不确定情况下的长期负荷预测模型选择

IF 1.8 Q3 MANAGEMENT
Aditya Thangjam, Sanjita Jaipuria, Pradeep Kumar Dadabada
{"title":"不确定情况下的长期负荷预测模型选择","authors":"Aditya Thangjam, Sanjita Jaipuria, Pradeep Kumar Dadabada","doi":"10.1108/jm2-09-2023-0211","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>The purpose of this study is to propose a systematic model selection procedure for long-term load forecasting (LTLF) for ex-ante and ex-post cases considering uncertainty in exogenous predictors.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>The different variants of regression models, namely, Polynomial Regression (PR), Generalised Additive Model (GAM), Quantile Polynomial Regression (QPR) and Quantile Spline Regression (QSR), incorporating uncertainty in exogenous predictors like population, Real Gross State Product (RGSP) and Real Per Capita Income (RPCI), temperature and indicators of breakpoints and calendar effects, are considered for LTLF. Initially, the Backward Feature Elimination procedure is used to identify the optimal set of predictors for LTLF. Then, the consistency in model accuracies is evaluated using point and probabilistic forecast error metrics for ex-ante and ex-post cases.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>From this study, it is found PR model outperformed in ex-ante condition, while QPR model outperformed in ex-post condition. Further, QPR model performed consistently across validation and testing periods. Overall, QPR model excelled in capturing uncertainty in exogenous predictors, thereby reducing over-forecast error and risk of overinvestment.</p><!--/ Abstract__block -->\n<h3>Research limitations/implications</h3>\n<p>These findings can help utilities to align model selection strategies with their risk tolerance.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>To propose the systematic model selection procedure in this study, the consistent performance of PR, GAM, QPR and QSR models are evaluated using point forecast accuracy metrics Mean Absolute Percentage Error, Root Mean Squared Error and probabilistic forecast accuracy metric Pinball Score for ex-ante and ex-post cases considering uncertainty in the considered exogenous predictors such as RGSP, RPCI, population and temperature.</p><!--/ Abstract__block -->","PeriodicalId":16349,"journal":{"name":"Journal of Modelling in Management","volume":null,"pages":null},"PeriodicalIF":1.8000,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Model selection for long-term load forecasting under uncertainty\",\"authors\":\"Aditya Thangjam, Sanjita Jaipuria, Pradeep Kumar Dadabada\",\"doi\":\"10.1108/jm2-09-2023-0211\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3>Purpose</h3>\\n<p>The purpose of this study is to propose a systematic model selection procedure for long-term load forecasting (LTLF) for ex-ante and ex-post cases considering uncertainty in exogenous predictors.</p><!--/ Abstract__block -->\\n<h3>Design/methodology/approach</h3>\\n<p>The different variants of regression models, namely, Polynomial Regression (PR), Generalised Additive Model (GAM), Quantile Polynomial Regression (QPR) and Quantile Spline Regression (QSR), incorporating uncertainty in exogenous predictors like population, Real Gross State Product (RGSP) and Real Per Capita Income (RPCI), temperature and indicators of breakpoints and calendar effects, are considered for LTLF. Initially, the Backward Feature Elimination procedure is used to identify the optimal set of predictors for LTLF. Then, the consistency in model accuracies is evaluated using point and probabilistic forecast error metrics for ex-ante and ex-post cases.</p><!--/ Abstract__block -->\\n<h3>Findings</h3>\\n<p>From this study, it is found PR model outperformed in ex-ante condition, while QPR model outperformed in ex-post condition. Further, QPR model performed consistently across validation and testing periods. Overall, QPR model excelled in capturing uncertainty in exogenous predictors, thereby reducing over-forecast error and risk of overinvestment.</p><!--/ Abstract__block -->\\n<h3>Research limitations/implications</h3>\\n<p>These findings can help utilities to align model selection strategies with their risk tolerance.</p><!--/ Abstract__block -->\\n<h3>Originality/value</h3>\\n<p>To propose the systematic model selection procedure in this study, the consistent performance of PR, GAM, QPR and QSR models are evaluated using point forecast accuracy metrics Mean Absolute Percentage Error, Root Mean Squared Error and probabilistic forecast accuracy metric Pinball Score for ex-ante and ex-post cases considering uncertainty in the considered exogenous predictors such as RGSP, RPCI, population and temperature.</p><!--/ Abstract__block -->\",\"PeriodicalId\":16349,\"journal\":{\"name\":\"Journal of Modelling in Management\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2024-07-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Modelling in Management\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1108/jm2-09-2023-0211\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MANAGEMENT\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Modelling in Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/jm2-09-2023-0211","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MANAGEMENT","Score":null,"Total":0}
引用次数: 0

