基于小波-神经网络的风速及风力发电量预测

Wind Speed and Generated Wind Power Forecast Based on Wavelet-Neural Network

风能作为可再生清洁能源已得到世界各国的广泛应用。由于风速的不确定性,给保障风力可靠性发电带来了一定的困难。提出了一种较为准确的小波–神经网络法预测风速。该方法利用小波函数将原始波形进行不同尺度的分解,将分解得到的周期分量用时间序列进行预测,其余部分采用神经网络进行预测,最后将信号序列进行重构得到完整的风速预测结果。在神经–网络学习过程中加入了微分进化算法,提高了其收敛速度,解决了局部最小化问题。通过实例分析证明了该算法能较为准确地预测风速。

As a renewable and clean energy source, wind power are being widely utilized all over the world. However, the uncertainty of wind speed makes troubles in ensuring the reliability of wind power generation. For this reason, a wind speed forecasting method based on wavelet-neural network is proposed. In the proposed method, the original waveform is decomposed in different scales by wavelet function and the decomposed periodic components are forecasted by time series, and the rest parts are forecasted by neural network, finally the signal series are reconstructed to obtain complete wind speed forecasting result. Adding differential evolution algorithm, the convergence speed of the proposed method is improved and the local minimum problem is also solved. Results of case analysis show that the proposed method can be used to forecast wind speed more accurately.