{"title":"基于小波变换、时间序列时滞神经网络和误差预测算法的日前电价预测新方法","authors":"Abhinav Aggarwal, M. M. Tripathi","doi":"10.1109/CERA.2017.8343326","DOIUrl":null,"url":null,"abstract":"This paper presents a novel hybrid intelligent algorithm to forecast day-ahead electricity prices in the ISO New England market for 2014. The proposed algorithm is consisting of signal processing technique based on wavelet transform (WT), a Time Series Time Delay Artificial Neural Network (TSDNN) based prediction network and an error predicting algorithm (EP) based on TSDNN. A comprehensive comparative analysis using the proposed hybrid model, with the specified data from ISO New England website shows significant improvement in forecast error by more than 71.8% for daily price forecasts. Furthermore, a high degree of accuracy of the proposed model is established due to low values obtained for the root mean square error (RMS) and mean absolute error (MAE). The analysis of the performance of the algorithm using both, standard and new performance parameters-Are done to measure the robustness of the proposed hybrid intelligent model. In addition, the rapid adaptability of the proposed hybrid model is also evaluated using the ISO NE electricity market.","PeriodicalId":286358,"journal":{"name":"2017 6th International Conference on Computer Applications In Electrical Engineering-Recent Advances (CERA)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"A novel hybrid approach using wavelet transform, time series time delay neural network, and error predicting algorithm for day-ahead electricity price forecasting\",\"authors\":\"Abhinav Aggarwal, M. M. Tripathi\",\"doi\":\"10.1109/CERA.2017.8343326\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a novel hybrid intelligent algorithm to forecast day-ahead electricity prices in the ISO New England market for 2014. The proposed algorithm is consisting of signal processing technique based on wavelet transform (WT), a Time Series Time Delay Artificial Neural Network (TSDNN) based prediction network and an error predicting algorithm (EP) based on TSDNN. A comprehensive comparative analysis using the proposed hybrid model, with the specified data from ISO New England website shows significant improvement in forecast error by more than 71.8% for daily price forecasts. Furthermore, a high degree of accuracy of the proposed model is established due to low values obtained for the root mean square error (RMS) and mean absolute error (MAE). The analysis of the performance of the algorithm using both, standard and new performance parameters-Are done to measure the robustness of the proposed hybrid intelligent model. In addition, the rapid adaptability of the proposed hybrid model is also evaluated using the ISO NE electricity market.\",\"PeriodicalId\":286358,\"journal\":{\"name\":\"2017 6th International Conference on Computer Applications In Electrical Engineering-Recent Advances (CERA)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 6th International Conference on Computer Applications In Electrical Engineering-Recent Advances (CERA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CERA.2017.8343326\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 6th International Conference on Computer Applications In Electrical Engineering-Recent Advances (CERA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CERA.2017.8343326","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A novel hybrid approach using wavelet transform, time series time delay neural network, and error predicting algorithm for day-ahead electricity price forecasting
This paper presents a novel hybrid intelligent algorithm to forecast day-ahead electricity prices in the ISO New England market for 2014. The proposed algorithm is consisting of signal processing technique based on wavelet transform (WT), a Time Series Time Delay Artificial Neural Network (TSDNN) based prediction network and an error predicting algorithm (EP) based on TSDNN. A comprehensive comparative analysis using the proposed hybrid model, with the specified data from ISO New England website shows significant improvement in forecast error by more than 71.8% for daily price forecasts. Furthermore, a high degree of accuracy of the proposed model is established due to low values obtained for the root mean square error (RMS) and mean absolute error (MAE). The analysis of the performance of the algorithm using both, standard and new performance parameters-Are done to measure the robustness of the proposed hybrid intelligent model. In addition, the rapid adaptability of the proposed hybrid model is also evaluated using the ISO NE electricity market.