Wei Rao, H B Wang, Yangyang Cui et al. · Journal of Circuits Systems and Computers · 2025
Renewable energy development and the pressing demand for optimized energy management make distributed energy storage Systems in multi-energy systems more relevant to China. This paper will discuss an optimization strategy for the “Hubei Electric Power Special Network” using distributed energy storage and multi-energy coupling within a P2P market mechanism based on VPP IoT frameworks. We develop an innovative, advanced P2P market structure based on optimized energy exchange algorithms, storage management algorithms and cooperative behaviors between prosumers. Multi-energy coupling is used among electricity, heat and gas to ensure strategy-based storage virtualization in terms of cost efficiency, a multi-objective optimization model and maximized battery storage efficiency. The whole transaction process uses blockchain for safe registration, while the use of Nash bargaining under uncertainty can ensure the fair distribution of multi-energy trading as the contribution from each party. Performance test in the Hubei Electric Power Special Network is discussed along with the performance in terms of time, heating power, electricity demand, storage price and energy trading efficiency. Implementing the proposed strategy on top of the VPP operation and advanced energy management may effectively support a further possibility of being added to China’s changing energy future scenario, which can be considered in such contexts.
Cited by 0
Li Qun Lv, Lingfeng Yang, Jeng-Shyang Pan et al. · Journal of King Saud University - Computer and Information Sciences · 2026
Abstract In tackling constrained multi-objective optimization problems, conventional multi-objective wolf pack algorithm often exhibits poor feasibility and diversity, primarily due to the lack of explicit constraint-handling mechanisms and strong reliance on the leader wolf leading to population aggregation. To overcome these issues, this paper proposes a constrained multi-objective wolf pack algorithm based on cooperative optimization and tiered hunting (CTCMOWPA). The cooperative optimization technique is designed to balance exploration of the infeasible region and exploitation within the feasible region. It maintains two cooperative populations with distinct roles. The main population preserves feasibility by applying the CDP. The secondary population first explores the unconstrained Pareto Front and then employs an adaptive $$\varepsilon$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>ε</mml:mi> </mml:math> constraint-handling method to guide the search toward feasible regions. Moreover, information exchange between these populations enhances adaptability to diverse constraints. Additionally, a tiered hunting strategy categorizes wolves into elite wolves characterized by lower fitness that besiege the leader wolf to inherit its information, and exploration wolves distinguished by higher fitness that are dually guided by the leader and elite wolves, thereby suppressing aggregation while maintaining diversity and convergence. Experimental comparisons with six advanced algorithms on three benchmark suites demonstrate that CTCMOWPA achieves the best IGD values on 19 out of 38 test problems and outperforms the comparison algorithms in feasibility and diversity.
Cited by 0Open access
Rezaei, Arian · Memorial University Research Repository (Memorial University) · 2025
This thesis presents a comprehensive framework for modelling and multi-objective optimization of industrial hydrocracking and hydroprocessing units that e↵ectively addresses the challenges associated with complex process dynamics and data quality. The proposed framework combines advanced machine learning techniques, explainability methods and multi-objective optimization algorithms to improve the operational performance and efficiency of hydrocracking units. The framework begins with data preparation based on cycles and modes of operation. Data preprocessing involves addressing missing data using the iterative imputation method, followed by detection and removal of anomalies using the 3-! rule and Isolation Forest algorithm. An extensive comparative analysis was performed for product yield prediction using a diverse set of machine learning algorithms, including Decision Trees, Support Vector Regression, Random Forests, Deep Neural Networks, XGBoost, LightGBM and CatBoost. Through comprehensive performance assessment, CatBoost emerged as the most robust predictive algorithm, demonstrating exceptional potential in mitigating overfitting and significantly enhancing predictive accuracy across datasets. Subsequently, SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) analyses were employed to explain model predictions and identify key influencing input variables to manipulate for optimization. The multi-objective optimization is then performed using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), exploring various scenarios to maximize desired products’ yields or volume swell during cracking. The framework is implemented and validated through two case studies, achieving higher prediction accuracy and providing optimization results that significantly enhance operational performance and profitability. This research highlights the potential of integrating machine learning and optimization techniques to advance industrial processes. Future work could explore using reinforcement learning and digital twins for real-time optimization and control.
