{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/38028"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/38028","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"A generalized ANN-based model for short-term load forecasting","abstract":"Short-term load forecasting (STLF) deals with forecasting of hourly system demand with a lead time ranging from one hour to 168 hours. The basic objective of the STLF is to provide for economic, reliable and secure operation of the power system. This dissertation establishes a new approach to artificial neural network (ANN) based STLF. It first decomposes the prediction problem into representation and function approximation problems. The representation problem is solved using phase-space embedding which identifies time delay variables from load time series that are used in forecasting. The concept is inherently different from the methods used so far because it does not use correlated variables for forecasting. Temperature variables are included as well using identified embedding parameters. Function approximation problem is approached using ANN ensemble and active selection of a training set. Training set is selected based on predicted weather parameters for a prediction horizon. Selection is done applying the k-nearest neighbors technique in a temperature-based vector space. A novel approach of pilot set simulation is used to determine the number of hidden units for every forecast period. Ensemble consists of two ANNs which are trained and cross validated on complementary training sets. Final prediction is obtained by a simple average of two trained ANNs. The described technique is used for predicting one week’s load in four selected months in summer peaking and winter peaking US utilities. Mean absolute percent errors (MAPEs) for 24-hour lead time predictions are slightly greater than 2% for all months. For 120-hour lead time (weekday) predictions, MAPEs are around 2.3%. MAPEs for 48- hour lead time (weekend) predictions are around 2.5%. Maximal errors for these cases are around 7%. Predictions for one-hour lead time are slightly higher than 1% for all months, with maximal errors not exceeding 4.99%. Peak load MAPEs are 2.3% for both utilities. Maximal peak-load errors do not exceed 6%. The technique shows very good performance faced with sudden and large changes in weather. For changes in temperature larger than 20° F for two consecutive days, forecasting error is smaller than 3.58%.","abstract_html":"Short-term load forecasting (STLF) deals with forecasting of hourly system demand with a lead time ranging from one hour to 168 hours. The basic objective of the STLF is to provide for economic, reliable and secure operation of the power system. This dissertation establishes a new approach to artificial neural network (ANN) based STLF. It first decomposes the prediction problem into representation and function approximation problems. The representation problem is solved using phase-space embedding which identifies time delay variables from load time series that are used in forecasting. The concept is inherently different from the methods used so far because it does not use correlated variables for forecasting. Temperature variables are included as well using identified embedding parameters. Function approximation problem is approached using ANN ensemble and active selection of a training set. Training set is selected based on predicted weather parameters for a prediction horizon. Selection is done applying the k-nearest neighbors technique in a temperature-based vector space. A novel approach of pilot set simulation is used to determine the number of hidden units for every forecast period. Ensemble consists of two ANNs which are trained and cross validated on complementary training sets. Final prediction is obtained by a simple average of two trained ANNs. The described technique is used for predicting one week’s load in four selected months in summer peaking and winter peaking US utilities. Mean absolute percent errors (MAPEs) for 24-hour lead time predictions are slightly greater than 2% for all months. For 120-hour lead time (weekday) predictions, MAPEs are around 2.3%. MAPEs for 48- hour lead time (weekend) predictions are around 2.5%. Maximal errors for these cases are around 7%. Predictions for one-hour lead time are slightly higher than 1% for all months, with maximal errors not exceeding 4.99%. Peak load MAPEs are 2.3% for both utilities. Maximal peak-load errors do not exceed 6%. The technique shows very good performance faced with sudden and large changes in weather. For changes in temperature larger than 20° F for two consecutive days, forecasting error is smaller than 3.58%.","abstract_has_math":false,"creators":["Drezga, Irislav"],"institution":"Virginia Tech","degree_name":"Ph. D.","degree_level":"doctoral","degree_discipline":"Electrical Engineering","degree_department":"Electrical Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Rahman, Saifur"],"committee_members":["Broadwater, Robert P.","VanLandingham, Hugh F.","Conners, Richard W.","Sarin, Subhash C."],"year":1996,"date_issued":"1996-12-05","date_published":"1996-12-05","updated_at":"2026-07-22T22:19:06Z","subjects":["artificial neural networks","phase-space embedding","short-term load forecasting","error analysis"],"languages":["en"],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-06062008-151653"],"render_values":[{"text":"etd-06062008-151653","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/38028","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Rahman, Saifur"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Broadwater, Robert P.","VanLandingham, Hugh F.","Conners, Richard W.","Sarin, Subhash C."]