Search

This study explores the improvement of wireless charging network configurations for electric cars (EVs) using genetic algorithms, with the goal of increasing charging efficiency and network performance. The network optimization process takes into account the starting characteristics of include their geographical coordinates, power capacity, and beginning energy levels. Examination of the distance matrix exposes diverse distances between nodes, which impact energy consumption and charging efficiency. The energy consumption estimates between pairs of nodes illustrate the charging needs across the network, revealing that nodes that are farther away have greater energy consumption. The use of genetic algorithms yields a wide range of layouts that are assessed based on their fitness ratings, indicating the excellence of configurations in terms of coverage and connection. Percentage change study demonstrates the modifications in power capacity and node energy levels after optimization, showing prospective improvements in charging capabilities and efficiency. The correlation between node location and energy use is apparent, as nodes in closer proximity demonstrate decreased energy utilization. The convergence of fitness scores demonstrates the algorithm's effectiveness in achieving solutions that are very close to ideal, resulting in significant improvements in charging coverage and energy efficiency. The study highlights the effectiveness of genetic algorithms in improving wireless charging networks, providing valuable information on spatial optimization tactics, energy use patterns, and the resulting improvements in network performance. These results have implications for creating wireless charging infrastructures that are more efficient and long-lasting, in order to satisfy the changing needs of electric car charging networks.

Electric vehicles (EVs) play a crucial role in tackling environmental issues in the transportation industry. The incorporation of effective charging infrastructure is crucial in promoting the broad acceptance of electric vehicles (EVs). This work investigates the optimization of the location of wireless charging infrastructure in urban contexts using genetic algorithms (GAs). The location data, which includes latitude and longitude coordinates, showed a wide range of spatial distributions that are ideal for deploying charging stations. These distributions display variances that are favorable for strategically placing the infrastructure. The examination of power consumption data revealed significant variations in energy demand across different sites, ranging from 180 kWh to 300 kWh. These differences indicate that each location has its own distinct energy needs. The population density statistics exhibited a spectrum of values, ranging from 600 individuals per square unit. The population density is 1200 persons per square kilometer. The abbreviation "km" refers to kilometers, which is used to indicate different levels of prospective electric vehicle (EV) users. In addition, the distance data provided information about the lengths between prospective locations for charging stations, which varied from 400 km to 1200 km. These distances had an impact on the concerns of connection and transmission efficiency. The research highlights the intricate nature of the elements that affect the ideal location of infrastructure, underlining the need for a methodical approach to optimization. Integrating these statistics provides a foundation for developing an objective function in the GA framework to optimize the location of charging infrastructure. The study's results provide valuable understanding of the many factors that influence the location of charging infrastructure. The goal is to promote the development of efficient and easily accessible electric vehicle charging networks in metropolitan areas.

This study examines the relative effectiveness of Genetic Algorithms (GA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), and Linear Programming (LP) in optimizing hybrid energy microgrids. Drawing upon empirical data derived from the study, the research explores many facets, including economic efficacy, environmental viability, and microgrid robustness. The use of GA showcases a significant 10% decrease in overall system expenses, highlighting its efficacy in augmenting economic feasibility. PSO diligently tracks, attaining an 8% decrease, while SA and LP make significant contributions but provide somewhat lesser cost reductions at 7% and 6%, correspondingly. Within the domain of renewable energy integration, GA and PSO have emerged as frontrunners, with remarkable advancements of 12% and 10%, respectively. SA and LP provide commendable contributions, demonstrating their effectiveness in optimizing the usage of renewable energy sources inside the microgrid, as seen by their respective increases of 8% and 7%. The environmental factor, as quantified by the decrease of carbon emissions, highlights the commendable efficacy of GA and PSO, resulting in significant reductions of 15% and 12% respectively. SA and LP provide praiseworthy environmental efforts, achieving reductions of 10% and 8% respectively. The resilience index highlights the strength of GA and PSO in assessing the resilience of the microgrid, with GA showing an increase of 0.05 and PSO showing an increase of 0.04. SA and LP make a significant contribution, with increments of 0.03 and 0.02, underscoring the potential of evolutionary and swarm-based methodologies to bolster the microgrid’s resilience against disturbances. Scenario analysis effectively brings unpredictability into the operational environment of the microgrid, continually showcasing the remarkable flexibility of GA (Genetic Algorithm) and PSO (Particle Swarm Optimization) over a wide range of situations. SA and LP demonstrate consistent efficacy but with somewhat reduced flexibility. Statistical evaluations provide compelling evidence confirming the exceptional efficacy of GA and PSO in improving microgrid metrics. Ultimately, this research provides valuable perspectives on the intricate trade-offs between various optimization techniques, empowering decision-makers to choose strategies that align with specific microgrid objectives. Moreover, it contributes to the wider discussion on resilient, sustainable, and economically feasible energy infrastructures.