Cited by 0Open access
Krisztián Mihály, Gyula Kulcsár · International Journal of Industrial Engineering and Management · 2023
A New Many-Objective Hybrid Method to Solve Scheduling ProblemsThis paper proposes a new hybrid method to solve extended scheduling problems that can include multiple resources, projects, and tasks with specific attributes, relationships, and constraints, as well as many objective functions with individual optimization directions and variable importance.A new decision-making procedure is proposed to combine metaheuristic search strategies, constructive algorithms, and many-objective comparison models.This paper also presents a concrete realization in which an advanced mixture search algorithm drives a flexible controllable constructive algorithm, and a relative qualification model ensures multi-objective optimization.Some numerical results illustrate the effectiveness of the proposed hybrid method.
Cited by 1Open access
Zhonglei Xia, Jian Li · 2025
With the transformation of the construction industry towards greenization and intelligence, multi-objective collaborative control and intelligent platform construction for green construction have become key requirements for the industry's development. The current research has problems such as insufficient handling of dynamic coupling relationships in multi-objective optimization, limited algorithm adaptability, and fragmented platform functionality. Therefore, this study focuses on green construction and platform development in the construction process, proposing solutions based on advanced algorithms. By improving the swarm intelligence algorithm, introducing chaotic mapping to optimize the initial population distribution, and combining adaptive weight coefficients to balance global and local search, the convergence speed and optimization accuracy of multi-objective optimization are improved; Build a four objective optimization model covering construction period, cost, carbon emissions, and quality, and achieve the integration and quantification of qualitative and quantitative indicators; Design a layered platform architecture that includes perception layer, data layer, core layer, and application layer, forming a closed-loop management of “data collection model optimization decision output”. The experimental results show that this scheme can effectively shorten the construction period, reduce costs and carbon emissions, while maintaining stable quality, verifying its scientific and practical value in the full process control of green construction, and providing theoretical and technical support for the high-quality and sustainable development of the construction industry.
Cited by 0
Areg Grigoryan, Armine Gevorg Avetisyan, Tatevik Razmik Melkonyan et al. · Advances in Science and Technology – Research Journal · 2026
This study presents optimization techniques aimed at improving the performance of magnetorheological (MR) brakes through the application of heuristic algorithms and machine learning methods.MR fluids, characterized by their rapid and reversible transition between fluid and semi-solid states under the influence of a magnetic field, are widely used in automotive systems, robotics, and vibration control applications.The research focuses on optimizing key performance metrics -namely, the electromagnetic force acting on the front of the MR fluid magnetic particle bridge and the velocity of the bridge front -using both single-and multi-objective optimization approaches.Two distinct methodologies were employed: (i) heuristic methods using an automated system based on the mathematical model of the electromagnetic system, and (ii) hybrid methods combining machine learning models with heuristic algorithms.The results demonstrate that machine learning-assisted optimization substantially reduces computational time while maintaining high predictive accuracy.Furthermore, multi-objective optimization identified optimal structural dimensions and voltage levels that achieve balanced performance across the selected criteria.These findings highlight the potential of hybrid optimization strategies for the efficient design of MR brake systems, supporting their broader integration into advanced engineering applications.
Cited by 0Open access
X.B. Liu, Fufu Wang, Yu Liu et al. · Drones · 2025
In UAV path-planning research, it is often difficult to achieve optimal performance for conflicting objectives. Therefore, the more promising approach is to find a balanced solution that mitigates the effects of subjective weighting, utilizing a multi-objective optimization algorithm to address the complex planning issues that involve multiple machines. Here, we introduce an advanced mathematical model for cooperative path planning among multiple UAVs in urban logistics scenarios, employing the non-dominated sorting black-winged kite algorithm (NSBKA) to address this multi-objective optimization challenge. To evaluate the efficacy of NSBKA, it was benchmarked against other algorithms using the Zitzler, Deb, and Thiele (ZDT) test problems, Deb, Thiele, Laumanns, and Zitzler (DTLZ) test problems, and test functions from the conference on evolutionary computation 2009 (CEC2009) for three types of multi-objective problems. Comparative analyses and statistical results indicate that the proposed algorithm outperforms on all 22 test functions. To verify the capability of NSBKA in addressing the multi-UAV cooperative problem model, the algorithm is applied to solve the problem. Simulation experiments for three UAVs and five UAVs show that the proposed algorithm can obtain a more reasonable collaborative path solution set for UAVs. Moreover, path planning based on NSBKA is generally superior to other algorithms in terms of energy saving, safety, and computing efficiency during planning. This affirms the effectiveness of the meta-heuristic algorithm in dealing with multiple objective multi-UAV cooperation problems and further enhances the robustness and competitiveness of NSBKA.
