Gas-fired Power Plants Research Articles

A transient study on a solar-assisted combined gas power cycle for sustainable multi-generation in hot and cold climates: Case studies of Dubai and Toronto

Efficiently managing heat losses continues to be a prominent obstacle within gas-fired power plants. The discharge of high-temperature gases from turbines and the considerable pressure generated by compressors present compelling opportunities for augmenting both power generation and overall efficiency. The present study analyzes a gas-fired power plant with two additional Rankine cycles and a concentrated solar power system to enhance efficiency and output power. Clean power generation and distilled water were the outputs of the proposed system. This study also sought to reduce greenhouse gas (GHG) emissions by using solar energy and diminishing the consumption of fossil fuels (CH4) in the combustion chamber. The proposed system was implemented in hot and cold climates. The Brayton cycle of the system was validated through data of a real-life power cycle on the southern coasts of Iran. Furthermore, a transient evaluation was conducted to explore the effects of climatic parameters on the power and desalination system. The contributions of solar irradiance, wind speed, and ambient temperature to the proposed system in a hot climate (Dubai, UAE) and a cold climate (Toronto, Canada) were evaluated. It was found that gas turbine efficiency, compression ratio, and gas turbine input temperature had the greatest effects on the system. Exergy analysis revealed that the combustion chamber, heliostats, the solar receiver, the multi-effect distillation (MED) unit, gas turbine 1, and the thermoelectric generator accounted for the largest portion of the exergy destruction. The case study indicated that the system would work best in climates like Toronto. The findings can be useful to investors and governments in such climates. The proposed system demonstrates its adaptability to regions sharing a climate resembling that of Toronto, making it a viable solution for a wide range of geographical areas. The design and functionality of the system have been meticulously crafted to accommodate the specific environmental conditions present in Toronto and its comparable regions. Gas-fired power plants across numerous countries widely employ the Brayton cycle as their primary operational framework. In this context, the proposed system presents a compelling opportunity to unlock valuable outcomes and advancements.

Designing main-group catalysts for low-temperature methane combustion by ozone

The catalytic combustion of methane at a low temperature is becoming increasingly key to controlling unburned CH4 emissions from natural gas vehicles and power plants, although the low activity of benchmark platinum-group-metal catalysts hinders its broad application. Based on automated reaction route mapping, we explore main-group elements catalysts containing Si and Al for low-temperature CH4 combustion with ozone. Computational screening of the active site predicts that strong Brønsted acid sites are promising for methane combustion. We experimentally demonstrate that catalysts containing strong Bronsted acid sites exhibit improved CH4 conversion at 250 °C, correlating with the theoretical predictions. The main-group catalyst (proton-type beta zeolite) delivered a reaction rate that is 442 times higher than that of a benchmark catalyst (5 wt% Pd-loaded Al2O3) at 190 °C and exhibits higher tolerance to steam and SO2. Our strategy demonstrates the rational design of earth-abundant catalysts based on automated reaction route mapping.

