Power load forecasting accuracy related to the development of the power system. There were so many factors influencing the power load, but their effects were not the same and what factors played a leading role could n...Power load forecasting accuracy related to the development of the power system. There were so many factors influencing the power load, but their effects were not the same and what factors played a leading role could not be determined empirically. Based on the analysis of the principal component, the paper forecasted the demands of power load with the method of the multivariate linear regression model prediction. Took the rural power grid load for example, the paper analyzed the impacts of different factors on power load, selected the forecast methods which were appropriate for using in this area, forecasted its 2014-2018 electricity load, and provided a reliable basis for grid planning.展开更多
In this paper,we propose a hybrid forecasting model(HFM)for the short-term electric load forecasting using artificial neural network(ANN),discrete Fourier transformation(DFT)and principal component analysis(PCA)techni...In this paper,we propose a hybrid forecasting model(HFM)for the short-term electric load forecasting using artificial neural network(ANN),discrete Fourier transformation(DFT)and principal component analysis(PCA)techniques in order to attain higher prediction accuracy.Firstly,we estimate Fourier coefficients by the DFT for predicting the next-day load curve with an ANN and obtain approximate load curves by applying the inverse discrete Fourier transformation.Approximate curves,together with other input variables,are given to the ANN to predict the next-day hourly load curves.Furthermore,we predict PCA scores to obtain approximate load curves in the first step,which are then given to the ANN again in the second step.Both DFT and PCA models use input variables such as calendrical and meteorological data as well as past electric loads.Applying those models for forecasting hourly electric load in the metropolitan area of Japan for January and May in 2018,we train our models using historical data since January 2008.The forecast results show that the HFM consisting of“ANN with DFT”and“ANN with PCA”predicts next-day hourly loads more accurately than the conventional three-layered ANN approach.Their corresponding mean average absolute errors show 2.7%for ANN with DFT,2.6%for ANN with PCA and 3.0%for the conventional ANN approach.We also find that in May,when electric demand is smaller with smaller fluctuations,forecasting errors are much smaller than January for all the models.Thus,we can conclude that the HFM would contribute to attaining significantly higher forecasting accuracy.展开更多
With the rapid growth of satellite traffic,the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-...With the rapid growth of satellite traffic,the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-term traffic loads in satellite networks,a forecasting algorithm based on principal component analysis and a generalized regression neural network( PCA-GRNN) is proposed. The PCA-GRNN algorithm exploits the hidden regularity of satellite networks and fully considers both the temporal and spatial correlations of satellite traffic. Specifically,it selects optimal time series of spatio-temporally correlated historical traffic from satellites as forecasting inputs and applies principal component analysis to reduce the input dimensions while preserving the main features of the data.Then,a generalized regression neural network is utilized to perform the final short-term load forecasting based on the obtained principal components. The PCA-GRNN algorithm is evaluated based on real-world traffic traces,and the results show that the PCA-GRNN method achieves a higher forecasting accuracy,has a shorter training time and is more robust than other state-of-the-art algorithms,even for incomplete traffic datasets. Therefore,the PCAGRNN algorithm can be regarded as a preferred solution for use in real-time traffic forecasting for realistic satellite networks.展开更多
Unlike the traditional fossil energy, wind, asthe clean renewable energy, can reduce the emission of thegreenhouse gas. To take full advantage of the environ-mental benefits of wind energy, wind power forecastinghas t...Unlike the traditional fossil energy, wind, asthe clean renewable energy, can reduce the emission of thegreenhouse gas. To take full advantage of the environ-mental benefits of wind energy, wind power forecastinghas to be studied to overcome the troubles brought by thevariable nature of wind. Power forecasting for regionalwind farm groups is the problem that many power systemoperators care about. The high-dimensional feature setswith redundant information are frequently encounteredwhen dealing with this problem. In this paper, two kinds offeature set construction methods are proposed which canachieve the proper feature set either by selecting thesubsets or by transforming the original variables withspecific combinations. The former method selects thesubset according to the criterion of minimal-redundancy-maximal-relevance (mRMR), while the latter does sobased on the method of principal component analysis(PCA). A locally weighted learning method is alsoproposed to utilize the processed feature set to producethe power forecast results. The proposed model is simpleand easy to use with parameters optimized automatically.Finally, a case study of 28 wind farms in East China isprovided to verify the effectiveness of the proposedmethod.展开更多
基金Supported by the Science and Technology Research Project Fund of Provincial Department of Education(12531004)Project of Heilongjiang Leading Talent Echelon Talented(2012)
文摘Power load forecasting accuracy related to the development of the power system. There were so many factors influencing the power load, but their effects were not the same and what factors played a leading role could not be determined empirically. Based on the analysis of the principal component, the paper forecasted the demands of power load with the method of the multivariate linear regression model prediction. Took the rural power grid load for example, the paper analyzed the impacts of different factors on power load, selected the forecast methods which were appropriate for using in this area, forecasted its 2014-2018 electricity load, and provided a reliable basis for grid planning.
