基于灰色理论的电力监控数据多因素预测模型

Multi-Factor Prediction Model of Power Monitoring Data Based on Grey Theory

随着大数据技术的发展,大数据技术被广泛地应用在电力负荷预测上,大数据技术的应用前提是需要海量的相关数据。灰色系统理论可以弥补大数据缺少样本信息的缺陷。我国电力负荷,既有逐年增长的确定性,又有随机变化的不确定性,可以视为典型的灰色系统,适合使用灰色模型建模预测。本文提出采用多因素的GM(1,1)优化模型,分析了10年的社会用电结构,并以不同结构的用电力监控数据为基础,建立并检验了基于有限电力数据多因素的灰色预测模型。全社会不同结构电力负荷预测结果表明,该模型预测的最大误差小于4.8%,预测结果证明了该模型的有效性和可用性。上述研究对于丰富电力负荷预测手段,弥补传统大数据技术在负荷预测方面需求数据量较高的局限性均具有十分重要的现实意义。

With the development of big data technology,it is widely used in power load forecasting.The premise of the application of big data technology is large amount of relevant data,the grey system theory can make up for the defects of big data of lack of sample information.The power load in China has both the certainty of increasing year by year and the uncertainty of random change,which can be regarded as a typical gray system and is suitable to use gray model for modeling and prediction.A multi-factor GM(1,1)optimization model is proposed to analyze the social electricity consumption structure in 10 years,and the multi-factor grey prediction model is established and tested by using the electricity consumption data of different structures.The results showed that the maximum error of the model is less than 4.8%,which proves the effectiveness of the model.This study is of great practical significance for enriching the means of power load forecasting and making up for the limitation of traditional big data technology in load forecasting.