Article
Thermodynamics
Yulong Xiao, Chongzhe Zou, Hetian Chi, Rengcun Fang
Summary: Wind power is a clean and widely used renewable energy source. Accurate forecasting is important for efficient and stable utilization of wind energy. Extracting features from complex wind power data can improve prediction models, which is a key issue for short-term forecasting.
Article
Automation & Control Systems
Ji Li, Quan Zhou, Huw Williams, Guoxiang Lu, Hongming Xu
Summary: Accurately predicting soft sensors is crucial for the development of modern combustion engines to achieve better performance, lower emissions, and reduced fuel consumption. In this article, a novel data-driven approach called statistics-guided accelerated swarm feature selection is proposed to find the most effective features for engine soft sensors.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Erol Egrioglu, Eren Bas
Summary: A new hybrid recurrent artificial neural network is proposed for nonlinear time series forecasting in this study. The network combines simple exponential smoothing and a single multiplicative neuron model to solve the insufficiency of classical forecasting methods in forecasting nonlinear and complex time series structures. The proposed method outperforms other artificial neural networks in terms of performance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Awais Mahmood, Muhammad Imran, Aun Irtaza, Qammar Abbas, Habib Dhahri, Esam Mohammed Asem Othman, Arif Jamal Malik, Aaqif Afzaal Abbasi
Summary: This paper proposes a novel approach to improve the performance of image search by using Particle Swarm Optimization and Genetic Algorithm for early iteration and Support Vector Machine for relevance feedback. Experimental results show that this method outperforms existing CBIR approaches.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
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
Computer Science, Artificial Intelligence
Abdolreza Rashno, Milad Shafipour, Sadegh Fadaei
Summary: This paper introduces a novel multi-objective particle swarm optimization feature selection method. It decodes feature vectors as particles and ranks them in a two-dimensional optimization space. The proposed method incorporates feature ranks to update particle velocity and position during the optimization process. Experimental results demonstrate the effectiveness of the method in finding Pareto Fronts of the best particles in multi-objective optimization space.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
An-Da Li, Bing Xue, Mengjie Zhang
Summary: This paper proposes an improved sticky binary PSO algorithm for feature selection problems, which aims to enhance evolutionary performance through new mechanisms such as an initialization strategy, dynamic bits masking, and genetic operations. Experimental results show that ISBPSO achieves higher accuracy with fewer features and reduces computation time compared to benchmark PSO-based FS methods.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Milad Shafipour, Abdolreza Rashno, Sadegh Fadaei
Summary: This paper introduces a feature selection method based on particle distance and feature ranking, which is mathematically proven and experimentally supported to outperform existing methods in multiple evaluation metrics.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Mrinalini Rana, Omdev Dahiya, Parminder Singh, Wadii Boulila, Adel Ammar
Summary: Data mining has become popular, but traditional methods are not sufficient with increasing data. Soft computing algorithms are used for mathematical optimization to obtain better results in less time. This paper proposes a framework for rule mining using a soft computing algorithm, specifically the Grouped-Artificial Bee Colony Optimization (G-ABC). The algorithm selects relevant attributes, verifies features, and applies mean-variance optimization and neural-based deep learning to validate the outcome.
Article
Economics
Gourav Kumar, Uday Pratap Singh, Sanjeev Jain
Summary: This paper presents a two-stage swarm intelligence based hybrid neural network approach for forecasting stock market index closing prices. The approach effectively performs feature selection and parameter optimization, while improving forecasting accuracy.
COMPUTATIONAL ECONOMICS
(2022)
Article
Energy & Fuels
Jie Liu, Quan Shi, Ruilian Han, Juan Yang
Summary: Accurate wind power forecasting is crucial for wind power grid integration. The proposed GA-PSO-CNN model, which optimizes network structure and parameters, shows improved performance compared to other models, reducing error metrics and convolution kernel size.