Comments: Nuclear Energy Gains (Some) Favor

Support for nuclear energy in the US is at its highest level in a decade, with 55% of Americans supporting it as a source of electricity. A Gallup poll conducted in March found 25% strongly favor, 30% somewhat favor, while 22% each strongly or somewhat oppose its usage. The report noted that oil prices have generally affected Americans’ responses since the survey was begun in 1994: high oil prices trended with more openness to nuclear energy, low oil prices trended with less favor. As of May, there were 436 nuclear power reactors in operation (connected to the grid) worldwide, providing about 10% of the world’s electricity. The countries with the most reactors are the US (93), France (56), and China (55). The largest reactors under construction were in the UK (gross electricity generation capacity of 1,720 MW). The largest-capacity nuclear reactors under construction worldwide were in China, with a total capacity of almost 22 GW (Statistica, May 2023). Projections for the potential growth of nuclear power in the next decades increased for the second consecutive year in the International Atomic Energy Agency’s 2022 outlook to 2050. Its high case scenario forecast for world nuclear generating capacity more than doubled to 873 GW net electrical (GWe) by 2050, compared with current levels of around 390 GWe, an increase of 81 GWe forecast in 2021. In the low case scenario, generating capacity remains flat. “We are at a defining moment in the world’s transition to a more secure, stable, and affordable energy future,” IAEA Director General Rafael Mariano Grossi said. “Driven by the impacts of climate change and the energy crisis, governments are reconsidering their portfolios in favor of nuclear power. But for the high case scenario to be achieved, a number of challenges need to be addressed, including regulatory and industrial harmonization and progress in high-level waste disposal.” The IAEA said the use of nuclear power has avoided about 70 gigatonnes of CO2 emissions over the past 50 years. Almost half of the CO2 emission reductions needed to reach net zero in 2050 will need to come from technologies that are currently under development but are not yet on the market. IAEA said accelerating the pace of innovation and demonstration of advanced nuclear reactors including small modular reactors (SMRs) is required if nuclear is to play a role in decarbonization beyond electricity by providing low-carbon heat or hydrogen to the industrial and transport sectors. Although the Biden administration has included nuclear energy as a key component in its clean energy plan, support for nuclear energy has historically been tenuous. In the evaluation of the risks vs. benefits of nuclear energy, the risks weigh heavily in the balance, partly because when nuclear power reactors failed, they failed dramatically. Fukushima, Chernobyl, Three Mile Island. While estimates of the number of directly related deaths or subsequent deaths resulting from radiation exposure via the accident or fallout are debated and vary widely, the association of fatalities with nuclear power reactor accidents/disasters is an immediately identified risk. Concerns about the risk of weapons proliferation, core meltdowns, and disposal of spent radioactive fuel are real and will need to be addressed transparently and convincingly by governments and regulators to gain wider public approval worldwide. Increasing nuclear generating capacity is not a quick fix. The complexity of the massive project, scale of investment, and long lead times are additional drawbacks. For comparison, a “typical” nuclear power plant requires 5 years (or more) to construct; natural gas-fired plants are frequently built in about 2 years. The United Nations (UN) estimates that the world’s population will grow from 7.8 billion in 2020 to around 8.5 billion in 2030 and 9.7 billion by 2050. Urbanization, which currently adds a city the size of Shanghai to the world’s urban population about every 4 months, is expected to result in approximately two-thirds of the world’s people living in urban areas by 2050 (up from about 55% now). The number of people without access to electricity has fallen substantially and is now below 1 billion, according to the UN. However, 733 million people, just over 9% of the world’s population, live without access. The challenge of meeting the rapidly growing energy demand, while reducing emissions, is considerable and highlights the needs for an energy mix which includes hydrocarbon, renewable, nuclear, and emerging and developing energy sources such as hydrogen.

Identifying optimal geographic locations for hybrid concentrated solar biomass (HCSB) power plants in Alberta and Ontario, Canada

ABSTRACT Solar thermal and biomass hybridization combine two energy sources that complement one another seasonally and diurnally, overcoming their respective disadvantages. In the current research, the feasibility of locating a new medium capacity (5–150 Mwe) hybrid concentrated solar biomass power plant is investigated in Alberta and Ontario. To address the above-mentioned goal, three critical criteria are considered to find the most suitable region. The amount of direct normal irradiation and the biomass feedstock in 50 km and 100 km radii are analyzed in different regions in Ontario and Alberta. The third factor is the distance to the substations. According to the results, although it is difficult to justify developing a hybrid concentrated solar biomass power plant in Ontario, at least five locations in Alberta meet the aforementioned criteria. By concentrating on substations located near natural gas power plants, Calgary, with four natural gas power plants, can be regarded as the most suitable region. According to the findings, we identified that by establishing a 100 Mwe hybrid concentrated solar biomass power plant that requires 359,478 tons of forestry biomass and costs between 3.7 and 4.9 mCAD/Mwe, about 5% of Calgary’s total electricity consumption would be met while reducing CO2 emissions by 32 tons.

Risk-assessment of carbon-dioxide recycling in a gas-fired power plant using CVaR-based convex optimization

With the rise of renewable resources’ penetration, the use of clean excessive renewable energy as the primary source of a Power to Gas (PtG) system for the reduction of CO2 pollution is quite advantageous. This paper presents a mixed integer linear formulation for modeling the optimal operation of a gas-fired power plant (GFPP)-PtG system that utilizes an excessive renewable resource, wind power, as the primary mover of the proposed PtG system for capturing and recycling the produced CO2 pollution. CO2 and CH4 gas storages are considered in the proposed PtG system to boost the operational efficiency of the system. Additionally, the scenario generation method models both wind power generation and electrical demand. The effective conditional value at risk (CVaR) method, which is a convex risk modeling approach, models the risks imposed by the generated scenarios for wind power and electrical demand. Due to the convexity of the proposed formulation for the PtG system and the risk modeling method, the ultimate model can be simply solved by using any available LP solver. To evaluate the outcomes of an optimization problem based on CVaR, a comparative analysis is conducted with chance constraints programming, which demonstrates the optimality and computational efficiency of the CVaR results due to convexity. The effectiveness of the proposed model is approved by modeling a test system based on real data, and the obtained numerical results are discussed comprehensively.

