Hybrid Optimization Research Articles

Using algorithmic game theory to improve supervised machine learning: A novel applicability approach in flood susceptibility mapping.

This study was carried out with the aim of applying Condorcet and Borda scoring algorithms based on Game Theory (GT) to determine flood points and Flood Susceptibility Mapping (FSM) based on Machine Learning Algorithms (MLA) including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in the Cheshmeh-Kileh watershed, Iran. Therefore, first, FS conditioning factors including Aspect (As), Elevation (El), Euclidean distance (Euc), Forest (F), NDVI, Precipitation (P), Plan Curvature (PlC), Profile Curvature (PrC), Residential (Re), Rangeland (Rl), Slope (Sl), Stream Power Index (SPI), Topographic Position Index (TPI), and Topographic Wetness Index (TWI) were quantified in each Sub-Watershed (SW). Based on this, flood and non-flood points were identified based on both GT algorithms. In the following, MLAs including Random Forest (RF), Support Vector Regression (SVR), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) were used for the distributional mapping of FS. Finally, based on optimal conjunct approaches, FS maps were presented in the study watershed. Based on the results, among the conjunct algorithms in FS classification, RF-Condorcet and RF-Borda models were selected as the most optimal MLA-GT hybrid models. The upstream SWs were highly susceptible. Also, the effectiveness of NDVI and forest conditioning factors in each classification approach was high. The similarity of SW prioritization based on Condorcet algorithm with RF-Condorcet algorithm was about 86.70%. Meanwhile, the degree of similarity in RF-Borda conjunct algorithm was around 73.33%. These results showed that Condorcet algorithm had an optimal classification compared to Borda scoring algorithm.

Study on Multi-Objective Optimization of Construction Project Based on Improved Genetic Algorithm and Particle Swarm Optimization

Construction projects require concurrent consideration of the three major objectives of construction period, cost, and quality. To address the multi-objective optimization issues of construction projects, mathematical models of construction period, quality, and cost are established, respectively, and multi-objective optimization models are constructed for different construction objectives. A hybrid optimization method combining an improved genetic algorithm (GA) with a time-varying mutation rate and a particle swarm algorithm (PSO) is proposed to optimize construction projects, which overcomes the shortcomings of the original GA and improves the global optimality and stability of results. Various construction projects were considered, and different construction objectives were analyzed individually. Finally, an uncertainty analysis is developed for the proposed GA-PSO algorithm and compared with GA and PSO. The results indicate that the proposed hybrid approach outperforms the PSO and GA algorithms in providing a better and more stable multi-objective optimized construction solution, with performance improvements of 4.3–8.5% and volatility reductions of 37.5–64.4%. This provides a reference for the optimal design of wind farms, buildings, and other construction projects.

Multi-Energy Load Prediction Method for Integrated Energy System Based on Fennec Fox Optimization Algorithm and Hybrid Kernel Extreme Learning Machine.

To meet the challenges of energy sustainability, the integrated energy system (IES) has become a key component in promoting the development of innovative energy systems. Accurate and reliable multivariate load prediction is a prerequisite for IES optimal scheduling and steady running, but the uncertainty of load fluctuation and many influencing factors increase the difficulty of forecasting. Therefore, this article puts forward a multi-energy load prediction approach of the IES, which combines the fennec fox optimization algorithm (FFA) and hybrid kernel extreme learning machine. Firstly, the comprehensive weight method is used to combine the entropy weight method and Pearson correlation coefficient, fully considering the information content and correlation, selecting the key factors affecting the prediction, and ensuring that the input features can effectively modify the prediction results. Secondly, the coupling relationship between the multi-energy load is learned and predicted using the hybrid kernel extreme learning machine. At the same time, the FFA is used for parameter optimization, which reduces the randomness of parameter setting. Finally, the approach is utilized for the measured data at Arizona State University to verify its effectiveness in multi-energy load forecasting. The results indicate that the mean absolute error (MAE) of the proposed method is 0.0959, 0.3103 and 0.0443, respectively. The root mean square error (RMSE) is 0.1378, 0.3848 and 0.0578, respectively. The weighted mean absolute percentage error (WMAPE) is only 1.915%. Compared to other models, this model has a higher accuracy, with the maximum reductions on MAE, RMSE and WMAPE of 0.3833, 0.491 and 2.8138%, respectively.

