Abstract:Annual electricity consumption forecasting is one of the important foundations of power system planning. Considering that the long-term electricity consumption curves of developing countries usually present approximately exponential growth trends and linear and accelerated growth rate trends may also appear in certain periods, this paper first proposes a small-sample adaptive hybrid model (AHM) to extrapolate the above curves. The iterative trend extrapolation equation of the proposed model can simulate the li… Show more
“…Amina et al [15] implemented a novel fuzzy wavelet neural network model for electricity consumption forecasting in the power system of the Greek Island of Crete, which provided significantly better results. In [16], a small-sample adaptive hybrid model (AHM) based on trend extrapolation method was proposed to forecast electricity consumption in China from 1991 to 2014, which showed robustness to stochastic changes and obtained more precise forecasting results. Al-Ghandoor et al [17] presented an empirical model based on multivariate linear regression of time series for the Jordanian industrial sector, which identified the main influential factors of electricity consumption.…”
The electricity consumption forecasting is a challenging task, because the predictive accuracy is easily affected by multiple external factors, such as society, economics, environment, as well as the renewable energy, including hydro power, wind power and solar power. Particularly, in the smart grid with large amount of data, how to extract valuable information of those external factors timely is the key to the success of electricity consumption forecasting. A method of probability density forecasting based on Least Absolute Shrinkage and Selection Operator-Quantile Regression Neural Network (LASSO-QRNN) is proposed in this paper. First, important features are extracted from external factors affecting the electricity consumption forecasting by LASSO regression. Then, the LASSO-QRNN model is constructed to predict annual electricity consumption. The results of electricity consumption forecasting under different quantiles in the next several years are evaluated. Besides, we introduce kernel density estimation into our LASSO-QRNN model, which can give a probability distribution instead of a single-valued prediction. The prediction accuracy is evaluated through the empirical analyses from the Guangdong province dataset in China and the California dataset in the United States. The simulation results demonstrate that the proposed method provides better performance for electricity consumption forecasting, in comparison with existing quantile regression neural network (QRNN), back-propagation of errors neural network (BP), radial basis function neural network (RBF) methods, quantile regression (QR) and nonlinear quantile regression (NLQR). LASSO-QRNN can not only better learn the high-dimensional data in electricity consumption forecasting, but also provide more precise results.
“…Amina et al [15] implemented a novel fuzzy wavelet neural network model for electricity consumption forecasting in the power system of the Greek Island of Crete, which provided significantly better results. In [16], a small-sample adaptive hybrid model (AHM) based on trend extrapolation method was proposed to forecast electricity consumption in China from 1991 to 2014, which showed robustness to stochastic changes and obtained more precise forecasting results. Al-Ghandoor et al [17] presented an empirical model based on multivariate linear regression of time series for the Jordanian industrial sector, which identified the main influential factors of electricity consumption.…”
The electricity consumption forecasting is a challenging task, because the predictive accuracy is easily affected by multiple external factors, such as society, economics, environment, as well as the renewable energy, including hydro power, wind power and solar power. Particularly, in the smart grid with large amount of data, how to extract valuable information of those external factors timely is the key to the success of electricity consumption forecasting. A method of probability density forecasting based on Least Absolute Shrinkage and Selection Operator-Quantile Regression Neural Network (LASSO-QRNN) is proposed in this paper. First, important features are extracted from external factors affecting the electricity consumption forecasting by LASSO regression. Then, the LASSO-QRNN model is constructed to predict annual electricity consumption. The results of electricity consumption forecasting under different quantiles in the next several years are evaluated. Besides, we introduce kernel density estimation into our LASSO-QRNN model, which can give a probability distribution instead of a single-valued prediction. The prediction accuracy is evaluated through the empirical analyses from the Guangdong province dataset in China and the California dataset in the United States. The simulation results demonstrate that the proposed method provides better performance for electricity consumption forecasting, in comparison with existing quantile regression neural network (QRNN), back-propagation of errors neural network (BP), radial basis function neural network (RBF) methods, quantile regression (QR) and nonlinear quantile regression (NLQR). LASSO-QRNN can not only better learn the high-dimensional data in electricity consumption forecasting, but also provide more precise results.
“…In the matter of energy demand, various forecasting models have been applied to predict the electricity consumption. Traditional methods such as regression analysis (RA), time series analysis, nonparametric method, and small-sample adaptive hybrid model as well as soft computing techniques such as fuzzy logic, genetic algorithm, and neural networks are being extensively used [12][13][14][15][16][17]. Support vector regression, ant colony, and particle swarm optimization are new techniques being adopted for energy demand forecasting.…”
Due to the deregulation of retail electricity market, consumers can choose retail electric suppliers freely, and market entities are facing fierce competition because of the increasing number of new entrants. Under these circumstances, forecasting the changes in all market entities, when market share stabilized, is important for suppliers making marketing decisions. In this paper, a market share forecasting model was established based on Markov chain, and a system dynamics model was constructed to forecast the electricity consumption based on the analysis of five factors which are economic development, policy factors, environmental factors, power energy substitution, and power grid development. For a real application, the retail electricity market of Guangdong province in China was selected. The total, industrial, and commercial electricity consumption in Guangdong from 2016 to 2020 were predicted under different scenarios, and the market shares of the main market entities were analyzed using Markov chain model. Results indicated that the direct trading electricity would account for 70% to 90% of the total electricity consumption in the future. This provided valuable reference for the decision-making of suppliers and the development of electricity industry.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.