Towards nearly zero emissions natural gas-fired power plants using cryogenic carbon dioxide capture technology

Cryogenic carbon capture (CCC) is one of the most recent and promising technologies for reducing carbon dioxide emissions, hence mitigating the global warming. The present research aims at exploring the feasibility of integrating it into existing thermal power plants in Egypt that are commonly operated by natural gas.A simulation model is developed using Aspen Plus Dynamics software to accurately predict the behavior of the thermal power plant after applying such integration. The model incorporates the CCC cycle established by Sustainable Energy Solutions into a natural gas power plant of Abu Qir, Egypt. The integral plant is benchmarked at various part loads scenarios. The study investigates the ability of capturing up to 99% of the emitted CO2 and determines the consequent penalties in the generated power and the overall thermal efficiency.The results demonstrated successful integration of the thermal power plant and the CCC revealing smooth operation and safe transition between different part loads. By capturing 99% of the emitted CO2, both the generated power and the overall efficiency dropped maximally by 10.73%. The integration led to a maximum energy penalty of 0.840 MJe/kgCO2 which is much smaller than other conventional carbon capture techniques.Applying this technology to all thermal power plants in Egypt, about 89 M tonnes of CO2 emissions will be captured annually. Further integrations of CCC-ECL into other chemical and industrial facilities would significantly lead to a cleaner environment.

Microalgae Biofuel for a Heavy-Duty Transport Sector within Planetary Boundaries.

In this contribution, we study the extent to which 68 scenarios for microalgae biofuels could help the heavy-duty transport sector operate within planetary boundaries. The proposed scenarios are built considering a range of alternative configurations based on three types of fuel production processes (i.e., transesterification, hydrodeoxygenation, and hydrothermal liquefaction), different carbon sources (such as natural gas power plants and direct air capture), byproduct treatments, and two electricity mixes. Our results reveal that microalgae biofuels could significantly reduce the environmental and human health impacts of the business-as-usual (fossil-based) heavy-duty transport sector. Moreover, relative to standard biofuels that show large land-use requirements, we find that microalgae biofuels also decrease the damage on biosphere integrity substantially. Notably, pathways resorting to hydrodeoxygenation of microalgae oil and direct air capture and carbon storage could reduce the current impact induced globally on climate change by the heavy transport by 77%, while attaining six-fold reductions in biosphere integrity impacts, both relative to conventional biofuels.

Predicting solvent degradation in absorption–based CO2 capture from industrial flue gases

This work aims to predict solvent degradation rates in absorption-based CO2 capture processes using a 30 wt% aqueous monoethanolamine (MEA) solvent. A degradation model for MEA is developed and used to predict solvent degradation in full-scale capture processes. Mass transfer resistances and the solubility of O2 are considered to obtain a generalized and consistent degradation model. Degradation is evaluated for the capture process for flue gases with typical industrial compositions; a natural gas-fired power plant, a waste-to-energy plant, a coal-fired– power plant, and a cement plant. The impact of process modifications, such as absorber intercooling, dissolved O2 removal, a reduction in solvent residence times, and increased stripper pressures on degradation is evaluated.The predicted degradation rate in the capture processes is approximately 90 to 150 g MEA/ton CO2 captured, and the composition of the flue gas was found to have a significant influence on the distribution of degradation throughout the process. Modifications to the process can significantly affect the overall degradation rate. Both absorber intercooling and removal of dissolved O2 may reduce the overall degradation by up to 40%, depending on the composition of the flue gas. A reduction in solvent residence times or pressure in the stripper has limited effects on the degradation in the case of MEA, because of the amine’s relatively low stability towards oxidative degradation. However, these process modifications look promising for more stable solvents.

