Article
Computer Science, Artificial Intelligence
Joao Luiz Junho Pereira, Guilherme Ferreira Gomes
Summary: In order to tackle challenging engineering problems, the state-of-the-art in multi-objective optimization is shifting towards using meta-heuristics and a posteriori decision-making methods. The Multi-objective Sunflower Optimization (MOSFO) algorithm, inspired by the phototropic life cycle of sunflowers, was created and validated in this work. MOSFO demonstrated significant convergence and coverage capabilities and outperformed other popular and recent algorithms in most of the test functions, making it a promising method for problems with multiple objectives.
Article
Computer Science, Artificial Intelligence
Sumit Kumar, Natee Panagant, Ghanshyam G. Tejani, Nantiwat Pholdee, Sujin Bureerat, Nikunj Mashru, Pinank Patel
Summary: Multi-objective structure optimization is a complex design issue that involves dealing with multiple conflicting objectives and various constraints. A powerful optimizer called MOMVO2arc has been proposed and evaluated for solving large structure optimization problems with less computation time.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Joao Luiz Junho Pereira, Guilherme Antonio Oliver, Matheus Brendon Francisco, Sebastiao Simoes Cunha, Guilherme Ferreira Gomes
Summary: The Multi-objective Lichtenberg Algorithm is a hybrid meta-heuristic algorithm capable of dealing with multiple objectives, distributing points for evaluation through Lichtenberg patterns in each iteration. It has shown promising results in terms of convergence and maximum spread, outperforming traditional and recent algorithms.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yunus Demir
Summary: In this study, the fabric dyeing process in a towel manufacturing factory is examined, with a focus on batching towel fabric bolts with different quantities and features from different orders using multi-port dyeing machines. The research differs from previous studies by simultaneously optimizing three different objectives: total tardiness, total number of washes, and total machine fixed cost. A lexicographic optimization approach is adopted to prioritize these objectives based on the company's requirements, and a novel lexicographic multi-objective genetic algorithm is proposed to effectively solve large-sized problems. Overall, this study addresses a real-life problem in the textile industry and introduces innovative techniques for optimizing multiple objectives in a scheduling context.
APPLIED SOFT COMPUTING
(2023)
Article
Mathematical & Computational Biology
Chao Wang, Jian Li, Haidi Rao, Aiwen Chen, Jun Jiao, Nengfeng Zou, Lichuan Gu
Summary: This paper introduces a new multi-objective grasshopper optimization algorithm framework that achieves a balance between exploration and exploitation through grouping and co-evolution mechanisms, improving convergence and diversity.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2021)
Article
Computer Science, Interdisciplinary Applications
Sumit Kumar, Ghanshyam G. Tejani, Nantiwat Pholdee, Sujin Bureerat
Summary: This article proposes a modified heat transfer search method for multi-objective structural optimization, which outperforms other optimizers in terms of effectiveness. The new method considers design solutions as molecules interacting with the system and surrounding molecules through heat transfer phases.
ENGINEERING WITH COMPUTERS
(2021)
Article
Computer Science, Artificial Intelligence
Wanting Yang, Jianchang Liu, Wei Zhang, Xinnan Zhang
Summary: This paper proposes a resource allocation-based multi-objective optimization evolutionary algorithm to address the curse of dimensionality in large-scale multi-objective optimization problems. The algorithm divides decision variables into convergence-related variables and diversity-related variables using a proposed variable classification method. It then applies resource allocation-based convergence optimization for the former and diversity optimization for the latter. Experimental results show that the proposed algorithm performs competitively compared to state-of-the-art algorithms.
Article
Computer Science, Interdisciplinary Applications
Sandra M. Venske, Carolina P. Almeida, Ricardo Luders, Myriam R. Delgado
Summary: Hyper-heuristics are a generalized and robust solution for combinatorial optimization, and this paper studies four selection hyper-heuristics and proposes a new approach to improve their performance. Experimental results show that the proposed method outperforms other approaches in solving quadratic assignment problems.
COMPUTERS & OPERATIONS RESEARCH
(2022)
Review
Computer Science, Artificial Intelligence
Gunjan
Summary: This paper provides a systematic review of multi-objective optimization (MOO) techniques in wireless sensor networks (WSNs) and studies the applications of MOO in different domains, particularly in the area of WSNs. Furthermore, the integration of WSNs with MOO is explored.