摘要

目的本研究的目的是针对考虑到外生预测因子不确定性的事前和事后长期负荷预测(LTLF),提出一种系统的模型选择程序。设计/方法/途径 LTLF 考虑了不同回归模型的变体,即多项式回归(PR)、广义相加模型(GAM)、定量多项式回归(QPR)和定量样条回归(QSR),并纳入了人口、实际国家生产总值(RGSP)和实际人均收入(RPCI)、温度和断点指标以及日历效应等外生预测因子的不确定性。首先,使用后向特征消除程序来确定 LTLF 的最佳预测因子集。然后,使用事前和事后的点预测误差和概率预测误差指标对模型准确性的一致性进行评估。此外,QPR 模型在验证和测试期间表现一致。总体而言,QPR 模型在捕捉外生预测因素的不确定性方面表现出色,从而减少了过度预测误差和过度投资风险。原创性/价值为了在本研究中提出系统的模型选择程序,使用点预测准确度指标平均绝对百分比误差、均方根误差和概率预测准确度指标弹球得分对事前和事后情况下的 PR、GAM、QPR 和 QSR 模型的一致性能进行了评估,并考虑了所考虑的外生预测因子(如 RGSP、RPCI、人口和温度)的不确定性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Model selection for long-term load forecasting under uncertainty

Purpose

The purpose of this study is to propose a systematic model selection procedure for long-term load forecasting (LTLF) for ex-ante and ex-post cases considering uncertainty in exogenous predictors.

Design/methodology/approach

The different variants of regression models, namely, Polynomial Regression (PR), Generalised Additive Model (GAM), Quantile Polynomial Regression (QPR) and Quantile Spline Regression (QSR), incorporating uncertainty in exogenous predictors like population, Real Gross State Product (RGSP) and Real Per Capita Income (RPCI), temperature and indicators of breakpoints and calendar effects, are considered for LTLF. Initially, the Backward Feature Elimination procedure is used to identify the optimal set of predictors for LTLF. Then, the consistency in model accuracies is evaluated using point and probabilistic forecast error metrics for ex-ante and ex-post cases.

Findings

From this study, it is found PR model outperformed in ex-ante condition, while QPR model outperformed in ex-post condition. Further, QPR model performed consistently across validation and testing periods. Overall, QPR model excelled in capturing uncertainty in exogenous predictors, thereby reducing over-forecast error and risk of overinvestment.

Research limitations/implications

These findings can help utilities to align model selection strategies with their risk tolerance.

Originality/value

To propose the systematic model selection procedure in this study, the consistent performance of PR, GAM, QPR and QSR models are evaluated using point forecast accuracy metrics Mean Absolute Percentage Error, Root Mean Squared Error and probabilistic forecast accuracy metric Pinball Score for ex-ante and ex-post cases considering uncertainty in the considered exogenous predictors such as RGSP, RPCI, population and temperature.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.50
自引率
12.50%
发文量
52
期刊介绍: Journal of Modelling in Management (JM2) provides a forum for academics and researchers with a strong interest in business and management modelling. The journal analyses the conceptual antecedents and theoretical underpinnings leading to research modelling processes which derive useful consequences in terms of management science, business and management implementation and applications. JM2 is focused on the utilization of management data, which is amenable to research modelling processes, and welcomes academic papers that not only encompass the whole research process (from conceptualization to managerial implications) but also make explicit the individual links between ''antecedents and modelling'' (how to tackle certain problems) and ''modelling and consequences'' (how to apply the models and draw appropriate conclusions). The journal is particularly interested in innovative methodological and statistical modelling processes and those models that result in clear and justified managerial decisions. JM2 specifically promotes and supports research writing, that engages in an academically rigorous manner, in areas related to research modelling such as: A priori theorizing conceptual models, Artificial intelligence, machine learning, Association rule mining, clustering, feature selection, Business analytics: Descriptive, Predictive, and Prescriptive Analytics, Causal analytics: structural equation modeling, partial least squares modeling, Computable general equilibrium models, Computer-based models, Data mining, data analytics with big data, Decision support systems and business intelligence, Econometric models, Fuzzy logic modeling, Generalized linear models, Multi-attribute decision-making models, Non-linear models, Optimization, Simulation models, Statistical decision models, Statistical inference making and probabilistic modeling, Text mining, web mining, and visual analytics, Uncertainty-based reasoning models.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信