Meta-algorithmic optimized power allocation in cybertwin-based sixth generation cooperative communication system

The sixth-generation (6G) communication paradigm, powered by an Internet of Everything (IoE), promises unprecedented data density and transformative applications across various sectors like smart cities, healthcare, transportation, and agriculture. This study explores an emerging hybrid cybertwin-enabled 6G cooperative network architecture, focusing on secrecy capacity analysis. The approach involves Base Stations (BS) employing Non-Orthogonal Multiple Access (NOMA) techniques to transmit data to cybertwin hosts and servers via direct wireless links with Nakagami-m fading. Additionally, a Power Line Communication (PLC) link, subjected to Rayleigh fading, supplements the wireless link for communication between cybertwin hosts and servers. Bio-meta-heuristic optimization algorithms are introduced to optimize NOMA power allocation, specifically Grey Wolf Optimization (GWO) and a hybrid of Grey Wolf Optimization with Krill Herd Optimization (KHO). The system's capability to ensure secure data transmission while mitigating eavesdropping risks is assessed through thorough secrecy capacity and throughput analyses. Simulation results highlight the efficacy of the hybrid GWO-KHO-based NOMA power allocation scheme, showcasing superior efficiency over traditional methods. This study contributes novel insights into optimized power allocation and efficiency in cybertwin-enabled 6G networks, underscoring the significance of hybrid optimization approaches in future communication systems.

Multi-objective nature inspired hybrid optimization algorithm to improve prediction accuracy on imbalance medical datasets

Multi-objective nature inspired hybrid optimization algorithm to improve prediction accuracy on imbalance medical datasets

Experimental study on the mechanical properties and impermeability of basalt-PVA hybrid fibre reinforced concrete

Numerous studies have indicated that the incorporation of chopped fibres can significantly improve the mechanical properties and durability of concrete. To further explore the effect of chopped basalt fibres, PVA fibres and their hybrid fibres on the improvement of concrete mechanics and impermeability, mechanical property and impermeability tests of chopped basalt fibres/PVA fibres of different lengths and hybrid ratios mixed with concrete of disparate benchmark strengths were carried out. By comparing the characteristic values of each group and their variation rules, the optimal length and hybrid ratio of the fibres were determined. The results show that the enhancement effect of chopped basalt fibres of different lengths on the mechanical and impermeability properties of concrete is different, showing a trend of first increasing and then decreasing. The enhancement effect of chopped basalt fibres on the mechanical and impermeability performance of concrete with different benchmark strengths is better than that of PVA fibres. Compared with those of the C30 plain concrete, the mechanical and impermeability properties of the chopped basalt-PVA hybrid fibre concrete significantly improve to varying degrees. When the proportion of chopped basalt fibres is greater than or equal to the proportion of PVA fibres, a positive hybrid effect on the mechanical and impermeability performance of concrete with the same benchmark strength occurs. With increasing benchmark strength, the enhancement effect of the two types of fibres on the mechanics and impermeability of the concrete decreases. The attenuation range of PVA fibres is greater than that of chopped basalt fibres, and even a reduction in the mechanical and impermeability properties of concrete occurs. This results in the enhancement effect of chopped basalt-PVA hybrid fibres on concrete mechanics as well as a significant decrease in the impermeability. The improvement rates of the compressive performance and impermeability of concrete by a single or a hybrid of the two fibres are highly similar, and the enhancement effect of the fibre compressive performance is significantly greater than that of the impermeability.

