Feature selection for energy system modeling: Identification of relevant time series information

作     者：Inga M.Muller 

作者机构：Chair of Renewable and Sustainable Energy SystemsTechnical University of MunichAccisstrasse 21Munich 80333Germany 

出 版 物：《能源与人工智能(英文)》 (Energy and AI)

年 卷 期：2021年第4卷第2期

页      面：16-29页

核心收录：

学科分类：08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was funded in part through the NIAID Division of Intramural Research and the NIAID Division of Clinical Research, Battelle Memorial Institute’s prime contract with the U.S. National Institute of Allergy and Infectious Diseases (NIAID) under contract HHSN272200700016I and an NIH grant in aid to R.S.B. (AI110700 and AI132178). K.R.H., J.K.B., and M.R.H. performed this work as employees of Battelle Memorial Institute. Subcontractors to Battelle Memorial Institute who performed this work are as follows: S.C., D.T., E.P., and J.D., all employees of Tunnell Government Services, Inc. M.G.L., an employee of Lovelace Respiratory Research Institute C.B. and P.J.S., employees of MedRelief D.L., an employee of Charles River Laboratories.We thank Russell Byrum, Danny Ragland, and Marisa St. Claire and the entire IRF Comparative Medicine and Imaging staff for successful implementation of SPECT scanning procedures in mice in the biosafety level 4 environment. We thank Laura Bollinger for critically editing the manuscript and Jiro Wada for figure development. We also thank Matthias Schnell, Thomas Jefferson University, for his critical review of the manuscript. This work was funded in part through the NIAID Division of Intramural Research and the NIAID Division of Clinical Research, Battelle Memorial Institute's prime contract with the U.S. National Institute of Allergy and Infectious Diseases (NIAID) under contract HHSN272200700016I and an NIH grant in aid to R.S.B. (AI110700 and AI132178). K.R.H., J.K.B., and M.R.H. performed this work as employees of Battelle Memorial Institute. Subcontractors to Battelle Memorial Institute who performed this work are as follows: S.C., D.T., E.P., and J.D., all employees of Tunnell Government Services, Inc. M.G.L., an employee of Lovelace Respiratory Research Institute C.B. and P.J.S., employees of MedRelief D.L., an employee of Charles River Laboratories. 

主　　题：Energy system modeling Feature selection Time series analysis Nested modeling Clustering Regression Intermittent renewable energies 

摘      要：Heuristic or clustering based time series aggregation methods are often used to reduce temporal complexity of energy system models by selecting representative days.However,these methods potentially neglect relevant information of time series(e.g.,distribution parameters).To identify relevant time series parameters,feature selection algorithms can be applied.The present research contributes by(a)developing a new feature selection approach based on clustering,nested modeling and regression(CNR)which is designed for applications requiring high selectivity and using different data sets,(b)comparing and evaluating CNR with feature selection methods available from the literature(e.g.,LASSO)and(c)identifying relevant information of the time series applied in energy system models,in particular those of demand,photovoltaic and wind.Results show that CNR achieves on average up to 101%lower mean absolute errors when methods are directly compared.Thus,CNR better identifies relevant information when the number of selected features is restricted.The disadvantage of CNR,however,is its high computational effort.A potential remedy to counter this is the combination with another method(e.g.,as pre-feature selection).In terms of relevant information,energy systems including photovoltaic are mainly characterized by the correlation between demand and photovoltaic time series as well as the range and the 35%quantile of demand.When energy systems include wind power,the minimum and mean of wind as well as the correlation between demand and wind time series are relevant characteristics.The implications of these findings are discussed.