},{"key":"dc:contributor.department","label":"Department","values":["Electrical Engineering"]},{"key":"dc:creator","label":"Author","values":["Drezga, Irislav"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-03-14T21:12:11Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-03-14T21:12:11Z","2008-06-06"]},{"key":"dc:date.issued","label":"Date","values":["1996-12-05"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]},{"key":"dc:type.dcmitype","label":"Dc Type Dcmitype","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph. D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["artificial neural networks","phase-space embedding","short-term load forecasting","error analysis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-06062008-151653"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/38028"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Short-term load forecasting (STLF) deals with forecasting of hourly system demand with a lead time ranging from one hour to 168 hours. The basic objective of the STLF is to provide for economic, reliable and secure operation of the power system. This dissertation establishes a new approach to artificial neural network (ANN) based STLF. It first decomposes the prediction problem into representation and function approximation problems. The representation problem is solved using phase-space embedding which identifies time delay variables from load time series that are used in forecasting. The concept is inherently different from the methods used so far because it does not use correlated variables for forecasting. Temperature variables are included as well using identified embedding parameters. Function approximation problem is approached using ANN ensemble and active selection of a training set. Training set is selected based on predicted weather parameters for a prediction horizon. Selection is done applying the k-nearest neighbors technique in a temperature-based vector space. A novel approach of pilot set simulation is used to determine the number of hidden units for every forecast period. Ensemble consists of two ANNs which are trained and cross validated on complementary training sets. Final prediction is obtained by a simple average of two trained ANNs. The described technique is used for predicting one week’s load in four selected months in summer peaking and winter peaking US utilities. Mean absolute percent errors (MAPEs) for 24-hour lead time predictions are slightly greater than 2% for all months. For 120-hour lead time (weekday) predictions, MAPEs are around 2.3%. MAPEs for 48- hour lead time (weekend) predictions are around 2.5%. Maximal errors for these cases are around 7%. Predictions for one-hour lead time are slightly higher than 1% for all months, with maximal errors not exceeding 4.99%. Peak load MAPEs are 2.3% for both utilities. Maximal peak-load errors do not exceed 6%. The technique shows very good performance faced with sudden and large changes in weather. For changes in temperature larger than 20° F for two consecutive days, forecasting error is smaller than 3.58%."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph. D."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["BTD"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A generalized ANN-based model for short-term load forecasting"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Rahman, Saifur"],"dc:contributor.committeemember":["Broadwater, Robert P.","VanLandingham, Hugh F.","Conners, Richard W.","Sarin, Subhash C."],"dc:contributor.department":["Electrical Engineering"],"dc:creator":["Drezga, Irislav"],"dc:date.accessioned":["2014-03-14T21:12:11Z"],"dc:date.available":["2014-03-14T21:12:11Z","2008-06-06"],"dc:date.issued":["1996-12-05"],"dc:description.abstract":["Short-term load forecasting (STLF) deals with forecasting of hourly system demand with a lead time ranging from one hour to 168 hours. The basic objective of the STLF is to provide for economic, reliable and secure operation of the power system. This dissertation establishes a new approach to artificial neural network (ANN) based STLF. It first decomposes the prediction problem into representation and function approximation problems. The representation problem is solved using phase-space embedding which identifies time delay variables from load time series that are used in forecasting. The concept is inherently different from the methods used so far because it does not use correlated variables for forecasting. Temperature variables are included as well using identified embedding parameters. Function approximation problem is approached using ANN ensemble and active selection of a training set. Training set is selected based on predicted weather parameters for a prediction horizon. Selection is done applying the k-nearest neighbors technique in a temperature-based vector space. A novel approach of pilot set simulation is used to determine the number of hidden units for every forecast period. Ensemble consists of two ANNs which are trained and cross validated on complementary training sets. Final prediction is obtained by a simple average of two trained ANNs. The described technique is used for predicting one week’s load in four selected months in summer peaking and winter peaking US utilities. Mean absolute percent errors (MAPEs) for 24-hour lead time predictions are slightly greater than 2% for all months. For 120-hour lead time (weekday) predictions, MAPEs are around 2.3%. MAPEs for 48- hour lead time (weekend) predictions are around 2.5%. Maximal errors for these cases are around 7%. Predictions for one-hour lead time are slightly higher than 1% for all months, with maximal errors not exceeding 4.99%. Peak load MAPEs are 2.3% for both utilities. Maximal peak-load errors do not exceed 6%. The technique shows very good performance faced with sudden and large changes in weather. For changes in temperature larger than 20° F for two consecutive days, forecasting error is smaller than 3.58%."],"dc:description.degree":["Ph. D."],"dc:format.medium":["BTD"],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["etd-06062008-151653"],"dc:identifier.uri":["http://hdl.handle.net/10919/38028"],"dc:language.iso":["en"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["artificial neural networks","phase-space embedding","short-term load forecasting","error analysis"],"dc:title":["A generalized ANN-based model for short-term load forecasting"],"dc:type":["Dissertation"],"dc:type.dcmitype":["Text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["doctoral"],"thesis:degree_name":["Ph. D."],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:06Z"}