{"title":"基于统计-神经-计算智能混合方法的电力负荷预测","authors":"M. Gavrilas, O. Ivanov, G. Gavrilas","doi":"10.1109/NEUREL.2014.7011461","DOIUrl":null,"url":null,"abstract":"This paper presents a medium term load forecasting methodology based on a mixed statistical computational intelligence model. The methodology can be used by any entity (such as transmission and distribution operators, electricity suppliers or energy managers) interested in planning different activities with electricity. The methodology produces daily load profiles forecasts for all the 365 days of the next year. The statistical model predicts annual energy consumption and monthly and daily consumptions based on traditional regression models, while typical load profiles for each day of the week and every week of the year are produced using computational intelligence techniques based on self-organizing models with Kohonen neural networks or a heuristic optimization technique, namely the Gravitational Search Algorithm.","PeriodicalId":402208,"journal":{"name":"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Electricity load forecasting based on a mixed statistical-neural-computational intelligence approach\",\"authors\":\"M. Gavrilas, O. Ivanov, G. Gavrilas\",\"doi\":\"10.1109/NEUREL.2014.7011461\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a medium term load forecasting methodology based on a mixed statistical computational intelligence model. The methodology can be used by any entity (such as transmission and distribution operators, electricity suppliers or energy managers) interested in planning different activities with electricity. The methodology produces daily load profiles forecasts for all the 365 days of the next year. The statistical model predicts annual energy consumption and monthly and daily consumptions based on traditional regression models, while typical load profiles for each day of the week and every week of the year are produced using computational intelligence techniques based on self-organizing models with Kohonen neural networks or a heuristic optimization technique, namely the Gravitational Search Algorithm.\",\"PeriodicalId\":402208,\"journal\":{\"name\":\"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NEUREL.2014.7011461\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NEUREL.2014.7011461","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Electricity load forecasting based on a mixed statistical-neural-computational intelligence approach
This paper presents a medium term load forecasting methodology based on a mixed statistical computational intelligence model. The methodology can be used by any entity (such as transmission and distribution operators, electricity suppliers or energy managers) interested in planning different activities with electricity. The methodology produces daily load profiles forecasts for all the 365 days of the next year. The statistical model predicts annual energy consumption and monthly and daily consumptions based on traditional regression models, while typical load profiles for each day of the week and every week of the year are produced using computational intelligence techniques based on self-organizing models with Kohonen neural networks or a heuristic optimization technique, namely the Gravitational Search Algorithm.