The paper examines the use of genetic algorithm (GA) methods to optimize hybrid renewable energy microgrids by merging various renewable sources and energy storage technologies. An examination of meteorological data over many days reveals fluctuations in solar irradiance ranging from 4.8 kW/m² to 5.5 kW/m² and wind speed oscillating between 3.9 m/s and 4.5 m/s, indicating the presence of dynamic weather conditions. An analysis of energy generating capabilities reveals a wide range of potentials, with solar capacities varying from 80 kW to 150 kW and wind capacities ranging from 60 kW to 120 kW across different sources. An analysis of Energy Storage System (ESS) specifications shows a range of values for maximum capacities, charge/discharge efficiencies (ranging from 85% to 96%), and maximum charge/discharge rates (from 60 kW to 100 kW), highlighting the need for flexible energy storage systems. The examination of microgrid load profiles reveals the presence of diverse energy needs, with residential loads oscillating between 48 kW and 55 kW, commercial loads ranging from 40 kW to 47 kW, and industrial loads spanning from 30 kW to 36 kW. A percentage change study reveals the ability to adapt, with solar irradiance and wind speed showing mild fluctuations of roughly 14% and nearly 15% respectively. In contrast, renewable source capacity demonstrate significant percentage changes ranging from around 40% to 50%. These results highlight the ever-changing characteristics of renewable energy sources, underlining the need for strong optimization tactics in microgrid systems. The study emphasizes the potential of GA-based approaches in developing efficient microgrids, promoting sustainable and dependable energy solutions in the face of changing environmental circumstances and varied energy requirements.

The United Nations predicts that by 2050, 70% of people will live in cities, which will bring significant environmental challenges, including climate change and resource depletion. In India, the residential sector account for 30% of total energy consumption. Therefore, it is crucial to optimize energy use in residential structures to address urban population growth, density, and energy efficiency. This study explores the use of genetic algorithms for multi-objective optimization in the design of energy efficient residential urban forms linking urban population growth and environmental concerns. Urban form significantly influences energy consumption within neighborhoods. However, introducing genetic algorithms into urban planning, a field not typically associated with such computational methods, presents considerable challenges. This research addresses complexities such as simulating and optimizing energy use by focusing on the control of solar radiation and the enhancement of natural daylight within residential neighborhoods. It further seeks to enhance the quality of life in open spaces by improving the sky view factor and the sense of spaciousness, adding another layer of complexity to the optimization. In response to these complexities, a framework is developed using the Biomorpher plugin, integrating genetic algorithms in Grasshopper. This research, carried out in Ahmedabad, India, progresses in two primary phases. The experiment progresses in two phases: first, developing prototypes considering factors like Floor Space Index and building types; and second, refining these through multiple design iterations based on environmental criteria. The study generates a diverse range of optimized scenarios, such as low-rise, mid-rise, and high-rise densities, to understand the relationship between residential form and energy consumption. The research identifies energy-efficient configurations through analysis, offering adaptable solutions tailored to specific environmental and spatial contexts.Additionally, it offers a replicable methodology for urban designers and policymakers.

Irrigating the remote regions of southern Algeria, which generally use diesel generators, with clean, environmentally-friendly energy is a challenge. Taking into account the solar and wind potential of the Adrar region, a renewable system using both sources seems more cost-effective. The realization of hybrid renewable energy systems takes into account several technical, economic and environmental aspects. This study consists in finding an efficient and adequate energy supply for the irrigation of one hectare of date palm in the Adrar region. It proposes a mathematical modelling for the given problem in different possible models, for this, we used the basic concepts of multi-objective optimization (bi-objective), and the adaptation of the concept of genetic algorithms to find solutions. The theoretical foundations discussed in this research have enabled us to design and implement a software that optimizes the hybrid pumping system used for the irrigation of date palms by minimizing the total cost and reducing CO2 emissions produced by the diesel group.

This paper applied mathematical models to conduct an in-depth discussion and empirical analysis of financial market risk management. The daily rate of return data on the S&P 500 index, selected through data processing, included data cleaning, return calculation, data standardization, construction of the GARCH (1, 1) model, and a Copula model for predicting and analyzing risks. Empirical results indicate that the GARCH model has good simulation in capturing the market volatility change, while the Copula model holds clear advantages in modeling multivariate risk dependencies. In the modern economy, managing risks in the financial market plays a vital role. Optimization algorithms such as genetic algorithms and Bayesian optimization significantly improve the prediction accuracy and computational efficiency of the model. Compared with traditional historical simulation methods, these models perform better in risk prediction indicators (VaR and ES), proving their practicality and effectiveness in actual risk management. The research results verify that advanced mathematical models and optimization methods have important application value in financial market risk management, providing a scientific decision-making basis for investors and risk managers.

