摘要
以某1000 MW机组为研究对象,通过对机组历史日负荷数据进行聚类分析,得到机组负荷的相似性特征。然后提出了一种适用于火电机组负荷预测的历史匹配预测算法(History matching and forecasting algorithm,HMF),HMF算法将预测时间点之前几个小时的负荷序列与同时段的历史负荷数据进行相似性匹配,利用最相似日的负荷变化趋势对未来负荷做出预测。算例测试表明:HMF算法未来3 h的负荷预测平均误差为4.412%,比传统的自回归滑动平均模型(Autoregressive moving average model,ARMA)具有更高的预测精度,且在变负荷过程中也能取得较好的预测效果。
With a 1000 MW unit as the research object,the similarity characteristics of the unit load are obtained by performing the clustering analysis of historical daily load data.Then a short-term load forecasting method for thermal power units based on HMF(History matching and forecasting algorithm)is proposed.The load series of several hours before the predicted time point is matched with the historical load data of the same segment,and the future load is forecasted by the load trend of the most similar day.The example test shows that the average prediction error of the HMF model in the next 3 hours is 4.412%,which has better prediction accuracy than the traditional ARMA forecasting model.Moreover,it can also achieve good prediction results in the process of load change.
作者
丁伟
任少君
司风琪
郭鼎
DING Wei;REN Shao-jun;SI Feng-qi;GU Ding(Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education,Southeast University,Nanjing,China,Post Code:210096;Zhejiang Zheneng Technology Research Institute Co.Ltd.,Hangzhou,China,Post Code:311121)
出处
《热能动力工程》
CAS
CSCD
北大核心
2020年第1期191-197,共7页
Journal of Engineering for Thermal Energy and Power
基金
浙江省重大科技项目(2017C01082)。
关键词
负荷预测
负荷特性
聚类
相似性
HMF
load forecasting
load characteristics
clustering
similarity
HMF
