Meta-learning in multivariate load demand forecasting with exogenous meta-features

Although many studies have examined various types of single load demand prediction algorithms, it is yet a challenging decision to select the best predictor. Geographical characteristics are one of the most effective factors in load consumption patterns, the performance of the algorithms, and the ac...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy efficiency 2020-06, Vol.13 (5), p.871-887
Hauptverfasser: Arjmand, Azadeh, Samizadeh, Reza, Dehghani Saryazdi, Mohammad
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 887
container_issue 5
container_start_page 871
container_title Energy efficiency
container_volume 13
creator Arjmand, Azadeh
Samizadeh, Reza
Dehghani Saryazdi, Mohammad
description Although many studies have examined various types of single load demand prediction algorithms, it is yet a challenging decision to select the best predictor. Geographical characteristics are one of the most effective factors in load consumption patterns, the performance of the algorithms, and the accuracy of predictions. Therefore, developing a general framework in which meteorological characteristics determine the best predictor can be of importance. Meta-learning models, which are less considered in this area, propose a framework for algorithm selection by using a set of meta-features. In this paper, a meta-learning system is developed using exogenous weather variables as meta-features. The proposed system selects the best predictor among a pool of candidate forecasting algorithms including ARIMA, ARIMAX, MLR, NAR, NARX, and SVR. In statistical approaches, the volatility of the mean and variance of the load demand is modeled by GARCH process. The selection process uses a set of meta-features built on temperature and dew point. The empirical tests were performed on 30 samples of daily load demand taken from ten various geographical zones in Ontario, Canada. The achievements reveal that the characteristics of weather meta-features such as range of variation, skewness, and kurtosis play an important role in assigning the most suitable predictor to each sample set and both groups of statistical and artificial intelligence-based predictors were selected in different sample sets.
doi_str_mv 10.1007/s12053-020-09851-x
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2417168000</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2417168000</sourcerecordid><originalsourceid>FETCH-LOGICAL-c367t-338c575b2ee3e7aacd9fcada3ddfd05976c122622b4ef6248168e306e2bdd5ce3</originalsourceid><addsrcrecordid>eNp9kE1LxDAQhoMouOj-AU8Fz9FJ0ibdoyx-wYogCt5CmkzXSj_WJNX135u1ojdhYObwvO_AQ8gJgzMGoM4D41AIChwoLMqC0e0embFCAZW5Kvd_b_l8SOYhNBUIxqVIMyMPdxgNbdH4vunXWdNn3djG5t34xkTM2sG4zGFnepfVg0drQtxxH018yXA7rLEfxpB1u5IaTRw9hmNyUJs24PxnH5Gnq8vH5Q1d3V_fLi9W1AqpIhWitIUqKo4oUBlj3aK2xhnhXO2gWChpGeeS8yrHWvK8ZLJEARJ55VxhURyR06l344e3EUPUr8Po-_RS85yphANAovhEWT-E4LHWG990xn9qBnqnT0_6dNKnv_XpbQqJKRQS3K_R_1X_k_oCSMR05A</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2417168000</pqid></control><display><type>article</type><title>Meta-learning in multivariate load demand forecasting with exogenous meta-features</title><source>SpringerNature Journals</source><source>Alma/SFX Local Collection</source><creator>Arjmand, Azadeh ; Samizadeh, Reza ; Dehghani Saryazdi, Mohammad</creator><creatorcontrib>Arjmand, Azadeh ; Samizadeh, Reza ; Dehghani Saryazdi, Mohammad</creatorcontrib><description>Although many studies have examined various types of single load demand prediction algorithms, it is yet a challenging decision to select the best predictor. Geographical characteristics are one of the most effective factors in load consumption patterns, the performance of the algorithms, and the accuracy of predictions. Therefore, developing a general framework in which meteorological characteristics determine the best predictor can be of importance. Meta-learning models, which are less considered in this area, propose a framework for algorithm selection by using a set of meta-features. In this paper, a meta-learning system is developed using exogenous weather variables as meta-features. The proposed system selects the best predictor among a pool of candidate forecasting algorithms including ARIMA, ARIMAX, MLR, NAR, NARX, and SVR. In statistical approaches, the volatility of the mean and variance of the load demand is modeled by GARCH process. The selection process uses a set of meta-features built on temperature and dew point. The empirical tests were performed on 30 samples of daily load demand taken from ten various geographical zones in Ontario, Canada. The achievements reveal that the characteristics of weather meta-features such as range of variation, skewness, and kurtosis play an important role in assigning the most suitable predictor to each sample set and both groups of statistical and artificial intelligence-based predictors were selected in different sample sets.