文摘In this paper,we propose a hybrid forecasting model(HFM)for the short-term electric load forecasting using artificial neural network(ANN),discrete Fourier transformation(DFT)and principal component analysis(PCA)techniques in order to attain higher prediction accuracy.Firstly,we estimate Fourier coefficients by the DFT for predicting the next-day load curve with an ANN and obtain approximate load curves by applying the inverse discrete Fourier transformation.Approximate curves,together with other input variables,are given to the ANN to predict the next-day hourly load curves.Furthermore,we predict PCA scores to obtain approximate load curves in the first step,which are then given to the ANN again in the second step.Both DFT and PCA models use input variables such as calendrical and meteorological data as well as past electric loads.Applying those models for forecasting hourly electric load in the metropolitan area of Japan for January and May in 2018,we train our models using historical data since January 2008.The forecast results show that the HFM consisting of“ANN with DFT”and“ANN with PCA”predicts next-day hourly loads more accurately than the conventional three-layered ANN approach.Their corresponding mean average absolute errors show 2.7%for ANN with DFT,2.6%for ANN with PCA and 3.0%for the conventional ANN approach.We also find that in May,when electric demand is smaller with smaller fluctuations,forecasting errors are much smaller than January for all the models.Thus,we can conclude that the HFM would contribute to attaining significantly higher forecasting accuracy.
基金supported by the National Natural Science Fundation for Distinguished Young Scholars ( 61425012 )the Fundamental Research Funds for the Central Universities of China ( 2014PTB-00-02)
文摘With the rapid growth of satellite traffic,the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-term traffic loads in satellite networks,a forecasting algorithm based on principal component analysis and a generalized regression neural network( PCA-GRNN) is proposed. The PCA-GRNN algorithm exploits the hidden regularity of satellite networks and fully considers both the temporal and spatial correlations of satellite traffic. Specifically,it selects optimal time series of spatio-temporally correlated historical traffic from satellites as forecasting inputs and applies principal component analysis to reduce the input dimensions while preserving the main features of the data.Then,a generalized regression neural network is utilized to perform the final short-term load forecasting based on the obtained principal components. The PCA-GRNN algorithm is evaluated based on real-world traffic traces,and the results show that the PCA-GRNN method achieves a higher forecasting accuracy,has a shorter training time and is more robust than other state-of-the-art algorithms,even for incomplete traffic datasets. Therefore,the PCAGRNN algorithm can be regarded as a preferred solution for use in real-time traffic forecasting for realistic satellite networks.
文摘Unlike the traditional fossil energy, wind, asthe clean renewable energy, can reduce the emission of thegreenhouse gas. To take full advantage of the environ-mental benefits of wind energy, wind power forecastinghas to be studied to overcome the troubles brought by thevariable nature of wind. Power forecasting for regionalwind farm groups is the problem that many power systemoperators care about. The high-dimensional feature setswith redundant information are frequently encounteredwhen dealing with this problem. In this paper, two kinds offeature set construction methods are proposed which canachieve the proper feature set either by selecting thesubsets or by transforming the original variables withspecific combinations. The former method selects thesubset according to the criterion of minimal-redundancy-maximal-relevance (mRMR), while the latter does sobased on the method of principal component analysis(PCA). A locally weighted learning method is alsoproposed to utilize the processed feature set to producethe power forecast results. The proposed model is simpleand easy to use with parameters optimized automatically.Finally, a case study of 28 wind farms in East China isprovided to verify the effectiveness of the proposedmethod.