检索结果-内蒙古大学图书馆

NEURAL COMPUTING & APPLICATIONS 2023年第1期35卷 487-516页

作者： Sulaiman, Mohd Herwan Mustaffa, Zuriani Saari, Mohd Mawardi Daniyal, Hamdan Mirjalili, Seyedali Univ Malaysia Pahang UMP Fac Elect & Elect Engn Technol Pekan 26600 Pahang Malaysia Univ Malaysia Pahang UMP Fac Comp Pekan 26600 Pahang Malaysia Torrens Univ Australia Ctr Artificial Intelligence Res & Optimisat Brisbane Qld Australia Yonsei Univ Yonsei Frontier Lab Seoul South Korea

This paper proposes a new evolutionary algorithm namely evolutionary mating algorithm (EMA) to solve constrained optimization problems. The algorithm is based on the adoption of random mating concept from Hardy-Weinberg equilibrium and crossover index in order to produce new offspring. In this algorithm, effect of the environmental factor (i.e. the presence of predator) has also been considered and treated as an exploratory mechanism. The EMA is initially tested on the 23 benchmark functions to analyze its effectiveness in finding optimal solutions for different search spaces. It is then applied to Optimal Power Flow (OPF) problems with the incorporation of Flexible AC Transmission Systems (FACTS) devices and stochastic wind power generation. The extensive comparative studies with other algorithms demonstrate that EMA provides better results and can be used in solving real optimization problems from various fields.

关键词： evolutionary mating algorithm FACTS devices Optimal power flow Optimization techniques

来源：评论

学校读者我要写书评

暂无评论

Forecasting solar power generation using evolutionary mating algorithm-deep neural networks

引用

Energy and AI 2024年第2期16卷 346-362页

作者： Mohd Herwan Sulaiman Zuriani Mustaffa Faculty of Electrical&Electronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah(UMPSA)26600 Pekan PahangMalaysia Faculty of Computing Universiti Malaysia Pahang Al-Sultan Abdullah(UMPSA)26600 Pekan PahangMalaysia

This paper proposes an integration of recent metaheuristic algorithm namely evolutionary mating algorithm (EMA) in optimizing the weights and biases of deep neural networks (DNN) for forecasting the solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC power output using real solar power plant measurements spanning a 34-day period, recorded at 15-minute intervals. The intricate nonlinear relationship between solar irradiation, ambient temperature, and module temperature is captured for accurate prediction. Additionally, the paper conducts a comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles mating Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search algorithm (HSA-DNN), DNN with Adaptive Moment Estimation optimizer (ADAM) and Nonlinear AutoRegressive with eXogenous inputs (NARX). The experimental results distinctly highlight the exceptional performance of EMA-DNN by attaining the lowest Root Mean Squared Error (RMSE) during testing. This contribution not only advances solar power forecasting methodologies but also underscores the potential of merging metaheuristic algorithms with contemporary neural networks for improved accuracy and reliability.

关键词： Deep learning neural networks evolutionary mating algorithm Feed forward neural networks Metaheuristic Optimizers Solar PV

来源：评论

学校读者我要写书评

暂无评论

Pneumatic servo position control optimization using adaptive-domain prescribed performance control with evolutionary mating algorithm

引用

RESULTS IN CONTROL AND OPTIMIZATION 2024年 15卷

作者： Irawan, Addie Sulaiman, Mohd Herwan Ramli, Mohd Syakirin Azahar, Mohd Iskandar Putra Univ Malaysia Pahang Al Sultan Abdullah Fac Elect & Elect Engn Technol Pekan 26600 Pahang Malaysia

Pneumatic servo systems face challenges such as friction, compressibility, and nonlinear dynamics, necessitating advanced control techniques. Research suggests model-based, model-free, hybrid, and optimization-based methods have their strengths. Therefore, this study presents an optimal control strategy using Adaptive Domain Prescribed Performance Control (AD-PPC) cascaded with PID and optimized using the evolutionary mating algorithm (EMA) for a pneumatic servo system (PSS). The goal is to achieve faster transient control and stable rod-piston positioning with minimal friction through the hysteresis phenomenon of the targeted proportional valve-controlled double-acting pneumatic cylinder (PPVDC) representing the PSS. The novel EMA optimizes the cascaded controller based on the tracking error as its objective function. Simulation studies verify the proposed AD-PPC-PID controller with the PPVDC model plant, iteratively optimized by the EMA. The analytical study compares this setup ' s control system and optimization model with the same control system model using alternative optimization methods. The testing employs step and multi-step signals for PPVDC ' s rod-piston position input. Results show that the EMA-tuned AD-PPC-PID outperforms AD-PPC-PID controller with other optimizers. For both input trajectory tests, EMA-tuned AD-PPC-PID shows faster response times, with average improvements of 30 % in settling times and 70 % in tracking performance metrics compared to other optimizers, making it robust for nonlinear system applications like PPVDC rod-piston positioning.