Article
Computer Science, Artificial Intelligence
Pei Hu, Jeng-Shyang Pan, Shu-Chuan Chu, Chaoli Sun
Summary: In this paper, a multi-surrogate assisted binary particle swarm optimization method is proposed for feature selection on large-scale datasets. Two surrogate models are trained to approximate the fitness values of individuals in two sub-populations, and a new population is generated through communication between the two sub-populations. Additionally, a dynamic transfer function is introduced to balance global and local search for finding optimal solutions with limited computational resources.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Zhi Jiang, Yong Zhang, Jun Wang
Summary: The paper proposes a new ensemble feature selection algorithm, MDEFS, which can handle large-scale data, reduce computational costs, and improve the accuracy of feature selection results.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Salihu A. Abdulkarim, Andries P. Engelbrecht
Summary: Several studies have applied particle swarm optimization algorithms to train neural networks for time series forecasting, with good performance results. This study introduces a dynamic PSO algorithm for training NNs in forecasting non-stationary time series, outperforming standard PSO and Rprop algorithms. These findings suggest the potential of dynamic PSO in real-world forecasting applications.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Green & Sustainable Science & Technology
Vinoth Kannan Viswanathan, Abdul Razak Kaladgi, Pushparaj Thomai, Umit Agbulut, Mamdooh Alwetaishi, Zafar Said, Saboor Shaik, Asif Afzal
Summary: In this research, meta-heuristic optimization algorithms and experimental design methods were combined to optimize the engine behavior. Artificial neural networks were used to forecast the performance and emission behaviors. The results showed that this approach achieved high accuracy in optimizing and predicting engine behavior.
Article
Green & Sustainable Science & Technology
Azim Heydari, Meysam Majidi Nezhad, Davide Astiaso Garcia, Farshid Keynia, Livio De Santoli
Summary: The study developed a new hybrid intelligent model based on LSTM and MVO algorithms to predict and analyze air pollution from Combined Cycle Power Plants. Applying real data from a plant in Iran, the model showed higher accuracy compared to other combined forecasting benchmark models when considering different network input variables.
CLEAN TECHNOLOGIES AND ENVIRONMENTAL POLICY
(2022)
Article
Computer Science, Interdisciplinary Applications
Iraj Naruei, Farshid Keynia
Summary: Nowadays, optimization algorithms inspired by the natural behavior of agents, such as humans, animals, or plants, have become popular in solving various scientific problems. The wild horse optimizer algorithm is inspired by the social behavior of wild horses, particularly their decency behavior where foals leave groups to prevent mating with relatives. The proposed algorithm has shown competitive results compared to other optimization methods in testing.
ENGINEERING WITH COMPUTERS
(2022)
Article
Computer Science, Hardware & Architecture
Saeed Roohollahi, Amid Khatibi Bardsiri, Farshid Keynia
Summary: The existing network measures and sampling algorithms are designed for deterministic binary graphs with fixed weights, which leads to the loss of information contained in the time-varying edge weights of networks. Researchers propose using stochastic graphs with random variables associated with edge weights as a suitable model for analyzing complex social networks. Experimental evaluations are conducted to study the performance of the proposed sampling algorithms based on relative cost, Kendall correlation coefficient, Kolmogorov-Smirnov D statistics, and relative error.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Engineering, Electrical & Electronic
Farshid Keynia, Gholamreza Memarzadeh
Summary: The paper proposes a method based on forecasting wind power production, electricity price, and Financial Loss/Gain (FLG) in coordination with energy storage to improve the participation and profit of wind power producers in the electricity energy market.
IET GENERATION TRANSMISSION & DISTRIBUTION
(2022)
Editorial Material
Green & Sustainable Science & Technology
Ricardo J. Bessa, Pierre Pinson, George Kariniotakis, Dipti Srinivasan, Charlie Smith, Nima Amjady, Hamidreza Zareipour
Summary: The papers in this special section discuss the advances in renewable energy forecasting, predictability, business models, and applications in the power industry. While there has been significant research and adoption of these technologies in the energy industry, deterministic forecasts are still more commonly used due to a lack of understanding and standardization of uncertainty forecast products and the longer computational time associated with stochastic and robust optimization approaches. Additionally, proven business cases are needed to demonstrate the benefits of uncertainty forecasts to end-users.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2022)
Article
Computer Science, Information Systems
Mehdi Salamati, Xin Wang, Jennifer Winter, Hamidreza Zareipour
Summary: This research develops two multi-modal wide-corridor routing methods that consider the arrangement of different modes and the width of the corridor. Comparative analysis shows that the second method performs better in finding a multi-modal corridor.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Review