The research is the optimization design of the bridge from the structure of the bridge, proper material utilization, and improving the performance of the bridge. First, the static model of the bridge structure was established, and then the finite analysis and rigid body mechanics models were utilized to separately detail the dead load, live load, and exceptional load. Based on the above analyses, optimization methods such as mathematical programming and genetic algorithms were used for optimizing the design of bridge structures. The tests demonstrated that the bridge’s weight can be significantly reduced by optimal design, the efficiency of usage in materials is enhanced, and the rigidity and stability of the structure advanced significantly. It is verified through checking the comparative analysis before and after optimization that the efficiency of the optimization method has been proved and the critical application value of optimization design in bridge engineering. The research conclusions provide new ideas and methods for bridge structure design, which has important theoretical and practical significance.

Currently, automation of processes in which a robot can replace a human is widespread. To solve this problem, robots must be able to move independently from one position to another. Currently, many different approaches have been developed to solve this problem, such as neural networks, the method of potential fields, fuzzy logic methods, genetic algorithms, and computer vision. One of the most effective methods of solving the navigation problem is the method of building a navigation system based on the use of algorithms for localization, mapping, and automatic obstacle avoidance. One of the most effective obstacle avoidance algorithms is the D-star algorithm, which, despite its effectiveness, has some drawbacks. The method of potential fields and neural networks also showed good results, but each of them separately has several significant drawbacks. Based on the method of building a navigation system, the method of potential fields and neural networks, a modified method has been developed that allows a mobile robot to perform autonomous movement in an environment with obstacles. This modification eliminates some of the problems that arise when implementing the navigation system and combines the advantages of the methods used.

Through a meta-heuristic framework, this study examines various wastewater treatment methods in detail and proposes a novel application of genetic algorithms (GAs) in plant optimization. ASM models are adapted to include ion speciation and pairing models, and microplastics (MPs) are challenged, indicating the need for further research. An integrated model accounts for carbon, nitrogen, phosphorus, oxygen, and hydrogen, emphasizing pH’s crucial role in biological treatment processes by examining microbial growth rates and organic compound removal. By applying natural selection and evolutionary processes, GAs are investigated as an optimization tool for plants, improving gene sequence structures and, by extension, treatment processes. The importance of this is particularly evident when dealing with non-standard numerical solutions and algebraic calculations. A robust and adaptable wastewater treatment strategy that accommodates variable weather conditions is provided by the study, which illustrates GAs, their stopping conditions, and the selection process for fitness functions.

This study investigates the optimization of the size of a solar wind hybrid microgrid using Particle Swarm Optimization (PSO) to improve energy production efficiency, economic feasibility, and overall sustainability. By using past solar and wind resource data, load demand profiles, and system component specifications, the PSO algorithm effectively maximized the capabilities of solar panels and wind turbines. The findings indicate a significant rise in daily energy production, with a 15% enhancement in solar panel capability and a 12% boost in wind turbine capability. The increased energy production plays a crucial role in dealing with the natural irregularity of renewable resources, hence enhancing the resilience and self-reliance of the microgrid. The economic calculations demonstrate significant improvements in the economic feasibility of the microgrid designs. The Levelized Cost of Energy (LCOE) undergoes a significant 10% decrease, suggesting a more economically efficient energy generation. Moreover, the payback time for the original expenditure is reduced by 15%, indicating faster returns on investment. The economic improvements highlight the practical advantages of using PSO for microgrid size, in line with the goal of creating sustainable energy solutions while minimizing economic costs. The improved performance of Particle Swarm Optimization (PSO) is shown by a thorough comparison study with other optimization approaches, such as Genetic Algorithms (GA) and Simulated Annealing (SA). The superior convergence rate of PSO, together with a 15% enhancement in solution quality relative to GA and SA, underscores the efficiency and efficacy of PSO in traversing the complex solution space associated with microgrid size. PSO's comparative advantage makes it an effective tool for tackling the intricacies of integrating renewable energy, highlighting its potential for extensive use in microgrid design and optimization. The sensitivity evaluations demonstrate that the solutions optimized by the PSO are resilient even when important parameters vary, thereby highlighting the stability and dependability of the approach. In addition to technical and economic factors, the study evaluates the environmental consequences and social aspects of the optimum microgrid designs. The land use efficiency has seen a 10% enhancement, demonstrating the optimum application of area for renewable energy infrastructure. In addition, there is a 7% improvement in community approval, which demonstrates the algorithm's ability to effectively handle social aspects and promote a comprehensive and socially acceptable approach to renewable energy projects.