NEURAL PROCESSING LETTERS
(2023)
Article
Chemistry, Multidisciplinary
Haya Alshareef, Mashael Maashi
Summary: This study applies a multi-objective hyper-heuristic method to address the software module clustering problem, aiming to optimize module coupling and cohesion for better software maintenance and modularization quality.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
C. G. Marcelino, V Torres, L. Carvalho, M. Matos, V Miranda
Summary: This study proposes a new multi-objective optimization model for identifying critical assets involved in outage events based on past performance indicators. The approach retrieves the minimal set of assets from large historical interruption datasets that most contribute to the performance indicators.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2022)
Review
Chemistry, Multidisciplinary
Zitong Wang, Yan Pei, Jianqiang Li
Summary: The multi-objective optimization problem is challenging due to conflicts among various objectives and functions. The research and application of multi-objective evolutionary algorithms (MOEA) have made significant progress in solving such problems. This survey provides a comprehensive investigation of MOEA algorithms, classifies them by evolutionary mechanism, and suggests the combination of chaotic evolution algorithm with representative search strategies for improving the search capability of MOEAs.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Interdisciplinary Applications
Yuan Tian, Tifan Xiong, Zhenyuan Liu, Yi Mei, Li Wan
Summary: This paper proposes a new extension of the multi-skill resource-constrained project scheduling problem with skill switches. It develops a mixed-integer programming model to minimize project completion time and total cost. The paper also proposes a new solution representation scheme, a schedule builder scheme, and mutation operators to improve the performance of the multi-objective evolution strategy framework. Experimental results show that the proposed methods can effectively improve the convergence, spread, and diversity of the Pareto Front.
COMPUTERS & INDUSTRIAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Awsan Mohammed, Maged S. Al-shaibani, Salih O. Duffuaa
Summary: This paper proposes a novel metaheuristic approach for designing supply chain network problems in the case of multi-objective supply chains. The algorithm hybridizes three meta-heuristic approaches and is combined with a linear programming approach. The proposed algorithm outperforms other algorithms in terms of computational time and performance metrics.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Yan Zhang, Bingdong Li, Wenjing Hong, Aimin Zhou
Summary: This paper introduces MOCPSO, a Multi-Objective Cooperative Particle Swarm Optimization Algorithm with Dual Search Strategies, to address the limited local search capabilities and insufficient randomness of most PSOs in large-scale multi-objective optimization problems. Experimental results demonstrate that MOCPSO outperforms existing state-of-the-art large-scale multi-objective evolutionary algorithms on benchmark LSMOPs.
Article
Green & Sustainable Science & Technology
Hongjing He, Yongyi Huang, Akito Nakadomari, Hasan Masrur, Narayanan Krishnan, Ashraf M. Hemeida, Alexey Mikhaylov, Tomonobu Senjyu
Summary: Remote island power systems with renewable energy technologies face high equipment costs. Electrolysis of seawater to produce green hydrogen and sodium hypochlorite can reduce costs. A study comparing different cases shows that the approach can cut costs and decrease carbon emissions compared to traditional methods.
Article
Engineering, Multidisciplinary
Soliman Abd Elmonsef Sarhan, Hassan A. Youness, Ayman M. Bahaa-Eldin
Summary: Digital forensics is a prime field in law enforcement and a major research topic in cybersecurity. This paper proposes a novel framework and methodology to extract valuable information from encrypted traffic and analyze it for forensic investigation.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Sakthivel Ganesan, Prince Winston David, Praveen Kumar Balachandran, Tomonobu Senjyu
Summary: Large solar power plants provide an alternative to conventional energy sources and are crucial for sustainable power generation. However, fault identification in photovoltaic arrays can be challenging due to various factors. This paper proposes a new fault identification scheme that can detect line-to-line faults and open-circuit faults with minimum sensor requirements and regardless of detection challenges.
ELECTRICAL ENGINEERING
(2023)
Article
Energy & Fuels
Mark Kipngetich Kiptoo, Oludamilare Bode Adewuyi, Harun Or Rashid Howlader, Akito Nakadomari, Tomonobu Senjyu
Summary: This paper discusses a bi-objective joint optimization planning approach for a renewable energy-based microgrid. The approach combines component sizing and short-term operational planning into a single model with demand response strategies. The study compares different demand response programs to determine the most cost-effective planning approach. Simulation scenarios are formulated and solved using an optimization solver, and the results show that including the demand response program leads to a significant reduction in costs and system component capacities, increasing the overall system flexibility.
Article
Energy & Fuels
Junchao Cheng, Yongyi Huang, Hongjing He, Abdul Matin Ibrahimi, Tomonobu Senjyu
Summary: In this study, EVs are combined with the CCHP system and the influence of the season on user's demand is considered. By using the PSO algorithm, the system is optimized in both FEL and FTL modes. The results show that the participation of EVs can reduce costs, especially in FTL mode, and FEL mode is more economical in spring and winter, while FTL mode is more economical in summer and winter. Additionally, CO2 emissions are higher in FTL mode compared to FEL mode.
Article
Energy & Fuels
Soichiro Ueda, Atsushi Yona, Shriram Srinivasarangan Rangarajan, Edward Randolph Collins, Hiroshi Takahashi, Ashraf Mohamed Hemeida, Tomonobu Senjyu
Summary: The urgent need to reduce greenhouse gas emissions has led to the introduction of electric vehicles worldwide. Renewable energy sources that don't emit greenhouse gases must be used, but the uncertainty in their supply needs to be considered. In this study, the amount of electricity generated by renewable energy was predicted using model predictive control. The economic impact of implementing EV demand response on the electricity demand side was simulated, and it was found that demand response leads to a faster return on investment.
