Article
Engineering, Chemical
Whei-Min Lin, Wen-Chang Tsai
Summary: The objective of this study is to analyze feeder loss minimization and load balance under given constrains. A fuzzy indexing algorithm for feeder switching is proposed in this paper, with membership functions defined for switches. With the developed method, numerical operations for indices are used instead of traditional fuzzy algorithms, greatly reducing computation time and enhancing efficiency. The proposed algorithm is effective in balancing the load and reducing loss and costs.
Article
Computer Science, Information Systems
Yen-Chih Huang, Wen-Ching Chang, Hsuan Hsu, Cheng-Chien Kuo
Summary: This paper explores the impact of distributed generation on power grids and conducts feeder reconfiguration using optimal algorithms, verifying power loss reduction and recommending locations for distributed energy. The proposed method maintains voltage within specified limits and achieves significant power loss reductions in practical systems.
Article
Computer Science, Artificial Intelligence
Ping Guo, Bin Guo
Summary: This paper proposes a hybrid evolutionary algorithm NERS_HEAD for solving the graph coloring problem. The algorithm introduces a new elite replacement strategy to increase the diversity of the evolutionary population and enables the algorithm to jump out of local optimum states. Experimental results on 59 DIMACS benchmark instances demonstrate that NERS_HEAD can effectively improve the efficiency and success rate of solving graph coloring problems.
Article
Automation & Control Systems
Yousef Abdi, Mohammad Asadpour, Yousef Seyfari
Summary: In this study, a hybrid micro multi-objective evolutionary algorithm called mu MOSM is proposed to effectively address diversity loss and accelerate the convergence rate in approximating Pareto front solutions.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Mathematics
Marius Gavrilescu, Sabina-Adriana Floria, Florin Leon, Silvia Curteanu
Summary: This paper introduces a novel neural network optimization method that combines improved evolutionary competitive algorithm and gradient-based backpropagation. By incorporating backpropagation and self-adaptive hyperparameter adjustment strategy, this method generates regression models that are better correlated with the desired outputs and provides more accurate predictions.
Article
Engineering, Multidisciplinary
Mohamed A. Abdelkader, Zeinab H. Osman, Mostafa A. Elshahed
Summary: This paper introduces an analytical approach for reducing losses in radial distribution networks, with the development of an algorithm named PSRH that outperforms AI techniques in terms of computational steps. The results show promising outcomes and superior performance when considering the outages of DGs.
AIN SHAMS ENGINEERING JOURNAL
(2021)
Article
Energy & Fuels
F. Sheidaei, A. Ahmarinejad, M. Tabrizian, M. Babaei
Summary: This paper presents a multi-objective optimization framework for solving the distribution feeder reconfiguration problem, considering factors such as demand response, renewable energy sources, and electrical energy storages. The results indicate that increasing system reliability and reducing losses lead to higher local generation unit production and operating costs. Additionally, considering dynamic topology and implementing demand response programs can effectively reduce losses and enhance reliability.
JOURNAL OF ENERGY STORAGE
(2021)
Article
Computer Science, Artificial Intelligence
Yongcun Liu, Handing Wang
Summary: This study proposes a novel algorithm that combines global and local search strategies to address the challenge of multiple disconnected regions in the search space. The algorithm achieves competitive results with only hundreds of function evaluations and can handle mixed-variable optimization problems. The global module uses hybrid evolutionary operators and a Gower distance based surrogate model, while the local module performs competitive switching in different local regions and improves evaluation accuracy with local surrogate models. The algorithm is demonstrated to be effective through artificial benchmark tests and convolutional neural network hyperparameter optimization problems.
APPLIED SOFT COMPUTING
(2023)
Article
Mathematics
Minglei Fang, Min Wang, Defeng Ding
Summary: In this study, a new modified hybrid conjugate gradient projection method is proposed for solving large-scale nonlinear monotone equations. The method includes projection techniques and a sufficient descent property independent of line search technique. Global convergence of the method is proven under suitable assumptions. Numerical results demonstrate the robustness of the suggested strategy and provide comparisons with other methods.