Enhancing ammonia decomposition in ammonium hydroxide/diesel emulsion through hybrid nanocomposite and optimization for improved and greener combustion

In this study, a hybrid nanocomposite was synthesized and characterized to intensify ammonia decomposition in ammonium hydroxide (AH) emulsified diesel fuel. The optimal concentrations of AH and zinc oxide/carbon nanotube (ZnO/CNT) nanocomposite in diesel fuel were evaluated using response surface methodology for effectual and greener combustion. The range of AH concentration was varied from 10 % to 30 %, and ZnO/CNT nanocomposite concentration ranged from 50 ppm to 150 ppm in diesel fuel. Validation experiments were performed to confirm the optimized parameters’ competence compared to regular diesel fuel (RDF). Fourier Transform Infrared and X-ray Diffraction analyses verified successful ZnO/CNT nanocomposite synthesis with desired structural and chemical properties. Optimization results indicated that an 17.2 % volume concentration of AH and 82.3 ppm of ZnO/CNT nanocomposite in RDF yielded efficient combustion with reduced emissions. Validation results showed that the inclusion of 17 % AH in RDF decreased engine brake thermal efficiency (BTE) by 11.1 % and increased brake specific fuel consumption (BSFC), hydrocarbon (HC), carbon monoxide (CO), and oxides of nitrogen (NOx) emissions by 11.3 %, 9.1 %, 9.9 %, and 3 %, respectively. Furthermore, the presence of the nanocomposite (82.3 ppm) enhanced BTE by 10.1 % and reduced BSFC, HC, CO, and NOx emissions by 6.9 %, 6.2 %, 6.9 %, and 5.9 %, respectively. The advancements in fuel additives, such as ZnO/CNT nanocomposites in AH emulsified diesel fuel, have the potential to create more fuel-efficient and cleaner diesel engines. These improvements can significantly contribute to sustainable energy solutions.

Hybrid optimization algorithm based on chaos game and differential evolution for constrained optimization of structures

ABSTRACT A novel hybrid optimization algorithm, chaos game optimization–differential evolution (CGO-DE), is developed in this study for the size optimization of structures. The key contribution lies in the synergistic combination of chaos game optimization (CGO) and differential evolution (DE), using their respective strengths in exploration and exploitation to effectively identify global optima. The innovative approach independently applies CGO and DE to subpopulations, preventing premature convergence and enhancing overall performance while ensuring accuracy, accounting for design factors and respecting constraints. Comprehensive numerical evaluations on established structural benchmarks (three-bar truss, welded beam and cantilever beam) and large-scale structures (272-bar and 942-bar truss tower) demonstrate the versatility and efficiency of CGO-DE in solving complex optimization problems across various engineering applications. The results underscore the ability of the algorithm to achieve optimal solutions and improve designs compared to other optimization techniques, highlighting its potential as a powerful tool for engineering optimization.

Study on the impact of hybridization of spherical fillers with size differences and sheet fillers on the thermal conductivity and anticorrosive performance of composite coatings

AbstractThe improvement of anti‐corrosion performance and enhancement of functionality in anti‐corrosion coatings are essential. Boron nitride (BN), as a two‐dimensional thermal conductive filler, is incorporated into composite coatings to provide corrosion resistance and thermal conductivity. The combination of BN with zero‐dimensional filler alumina (Al2O3) proves to be an effective method for enhancing the thermal conductivity of composite coatings. In this study, micro alumina (Micro‐Al2O3) and/or nano alumina (Nano‐Al2O3) were combined with BN to be integrated into waterborne epoxy resin (WER), resulting in different composite coatings (BN@Micro‐Al2O3/WER, BN@Nano‐Al2O3/WER, and BN@Micro‐Al2O3/Nano‐Al2O3/WER). The influence of different hybrid modes of two‐dimensional and zero‐dimensional thermal conductive fillers on corrosion resistance and thermal conductivity was discussed. The composite coating BN@Micro‐Al2O3/Nano‐Al2O3/WER exhibits the highest thermal conductivity at 0.789 W/mK with a filler loading of 30 wt% BN, 4 wt% Micro‐Al2O3, and 6 wt% Nano‐Al2O3. Meanwhile, the composite coating BN@Nano‐Al2O3 demonstrates superior anti‐corrosion performance at a filler loading of 20 wt% BN and 10 wt% Nano‐Al2O3. After immersion in a 28‐day period in a NaCl solution with a concentration of 3.5%, the impedance modulus remains above 109 Ω·cm2, while corrosion current density is measured at 7.3367 × 10−8 A/cm2. The hybrid mode involving two‐dimensional and zero‐dimensional thermal conductive fillers can effectively improve the composite coatings' corrosion resistance and thermal conductivity. There are variations in the optimal hybrid methods for incorporating two‐dimensional and zero‐dimensional thermal conductive fillers to enhance anti‐corrosion and heat conduction effectiveness of coatings.Highlights The properties of coating is improved by the incorporation of BN and Al2O3. The prepared coating performs good thermal conductivity. The synergy of BN and Al2O3 can improve thermal conductivity significantly. The obtained coating performs good corrosion resistance. The synergy of BN and Al2O3 can also improve anti‐corrosion effectively.

