Article
Thermodynamics
Zongyi Xing, Junlin Zhu, Zhenyu Zhang, Yong Qin, Limin Jia
Summary: This article proposes an energy consumption optimization model for tramway operation based on an improved PSO algorithm. By establishing an energy consumption model and applying the improved algorithm, the operational cost of tramway is reduced. The effectiveness of the developed method is validated using the Guangzhou Haizhu tramway as an example.
Article
Operations Research & Management Science
Erfan Babaee Tirkolaee, Alireza Goli, Abbas Mardani
Summary: The present paper addresses a novel two-echelon multi-product Location-Allocation-Routing problem (LARP) in a Supply Chain Network (SCN). It aims to minimize the total cost and integrate issues such as disruption, environmental pollution, and energy-efficient vehicles. Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO) algorithms are developed to solve the NP-hard problem. The proposed algorithms yield high-quality results and are validated with a case study and sensitivity analyses.
ANNALS OF OPERATIONS RESEARCH
(2023)
Article
Geosciences, Multidisciplinary
Xuehui Liu, Guisheng Hou, Lei Yang
Summary: This study considers the impact of high energy consumption in data centers on the environment and proposes a method to reduce energy consumption using clean energy and waste heat. The research results show that using natural gas and wind energy as the main energy supply can effectively reduce the overall energy consumption of data centers.
FRONTIERS IN EARTH SCIENCE
(2023)
Article
Thermodynamics
Lei Lei, Bing Wu, Xin Fang, Li Chen, Hao Wu, Wei Liu
Summary: This study proposes a dynamic anomaly detection algorithm for building energy consumption data, which combines unsupervised clustering algorithm with supervised algorithm to establish a semi-supervised matching mechanism. The algorithm has been tested and proved effective in detecting various forms of outliers in building energy consumption data.
Article
Engineering, Marine
Miao Su, Zhenqing Su, Shengli Cao, Keun-Sik Park, Sung-Hoon Bae
Summary: This study develops a fuel consumption prediction model based on machine learning and a fuel consumption optimization model based on particle swarm optimization for ships. The XGBoost deep learning model outperforms conventional prediction models in fuel consumption prediction, with an R-2 of 0.97. Additionally, the particle swarm optimization method effectively reduces fuel consumption in the fuel consumption optimization stage. This study helps PCTC companies control shipping costs and save energy, while providing insights for shipping businesses to meet environmental demands.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Diana Cristina Valencia-Rodriguez, Carlos A. Coello Coello
Summary: Particle Swarm Optimization (PSO) is a bio-inspired metaheuristic algorithm that utilizes information exchange between particles to explore the search space. This study focuses on the influence of the number of connections among particles in Multi-Objective Particle Swarm Optimizers (MOPSOs) using random regular graphs as the swarm topology. Experimental results indicate that a higher connection degree can lead to algorithm instability in various problems, and MOPSOs with the same connection degree exhibit similar behavior.
SWARM AND EVOLUTIONARY COMPUTATION
(2023)
Review
Computer Science, Interdisciplinary Applications
Jeffrey O. O. Agushaka, Absalom E. E. Ezugwu, Laith Abualigah, Samaher Khalaf Alharbi, Hamiden Abd El-Wahed Khalifa
Summary: In this paper, a comprehensive comparison was conducted to evaluate the impact of population size, number of iterations, and different initialization methods on the performance of population-based metaheuristic optimizers. The results indicated that population size and number of iterations affect the algorithm performance, and certain algorithms are sensitive to the initialization schemes. Good population diversity and a suitable number of iterations are likely to lead to optimal solutions.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Yamin Han, Bo Yang, Heejung Byun
Summary: This study optimizes the deployment of actuators in wireless sensor networks using the hierarchical intermittent communication particle swarm optimization (HICPSO) method, considering the coverage rate of actuators to sensor nodes and the energy consumption rate of sensor nodes as optimization goals to balance energy consumption among sensor nodes and solve energy hole problem. The proposed method effectively increases the coverage rate of actuators to sensor nodes, reduces the energy consumption rate of the sensor nodes, and reduces the packet drop ratio, showing improved performance compared to traditional methods.