JOURNAL OF MATHEMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Wojciech Kwedlo
Summary: The study introduces a new hybrid evolutionary algorithm for Gaussian mixture model-based clustering, which demonstrates superior performance in learning mixtures with higher log-likelihoods and producing data partitions that best correspond to the original datasets' classifications, compared to other benchmark algorithms with the same computational budget.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Bo Jiang, Hongtao Lei, Wenhua Li, Rui Wang
Summary: This paper investigates the design of hybrid renewable energy systems (HRES) and proposes a novel multi-objective evolutionary algorithm with a special environmental selection strategy to enhance the diversity of solutions. The effectiveness, superiority, and generalizability are validated through experiments and comparison with state-of-the-art algorithms.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Information Systems
Yiming Wang, Weifeng Gao, Maoguo Gong, Hong Li, Jin Xie
Summary: This paper proposes a new two-stage based evolutionary algorithm for balancing convergence and diversity in multi-objective optimization problems. Experimental results show that the algorithm has competitive performance.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Kapil N. Vhatkar, Girish P. Bhole
Summary: Cloud computing based microservice and container usage have become essential in various fields and industries due to their high-performance capability and advantages. However, issues in container automation and management still exist. This paper introduces an optimized container resource allocation model and proposes a hybridized algorithm for optimal resource allocation.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Matthew Fox, Shengxiang Yang, Fabio Caraffini
Summary: Prediction in evolutionary dynamic optimization is still under investigation and presents unsolved challenges. This paper introduces a new benchmark problem called Moving Peaks Benchmark with Attractors to evaluate EDO algorithms with prediction capabilities. The benchmark problem has adjustable dynamics and incorporates an attractor heuristic to guide the movement of peaks. A new performance measure is introduced for comparing algorithms that use prediction. Experimental results show that the proposed benchmark is suitable for the EDO domain and algorithms with prediction capabilities achieve higher accuracy than their competitors.
SWARM AND EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Gaurav Dhiman, Mukesh Soni, Hari Mohan Pandey, Adam Slowik, Harsimran Kaur
Summary: A novel hybrid many-objective evolutionary algorithm H-RVEA is proposed and compared with five state-of-the-art algorithms, showing superior performance. Experimental results validate the effectiveness of the algorithm in solving real-life many-objective problems.
ENGINEERING WITH COMPUTERS
(2021)
Article
Thermodynamics
Hamidreza Hamidpour, Jamshid Aghaei, Sasan Pirouzi, Taher Niknam, Ahmad Nikoobakht, Matti Lehtonen, Miadreza Shafie-khah, Joao P. S. Catalao
Summary: In recent years, the power system has entered a new technological era with increased commitment to wind farms and energy storage systems, requiring disruptive changes to existing power system structures and procedures. This paper proposes a flexible coordinated power system expansion planning model that considers local wind farms, energy storage systems, and incentive-based demand response programs.
Article
Computer Science, Information Systems
Amir Reza Aqamohammadi, Taher Niknam, Sattar Shojaeiyan, Pierluigi Siano, Moslem Dehghani
Summary: This study proposes a smart fault detection method (FDM) for microgrids (MGs) based on the Hilbert-Huang transform (HHT) and deep neural networks (DNNs). The method aims to rapidly detect fault type, phase, and location data to protect MGs and restore services. The approach preprocesses branch current measurements using HHT and extracts features using singular value decomposition (SVD) for input to DNNs. Compared to previous studies, this method achieves higher fault-type identification accuracy and can determine new fault locations. Evaluation on IEEE 34-bus and MG systems demonstrates its effectiveness in terms of detection precision, computing time, and robustness to measurement uncertainties.
Article
Computer Science, Information Systems
Mohammad Ghiasi, Taher Niknam, Moslem Dehghani, Hamid Reza Baghaee, Zhanle Wang, Mohammad Mehdi Ghanbarian, Frede Blaabjerg, Tomislav Dragicevic
Summary: This article introduces an enhanced control strategy for renewable energy resources connected to microgrids through voltage-sourced converters. The strategy includes various controllers designed using the finite control set-model predictive control (FCS-MPC) strategy. The controllers can be applied in both grid-connected and island operation modes. The proposed method improves the computation power by eightfold and is proven to be superior theoretically. Simulation and hardware experiments validate the efficiency, authenticity, and compatibility of the proposed control strategy.
IEEE SYSTEMS JOURNAL
(2023)
Article
Green & Sustainable Science & Technology
Marzieh Mokarram, Jamshid Aghaei, Mohammad Jafar Mokarram, Goncalo Pinto Mendes, Behnam Mohammadi-Ivatloo
Summary: The study aims to predict solar energy generation in order to ensure the successful operation of solar power plants. Multiple linear regression and feature selection techniques are used to calculate energy generation, while long short-term memory (LSTM) is used to predict energy generation levels based on climate conditions. The results show that temperature, solar radiation, relative humidity, wind speed, wind direction, and vapor pressure deficit are the most significant parameters for predicting energy generation. The LSTM method proves to be highly accurate in predicting fluctuating energy generation patterns.
IET RENEWABLE POWER GENERATION
(2023)
Article
Energy & Fuels
Mohammadali Norouzi, Jamshid Aghaei, Taher Niknam, Mohammadali Alipour, Sasan Pirouzi, Matti Lehtonen
Summary: This paper presents a data-driven model, RFEMS, to optimize the operation of MGs based on risk-averse flexi-intelligent energy management system. The proposed model uses a hybrid deep-learning model to forecast uncertain parameters and optimize the MG operation based on the obtained uncertainty forecasting results. The results show improved performance in wind, solar, load, and price forecasting, as well as significant improvements in operating indices in test networks.
