摘要
不断改进电力负荷预测技术,探索精度更高的预测模型,是当前电力体制改革大背景下一个具有巨大现实意义的的课题。针对电力负荷具有趋势性、季节性、周期性和随机性等特性,该文采用传统的灰色GM(1,1)模型和时间序列(Time-Series Analysis)相结合的方法,首先用灰色模型拟合电力负荷的非线性增长趋势,再用时间序列模型表征负荷变化中的季节性和周期性,两种算法相互结合弥补了单个算法的缺陷,最后采用马尔科夫链(Markov chain)对预测结果进行修正。实验结果显示,马尔科夫修正后的灰色时间序列预测结果精度高于单个算法模型的精度,也高于修正前的精度。这是一种精度更高的预测模型,能够为实际应用提供一定的理论支持。
Constantly improving the power load forecasting technology,and exploring a more accurate prediction model are subjects which have great practical significance on the background of the reform of electric power system at present.Because of the characteristics of trend,season,periodicity and randomness in power load,the GM(1,1)model is combined with time series in this paper.The grey model is used to fit the nonlinear growth trend of the power load,and the time series model is used to characterize the seasonal and periodicity of the load change,so as to make up for the defect of single algorithm.Finally,the Markoff chain is used to correct the prediction results.The results show that the accuracy of Markoff-modified grey-time series prediction result is higher than the accuracy of the single algorithm,and also is that before the correction.So this is a more accurate prediction model,which can provide some theoretical support for practical application.
作者
吕雪松
潘冬
王凯
毕京虎
LV Xue-song;PAN Dong;WANG Kai;BI Jing-hu(Jiangxi Electric Power Co.,Ltd.,Nanchang 330000 China;Yantai Dongfang Wisdom Electric Co.,Ltd.,Yantai 264003 China)
出处
《自动化技术与应用》
2022年第3期132-136,176,共6页
Techniques of Automation and Applications
