• Energy Research

Precisely predicting natural gas prices (NGPs) is important because it can provide the necessary decision-making basis for energy scheduling, planning and control. However, NGPs are affected by many factors and exhibit the characteristics of nonlinearity and randomness, which makes accurate predictions challenging. Therefore, in this paper, the information gain of multisource data and the global optimization ability of the gray wolf algorithm are used to build a multifactor-driven NGP hybrid forecasting model to improve the prediction performance. First, the emotional tendency and readability of news text are extracted and calculated by using VADER and textstat tools, respectively. Then the network search index is filtered and integrated by using the correlation coefficient method and the CRITIC method to form alternative variables of multisource data (news and search index). Second, the gray wolf optimization algorithm is used to find and determine the best key parameter group in long short-term memory model. Finally, the spot price of natural gas in Henry Hub from March 1, 2012 to February 28, 2022 is selected as the prediction object, and multi-scenario numerical experiments are carried out to verify the effectiveness of the proposed model. The ablation experiment results show that the information gain brought by multisource data can effectively improve the prediction effect of NGPs. Furthermore, the proposed model has the best prediction performance in different scenarios and can be regarded as a promising prediction tool.

Precisely predicting natural gas prices (NGPs) is important because it can provide the necessary decision-making basis for energy scheduling, planning and control. However, NGPs are affected by many factors and exhibit the characteristics of nonlinearity and randomness, which makes accurate predictions challenging. Therefore, in this paper, the information gain of multisource data and the global optimization ability of the gray wolf algorithm are used to build a multifactor-driven NGP hybrid forecasting model to improve the prediction performance. First, the emotional tendency and readability of news text are extracted and calculated by using VADER and textstat tools, respectively. Then the network search index is filtered and integrated by using the correlation coefficient method and the CRITIC method to form alternative variables of multisource data (news and search index). Second, the gray wolf optimization algorithm is used to find and determine the best key parameter group in long short-term memory model. Finally, the spot price of natural gas in Henry Hub from March 1, 2012 to February 28, 2022 is selected as the prediction object, and multi-scenario numerical experiments are carried out to verify the effectiveness of the proposed model. The ablation experiment results show that the information gain brought by multisource data can effectively improve the prediction effect of NGPs. Furthermore, the proposed model has the best prediction performance in different scenarios and can be regarded as a promising prediction tool.

Abstract Accurate installed capacity forecasting can provide effective decision-making support for planning development strategies and establishing national electricity policies. First, considering the data limitation in quantity and accuracy, this paper proposes a multi-factor installed capacity forecasting framework combining the fuzzy time series method and support vector regression. Compared with four benchmark models, the proposed model shows advantages in installed capacity prediction. Second, the predictability dynamics of national installed capacity are explored from the perspective of country clusters. It is revealed that highly predictable countries usually obtain high forecasting accuracy with all forecasting models and are less sensitive to forecasting models. Using the k-means clustering method, this paper divides 136 sample countries into four categories according to the predictability. Third, based on the mean impact value analysis, this paper differentiates and ranks the importance of input variables on installed capacity development. The two most important factors influencing installed capacity are installed capacity development in the previous period and population. Overall, these results are of practical value to the operating decisions of electric power enterprises and the electricity plans of governments.

Abstract Accurate installed capacity forecasting can provide effective decision-making support for planning development strategies and establishing national electricity policies. First, considering the data limitation in quantity and accuracy, this paper proposes a multi-factor installed capacity forecasting framework combining the fuzzy time series method and support vector regression. Compared with four benchmark models, the proposed model shows advantages in installed capacity prediction. Second, the predictability dynamics of national installed capacity are explored from the perspective of country clusters. It is revealed that highly predictable countries usually obtain high forecasting accuracy with all forecasting models and are less sensitive to forecasting models. Using the k-means clustering method, this paper divides 136 sample countries into four categories according to the predictability. Third, based on the mean impact value analysis, this paper differentiates and ranks the importance of input variables on installed capacity development. The two most important factors influencing installed capacity are installed capacity development in the previous period and population. Overall, these results are of practical value to the operating decisions of electric power enterprises and the electricity plans of governments.