Green & Sustainable Science & Technology
Anton V. Vykhodtsev, Darren Jang, Qianpu Wang, William Rosehart, Hamidreza Zareipour
Summary: The penetration of lithium-ion battery energy storage systems (LIBESS) into power systems is rapidly increasing worldwide, as they are considered important tools for decarbonizing, digitalizing, and democratizing electricity grids. However, the economic and technical viability of battery projects requires careful assessment due to high capital expenditures, performance degradation, and regulatory uncertainties. Current modeling approaches may lead to violations of safe operation and misleading economic benefit estimates.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
Article
Green & Sustainable Science & Technology
Azim Heydari, Meysam Majidi Nezhad, Farshid Keynia, Afef Fekih, Nasser Shahsavari-Pour, Davide Astiaso Garcia, Giuseppe Piras
Summary: This paper introduces a new optimization strategy for hybrid-renewable energy systems in microgrids. The strategy combines a multi-objective optimization algorithm, the Taguchi method, and a fuzzy decision-making approach to achieve the best utilization of renewable energy sources while minimizing the cost of energy and power supply probability loss. The strategy was implemented and tested on the design optimization of a hybrid renewable energy system for different scenarios in Sonderborg, Denmark.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Green & Sustainable Science & Technology
Juan Arteaga, Mostafa Farrokhabadi, Nima Amjady, Hamidreza Zareipour
Summary: In this paper, an optimal sizing model for a solar plus energy storage (PV-ESS) system for behind the meter applications is proposed. A dynamic optimization algorithm is presented to maximize the net worth of a project, considering decreasing technology costs in the future. The proposed model efficiently solves the optimization problem using parallel computation, and simulation results demonstrate its ability to minimize the total project cost.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Energy & Fuels
Hugo Bezerra Menezes Leite, Hamidreza Zareipour
Summary: In this paper, a new hybrid methodology is proposed to provide accurate solar energy forecasts for small-scale BTM PV sites. The method utilizes XGBoost and CatBoost techniques and incorporates neighboring solar farms' power predictions as a feature to improve model accuracy. Numerical results show that training the models using data from the previous, current, and future months can enhance accuracy. Finally, incorporating solar energy predictions from neighboring solar farms further increases forecast accuracy.
Article
Green & Sustainable Science & Technology
Maryam Nejati, Nima Amjady, Hamidreza Zareipour
Summary: This paper proposes a new multi-resolution closed-loop wind power forecasting method that improves the accuracy of wind power prediction by making predictions at two different resolutions and measuring inconsistencies through a difference signal.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Chemistry, Multidisciplinary
Lu Wei, Jiaqi Qu, Liliang Wang, Feng Liu, Zheng Qian, Hamidreza Zareipour
Summary: This paper proposes a novel fault diagnosis method for wind turbines with alarms that collaboratively uses labeled and unlabeled alarms to improve diagnosis accuracy. The proposed method can assist wind turbine operators in quickly identifying the types of faults that trigger alarms, reducing operation and maintenance costs and downtime losses.
APPLIED SCIENCES-BASEL
(2023)
Article
Multidisciplinary Sciences
Daniel Manfre Jaimes, Manuel Zamudio Lopez, Hamidreza Zareipour, Mike Quashie
Summary: This paper proposes a new hybrid model for electricity market price forecasting. The model combines LSTM neural networks and XGBoost models vertically, and designs five models horizontally to extend the forecasting horizon. The results demonstrate that the proposed methodology is effective in enhancing forecasting accuracy and price spike detection.
Article
Energy & Fuels
Mostafa Farrokhabadi, Jethro Browell, Yi Wang, Stephen Makonin, Wencong Su, Hamidreza Zareipour
Summary: The COVID-19 related shutdowns have had significant impacts on electric grid operations globally, leading to a dramatic decrease in electricity demand and a shift in demand patterns. Existing energy forecasting systems struggle to accurately predict these demand changes, exposing operators to risks and worsening the economic impact of the pandemic. Therefore, organizing the "IEEE DataPort Day-Ahead Electricity Demand Forecasting Competition: Post-COVID Paradigm" to promote the development and dissemination of advanced load forecasting techniques is of great importance.
IEEE OPEN ACCESS JOURNAL OF POWER AND ENERGY
(2022)
Article
Energy & Fuels
Shubhrajit Bhattacharjee, Ramteen Sioshansi, Hamidreza Zareipour
Summary: This paper examines the market implications of energy-storage participation models and state-of-energy (SOE) management. The research finds that self-scheduling energy storage is suboptimal and relying solely on the energy-storage firm to manage SOE can lead to strategic behavior. These findings are important for guiding ongoing market-design reforms.
IEEE OPEN ACCESS JOURNAL OF POWER AND ENERGY
(2022)