Panel semiparametric quantile regression neural network for electricity consumption forecasting

Elevating hourly PM2.5 forecasting in Istanbul, Türkiye: Leveraging ERA5 reanalysis and genetic algorithms in a comparative machine learning model analysis

Rapid urbanization and industrialization have intensified air pollution, posing severe health risks and necessitating accurate PM2.5 predictions for effective urban air quality management. This study distinguishes itself by utilizing high-resolution ERA5 reanalysis data for a grid-based spatial analysis of Istanbul, Türkiye, a densely populated city with diverse pollutant sources. It assesses the predictive accuracy of advanced machine learning (ML) models-Multiple Linear Regression (MLR), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting (LGB), Random Forest (RF), and Nonlinear Autoregressive with Exogenous Inputs (NARX). Notably, it introduces genetic algorithm optimization for the NARX model to enhance its performance. The models were trained on hourly PM2.5 concentrations from twenty monitoring stations across 2020-2021. Istanbul was divided into seven regions based on ERA5 grid distributions to examine PM2.5 spatial variability. Seventeen input variables from ERA5, including meteorological, land cover, and vegetation parameters, were analyzed using the Neighborhood Component Analysis (NCA) method to identify the most predictive variables. Comparative analysis showed that while all models provided valuable insights (RF > LGB > XGB > MLR), the NARX model outperformed them, particularly with the complex dataset used. The NARX model achieved a high R-value (0.89), low RMSE (5.24 μg/m³), and low MAE (2.94 μg/m³). It performed best in autumn and winter, with the highest accuracy in Region-1 (R-value 0.94) and the lowest in Region-5 (R-value 0.75). This study's success in a complex urban setting with limited monitoring underscores the robustness of the NARX model and the methodology's potential for global application in similar urban contexts. By addressing temporal and spatial variability in air quality predictions, this research sets a new benchmark and highlights the importance of advanced data analysis techniques for developing targeted pollution control strategies and public health policies.

Advanced convolutional neural network modeling for fuel cell system optimization and efficiency in methane, methanol, and diesel reforming

Fuel cell systems (FCSs) have been widely used for niche applications in the market. Furthermore, the research community has worked on using FCSs for different sectors, such as transportation, stationary power generation, marine and maritime, aerospace, military and defense, telecommunications, and material handling. The reformation of various fuels, such as methanol, methane, and diesel can be utilized to generate hydrogen for FCSs. This study introduces an advanced convolutional neural network (CNN) model designed to accurately forecast hydrogen yield and carbon monoxide volume percentages during the reformation processes of methane, methanol, and diesel. Moreover, the CNN model has been tailored to accurately estimate methane conversion rates in methane reforming processes. The proposed CNN models are created by combining the 3D-CNN and 2D-CNN models. The Keras Tuner approach in Python is employed in this study to find the ideal values for different hyperparameters such as batch size, learning rate, time steps, and optimization method selection. The accuracy of the proposed CNN model is evaluated by using the root mean square error (RMSE), mean absolute percentage error (MAE), mean absolute error (MAE), and R2. The results indicate that the proposed CNN model is better than other artificial intelligence (AI) techniques and standard CNN for performance estimation of reforming processes of methane, diesel, and methanol. The results also show that the suggested CNN model can be used to accurately estimate critical output parameters for reforming various fuels. The proposed method performs better in CO prediction than the support vector machine (SVM), with an R2 of 0.9989 against 0.9827. This novel methodology not only improves performance estimation for reforming processes but also provides a valuable tool for accurately estimating output parameters across various fuel types.

Decoupling analysis and forecast of economic growth from electricity consumption in the Yangtze River Delta region, China

Decoupling economic growth from electricity consumption is essential for energy conservation and emission reduction. Firstly, this paper applies the LMDI decomposition model to analyze the driving factors of electricity consumption in the Yangtze River Delta region. Secondly, scenario analysis and Monte Carlo technique are combined to research the evolutionary trend of electricity consumption from 2020 to 2035, so as to further analyze the decoupling state. Finally, using nonparametric kernel density estimation, this paper studies the evolution trend of decoupling state from 2005 to 2035. The results show that (1) economic growth is the main factor that promotes the increase of total electricity consumption. Domestic intensity and population scale contribute to the increase in total electricity consumption. The primary factor inhibiting the increase of total electricity consumption is production intensity, while industrial structure and urbanization level contribute to the decrease in total electricity consumption. (2) From 2005 to 2035, the decoupling level has been optimizing on the whole, and the internal gap has also reduced, but there still exists obvious internal gap. (3) Under the three scenarios, the evolution trend of production and domestic electricity consumption is the same. During 2020-2035, the production and domestic electricity consumption both show an increasing trend, with the total electricity consumption under the baseline scenario being the highest, followed by the general and the enhanced electricity-saving scenario. Combined with the empirical results of this paper, some policy recommendations are proposed.

Prediction of electricity energy consumption including COVID-19 precautions using the hybrid MLR-FFANN optimized with the stochastic fractal search with fitness distance balance algorithm

The increase in energy consumption is affected by the developments in technology as well as the global population growth. Increasing energy consumption makes it difficult to ensure electrical energy supply security. Meeting the energy demand can be achieved with the right planning. Proper planning is critical for both economical use of resources and low cost for the end consumer. On the other hand, erroneous estimation of demand may cause waste of resources and energy crisis. Accurate estimation is possible by accurately modeling the factors affecting electricity consumption. Apart from known factors such as seasonal conditions, days of the week and hours, modeling in extreme events such as pandemics that affect all our behaviors increases the success in modeling the future projection. This ensures that the security of electrical energy supply is carried out effectively with limited resources. For this purpose, in this study, a hybrid multiple linear regression-feedforward artificial neural network (MLR-FFANN) based algorithm model was proposed, taking into account the estimated impact of the COVID-19 pandemic on the energy consumption values of Bursa, an industrial city in Turkey. The aim of the hybrid MLR-FFANN approach was to simultaneously optimize the β polynomial for multiple linear regression and the weight and bias coefficients for the forward propagation neural network using the adaptive guided differential evolution, equilibrium optimizer, slime mold algorithm, and stochastic fractal search with fitness distance balance (SFSFDB) optimization algorithms. The success of the model whose parameters were optimized using the optimization algorithms was determined according to mean absolute error, mean absolute percentage error, and root mean square error evaluation criteria and statistical analysis of these results. According to the results of the analysis, the MLR-FFANN approach whose parameters were optimized with the SFSFDB algorithm was more successful in the training of the dataset containing the COVID-19 precautions.