Feasibility of innovative topography-based hybrid renewable electrical power system: A case study

Recently, climate change has attracted significant intension globally. Accordingly, numerous initiatives are under action for reducing the consumption of fossil fuels and increasing the share of renewable energy sources. This research work proposes an eco-friendly and sustainable electrical power system that could fully or partially fulfill requirements of the local load of the system under concern. The proposed power has the merit of utilizing topography of the site under concern, Al- Jabal Al-Gharbi district, Libya, to exploit the locally available resources such as biomass and sewage plants. The availability of resources was first studied, concluding that 110.87 × 106 m3⁄year are available for generating biogas and electricity. Moreover, biogas is extracted from biomass fermentation plants with a capacity of 244,845 tons/year produced from agricultural, municipality organic, livestock, and sewage residues in the proposed system. The feasibility of the proposed system is validated via a comprehensive economic and environmental comparison of different types of fuels. Furthermore, a mathematical model is developed for the Environmental Damage Cost (EDC) of CO2 emission for three scenarios: 1) disposing wastes, 2) firing fuel plus disposing of wastes, and 3) firing fuel plus biogas. The proposed system would save about 57% and 86% of CO2 from diesel and natural gas-fired power stations. Moreover, the Levelized Cost of Electricity (LCOE) generated from the proposed system is about 3.5 ¢⁄kWh, which is much lower than the actual cost of electricity generation in Libya (12 ¢/kWh). The annual savings of EDC due to CO2 is $6,968,613. This study could act as a pivot for implementing eco-friendly and sustainable energy source projects in the site under concern and/or similar sites.

4E Transient Analysis of a Solar-Hybrid Gas-Turbine Cycle Equipped with Heliostat and MED

The current study investigates a cogeneration cycle of power and freshwater integrated with a solar system. The solar system is of the heliostat type, which is considered to preheat the inlet air in the combustion chamber of a 25-MW gas turbine. The waste heat of the turbine output stream is used to produce freshwater. Parameters such as the ambient temperature and solar irradiance significantly affect the system’s performance; hence, all analyses, including those pertaining to energy, exergy, economics, and environment, were conducted transiently, with a one-hour time step throughout the year so that the impacts of these effective parameters could be examined. Besides the analysis assuming a constant mass flow rate for the air entering the compressor, the calculations were repeated with the assumption of a constant volumetric flow rate to evaluate the cycle in the same conditions as those of natural gas power plants. Given the constant volumetric flow rate, for every 10-degree increase in temperature, the compressor power consumption decreased by approximately 2%. Moreover, a sensitivity analysis of the cycle performance in terms of ambient temperature was performed, and the corresponding results are presented. Finally, some correlations are presented to estimate variations in compressor power consumption and net turbine power due to temperature variations. The results demonstrate that in Bushehr, Iran, every one-degree increase in ambient temperature leads to an approximately 0.67 percentage decrease in net-generated power. In the end, the performance of the cycle was investigated under climatic conditions and solar irradiation intensities in several cities in Iran and some cities in different countries in which heliostat power plants have already been established. The results obtained in these cities were compared; it was concluded that the lowest annual cost of electricity generation is related to Isfahan in Iran, which reduces the cost of electricity generation by more than 20% (2.32 Cents/kWh) compared to the base cycle.

Prospect and Challenges of Hydrate-Based Hydrogen Storage in the Low-Carbon Future

Hydrogen hydrate is a promising material for safe and potentially cost-effective hydrogen storage. In particular, hydrogen hydrate has potential for applications in large-scale stationary energy storage to dampen the temporal variation of renewable energy, for example, in the form of hydrogen-ready gas-fired power plants for generating energy when the renewable power is not available. Preliminary SWOT (strengths, weaknesses, opportunities, threats) analysis indicates that such hydrate-based hydrogen storage (HBHS) has intrinsic competitive edges. However, while the theoretical hydrogen density of the hydrate could reach ∼5 wt %, experiments have not achieved such a high hydrogen storage capacity under practical conditions. This low gravimetric hydrogen density, plus the slow kinetics of hydrogen inclusion in the hydrate, presents an outstanding challenge for commercializing the HBHS. Future research is urged to resolve both the gaps in knowledge and technological barriers for realizing this unconventional technology. Particular future directions include the elucidation of the working mechanism of hydrate promoters, rational designs of new promoters, upscaled experiments and demonstrations, the assessment of long-term stability of hydrogen hydrates, and systematic SWOT analysis. This paper offers an insightful view of the HBHS in low-emission economies.