关键词： Pneumatic actuator Prescribed performance control evolutionary mating algorithm Metaheuristic Data driven

来源：评论

学校读者我要写书评

暂无评论

Using the evolutionary mating algorithm for optimizing deep learning parameters for battery state of charge estimation of electric vehicle

引用

ENERGY 2023年 279卷

作者： Sulaiman, Mohd Herwan Mustaffa, Zuriani Zakaria, Nor Farizan Saari, Mohd Mawardi Univ Malaysia Pahang Fac Elect & Elect Engn Technol Pekan Pahang 26600 Malaysia Univ Malaysia Pahang Fac Comp Pekan Pahang 26600 Malaysia

This paper presents the application of a recent metaheuristic algorithm namely evolutionary mating algorithm (EMA) for optimizing the Deep Learning (DL) parameters to estimate the state of charge (SOC) of a battery for an electric vehicle in the real environment. The recorded data were obtained from 70 real driving trips of a BMW i3 EV, where the inputs of the DL were the voltage, current, battery temperature and ambient temperature while the output was the real SOC recorded during all trips. The data were divided into 60 trips for training and the final 10 trips for testing the performance of the developed EMA-DL model. The findings of the study demonstrated the promising results of EMA-DL in terms of obtaining the minimum error, which significantly increases the accuracy of the SOC estimation. To show the effectiveness of EMA-DL, comparison studies were conducted among other metaheuristic optimizers that were also used to optimize the DL parameters viz, Particles Swarm Optimization (PSO), Genetic algorithm (GA), Differential Evolution (DE) as well as the Adaptive Moment Estimation (ADAM). According to the simulation results, the proposed EMA-DL algorithm was found to outperform all the other compared algorithms based on the evaluated metrics. Thus, it can be employed as a proficient technique to accurately estimate the state of charge (SOC) of electric vehicle batteries.

关键词： Battery state of charge estimation Deep learning evolutionary mating algorithm Electric vehicles Metaheuristic algorithms Weights and biases optimization

来源：评论

学校读者我要写书评

暂无评论

Using the evolutionary mating algorithm for optimizing the user comfort and energy consumption in smart building

引用

JOURNAL OF BUILDING ENGINEERING 2023年 76卷

作者： Sulaiman, Mohd Herwan Mustaffa, Zuriani Univ Malaysia Pahang Fac Elect & Elect Engn Technol Pekan 26600 Pahang Malaysia Univ Malaysia Pahang Fac Comp Pekan 26600 Pahang Malaysia

This paper presents a simulation study focused on optimizing user comfort and energy consumption in smart buildings. Managing energy efficiently in smart buildings poses a significant challenge. The aim of this research is to achieve a high level of occupant comfort while minimizing energy usage. The study considers three fundamental parameters for measuring user comfort: thermal comfort, visual comfort, and indoor air quality (IAQ). Data from temperature, illumination, and CO2 sensors are collected to assess the indoor environment. Based on this information, smart building systems can dynamically adjust heating, cooling, lighting, and ventilation to optimize energy usage and ensure occupant comfort. To address the optimization problem, the evolutionary mating algorithm (EMA) is proposed. EMA belongs to the evolutionary computation group of nature-inspired metaheuristic algorithms and offers a promising solution. A comparative analysis is conducted with other well-known algorithms such as Particle Swarm Optimization (PSO), Differential Evolution (DE), Ant Colony Optimization (ACO), Biogeography Based Optimization (BBO), Teaching-Learning Based Optimization (TLBO), and Beluga Whale Optimization (BWO). The findings demonstrate the effectiveness of EMA in achieving optimum comfort with minimal energy consumption in smart building systems.

