neural networks is presented in this paper. Firstly, reconstruct attractors in phase spaces using chaotic theory,Secondly fit the attractor’s evolvement using BP neural networks, because selecting neural network’s input training data using Euclid distance and correlation, improve neural network’s associative memory and ratiocinative ability, can better fit the attractor’s evolvement. Lastly, result analysis of practical examples shows that the proposed hybrid model is effective and feasible.更多还原