Search

As sustainable urban communities continue to seek alternative energy sources, this study explores the inclusion of renewable resources in the energy mix. With a focus on liquefied natural gas (LNG) regasification, parabolic trough solar collectors, dual-loop power cycles, proton exchange membrane electrolysis, and hydrogen liquefaction cycle, this research conducts a comprehensive examination of an integrated system. The primary objective is to provide a diverse range of valuable outputs, including electricity, liquefied hydrogen, desalinated water, and cooling for coastal areas. Through careful analysis of regional geographic features, San Francisco emerges as a suitable location due to its favorable solar radiation intensity and existing LNG transportation infrastructure. The findings reveal that the integrated system has the potential to deliver approximately 5750.4 MWh of cooling, 14988.85 MWh of electricity, and 1,491,084 m3 of fresh water, thereby significantly contributing to the city's utility demands. In terms of data-driven optimization, artificial neural networks serve as intermediary mechanisms to establish correlations between the developed code and the optimization algorithm. The results demonstrate that the optimized system exhibits notable improvements in production capacity. Moreover, significant reductions in the levelized cost of electricity (0.19 Cent/kWh), fresh water (1.22 Cent/m3), and hydrogen (0.08 $/kg) are observed. Although the optimized case entails a 16.11% higher cost rate compared to the base system, it is projected to generate a 25.59% higher profit over its operational lifespan. Additionally, the payback period of the optimized system is shortened by 6.31%, making it an attractive long-term investment for sustainable urban development. [Display omitted] • Designing a solar and LNG-based multigeneration system for coastal areas. • Incorporating a hydrogen liquefaction unit for efficient storage of hydrogen. • Applying dynamic techno-economic and environmental appraisals to analyze the system. • Performing multi-criteria and machine learning approaches to optimize the system. • The payback period of the optimized system has been shortened by 5.31%. [ABSTRACT FROM AUTHOR]

This research introduces a stochastic scheduling approach that incorporates risk constraints for an energy hub (EH), considering uncertainties related to renewable generation and load demands. The proposed method utilizes the Conditional Value at Risk (CVaR) technique to assess and quantify risks. By striking a balance between reducing operational and emissions costs and increasing risk aversion, the approach presents a trade-off. The EH comprises various components such as a wind turbine (WT), photovoltaic (PV) cells, a fuel cell power plant (FCPP), a combined heat and power generation unit (CHP), and plug-in electric vehicles (PEVs). Uncertain variables encompass factors such as wind speed, solar irradiation, different demands, and market prices. To optimize profits and enhance the consumption curve, demand response programs (DRPs) for electrical, thermal, and cooling demands are implemented. To address the uncertainties associated with input random variables, the efficient k-means data clustering method is employed. A new slime mold algorithm, based on coughing and chaos theory, has been proposed to enhance the problem's solution. The algorithm incorporates innovative operators to improve its capabilities. By utilizing the coughing mechanism and chaos theory, the algorithm explores the solution space more effectively, resulting in improved outcomes for the problem at hand. The results demonstrate significant flexibility in EH management and are extensively discussed. Simulation results indicate that integrating PEVs, FCPP, and DRPs can lead to reductions of 2 %, 7 %, and 11 % in the EH's operating costs, respectively. Furthermore, considering PEVs, FCPP, and DRPs can improve the EH's risk cost by 1.98 %, 6.7 %, and 10.5 %, respectively. Based on the numerical results, in Case 4 led to a remarkable 12.65 % reduction in operational costs while simultaneously achieving a 15.43 % decrease in emission costs, showcasing the effectiveness of the proposed approach in optimizing energy management in an energy hub system. • Risk-Constrained Stochastic Scheduling: Introduces CVaR for EH risk management. • Balance Costs and Risk Aversion: Optimize cost, emissions, and risk. • Diverse EH Energy Sources: Integrates wind, solar, fuel cell, CHP, and EVs. • Demand Response Programs: Adjust consumption for efficiency and savings. • Innovative Solution Algorithm: Slime mold algorithm enhances EH management. [ABSTRACT FROM AUTHOR]

In recent years, the escalating demand for electric energy has underscored the need for robust prediction models capable of accurately anticipating consumption patterns. The imperative lies in enabling utilities and policymakers to optimize resource allocation, strategically plan infrastructure development, and ensure the stability and efficiency of the power grid. This study undertakes a comprehensive comparative analysis of machine learning techniques employed in predicting net electricity consumption in Turkey. The primary goal is to augment the accuracy and performance of electricity load forecasting, thereby contributing to effective energy management and fostering sustainable development within the power sector. Two machine learning models, including CatBoost and Extreme Gradient Boosting (XGBoost), are strategically integrated with optimization algorithms such as Sparrow Search Algorithm (SSA), Phasor Particle Swarm Optimization (PPSO), and Hybrid Grey Wolf Optimization (GWO). The core analysis centers on evaluating the performance of these integrated models based on key accuracy metrics and runtime efficiency. Notably, the results underscore that the XGBoost-SSA model emerges as the superior performer, exhibiting heightened accuracy and superior performance in predicting electricity consumption. This model showcases the highest coefficient of determination (R2) value and demonstrates lower errors during the testing phase, thereby presenting a promising and effective approach for electricity consumption prediction in the specific context of Turkey. • This study presents an advanced framework for electricity consumption prediction. • CatBoost and XGBoost hybridized with optimization algorithms for load forecasting. • Statistical criteria are used to rigorously evaluate model performance. • XGBoost-SSA model outperforms others, with higher accuracy in predicting electricity consumption. [ABSTRACT FROM AUTHOR]