Even though there are numerous CO₂ capture technologies (such as chemical and physical absorption), investigators are still trying to come up with novel methods that can minimize the energy requirements for their integration into thermal power plants, as well as the CAPEX and OPEX expenses. In this work, the technical and financial aspects of integrating two-stage polymeric membranes into a coal-fired power plant with a capacity of 330 MW were examined. The study researched the membrane post-combustion CO₂ capture process utilizing CHEMCAD version 8.1 software with several parameters and an expander to decrease the total cost. The simulation showed promising results regarding reducing power consumption after using an expander for both a high capture rate (>90%) and a CO₂ concentration of more than 95%. Thus, the CO₂ captured cost decreased from 58.4 EUR/t (no expander) to 48.7 EUR/t (with expander).

Presently, the utilization of biomass as an energy source has gained significant attention globally due to its capacity to provide constant feedstock. In 2020, biomass combustion generated 19 Mt of CO₂, representing an increase of 16% from the previous year. The increase in CO₂ emissions is fundamentally due to biomass gasification in power plants. Due to the growing demand to reduce greenhouse gas emissions, this paper aims to improve CO₂ capture technologies to face this challenge. In this context, the utilization of three stages of the polymer membrane process, using different compressor pressure values, has been technically and economically analyzed. The proposed solution was combined pre-combustion in a BIGCC process equipped with a Siemens gas turbine with an installed power capacity of 50 MW. The article simulated energy operations by using membranes of polymer and CHEMCAD software improved in the CO₂ integration research project. Consequently, polymeric membranes with CO₂ permeability of 1000 GPU were examined while CO₂ selectivity towards nitrogen was investigated to be 50. It was observed that by increasing the surface area of the polymer membrane (400,000–1,200,000 m²) an increase of 37% occurs in CO₂ capture efficiency. On the other hand, LCOE increased from 97 to 141 EUR/MWh. The avoided cost of CO₂ captured was 52.9 EUR/ton.

Despite the many technologies for CO₂ capture (e.g., chemical or physical absorption or adsorption), researchers are looking to develop other technologies that can reduce CAPEX and OPEX costs as well as the energy requirements associated with their integration into thermal power plants. The aim of this paper was to analyze the technical and economic integration of spiral wound membranes in a coal-fired power plant with an installed capacity of 330 MW (the case of the Rovinari power plant—in Romania). The study modeled energy processes using CHEMCAD version 8.1 software and polymer membranes developed in the CO₂ Hybrid research project. Thus, different configurations such as a single membrane step with and without the use of a vacuum pump and two membrane steps placed in series were analyzed. In all cases, a compressor placed before the membrane system was considered. The use of two serialized stages allows for both high efficiency (minimum 90%) and CO₂ purity of a minimum of 95%. However, the overall plant efficiency decreased from 45.78 to 23.96% and the LCOE increased from 75.6 to 170 €/kWh. The energy consumption required to capture 1 kg of CO₂ is 2.46 MJ_el and 4.52 MJ_th.

A sensitive analysis of CO₂ capture from a coal-fired power plant of 600 MW with membrane technology based on post-combustion process is demonstrated. This study aimed to determine the influence of the membrane materials used (e.g., CO₂ permeability was considered at 300, 1000, and 3000 GPU) on coal-fired power plant performance by investigating various parameters, such as the membrane number of stages, membrane surface area, and compressors’ pressure. The membrane surface area required varied from 200,000 to 800,000 m² to procure no less than 99% purity. The total power plant efficiency was reduced by different values after integrating membrane CO₂-capture technology based on the process design; nevertheless, the efficiency is profitable by around 13.5% when three membrane stages were harnessed instead of a two-stage configuration. Consequently, the levelized cost of energy (LCOE) decreased from 157 EUR/MWh (two stages of membrane) to 134 EUR/MWh (three stages of membrane).

Water desalination plants are significant consumers of electric power, making them some of the largest energy users in power grids. Their electricity consumption presents an urgent challenge for efficient and sustainable operation, and they are among the most power‐quality‐threatening customers for utilities. This study presents three distinct strategies to enhance prediction accuracy and extend forecasting horizons, aiming to reduce algorithmic and hardware delays. Additionally, it suggests effective methods to compensate for voltage fluctuations, voltage flicker, and dips arising from desalination plants. The paper also discusses forecasting harmonics and interharmonics in current signals. Furthermore, it integrates the above techniques into a comprehensive computing system, along with an active power filter (APF) scheme, within the Simulink framework. A comparison is drawn between the performance of predictive techniques in an APF and a conventional, non‐predictive APF. The proposed data augmentation method successfully increases prediction accuracy. By effectively forecasting upcoming waveforms, it reduces algorithmic and hardware delays. These techniques are designed to address multiple power quality issues simultaneously, including harmonics, interharmonics, flicker, and voltage dips, which often coexist in the spectrum as interharmonics. The suggested approach employs Long Short‐Term Memory (LSTM) networks combined with the Jetson TX2 embedded artificial intelligence computer to accelerate machine learning applications. This method has proven effective in predicting and classifying time series data, including harmonics, interharmonics, and raw current signals, achieving 100% accuracy. This eliminates the need for designing specific low‐pass filters. The evaluation results for this time‐domain deep learning‐based technique will be reported in the subsections below. The implementation is conducted in Python using the KERAS deep learning framework and TensorFlow backend, and it is evaluated on a workstation equipped with an Intel i7 processor running at 4.0 GHz and 48 GB of RAM.