EPA proposal targets power plant CO2

A new US Environmental Protection Agency proposal aims to dramatically slash carbon emissions from coal-fired and natural gas–fired power plants. The regulations would require these plants to cut nearly all their carbon dioxide emissions by 2035. The proposal doesn’t specify how plants should meet the new regulations, but the agency says that it considered readily available emission control technologies when developing the new pollution standards. For example, companies can fit coal and gas plants with carbon capture and storage systems, which capture CO 2 before it leaves the smokestack. Older plants can be retired. According to a fact sheet provided by the EPA, the power sector is one of the country’s largest sources of greenhouse gases, responsible for 25% of emissions in 2021. By targeting this sector, the plan would prevent 617 million metric tons of CO 2 from entering the atmosphere by 2042, the EPA estimates. The proposal is

Optimal bidding strategy of a gas-fired power plant in interdependent low-carbon electricity and natural gas markets

This work presents a bi-level optimization framework to determine the optimal bidding strategies for a strategic gas-fired power plant, exerting market power in interdependent pool-based electricity and natural gas markets, under a carbon emission trading scheme (CETS). The upper-level problem aims at maximizing the profits of the strategic player, while at the lower-level problem, the day-ahead electricity and natural gas markets are cleared sequentially, considering the provision of carbon emission allowances for conventional power producers and high penetration of wind power generation. The bi-level formulation is initially recast into a mathematical program with equilibrium constraints (MPEC), using the Karush-Kuhn-Tucker optimality conditions and duality theory, and is further reformulated into a mixed integer linear program. The proposed algorithm is applied to a Pennsylvania-New Jersey-Maryland (PJM) 5-bus power grid, incurred by transmission constraints and a single node natural gas network. Numerical simulations provide CETS-embedded electricity clearing prices and optimal bidding decisions for the strategic gas-fired power plant, under plausible power transmission congestions and natural gas prices increment scenarios.

Energy analysis of novel hybrid solar and natural gas combined cycle plants

The integration of renewable energy sources into standard energy systems is a fundamental step in the energy transition. The purpose of the paper is to investigate the integration of solar energy into a traditional natural gas-fired combined cycle power plant, while also evaluating the impact of intercooling, in terms of energy efficiency and CO2 emissions. Solar energy is integrated into the gas turbine topping cycle through parabolic trough collectors, with the aim of preheating the air leaving the compressor. Two additional configurations have been compared, based on one- and two-stage intercooled compression. The goal is to find the optimal hybrid configuration. To this purpose, a thermodynamic analysis of the overall plant has been performed, and a numerical model has been specifically developed to simulate the solar field. The model has been integrated into Thermoflex™ to simulate the overall combined cycle. Solar-to-electric conversion efficiency, based on solar energy input alone, has received specific attention to make relevant comparisons with conventional concentrated solar based power plants. Furthermore, net electric efficiency, electrical power share due to solar energy integration, natural gas savings, and CO2 emissions have been investigated. The solar-to-electric conversion efficiency has been shown to increase with the compression ratio while the net electric efficiency decreases. To achieve a trade-off between the need for high net electric efficiency and high solar integration, an optimization based on the Pareto front was carried out. The selected configuration consists of one intercooling stage and a compression ratio of 17.9, resulting in a solar conversion efficiency of 33%, which is much better than traditional solar-only power plants. Additionally, the net electric efficiency is 69.5%. To test this configuration under actual operating conditions, a one-year simulation was carried out in two cities with different climates: Messina and Torino. An average annual solar-to-electric efficiency of around 32% can be achieved in both cities, with natural gas savings of 7.7% and 5.8% per year for Messina and Torino, respectively.

A novel structure of natural gas, electricity, and methanol production using a combined reforming cycle: Integration of biogas upgrading, liquefied natural gas re-gasification, power plant, and methanol synthesis unit

A novel structure of natural gas, electricity, and methanol production using a combined reforming cycle: Integration of biogas upgrading, liquefied natural gas re-gasification, power plant, and methanol synthesis unit

Can Hydrogen Production Be Economically Viable on the Existing Gas-Fired Power Plant Location? New Empirical Evidence

The paper provides an economic model for the assessment of hydrogen production at the site of an existing thermal power plant, which is then integrated into the existing gas grid. The model uses projections of electricity prices, natural gas prices, and CO2 prices, as well as estimates of the cost of building a power-to-gas system for a 25-year period. The objective of this research is to calculate the yellow hydrogen production price for each lifetime year of the Power-to-gas system to evaluate yellow hydrogen competitiveness compared to the fossil alternatives. We test if an incentive scheme is needed to make this technology economically viable. The research also provides several sensitivity scenarios of electricity, natural gas, and CO2 price changes. Our research results clearly prove that yellow hydrogen is not yet competitive with fossil alternatives and needs incentive mechanisms for the time being. At given natural gas and CO2 prices, the incentive for hydrogen production needs to be 52.90 EUR/MWh in 2025 and 36.18 EUR/MWh in 2050. However, the role of hydrogen in the green transition could be very important as it provides ancillary services and balances energy sources in the power system.