Article
Energy & Fuels
Issoufou Tahirou Halidou, Harun Or Rashid Howlader, Mahmoud M. Gamil, M. H. Elkholy, Tomonobu Senjyu
Summary: The growing demand for electricity and reconstruction in Africa necessitates an effective and reliable energy supply system. The construction of reliable, clean, and affordable microgrids, whether isolated or connected to the main grid, is crucial for addressing energy supply issues in remote desert areas. This paper investigates the establishment of an efficient and cost-effective microgrid in the Djado Plateau of northeastern Niger. The study compares three cases and identifies the second case as the best option in terms of total life cycle cost and independence from the main grid, with a 11.19% lower life cycle cost compared to the first case and a 5.664% lower cost compared to the first scenario of the third case.
Article
Green & Sustainable Science & Technology
Mir Sayed Shah Danish, Tomonobu Senjyu
Summary: The present time is crucial for the energy sector as it undergoes a transition towards green energy and embraces the power of automation and artificial intelligence (AI) to optimize efficiencies. Competitive policies are needed to handle multidimensional endeavors through a single platform. Inadequate incentives and poor decision-making have led to shortcomings in energy policies, emphasizing the importance of promoting fairness, equality, equity, and inclusiveness. This study analyzes the challenges posed by the integration of AI in energy sectors and proposes a comprehensive framework for the development and implementation of modern energy policies.
Article
Green & Sustainable Science & Technology
Sathyavani Bandela, Tara Kalyani Sandipamu, Hari Priya Vemuganti, Shriram S. Rangarajan, E. Randolph Collins, Tomonobu Senjyu
Summary: Multicarrier based modulation techniques are commonly used in high or medium power applications to control multilevel inverters. However, traditional level-shifted pulse-width modulation (LSPWM) is not suitable for controlling newly proposed reduced switch count (RSC) MLI topologies. This research proposes a generalized LSPWM system based on logical expressions that can be used with symmetrical and asymmetrical RSC MLIs and can be extended to an arbitrary number of levels. The effectiveness of the proposed modulation strategy was evaluated using multiple 13-level asymmetrical RSC-MLI topologies, proving its satisfactory line-voltage total harmonic distortion (THD) performance.
Article
Energy & Fuels
Mark Kipngetich Kiptoo, Oludamilare Bode Adewuyi, Masahiro Furukakoi, Paras Mandal, Tomonobu Senjyu
Summary: This research proposes a comprehensive planning strategy, incorporating forecasting and demand response program (DRP) strategies, to address uncertainties in microgrid operation. Through simulations and multi-objective optimization, the approach allows for optimal sizing and operation planning, resulting in cost reductions and improved reliability.
Article
Green & Sustainable Science & Technology
Foday Conteh, Masahiro Furukakoi, Shriram Srinivasarangan Rangarajan, Edward Randolph Collins, Michael A. A. Conteh, Ahmed Rashwan, Tomonobu Senjyu
Summary: Sierra Leone is facing a persistent electricity gap that hinders its economic growth and development goals. This study assesses the country's energy supply and demand using the LEAP model and develops three scenarios to evaluate potential alternatives and reduce CO2 emissions. The results indicate an increase in electricity demand and a reduction in production and CO2 emissions, and provide recommendations for Sierra Leone's power system.
Editorial Material
Chemistry, Multidisciplinary
Marcos Tostado-Veliz, Paul Arevalo, Salah Kamel, Ragab A. El-Sehiemy, Tomonobu Senjyu
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Multidisciplinary
Mohammed Al-Jabbar, Ebtesam Al-Mansor, S. Abdel-Khalek, Salem Alkhalaf
Summary: This study proposes a technique for effective scene classification and intrusion detection of remote sensing images in the IoT environment using deep learning. The technique involves a two-stage process, with the first stage using a modified DarkNet-53 feature extractor, EOA-based hyperparameter tuning, and graph convolution network (GCN) based classification for scene classification, and the second stage employing variational autoencoder (VAE) based intrusion detection. Experimental results demonstrate the improved performance of the technique in scene classification and intrusion detection.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Engineering, Multidisciplinary
Hanan T. Halawani, Aisha M. Mashraqi, Souha K. Badr, Salem Alkhalaf
Summary: Sentiment analysis is a technique used in NLP to determine the sentiment expressed in text. This article presents an automated sentiment analysis model that combines deep learning and Harris Hawks Optimization. The model achieves promising performance in processing social media text.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Mathematics, Interdisciplinary Applications
Muhyaddin Rawa, Sultan Alghamdi, Martin Calasan, Obaid Aldosari, Ziad M. Ali, Salem Alkhalaf, Mihailo Micev, Shady H. E. Abdel Aleem
Summary: This paper introduces a novel approach to design AVR systems as 6ISO systems and compares generator voltage responses for different structural configurations and regulator parameter choices. The effectiveness of various controllers is investigated, leading to a proposed improvement in regulator parameter design using the PSO-AVOA algorithm.
FRACTAL AND FRACTIONAL
(2023)