Cited by 11Open access
Zong Li Liu, Jie Cao, Zhan Yuan · Applied Mechanics and Materials · 2010
The optimization of complex systems, such as production scheduling systems and control systems, often encounters some difficulties, such as large-scale, hard to model, time consuming to evaluate, NP-hard, multi-modal, uncertain and multi-objective, etc. It is always a hot research topic in academic and engineering fields to propose advanced theory and effective algorithms. As a novel evolutionary computing technique, particle swarm optimization (PSO) is characterized by not being limited by the representation of the optimization problems, and by global optimization ability, which has gained wide attentation and research from both academic and industry fields. The task assignment problem in the enterprise with directed graph model is presented. Task assignment problem with buffer zone is solved via a hybrid PSO algorithm. Simulation result shows that the model and the algorithm are effective to the problem.
Cited by 0
Zongli Liu, Jie Cao, Zhanting Yuan · 2014
Abstract. The optimization of complex systems, such as production scheduling systems and control systems, often encounters some difficulties, such as large-scale, hard to model, time consuming to evaluate, NP-hard, multi-modal, uncertain and multi-objective, etc. It is always a hot research topic in academic and engineering fields to propose advanced theory and effective algorithms. As a novel evolutionary computing technique, particle swarm optimization (PSO) is characterized by not being limited by the representation of the optimization problems, and by global optimization ability, which has gained wide attentation and research from both academic and industry fields. The task assignment problem in the enterprise with directed graph model is presented. Task assignment problem with buffer zone is solved via a hybrid PSO algorithm. Simulation result shows that the model and the algorithm are effective to the problem.
Cited by 0
Dmitriy Achkasov · 2026
The article analyzes and details the evolution of genetic algorithms for solving multi-criteria optimization problems. It considers pioneering algorithms such as VEGA (Vector Evaluated Genetic Algorithm) and FFGA (Fitness Function Genetic Algorithm), identifying their key limitations, including a tendency towards specialization and a lack of mechanisms for maintaining solution diversity. Particular focus is placed on the more advanced SPEA (Strength Pareto Evolutionary Algorithm), which integrates the concept of individual strength, an external archive for storing non-dominated solutions, and a clustering procedure to ensure uniform coverage of the Pareto front. The comparative analysis demonstrates that the sequential development of methods from VEGA to SPEA effectively addressed convergence and diversity issues, establishing multi-objective evolutionary algorithms as a powerful tool for finding optimal trade-offs in complex systems with conflicting criteria.
Cited by 0Open access
Stark, Sanja · Carl von Ossiezky University of Oldenburg · 2025
By introducing advanced information and communication technologies (ICT) into distribution grids, distributed energy resources can create island grids in the distribution system. Finding the optimal composition of an island grid is a complex optimization problem that can be solved with a Multi-Agent System (MAS). While agent-based restoration algorithms are a popular concept in the literature, the interdependencies between power and ICT systems during restoration have yet to be considered. This PhD project aims to fill this gap by developing an agent-based restoration algorithm that restores power and ICT systems in parallel. The restoration process is regarded as a multi-objective optimization problem and both the restored load and ICT should be maximized. Specifically, the effect of considering ICT restoration as a separate objective is studied by comparing a version of the algorithm with ICT and without ICT.
Cited by 0
Jintao Yang, Zhuo Liu, Shuo Huang et al. · Transactions on Economics Business and Management Research · 2023
This study delves into the challenges and complexities of vegetable sales management in modern commercial environments, particularly in fresh food supermarkets. By utilizing descriptive statistics and visual analysis of sales data, the study reveals the correlations between different vegetable categories and quantifies these correlations using Pearson's correlation coefficient. Subsequently, by integrating time series analysis and multi-objective programming, a mathematical model is constructed, aimed at maximizing profits under specific constraints. The innovation of this research lies in its comprehensive consideration of category-level sales management and the application of modern optimization algorithms for replenishment and pricing strategies. The uniqueness of this paper is in its integrative approach to the vegetable sales problem, providing refined mathematical models and advanced optimization methods. Finally, the paper thoroughly describes the steps of the research design, including sales data analysis, cost markup analysis, and the construction of an optimization model based on time series analysis and multi-objective programming, intending to offer supermarkets a vegetable sales management plan adaptable to market changes.