Advanced exergoeconomics of a steam power plant based on double-tier splitting of exergy destruction rates

The advanced exergy and exergoeconomic analysis methodologies excel over their conventional counterparts by quantifying endogenous/exogenous exergy destruction rates and related costs that reveal the interactions among system components. By quantifying avoidable/unavoidable losses, they also reveal the potentials for component improvements that are practically achievable. These data are imperative for improving the cost-effectiveness of thermal systems. This paper presents the performances of a complex gas-fired power plant obtained via an advanced exergoeconomic analysis. The study advances existing studies by undertaking second-tier splitting of exergy destruction cost rates and associated investment cost rates to determine avoidable endogenous, unavoidable endogenous, avoidable exogenous, and unavoidable exogenous cost rates of the plant’s components. Component exergy destruction cost rates were found to be predominantly unavoidable, while most of the component investment cost rates were avoidable. Except for the low pressure heater 3, exergy destruction cost rates are endogenous in all the plant components, contributing 84% of overall cost rates. The proportions of exergy destruction cost rates and investment cost rates of the plant that are avoidable endogenous were 21% and 28% respectively, while the respective portions that are avoidable exogenous were 4% and 27%. Furthermore, it was shown that as much as 96.3% improvements in overall plant cost-effectiveness were achievable by eliminating avoidable endogenous exergy destruction cost rates and investment cost rates for major components of the plant.

Temporally detailed modeling and analysis of global net zero energy systems focusing on variable renewable energy

This study newly develops a recursive-dynamic global energy model with an hourly temporal resolution for electricity and hydrogen balances, aiming to assess the role of variable renewable energy (VRE) in a carbon-neutral world. This model, formulated as a large-scale linear programming model (with 500 million each of variables and constraints), calculates the energy supply for 100 regions by 2050. The detailed temporal resolution enables the model to incorporate the variable output of VRE and system integration options, such as batteries, water electrolysis, curtailment, and the flexible charging of battery electric vehicles. Optimization results suggest that combing various technical options suitable for local energy situations is critical to reducing global CO2 emissions cost-effectively. Not only VRE but also CCS-equipped gas-fired and biomass-fired power plants largely contribute to decarbonizing power supply. The share of VRE in global power generation in 2050 is estimated to be 57% in a cost-effective case. The results also imply economic challenges for an energy system based on 100% renewable energy. For example, the average mitigation cost in 2050 is 69USD/tCO2 in the cost-effective case, while it increases to 139USD/tCO2 in the 100% renewable case. The robustness of this argument is tested by sensitivity analyses.

Analysis of Parameters That Affect the Efficiency of Gas Power Plants

This study aims to analyze the parameters that actively affect the efficiency of gas power plants in order to optimize their performance. The method used in this study was an analytical approach based on the results of performance tests conducted in 2018, 2020, and 2022 on gas power plants in the sumatera selatan area, based on thermodynamic equations. Based on the results of the study, it is explained that there is a very significant relationship between the inlet air temperature of the compressor, the inlet fuel temperature, and the turbine exhaust temperature and active power to the efficiency of gas-fired power plants, where an increase in the inlet air temperature to the compressor will reduce the compressor efficiency, which is predicted using linear regression with an R2=0.82. An increase in the exhaust temperature and active power will significantly reduce the thermal cycle efficiency, which is predicted using linear regression with an average R2 =0.96. In addition, an increase in the fuel mass flow rate and inlet fuel temperature will increase the turbine efficiency, which is predicted using linear regression with an average R2 =0.97. Therefore, the relationships obtained in this study can be used as a reference for energy companies and governments in developing more efficient gas-fired power plants in the future

Prediction of CO–NOxEmissions from a Natural Gas Power Plant Using Proper Machine Learning Models

Four machine learning (ML) models including a deep neural network, a long short‐term memory network, a random forest (RF), and an extreme gradient boosting are implemented to predict CO–NOxemissions from a natural gas power plant. A new feature optimization scheme (FOS) via a sequencing process of feature selection and hyperparameter optimization can intensify the ML models. Through the procedures of training, validation, and testing, reliable ML models need to take high prediction accuracy and fast training into account. After a few comparisons, it is found that 1) the FOS effectively improves the prediction accuracy by 18%–67%; 2) the FOS‐based RF model is an appropriate option to carry out the fast and accurate prediction of CO–NOxemissions by using the decision tree classifiers.