Based on empirical evidence from Yangtze River Delta, Pearl River Delta and Circum-Bohai-Sea region, this study applies the Input-Output (I-O) model and ArcGIS to analyze the interdependence and its dynamic evolution of the shipbuilding industry. In order to study the change cause of shipbuilding industrial structure, we decompose the I-O model to obtain the influential factors including domestic final demand, overseas export demand, intermediate input, intermediate demand import and final demand import. The results indicate that (1) the shipbuilding industry has a significant interdependence, which has showed the characteristics of high integration and interaction. Among the three different regions, the degree of interdependence of the Yangtze River Delta is most significant, followed by the Pearl River Delta and the Circum-Bohai region. (2) The interaction and integration of the shipbuilding industry have the trend of synchronous development. From the initial S-shapes of coastal distribution, the interaction gradually expands to inland cities radially. (3) The dependence of the shipbuilding industry has reduced but the self-supporting effect continuously strengthened, and industrialization is accelerating, which indicates the shipbuilding industry will further promote the optimization of industrial structure. (4) Shipbuilding industry has been expanding a lot, the main causes of changes in industrial structure are different, and the effect of intermediate inputs change plays a significant role in the Yangtze River Delta. In the Pearl River Delta, it is the changes effect of foreign export demand that counts. However, it is the effect of the final demand that makes contribution to the industrial structure change in Circum-Bohai-Sea region.

Based on empirical evidence from Yangtze River Delta, Pearl River Delta and Circum-Bohai-Sea region, this study applies the Input-Output (I-O) model and ArcGIS to analyze the interdependence and its dynamic evolution of the shipbuilding industry. In order to study the change cause of shipbuilding industrial structure, we decompose the I-O model to obtain the influential factors including domestic final demand, overseas export demand, intermediate input, intermediate demand import and final demand import. The results indicate that (1) the shipbuilding industry has a significant interdependence, which has showed the characteristics of high integration and interaction. Among the three different regions, the degree of interdependence of the Yangtze River Delta is most significant, followed by the Pearl River Delta and the Circum-Bohai region. (2) The interaction and integration of the shipbuilding industry have the trend of synchronous development. From the initial S-shapes of coastal distribution, the interaction gradually expands to inland cities radially. (3) The dependence of the shipbuilding industry has reduced but the self-supporting effect continuously strengthened, and industrialization is accelerating, which indicates the shipbuilding industry will further promote the optimization of industrial structure. (4) Shipbuilding industry has been expanding a lot, the main causes of changes in industrial structure are different, and the effect of intermediate inputs change plays a significant role in the Yangtze River Delta. In the Pearl River Delta, it is the changes effect of foreign export demand that counts. However, it is the effect of the final demand that makes contribution to the industrial structure change in Circum-Bohai-Sea region.

Accurate forecasting of the energy demand is crucial for the rational formulation of energy policies for energy management. In this paper, a novel ensemble forecasting model based on the artificial bee colony (ABC) algorithm for the energy demand was proposed and adopted. The ensemble model forecasts were based on multiple time variables, such as the gross domestic product (GDP), industrial structure, energy structure, technological innovation, urbanization rate, population, consumer price index, and past energy demand. The model was trained and tested using the primary energy demand data collected in China. Seven base models, including the regression-based model and machine learning models, were utilized and compared to verify the superior performance of the ensemble forecasting model proposed herein. The results revealed that (1) the proposed ensemble model is significantly superior to the benchmark prediction models and the simple average ensemble prediction model just in terms of the forecasting accuracy and hypothesis test, (2) the proposed ensemble approach with the ABC algorithm can be employed as a promising framework for energy demand forecasting in terms of the forecasting accuracy and hypothesis test, and (3) the forecasting results obtained for the future energy demand by the ensemble model revealed that the future energy demand of China will maintain a steady growth trend.

Accurate forecasting of the energy demand is crucial for the rational formulation of energy policies for energy management. In this paper, a novel ensemble forecasting model based on the artificial bee colony (ABC) algorithm for the energy demand was proposed and adopted. The ensemble model forecasts were based on multiple time variables, such as the gross domestic product (GDP), industrial structure, energy structure, technological innovation, urbanization rate, population, consumer price index, and past energy demand. The model was trained and tested using the primary energy demand data collected in China. Seven base models, including the regression-based model and machine learning models, were utilized and compared to verify the superior performance of the ensemble forecasting model proposed herein. The results revealed that (1) the proposed ensemble model is significantly superior to the benchmark prediction models and the simple average ensemble prediction model just in terms of the forecasting accuracy and hypothesis test, (2) the proposed ensemble approach with the ABC algorithm can be employed as a promising framework for energy demand forecasting in terms of the forecasting accuracy and hypothesis test, and (3) the forecasting results obtained for the future energy demand by the ensemble model revealed that the future energy demand of China will maintain a steady growth trend.