Forecasting of Coal Demand in China Based on Support Vector Machine Optimized by the Improved Gravitational Search Algorithm

Li, Yanbin; Li, Zhen

doi:10.3390/en12122249

Cited by 14 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The support vector machine (SVM) was first introduced in the kernel function; SVM has the advantages of universality, robustness, effectiveness, and simple calculation point, which can better solve the classification problem in the case of small samples, nonlinearity, and high dimension, and has strong generalization ability [9]. However, whether the parameters of support vector machine are appropriate or not will have a great impact on the training and convergence of data [10][11][12][13][14]. Particle swarm optimization (PSO) has not only global optimization ability but also efficient convergence and strong local optimization ability [15][16][17][18].…”

Section: Introductionmentioning

confidence: 99%

Economic Crisis Early Warning of Real Estate Companies Based on PSO-Optimized SVM

2022

Journal of Sensors

View full text Add to dashboard Cite

For the possible economic crisis of real estate companies, by analyzing the shortcomings of support vector machine (SVM) model, after optimization with particle swarm optimization (PSO), the PSO-SVM model was established by changing economic condition parameters and using data to warn the real estate economic crisis. Then, this model is used to warn the economic capacity of four real estate companies in Beijing. The results show that this model can further predict and analyze the solvency index, operating ability index, development ability index, profitability index, cash flow index, and comprehensive financial index of real estate companies and come to the conclusion that profitability index is the most important, and higher profitability can resist the harm brought by economic crisis. Finally, it analyzes the economic crisis that real estate companies may encounter and puts forward specific suggestions.

show abstract

Section: Introductionmentioning

confidence: 99%

Economic Crisis Early Warning of Real Estate Companies Based on PSO-Optimized SVM

2022

Journal of Sensors

View full text Add to dashboard Cite

show abstract

“…Many scholars and research institutes in the world have been committed to energy consumption prediction, and have developed a lot of models such as time series models [4][5], regression models [6][7][8][9][10][11][12], econometrics models [13], vector auto-regression models [14][15][16], and other models [17][18][19][20][21]. However, energy system is a complex system, which is affected and restricted by many factors during its development.…”

Section: Introductionmentioning

confidence: 99%

The Application of Machine Learning in Primary Energy Consumption in China: Comparative Analysis of Artificial Neural Networks and Multiple Linear Regression

Liang

Liu

Han

et al. 2022

Preprint

View full text Add to dashboard Cite

Energy is the main driving force for economic and social development. While a reliable prediction of a country's primary energy consumption (PEC) is paramount, it remains a daunting task because many factors in various sectors of society affect the primary energy consumption in complex nonlinear ways. Based on China's energy statistics from 1952 to 2019, 25 influencing factors are considered from five dimensions of economy, energy, environment, technology and policy, and the correlation analysis method is used to evaluate the relationship between the primary energy consumption and each influencing factor. In addition, multicollinearity of variables is diagnosed by R program. Multiple linear regression (MLR) and artificial neural networks (ANN) model are applied to fit PEC curve. The discriminatory machine learning algorithms are compared and analyzed. The results show that the MLR model has the advanced of fitting compared with ANN in small sample data. Moreover, forward selection (FS), backward elimination (BE), forced introduction (FI) and ridge regression (RR) are used to obtain the fitting equation of the PEC. The mean absolute percentage errors (MAPE) of FS, BE, FI, RR and ANN are 2.16%, 1.68%, 1.91%, 1.31% and 19.89%, respectively. Finally, scenario analysis is used to predict China's PEC in 2050.

show abstract

“…This method improves the model interpretability by using linear model and reduces the adverse impact of noise data on the forecast model by using Huber loss function (Gupta et al, 2020). We use the kernel function to mine the implicit nonlinearity law in the steam coal data (Li and Li, 2019;Vu et al, 2019;Ye et al, 2021). The combined model can improve the model performance based on the advantages of the sub-model (Wang et al, 1210;Zhou et al, 2019;Wang et al, 2020a;Wang et al, 2020b;Qiao et al, 2021;Zhang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Forecasting of Steam Coal Price Based on Robust Regularized Kernel Regression and Empirical Mode Decomposition

Tang

et al. 2021

Front. Energy Res.

View full text Add to dashboard Cite

Aiming at the problem of difficulties in modeling the nonlinear relation in the steam coal dataset, this article proposes a forecasting method for the price of steam coal based on robust regularized kernel regression and empirical mode decomposition. By selecting the polynomial kernel function, the robust loss function and L2 regular term to construct a robust regularized kernel regression model are used. The polynomial kernel function does not depend on the kernel parameters and can mine the global rules in the dataset so that improves the forecasting stability of the kernel model. This method maps the features to the high-dimensional space by using the polynomial kernel function to transform the nonlinear law in the original feature space into linear law in the high-dimensional space and helps learn the linear law in the high-dimensional feature space by using the linear model. The Huber loss function is selected to reduce the influence of abnormal noise in the dataset on the model performance, and the L2 regular term is used to reduce the risk of model overfitting. We use the combined model based on empirical mode decomposition (EMD) and auto regressive integrated moving average (ARIMA) model to compensate for the error of robust regularized kernel regression model, thus making up for the limitations of the single forecasting model. Finally, we use the steam coal dataset to verify the proposed model and such model has an optimal evaluation index value compared to other contrast models after the model performance is evaluated as per the evaluation index such as RMSE, MAE, and mean absolute percentage error.

show abstract

Forecasting of Coal Demand in China Based on Support Vector Machine Optimized by the Improved Gravitational Search Algorithm

Cited by 14 publications

References 31 publications

Economic Crisis Early Warning of Real Estate Companies Based on PSO-Optimized SVM

Economic Crisis Early Warning of Real Estate Companies Based on PSO-Optimized SVM

The Application of Machine Learning in Primary Energy Consumption in China: Comparative Analysis of Artificial Neural Networks and Multiple Linear Regression

Forecasting of Steam Coal Price Based on Robust Regularized Kernel Regression and Empirical Mode Decomposition

Contact Info

Product

Resources

About