This study introduces an iterative scheduling method that combines two approaches for managing repetitive construction projects: the Critical Path Method (CPM) and the Repetitive Scheduling Method (RSM). The primary objective of this study is to demonstrate how optimization techniques can be applied to minimize the cost of construction projects within a defined range, spanning from the shortest to the longest possible project durations. In the shortest project duration (as determined by CPM), all activities are allocated idle times based on precedence constraints, while in the longest duration (as determined by RSM), there is no idle time allocated. To calculate the optimal schedule, a computerized iterative method specifically designed for this purpose considers all possible combinations of activities with and without idle time. The optimum schedule is the one that minimizes the total project cost. The study reveals that by using an Excel spreadsheet, it is feasible to deterministically optimize the cost of repetitive construction projects, achieving the minimum cost. This minimization process can also be implemented as a Python application. Notably, this proposed system provides multiple optimal solutions, enabling managers to select the most suitable one. This advantage distin-guishes it from conventional methods, such as genetic algorithms and other optimization techniques. However, there are some limitations when applying this application, one of which is the maximum capacity available to run the application.

This study investigates the optimization of the size of a solar-wind hybrid microgrid using Particle Swarm Optimization (PSO) to improve energy production efficiency, economic feasibility, and overall sustainability. By using past solar and wind resource data, load demand profiles, and system component specifications, the PSO algorithm effectively maximized the capabilities of solar panels and wind turbines. The findings indicate a significant rise in daily energy production, with a 15% enhancement in solar panel capability and a 12% boost in wind turbine capability. The increased energy production plays a crucial role in dealing with the natural irregularity of renewable resources, hence enhancing the resilience and self-reliance of the microgrid. The economic calculations demonstrate significant improvements in the economic feasibility of the microgrid designs. The Levelized Cost of Energy (LCOE) undergoes a significant 10% decrease, suggesting a more economically efficient energy generation. Moreover, the payback time for the original expenditure is reduced by 15%, indicating faster returns on investment. The economic improvements highlight the practical advantages of using PSO for microgrid size, in line with the goal of creating sustainable energy solutions while minimizing economic costs. The improved performance of Particle Swarm Optimization (PSO) is shown by a thorough comparison study with other optimization approaches, such as Genetic Algorithms (GA) and Simulated Annealing (SA). The superior convergence rate of PSO, together with a 15% enhancement in solution quality relative to GA and SA, underscores the efficiency and efficacy of PSO in traversing the complex solution space associated with microgrid size. PSO’s comparative advantage makes it an effective tool for tackling the intricacies of integrating renewable energy, highlighting its potential for extensive use in microgrid design and optimization. The sensitivity evaluations demonstrate that the solutions optimized by the PSO are resilient even when important parameters vary, thereby highlighting the stability and dependability of the approach. In addition to technical and economic factors, the study evaluates the environmental consequences and social aspects of the optimum microgrid designs. The land use efficiency has seen a 10% enhancement, demonstrating the optimum application of area for renewable energy infrastructure. In addition, there is a 7% improvement in community approval, which demonstrates the algorithm’s ability to effectively handle social aspects and promote a comprehensive and socially acceptable approach to renewable energy projects.

The study explores the enhancement of wind-solar hybrid microgrids via the use of Swarm Intelligence Algorithms (SIAs). It assesses the efficacy of these algorithms in efficiently managing renewable energy sources, load demands, and battery storage inside the microgrid system. An examination of actual data highlights the influence of environmental elements on the production of electricity, as seen by the diverse wind speeds resulting in power outputs that range from 15 kW at 4 m/s to 30 kW at 7 m/s. This underscores the clear and direct relationship between wind speed and the amount of power created. Likewise, solar irradiance levels demonstrate oscillations ranging from 500 W/m² to 800 W/m², therefore yielding power outputs that include a range of 15 kW to 24 kW, so illuminating the profound impact of solar irradiance on energy capture. The dynamic energy consumption patterns are exposed by the varying load demands, whereby the demand levels oscillate between 20 kW and 28 kW. This highlights the crucial significance of demand variability in determining energy needs. In addition, the data on battery storage reveals a range of charge levels, ranging from 25 kWh to 40 kWh, which underscores its pivotal function in the equilibrium of energy supply and consumption. When evaluating SIAs, it becomes evident that Particle Swarm Optimization (PSO) surpasses both Ant Colony Optimization (ACO) and Genetic Algorithms (GA) in obtaining an impressive 80% renewable energy penetration rate. PSO effectively reduces operating costs by 15%, demonstrating its exceptional proficiency in optimizing microgrid operations. This study provides valuable insights into the intricate interplay among environmental conditions, load demands, battery storage, and algorithmic optimization in wind-solar hybrid microgrids.