Article
Thermodynamics
Mohammad Jafar Mokarram, Reza Rashiditabar, Mohsen Gitizadeh, Jamshid Aghaei
Summary: This paper presents a new framework for forecasting electricity power net-load in renewable energy systems, which is crucial for the economic well-being, stability, and security of power networks. The framework combines deep learning, fuzzy system, and discrete wavelet transforms to achieve high accuracy prediction. The proposed method achieves a forecast accuracy of 97.7% and further improves to 99.5% by incorporating wavelet transforms and fuzzy system simultaneously.
Article
Engineering, Electrical & Electronic
Moslem Dehghani, Taher Niknam, Mina GhasemiGarpachi, Hassan Haes Alhelou, Motahareh Pourbehzadi, Giti Javidi, Ehsan Sheybani
Summary: The purpose of this paper is to analyze cyber security issues in smart grids, including prior cyber-attacks, vulnerability issues, and enhanced security procedures. It is important to consider motivations, obstacles, and socio-economic conditions when designing public policies for smart grids. The paper evaluates a group of policies suggested by stakeholders and assesses their potential for developing cyber security. The study finds that the policies with the most attention are regulatory changes to foster innovation, regulation of new business models, and establishment of a cyber-security governance strategy.
IET GENERATION TRANSMISSION & DISTRIBUTION
(2023)
Article
Green & Sustainable Science & Technology
Ali Peivand, Ehsan Azad-Farsani, Hamid Reza Abdolmohammadi
Summary: To maintain the secure operation of the power system, the issue of wind curtailment caused by wind power fluctuations is addressed, especially with high wind power penetration and the incorporation of plug-in hybrid electric vehicles. A multi-objective decision-support model is proposed, optimizing the power generation schedules of thermal generators and wind power, and utilizing intelligent parking lots to promote economic dispatch of hybrid electric vehicles. The model aims to reduce the total operation cost and the sizing of battery energy storage systems.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Environmental Studies
Milad Haghani, Frances Sprei, Khashayar Kazemzadeh, Zahra Shahhoseini, Jamshid Aghaei
Summary: This article provides a comprehensive view of scholarly research on Electric Vehicles (EV) and determines the current research trends based on objective data analysis. The findings indicate that charging infrastructure, EV adoption, thermal management systems, and routing problems have been the major research topics in recent years. Additionally, the research reveals that the frequency of research on hybrid EV has either stabilized or declined in major subfields of EV research.
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2023)
Article
Computer Science, Artificial Intelligence
Shahabodin Afrasiabi, Mousa Afrasiabi, Mohammad Amin Jarrahi, Mohammad Mohammadi, Jamshid Aghaei, Mohammad Sadegh Javadi, Miadreza Shafie-Khah, Joao P. S. Catalao
Summary: In this article, a WAMS-based load modeling method is proposed, which combines impedance-current-power and induction motor, and utilizes deep learning techniques to understand the time-varying and complex behavior of the load. The method is shown to be effective and robust in numerical experiments, and outperforms other methods significantly.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Vali Talaeizadeh, Heidarali Shayanfar, Jamshid Aghaei
Summary: This paper proposes mathematical centralized/decentralized optimization frameworks for flexibility market structures, including a transmission-level centralized market, a local distribution-and centralized transmission-level market, a TSO priority market, and a TSO-DSO price equilibrium market. The paper also develops prioritization mechanisms to improve the performance of the real-time flexibility market. The proposed frameworks are evaluated through simulation experiments.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2023)
Article
Automation & Control Systems
Mohsen Farbood, Mokhtar Shasadeghi, Taher Niknam, Behrouz Safarinejadian, Afshin Izadian
Summary: The main aim of this article is to propose a MB-based robust model predictive control (MPC) for nonlinear systems, considering the model uncertainties and disturbances based on Takagi-Sugeno fuzzy models. The suggested RMPC consists of an offline part and an online MB-based MPC.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Sobhan Farjam Keleshteri, Taher Niknam, Mohammad Ghiasi, Hossein Chabok
Summary: This paper proposes a new approach for optimal siting and sizing of PEV charging stations in a coupled electrical and transportation network. The Pareto method is used to solve the problem and the Floyd-Warshall method is utilized to determine the shortest travel routes for PEVs. The obtained results confirm the effectiveness of the optimal planning of PEV charging stations.
JOURNAL OF ENGINEERING-JOE
(2023)
Article
Green & Sustainable Science & Technology
Ahmad Nikoobakht, Jamshid Aghaei
Summary: This paper discusses the improvement of energy efficiency in traditional energy systems under extreme natural disasters by integrating information and cyber technologies. It proposes a model of cyber-physical energy systems to model the integration and improve cost-benefit and energy performance under extreme natural disasters.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2023)
Article
Engineering, Electrical & Electronic
Pekka Manner, Ville Tikka, Samuli Honkapuro, Kyoesti Tikkanen, Jamshid Aghaei
Summary: This article proposes and demonstrates a method for home chargers to participate in the fast-reacting ancillary service market with only software modifications. Through laboratory testing and an economic feasibility study, the approach's potential business opportunity is proven.
IET GENERATION TRANSMISSION & DISTRIBUTION
(2023)