IEEE SENSORS JOURNAL
(2021)
Article
Multidisciplinary Sciences
Xiaomei Zhang, Zhuosi Tang
Summary: This research analyzes the factors that affect corporate green technology innovation and proposes a method for predicting and evaluating corporate performance. It constructs a computer model for the driving mechanism system of corporate green technology innovation and optimizes the BPNN model using the PSO algorithm. The research findings show that the PSO-BPNN algorithm is of vital practical value to corporate performance evaluation.
Article
Automation & Control Systems
Luis F. M. Sepulveda, Petterson S. Diniz, Joao O. B. Diniz, Stelmo M. B. Netto, Carolina L. S. Cipriano, Alexandre C. Araujo, Victor H. B. Lemos, Alexandre C. P. Pessoa, Darlan B. P. Quintanilha, Joao D. S. Almeida, Aristofanes C. Silva, Anselmo C. Paiva, Geraldo Braz, Marcia I. A. Silva, Eliana M. G. Monteiro, Italo F. S. Silva, Eduardo C. Fernandes
Summary: Forecasting consumers' energy consumption is a trend in energy supply companies, with a focus on improving prediction accuracy. Brazilian energy companies use a consumption range to verify inconsistencies in manual readings, and machine learning techniques can enhance consumption forecasts. The Optimized Gradient Boosting Regressor (OGBR) proposed in this study outperformed its unmodified version and the Seasonal and Trend decomposition using Loess (STL) in most cases of consumption.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Cian Steenkamp, Andries P. Engelbrecht
Summary: The scalability of the MGPSO algorithm for many objective optimization problems was investigated in this study. The algorithm demonstrated competitive performance across many objectives compared to other state-of-the-art algorithms, without needing specialized modifications. The use of multiple subswarms and guides in the algorithm helps balance and promote solution accuracy and diversity during the search process.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Engineering, Multidisciplinary
Jian Zhu, Jianhua Liu, Yuxiang Chen, Xingsi Xue, Shuihua Sun
Summary: The paper introduces the Binary Restructuring Particle Swarm Optimization (BRPSO) algorithm as an adaptation of the Restructuring Particle Swarm Optimization (RPSO) algorithm for solving discrete optimization problems. Unlike other binary metaheuristic algorithms, BRPSO does not use transfer functions, instead relying on comparison results and a novel perturbation term for the particle updating process. The algorithm requires fewer parameters and exhibits high exploration capability, as demonstrated by experiments on feature selection problems.
Article
Multidisciplinary Sciences
Yanjiao Wang, Jieru Han, Ziming Teng
Summary: This paper proposes an improved Group Teaching Optimization Algorithm (IGTOA) to enhance the convergence speed and accuracy. It assigns teachers independently to each individual, increasing the evolution direction and population diversity. It dynamically divides students into different groups to meet the needs of different evolutionary stages. Additionally, it improves the teaching method for average group students and proposes a population reconstruction mechanism.
SCIENTIFIC REPORTS
(2022)
Article
Thermodynamics
Wen-Ze Wu, Haodan Pang, Chengli Zheng, Wanli Xie, Chong Liu
Summary: This study develops a novel nonhomogeneous discrete grey model SFNDGM that introduces seasonality and a rolling mechanism to enhance the accuracy and performance of electricity consumption forecasting. Numerical results demonstrate that the model outperforms other benchmark models in predicting quarterly electricity consumption in Hubei.
Article
Geography
Xuesong Kong, Dianfeng Liu, Yasi Tian, Yaolin Liu
Summary: This study proposed a multi-objective spatial reconstruction model for rural settlements, considering social connections and other factors. The model's applicability was verified through five scenario designs, showing that social connections have a direct impact on the restructuring direction of rural settlements.
JOURNAL OF RURAL STUDIES
(2021)