Research on the Identification and Repair Methods of the Energy Consumption Anomalous Data in District Heating System
For district heating systems,accurate energy consumption prediction is an important prerequisite for efficient system management.Based on the operation data of the practical project,the anomaly data recognition method based on boxplot and isolation forest,and the filling method of MissForest are used for the preprocessing of the dataset.A comparative experiment was set up,and the energy consumption prediction models based on LightGBM are constructed to verify the effectiveness of the data preprocessing method proposed in this paper on the improvement of energy consumption prediction effect.The experimental results show that the data preprocessing method proposed in this paper can effectively and accurately identify and repair the abnormal data,and has a significant effect on the optimization of the predictive model.
district heating systemsmachine learningdata preprocessingenergy consumption prediction
NETL
NSTL
万方数据