</description><identifier>ISSN: 1570-646X</identifier><identifier>EISSN: 1570-6478</identifier><identifier>DOI: 10.1007/s12053-020-09851-x</identifier><language>eng</language><publisher>Dordrecht: Springer Netherlands</publisher><subject>Algorithms ; Artificial intelligence ; Autoregressive models ; Autoregressive processes ; Consumption patterns ; Demand ; Dew point ; Economic forecasting ; Economics and Management ; Energy ; Energy Efficiency ; Energy Policy ; Environment ; Environmental Economics ; Kurtosis ; Learning ; Original Paper ; Renewable and Green Energy ; Statistical analysis ; Statistical methods ; Statistics ; Sustainable Development ; Volatility ; Weather</subject><ispartof>Energy efficiency, 2020-06, Vol.13 (5), p.871-887</ispartof><rights>Springer Nature B.V. 2020</rights><rights>Springer Nature B.V. 2020.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c367t-338c575b2ee3e7aacd9fcada3ddfd05976c122622b4ef6248168e306e2bdd5ce3</citedby><cites>FETCH-LOGICAL-c367t-338c575b2ee3e7aacd9fcada3ddfd05976c122622b4ef6248168e306e2bdd5ce3</cites><orcidid>0000-0003-3238-0653</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s12053-020-09851-x$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s12053-020-09851-x$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Arjmand, Azadeh</creatorcontrib><creatorcontrib>Samizadeh, Reza</creatorcontrib><creatorcontrib>Dehghani Saryazdi, Mohammad</creatorcontrib><title>Meta-learning in multivariate load demand forecasting with exogenous meta-features</title><title>Energy efficiency</title><addtitle>Energy Efficiency</addtitle><description>Although many studies have examined various types of single load demand prediction algorithms, it is yet a challenging decision to select the best predictor. Geographical characteristics are one of the most effective factors in load consumption patterns, the performance of the algorithms, and the accuracy of predictions. Therefore, developing a general framework in which meteorological characteristics determine the best predictor can be of importance. Meta-learning models, which are less considered in this area, propose a framework for algorithm selection by using a set of meta-features. In this paper, a meta-learning system is developed using exogenous weather variables as meta-features. The proposed system selects the best predictor among a pool of candidate forecasting algorithms including ARIMA, ARIMAX, MLR, NAR, NARX, and SVR. In statistical approaches, the volatility of the mean and variance of the load demand is modeled by GARCH process. The selection process uses a set of meta-features built on temperature and dew point. The empirical tests were performed on 30 samples of daily load demand taken from ten various geographical zones in Ontario, Canada. The achievements reveal that the characteristics of weather meta-features such as range of variation, skewness, and kurtosis play an important role in assigning the most suitable predictor to each sample set and both groups of statistical and artificial intelligence-based predictors were selected in different sample sets.</description><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Autoregressive models</subject><subject>Autoregressive processes</subject><subject>Consumption patterns</subject><subject>Demand</subject><subject>Dew point</subject><subject>Economic forecasting</subject><subject>Economics and Management</subject><subject>Energy</subject><subject>Energy Efficiency</subject><subject>Energy Policy</subject><subject>Environment</subject><subject>Environmental Economics</subject><subject>Kurtosis</subject><subject>Learning</subject><subject>Original Paper</subject><subject>Renewable and Green Energy</subject><subject>Statistical analysis</subject><subject>Statistical methods</subject><subject>Statistics</subject><subject>Sustainable Development</subject><subject>Volatility</subject><subject>Weather</subject><issn>1570-646X</issn><issn>1570-6478</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>8G5</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>GUQSH</sourceid><sourceid>M2O</sourceid><recordid>eNp9kE1LxDAQhoMouOj-AU8Fz9FJ0ibdoyx-wYogCt5CmkzXSj_WJNX135u1ojdhYObwvO_AQ8gJgzMGoM4D41AIChwoLMqC0e0embFCAZW5Kvd_b_l8SOYhNBUIxqVIMyMPdxgNbdH4vunXWdNn3djG5t34xkTM2sG4zGFnepfVg0drQtxxH018yXA7rLEfxpB1u5IaTRw9hmNyUJs24PxnH5Gnq8vH5Q1d3V_fLi9W1AqpIhWitIUqKo4oUBlj3aK2xhnhXO2gWChpGeeS8yrHWvK8ZLJEARJ55VxhURyR06l344e3EUPUr8Po-_RS85yphANAovhEWT-E4LHWG990xn9qBnqnT0_6dNKnv_XpbQqJKRQS3K_R_1X_k_oCSMR05A</recordid><startdate>20200601</startdate><enddate>20200601</enddate><creator>Arjmand, Azadeh</creator><creator>Samizadeh, Reza</creator><creator>Dehghani Saryazdi, Mohammad</creator><general>Springer Netherlands</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7ST</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>88I</scope><scope>8FK</scope><scope>8FL</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>HCIFZ</scope><scope>K60</scope><scope>K6~</scope><scope>L.