Cited by 0Open access
Momchil Shopov, D. N. Gospodinova · 2025
Electrospinning is a widely used technique for producing nanofibers with applications ranging from biomedical engineering to advanced materials. However, the process is highly dependent on a complex interplay between multiple parameters, including solution properties, processing conditions, and environmental factors. This study presents a methodological approach to modelling and optimizing the electrospinning process, including Design of Experiments (DoE), mathematical modelling, and optimization techniques. The proposed approach employs genetic algorithms for multi-objective optimization to achieve precise control over fiber morphology and process efficiency. By leveraging software-driven process analysis, critical parameters are identified and optimized, ensuring high-quality fiber production with improved reproducibility.
Cited by 1
Celia Khelfa, Habiba Drias, Ilyes Khennak · 2024
As natural disasters rise, traditional infrastructure may be damaged or ineffective, complicating the delivery of medical supplies. Using drones to deliver these supplies to affected areas is increasingly seen as an effective and necessary solution. However, managing drones under these constraints quickly becomes a complex problem requiring intelligent methods. This paper presents a novel approach to address the Medical Supply Drone Delivery (MSDD) problem in post-disaster scenarios by modeling it as a multi-objective optimization problem. We introduce the Slime Mould Algorithm (SMA), designed to optimize drone management during post-disaster situations. Using generative AI techniques, specifically ChatGPT, we augment limited COVID-19 datasets from Algeria to create realistic scenarios. We compare the results of the proposed approach with those obtained using advanced versions of the Particle Swarm Optimization (PSO) and Harris Hawks Optimization (HHO) algorithms. The analysis of the experiment indicates that the proposed multi-objective SMA for the MSDD issue is highly competitive and provides significant performance enhancements.
Cited by 1
Dongwen Luo, Qing Cheng, Jinming Xing et al. · International Theory and Practice in Humanities and Social Sciences · 2025
The rapid advancement of low-carbon technologies, such as wind and nuclear power, introduces critical ethical challenges, including conflicts between environmental protection, land use, and community rights. This study presents a comprehensive framework to address these conflicts through data-driven optimization and ethical analysis. First, a robust data collection and modeling process is established to quantify energy demand and renewable adoption trends. Multi-objective optimization using the Multi-Objective Particle Swarm Optimization (MOPSO) and Mixed-Integer Programming (MIP) methods is then applied to balance conflicting objectives. The results reveal significant improvements in energy efficiency, carbon reduction, and stakeholder satisfaction, with MOPSO demonstrating superior performance. Ethical considerations are integrated through an impact vs. satisfaction analysis, which highlights the positive correlation between ecological benefits and public acceptance. Finally, a sensitivity analysis validates the robustness of the proposed solutions under varying conditions. The findings emphasize the potential of combining advanced algorithms with ethical frameworks to design sustainable and socially equitable low-carbon energy systems.
Cited by 1Open access
Ziyu Wu, Huimin Zhang, Mingcong Ma et al. · 2025
This study proposes a photovoltaic substation engineering site selection and line planning method based on intelligent algorithms to improve complex site selection areas' planning efficiency and scientificity. This method comprehensively utilizes unmanned aerial vehicle oblique photography, multi-objective genetic algorithm, differential evolution algorithm, and adaptive algorithm. Integrating advanced technology and optimization algorithms achieves efficient and accurate substation site selection and line planning. A multi-objective optimization model is proposed by collecting geographic information through drone technology and establishing a three-dimensional model, considering environmental impact, power supply reliability, and construction costs. This method was comprehensively compared with traditional genetic algorithms and other methods in the experimental stage. The experimental results show that the method proposed in this paper performs well in multiple indicators. Compared to traditional methods, this approach effectively reduces the total cost and significantly improves power supply reliability, achieving a 9% improvement. At the same time, the convergence speed has also been accelerated by 600 generations, reflecting the efficiency and superiority of the algorithm in solving complex problems. The method proposed in this paper improves the efficiency of substation site selection and line planning. It provides new ideas and technical means for research in related fields, verifying intelligent algorithms' practical application value and potential in power engineering.