Optimal allocation of EV charging station and capacitors considering reliability using a hybrid optimization approach

This paper proposes a novel approach for strategically placing EV charging stations (EVCS) and capacitors within electrical distribution networks (EDN) to mitigate issues arising from the widespread adoption of Electric Vehicles (EVs). The goal is to maximize the net present value (NPV) by reducing energy losses and minimizing system interruption costs while ensuring reliability. To achieve this, the paper introduces a hybrid optimization technique called HGP_CS, which combines Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Cuckoo Search optimization methods. By employing various compensation coefficients to assess failure rates and identify strategies for enhancing NPV, the approach aims to optimize the placement of EVCS and capacitors within the EDN. Validation is carried out in IEEE 33-bus and 118-bus systems to demonstrate the performance of the proposed approach. It is found that the proposed approach, compared to the base case, reduced the energy loss cost by 34.19% and 31.57% and also the Expected Interruption Costs (EIC) by 17.26% and 13.41%, for IEEE 33-bus and 118-bus system, respectively. Additionally, the proposed method is economically beneficial as it can attain higher profits. In IEEE 33- bus and 118 bus systems, the annual net profit using the proposed approach is 36,805 $/year and 271,670.72 $/year, respectively. Thus, the proposed technique enhances the overall system performance and significantly boosts profitability, making it a compelling choice for optimizing the placement of charging stations and reactive power sources in networks.

Wind Speed Forecasting Based on Phase Space Reconstruction and a Novel Optimization Algorithm

The wind power generation capacity is increasing rapidly every year. There needs to be a corresponding development in the management of wind power. Accurate wind speed forecasting is essential for a wind power management system. However, it is not easy to forecast wind speed precisely since wind speed time series data are usually nonlinear and fluctuant. This paper proposes a novel combined wind speed forecasting model that based on PSR (phase space reconstruction), NNCT (no negative constraint theory) and a novel GPSOGA (a hybrid optimization algorithm that combines global elite opposition-based learning strategy, particle swarm optimization and the genetic algorithm) optimization algorithm. SSA (singular spectrum analysis) is firstly applied to decompose the original wind speed time series into IMFs (intrinsic mode functions). Then, PSR is employed to reconstruct the intrinsic mode functions into input and output vectors of the forecasting model. A combined forecasting model is proposed that contains a CBP (cascade back propagation network), RNN (recurrent neural network), GRU (gated recurrent unit), and CNNRNN (convolutional neural network combined with recurrent neural network). The NNCT strategy is used to combine the output of the four predictors, and a new optimization algorithm is proposed to find the optimal combination parameters. In order to validate the performance of the proposed algorithm, we compare the forecasting results of the proposed algorithm with different models on four datasets. The experimental results demonstrate that the forecasting performance of the proposed algorithm is better than other comparison models in terms of different indicators. The DM (Diebold–Mariano) test, Akaike’s information criterion and the Nash–Sutcliffe efficiency coefficient confirm that the proposed algorithm outperforms the comparison models.