-</scope><scope>M0C</scope><scope>M2O</scope><scope>M2P</scope><scope>MBDVC</scope><scope>PATMY</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PYCSY</scope><scope>Q9U</scope><scope>SOI</scope><orcidid>https://orcid.org/0000-0003-3238-0653</orcidid></search><sort><creationdate>20200601</creationdate><title>Meta-learning in multivariate load demand forecasting with exogenous meta-features</title><author>Arjmand, Azadeh ; Samizadeh, Reza ; Dehghani Saryazdi, Mohammad</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c367t-338c575b2ee3e7aacd9fcada3ddfd05976c122622b4ef6248168e306e2bdd5ce3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Autoregressive models</topic><topic>Autoregressive processes</topic><topic>Consumption patterns</topic><topic>Demand</topic><topic>Dew point</topic><topic>Economic forecasting</topic><topic>Economics and Management</topic><topic>Energy</topic><topic>Energy Efficiency</topic><topic>Energy Policy</topic><topic>Environment</topic><topic>Environmental Economics</topic><topic>Kurtosis</topic><topic>Learning</topic><topic>Original Paper</topic><topic>Renewable and Green Energy</topic><topic>Statistical analysis</topic><topic>Statistical methods</topic><topic>Statistics</topic><topic>Sustainable Development</topic><topic>Volatility</topic><topic>Weather</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Arjmand, Azadeh</creatorcontrib><creatorcontrib>Samizadeh, Reza</creatorcontrib><creatorcontrib>Dehghani Saryazdi, Mohammad</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Environment Abstracts</collection><collection>Access via ABI/INFORM (ProQuest)</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Science Database (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>ABI/INFORM Professional Advanced</collection><collection>ABI/INFORM Global</collection><collection>Research Library</collection><collection>Science Database</collection><collection>Research Library (Corporate)</collection><collection>Environmental Science Database</collection><collection>ProQuest One Business</collection><collection>ProQuest One Business (Alumni)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Environmental Science Collection</collection><collection>ProQuest Central Basic</collection><collection>Environment Abstracts</collection><jtitle>Energy efficiency</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Arjmand, Azadeh</au><au>Samizadeh, Reza</au><au>Dehghani Saryazdi, Mohammad</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Meta-learning in multivariate load demand forecasting with exogenous meta-features</atitle><jtitle>Energy efficiency</jtitle><stitle>Energy Efficiency</stitle><date>2020-06-01</date><risdate>2020</risdate><volume>13</volume><issue>5</issue><spage>871</spage><epage>887</epage><pages>871-887</pages><issn>1570-646X</issn><eissn>1570-6478</eissn><abstract>Although many studies have examined various types of single load demand prediction algorithms, it is yet a challenging decision to select the best predictor. Geographical characteristics are one of the most effective factors in load consumption patterns, the performance of the algorithms, and the accuracy of predictions. Therefore, developing a general framework in which meteorological characteristics determine the best predictor can be of importance. Meta-learning models, which are less considered in this area, propose a framework for algorithm selection by using a set of meta-features. In this paper, a meta-learning system is developed using exogenous weather variables as meta-features. The proposed system selects the best predictor among a pool of candidate forecasting algorithms including ARIMA, ARIMAX, MLR, NAR, NARX, and SVR. In statistical approaches, the volatility of the mean and variance of the load demand is modeled by GARCH process. The selection process uses a set of meta-features built on temperature and dew point. The empirical tests were performed on 30 samples of daily load demand taken from ten various geographical zones in Ontario, Canada. The achievements reveal that the characteristics of weather meta-features such as range of variation, skewness, and kurtosis play an important role in assigning the most suitable predictor to each sample set and both groups of statistical and artificial intelligence-based predictors were selected in different sample sets.</abstract><cop>Dordrecht</cop><pub>Springer Netherlands</pub><doi>10.1007/s12053-020-09851-x</doi><tpages>17</tpages><orcidid>https://orcid.org/0000-0003-3238-0653</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1570-646X
ispartof Energy efficiency, 2020-06, Vol.13 (5), p.871-887
issn 1570-646X
1570-6478
language eng
recordid cdi_proquest_journals_2417168000
source SpringerNature Journals; Alma/SFX Local Collection
subjects Algorithms
Artificial intelligence
Autoregressive models
Autoregressive processes
Consumption patterns
Demand
Dew point
Economic forecasting
Economics and Management
Energy
Energy Efficiency
Energy Policy
Environment
Environmental Economics
Kurtosis
Learning
Original Paper
Renewable and Green Energy
Statistical analysis
Statistical methods
Statistics
Sustainable Development
Volatility
Weather
title Meta-learning in multivariate load demand forecasting with exogenous meta-features
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T06%3A19%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Meta-learning%20in%20multivariate%20load%20demand%20forecasting%20with%20exogenous%20meta-features&rft.jtitle=Energy%20efficiency&rft.au=Arjmand,%20Azadeh&rft.date=2020-06-01&rft.volume=13&rft.issue=5&rft.spage=871&rft.epage=887&rft.pages=871-887&rft.issn=1570-646X&rft.eissn=1570-6478&rft_id=info:doi/10.1007/s12053-020-09851-x&rft_dat=%3Cproquest_cross%3E2417168000%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2417168000&rft_id=info:pmid/&rfr_iscdi=true