Predicting carbon dioxide emissions in the United States of America using machine learning algorithms.

Carbon dioxide (CO2) emissions result from human activities like burning fossil fuels. CO2 is a greenhouse gas, contributing to global warming and climate change. Efforts to reduce CO2 emissions include transitioning to renewable energy. Monitoring and reducing CO2 emissions are crucial for mitigating climate change. Strategies include energy efficiency and renewable energy adoption. In the past few decades, several nations have experienced air pollution and environmental difficulties because of carbon dioxide (CO2) emissions. One of the most crucial methods for regulating and maximizing CO2 emission reductions is precise forecasting. Four machine learning algorithms with high forecasting precision and low data requirements were developed in this study to estimate CO2 emissions in the United States (US). Data from a dataset covering the years 1973/01 to 2022/07 that included information on different energy sources that had an impact on CO2 emissions were examined. Then, four algorithms performed the CO2 emissions forecast from the layer recurrent neural network with 10 nodes (L-RNN), a feed-forward neural network with 10 nodes (FFNN), a convolutional neural network with two layers with 10 and 5 filters (CNN1), and convolutional neural network with two layers and with 50 and 25 filters (CNN2) models. Each algorithm's forecast accuracy was assessed using eight indicators. The three preprocessing techniques used are (1) without any processing techniques, (2) processed using max-min normalization technique, and (3) processed using max-min normalization technique and decomposed by variation mode decomposition (VMD) technique with 7 intrinsic mode functions and 1000 iterations. The latter with L-RNN algorithm gave a high accuracy between the forecasting and actual values. The results of CO2 emissions from 2011/05 to 2022/07 have been forecasted, and the L-RNN algorithm had the highest forecast accuracy. The L-RNN model has the lowest value of 1.187028078, 135.5668592, and 11.64331822 for MAPE, MSE, and RMSE, respectively. The L-RNN model provides precise and timely forecasts that can help formulate plans to reduce carbon emissions and contribute to a more sustainable future. Moreover, the results of this investigation can improve our comprehension of the dynamics of carbon dioxide emissions, resulting in better-informed environmental policies and initiatives targeted at lowering carbon emissions.

Maximum power extraction and DC-Bus voltage regulation in grid-connected PV/BES system using modified incremental inductance with a novel inverter control.

Low ripples and variations in the DC-Bus voltage in single-phase Photovoltaic/Battery Energy Storage (PV/BES) grid-connected systems may cause significant harmonics distortion, instability, and reduction in power factor. The use of short-life electrolytic capacitor on the DC-Bus is considered a standard way for reducing these ripples and variations because of its large capacitance but results in short lifetime of the inverter. Replacing large electrolytic capacitors with small film capacitors can extend the lifetime of a PV/BES grid-connected system because small film capacitors have longer lifetime than large electrolytic capacitors. These film capacitors have low capacitance, which causes severe oscillations in the output current, and voltage drop due to huge ripples on the DC-Bus voltage. In this research, the main goal is to eliminate the output current ripples and voltage fluctuations associated with employing film capacitors. First, a modified incremental conductance (MIC) technique is proposed for tracking the maximum power by controlling the duty ratio of the DC-DC boost converter. Second, for the first time, a simple and novel d-q current regulation technique, which employs flowchart decision logic, is used in the DC-Bus control system for both the PV power system and the state of charge (SOC) of the BES. In this case, the DC-Bus controller is characterized by a cost-effective implementation because of its low sampling frequency. Although the presented approaches are successful in eliminating voltage distortion and fluctuations, they have unacceptable dynamic performance. Therefore, to improve the dynamic performance, BES was used to maintain a reliable and stable harvest from PV modules for varying loads while also increasing the dynamic performance of the overall system. The proposed PV/BES grid-connected systems, which employs a small 10-µF bus capacitor, is simulated and connected to the grid (230 V, 50 Hz). The DC-Bus voltage overshoot, undershoot and the total harmonics distortion (THD) of the output current for the proposed MIC are (1 V), (2.5 V) and (less than 5%), respectively. The average time response under rising radiation to track the global peak for MIC, traditional incremental conductance and variable step size incremental conductance are 1.403 s, 1.501 s and 1.113 s respectively. The obtained findings demonstrated the efficacy and superiority of the proposed d-q current control and MIC technique.