Enhancing on-grid renewable energy systems: Optimal configuration and diverse design strategies

This study explores the optimization of hybrid renewable energy systems in smart grids, incorporating configurations involving multiple sources such as solar photovoltaic, wind, and combined PV/wind systems with advanced battery storage strategies. The goal is to develop optimal sizing and energy management solutions that not only reduce the grid use factor but also enhance the sustainability and reliability of energy systems through innovative energy-saving methods and carbon-neutral approaches. Utilizing a novel methodology that integrates particle swarm optimization, long short-term memory, and genetic algorithms, this research identifies the most effective mix of renewable energy capacities alongside versatile energy storage solutions, to align energy production with consumption efficiently. The study demonstrates significant environmental benefits, crucial for sustainable management aimed at achieving carbon neutrality, including reducing CO2 emissions by 122.29 tons per year and maintaining a notably low levelized cost of energy at $0.0417/kWh. The model proves accurate in forecasting renewable energy generation, emphasizing its potential as a sustainable and cost-effective alternative to traditional energy sources. These findings underscore the critical importance of integrating optimal hybrid renewable systems that incorporate strategic energy storage, innovative optimization for energy savings, and robust measures towards achieving carbon neutrality, thus enhancing both energy sustainability and economic feasibility.

Epidemiological Model of the Regional Distribution and Analysis of Hepatitis B in Ghana: A Sub-Saharan African Country

Hepatitis B (HB) is a global public health burden which has impacted economies of many countries, particularly in sub-Saharan Africa. The effect is worse where there is lack of definite information regarding policy direction and capacity towards implementing interventions to control the transmission and spread of the infection. In this study, a SEIR deterministic compartmental model and a hybrid optimisation method for parameter estimation, similar to that of Awuah-Mensah et al. (2022), were used to analyse the regional distribution of HB in Ghana, a sub-Saharan African country. The regional epidemiological threshold parameters [Formula: see text] and herd immunity threshold parameters [Formula: see text] computed based on the estimated parameters for each of the regions ranged from a minimum of [Formula: see text] for Volta region in the southeast to a maximum of [Formula: see text] for Upper West region in the northwest of Ghana. These values of [Formula: see text] and [Formula: see text] indicated that HB persists in Ghana and the transmission and spread and the associated burden were found to generally increase from south to north of the country. Based on the estimated parameters, only Western region recorded a recovery rate of [Formula: see text]. The remaining nine regions recorded zero recovery rates. The trend of transmission and spread of the infection was also found to be positively related to poverty and health sector inequalities across the regions of the country.

A novel hybrid optimization model for evaluating and forecasting air quality grades.

Air pollution has a significant global impact on natural resources and public health. Accurate prediction of air pollution is crucial for effective prevention and control measures. However, due to regional variations, different cities may have varying primary pollutants, posing new challenges for accurate prediction. In this paper, we propose a novel method called FP-RF, which integrates clustering algorithms to categorize multiple cities according to their air quality index values. Subsequently, we apply functional principal component analysis to extract the primary components of air pollution within each cluster. Furthermore, an enhanced random forest algorithm is utilized to predict air quality grades for each city. We conduct experimental evaluations using authentic historical data from Anhui Province spanning from 2018 to 2023. The results unequivocally establish the effectiveness of our model, with an average accuracy rate of 98.6% in forecasting six pollution grades and 96.04% accuracy in predicting 16 prefecture-level cities, surpassing performance compared to other baseline models.

Optimal Placement of Fast Charging Station using Hybrid Optimization Algorithm

Optimal Placement of Fast Charging Station using Hybrid Optimization Algorithm

Development of hybrid sewing training-based dingo optimization algorithm for massive MIMO spectral efficiency maximization system

ABSTRACT A Base Station (BS) with several antenna elements serves a number of users in the frequency of the same time- slot in a huge multiuser “Multiple-Input Multiple-Output (MIMO)”. It has emerged as a viable method for the future generation of wireless networks due to its capacity to enhance both spectrum and efficiency of energy, even with straightforward linear processing like “Maximum Ratio Combining (MRC), Linear Minimum Mean Square Error (LMMSE) and Zero Forcing (ZF)”. In a power allocation scheduling method, only users who do not interfere with one another can change their power at any one time. These studies all take into account orthogonal channels. However, the “Spectral Efficiency (SE)” is reduced by the channels’ non-orthogonality. This encourages us to research how to maximize spectral efficiency in “Massive MIMO (M-MIMO)” systems by allocating power for both uplink and downlink transmission. Here, the Hybrid of Sewing Training and Dingo Optimization (HSTDO) is developed for executing the best resource allocation in the M-MIMO system to improve SE performance which helps to enhance the SE of the M-MIMO system. The simulation is carried out to compare the developed model with the conventional works to reveal the better spectral efficiency of the suggested algorithm.