Cited by 0
Haddou Yasser, Seghiour Abdelatif, Bendjeddou Yacine et al. · 2024
The Maximum Power Point Tracking (MPPT) algorithm subjected the PV parameters to changes under faulty and weather operations conditions during runtime, which influenced the results obtained. The aim of this research is to provide an interconnected algorithm for online optimization of PV parameters. The MPPT algorithm will dynamically adjust its operations, ensuring continual optimization in response to each update of PV parameters. We choose a custom block over other simulation techniques to allow parameter updating and provide more flexibility and customization options. This paper proposes a combined meta-heuristic algorithm based on multi-objective optimization for both parameter estimation and MPPT. The simulation results under different algorithms show the efficacy of this combination in online optimization and the capability of its implementation in the real-time optimization controller. The paper also discusses the results of simulations using different candidate algorithms. Finally, this paper recommends the adaptation of this approach for multiple problems that include parameter estimation at the first level and suggests the use of advanced algorithms and techniques for the sake of accelerating time processing.
Cited by 2
Tang Xinfa, Jingjing Wang, Yonghua Wang et al. · Energies · 2024
This paper presents an optimization method for scheduling a multi-energy VPP (Virtual Power Plant) supply–demand balance in the power market environment of Jiangxi Province. The primary objective of this method is to improve the operational efficiency of the power grid, reduce energy costs, and facilitate economical and efficient energy distribution in the power market. The method takes into account the characteristics and uncertainties of renewable energy sources such as solar and wind energy, and incorporates advanced multi-objective optimization algorithms. Furthermore, it integrates real-time market price feedback to achieve the accurate allocation of power supply and demand. Through a case study of a multi-energy VPP in Jiangxi Province, this paper examines the optimal combination model for various energy sources within VPP, and analyzes the impact of different market environments on supply–demand balance. The results demonstrate that the proposed scheduling optimization method significantly improves economic benefits while ensuring grid stability. Compared with traditional power supply models, it reduces average electricity costs by 15% and increases renewable energy utilization efficiency by 20%.
Cited by 4Open access
Tang Xinfa, Jingjing Wang, Yonghua Wang et al. · Preprints.org · 2024
This paper proposes an optimization method for the scheduling of a multi-energy virtual power plant supply-demand balance in the power market environment of Jiangxi Province. The objective of this method is to enhance the operational efficiency of the power grid, reduce energy costs, and facilitate economical and efficient energy distribution in the power market. The method comprehensively considers the characteristics and uncertainties of renewable energy sources such as solar and wind energy, and incorporates advanced multi-objective optimization algorithms. Additionally, real-time market price feedback is integrated to achieve accurate allocation of power supply and demand. Through a case study of a multi-energy virtual power plant in Jiangxi Province, this paper examines the optimal combination model for various energy sources within VPP, and analyzes the impact of different market environments on supply-demand balance. The results demonstrate that the proposed scheduling optimization method significantly improves economic benefits while ensuring grid stability. Compared with traditional power supply models, it reduces average electricity costs by 15% and increases renewable energy utilization efficiency by 20%.
Cited by 5Open access
Cheng Sun, Yunsong Han, Feng Han · BK BOOKS · 2016
The presented research work showcases a multi-objective performance-driven approach for form optimizing of green buildings. This integrated approach synergizes a building’s physical performance evaluation process with its form generation process. The approach is established by coupling Artificial Neural Networks (ANNs) with building information parametric models (BIM) and is driven by Genetic Algorithms (GAs). The resultant multi-objective building form optimization system is presented in this paper as the GANN-BIM model. The advantages of the GANN-BIM model are the following: Firstly, by adopting an advanced GA method, it is capable of handling multiple, conflicting design objectives, Secondly, by incorporating ANNs model, it can greatly reduce the amount of computation power needed for building performance evaluation, Thirdly, by connecting to BIM system, it is in compliance with an architect’s design work ow. This paper presents the framework and key technical components of the GANN-BIM model. Firstly, related works in the field of building performance optimization with advanced computation method are reviewed. Secondly, the limitations of current building performance optimization methods are addressed, which leads to the discussion of the GA + ANN method. Thirdly, the work flow and main technical components of GANN-BIM model are presented.
Cited by 9Open access