论文部分内容阅读
电力市场中,市场出清电价具有较强的波动性、周期性和随机性,实践证明单一的电价预测模型很难提高预测精度。针对该问题,提出一种基于多因素小波变换和多变量时间序列模型的日前电价预测方法。利用小波变换将历史电价序列和负荷序列分解和重构成概貌电价、细节电价和概貌负荷、细节负荷。用概貌电价和概貌负荷作变量建立多元时间序列模型,预测未来概貌电价;用单变量时间序列模型预测未来细节电价。将概貌电价和细节电价的预测结果求和作为最终的预测电价。采用上述方法对美国加州电力市场日前电价进行预测,并与对比模型进行了详细的比较分析,结果表明该方法能够提供更准确的预测电价。
In the electricity market, the market price has a strong volatility, periodicity and randomness. Practice has proved that it is difficult to improve the forecasting accuracy by a single electricity price forecasting model. In order to solve this problem, a method based on multi-factor wavelet transform and multivariable time series forecasting method is proposed. Using wavelet transform, historical price series and load series are decomposed and reconstructed into profile price, detail price, profile load and detail load. Using the profile electricity price and the profile load as the variables, a multiple time series model is established to predict the future profile electricity price. The single variable time series model is used to predict the future detail electricity price. Sum up the forecast results of the profile price and the detailed price as the final forecast price. The above method is used to predict the day-ahead electricity price of the California electricity market in the United States, and a comparative analysis is made with the comparative model. The results show that this method can provide more accurate forecast electricity prices.