An Improved Eyegaze Tracking Application for Early Prediction of Mental Health Using Convolution Neural Networks with Hybrid Optimization Approach

An Improved Eyegaze Tracking Application for Early Prediction of Mental Health Using Convolution Neural Networks with Hybrid Optimization Approach

Improved slime mould algorithm for optimal hybrid power system scheduling

Improved slime mould algorithm for optimal hybrid power system scheduling

Green mechanism: Opportunities for corporate investment in PV/battery/diesel hybrid systems with techno-economic and environmental analysis

In rural areas, diesel generators are prevalent due to their lower initial cost, despite inefficiencies and carbon emissions. Transitioning to PV/Battery/Diesel systems offers a solution by reducing costs and emissions. However, the high upfront expenses present a significant barrier, particularly for rural communities, necessitating external financial support. This study evaluates the benefits of adopting a PV/Battery/Diesel hybrid system over traditional diesel generators in a rural community with 25 customers and a daily demand of 50 kWh. The proposed system includes a 12 kWp photovoltaic array and a 48 kWh battery bank, simulated using Hybrid Optimization of Multiple Energy Resources (HOMER) software. Results indicate a 91% renewable fraction and a cost of energy of 0.279 USD/kWh, substantially lower than the 1.05 USD/kWh of diesel-only systems, with CO2 savings of 25 t per year. The paper advocates for a case study approach to green mechanism, urging energy and environmental companies to invest in these systems. By replacing diesel generators with hybrid PV/Diesel/Battery systems, companies can offer electricity at a reduced cost, driving adoption. Selling carbon credits from emission savings can generate additional income, leveraging CO2 tax incentives. Under scenarios where investors cover 50% of diesel costs, selling electricity yields 9581 USD annually, and selling CO2 credits generates 500 USD annually. This leads to a payback period of 9.83 years without CO2 credits and 9.18 years with CO2 credits, totaling 46,848 USD without CO2 credits and 52,927 USD with CO2 credits over the project's lifespan. Meanwhile, adjusting electricity pricing to 75% of diesel costs, this increases annual income from electricity sales to 14,372 USD. This reduces the payback period to 5.89 years without CO2 credits and 5.66 years with CO2 credits, totaling 105,094 USD without CO2 credits and 111,174 USD with CO2 credits at the end of the project.

A fuzzy-PID controller for load frequency control of a two-area power system using a hybrid algorithm

This paper presents the use of a new hybrid optimization approach known as particle swarm optimization and grey wolf optimizer (PSO-GWO) for improving frequency stability load frequency control (LFC) in tow-area power systems. The approach consists in optimizing the fuzzy proportional-integral-derivative (fuzzy-PID) controller parameters with meta-heuristic hybrid algorithm: PSO-GWO. This technique allows to have dynamic responses with the least possible frequency deviation in very short response times. The approach proposes to controls the tie-line power and the frequency deviation in the considered two-area power systems under variable perturbation in load and changing of system parameters in order to evaluate its effectiveness. The suggested hybrid algorithm-based fuzzy-PID controller is compared with various widely used control methods in the literature such as PID controller and algorithms such as PSO and GWO in order to evaluate its effectiveness and its robustness. Through the simulations carried out on MATLAB/Simulink, the proposed PSO-GWO fuzzy-PID and the objective function exhibit improved performance, achieving minimal objective values. The proposed technique proved to be quite powerful tool in the resolution of problems related to electrical power systems, particularly in load frequency control.