关键词： Comfort index evolutionary mating algorithm Energy consumption Metaheuristic algorithm Smart building

来源：评论

学校读者我要写书评

暂无评论

Enhanced multi-objective evolutionary mating algorithm with improved crowding distance and Levy flight for optimizing comfort index and energy consumption in smart buildings

Franklin Open

引用

Franklin Open 2025年 11卷

作者： Nordin, Muhammad Naim Bin Sulaiman, Mohd Herwan Zakaria, Nor Farizan Mustaffa, Zuriani Faculty of Electrical & Electronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Centre for Research in Advanced Fluid & Processes (Fluid Centre) Universiti Malaysia Pahang Al-Sultan Abdullah Gambang Campus Pahang Kuantan 26300 Malaysia Faculty of Computing Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia

This paper introduces a novel Multi-Objective evolutionary mating algorithm (MOEMA) designed to address the inherent challenges of optimizing comfort index and energy consumption in smart building systems. While current evolutionary mating algorithms (EMA) primarily focus on single-objective optimization and rely on weighted functions for handling multiple objectives, such approaches prove impractical for the complex trade-offs between comfort index and energy efficiency. The proposed MOEMA enhances the original EMA framework through two key innovations: an improved crowding distance function inspired by the Non-dominated Sorting Genetic algorithm (NSGA) to enhance solution diversity and selection pressure, and the integration of Levy flight mechanics to improve exploration efficiency by balancing local and global searches. These enhancements enable MOEMA to effectively navigate complex multi-objective landscapes, leading to more diverse and well-converged Pareto-optimal solutions. The algorithm's performance is thoroughly assessed using the chosen benchmark functions and validated through practical applications in smart building environments. It simultaneously optimizes various comfort parameters, including temperature, illuminance, and air quality, while minimizing energy consumption and maximizing the comfort index. Comparative analysis against established algorithms, like NSGA-II demonstrates MOEMA's effectiveness in achieving superior solution diversity and convergence characteristics. The results indicate that MOEMA offers a robust framework for handling the complex balance between the smart building's comfort index and energy usage where it achieves 0.03 % better at comfort index and with 10.65 % lower energy consumption than NSGA-II. It contributing to the broader fields of building automation and sustainable development while aligning with Industry 4.0 initiatives. © 2025 The Author(s)

关键词： Comfort index optimization Crowding distance Energy efficiency evolutionary mating algorithm Levy flight Multi-objective optimization Pareto optimization Smart buildings

来源：评论

学校读者我要写书评

暂无评论

Feature optimization with metaheuristics for Artificial Neural Network-based chiller power prediction

引用

JOURNAL OF BUILDING ENGINEERING 2025年 105卷

作者： Zakaria, Nor Farizan Sulaiman, Mohd Herwan Mustaffa, Zuriani Univ Malaysia Pahang Al Sultan Abdullah UMPSA Fac Elect & Elect Engn Technol Pekan 26600 Pahang Malaysia Univ Malaysia Pahang Al Sultan Abdullah Ctr Res Adv Fluid & Proc Fluid Ctr Gambang Campus Kuantan 26300 Pahang Malaysia Univ Malaysia Pahang Al Sultan Abdullah UMPSA Fac Comp Pekan Pahang Malaysia

Building energy efficiency is crucial for global sustainability efforts, with chillers representing major energy consumers in commercial buildings. Accurate prediction of chiller power consumption remains challenging due to complex operational parameters, with feature selection being critical for model performance. This study aims to develop an improved feature selection approach that enhances prediction accuracy while reducing computational complexity in chiller consumption forecasting. This paper presents a novel evolutionary mating algorithm (EMA) hybridized with Artificial Neural Networks (ANN) for optimizing feature selection. The EMA-ANN approach was compared against other metaheuristic-ANN hybrid models using operational data from a commercial building's chiller system. EMA-ANN demonstrated superior prediction accuracy with the lowest Mean Absolute Error (0.2235), Root Mean Square Error (0.4150), and highest coefficient of determination (R2 = 0.9689). The algorithm identified seven optimal features primarily comprising temperature and humidity parameters. The algorithm's unique evolutionary mating mechanism with adaptive crossover rate (Cr = 0.85), enabled effective feature space exploration, resulting in a 38.3 % reduction in RMSE and 6.0 % improvement in R2 compared to models without feature selection. This research contributes a novel hybrid model, identifies key features for chiller power prediction, and establishes a benchmark for evaluating feature selection algorithms in building energy applications.

关键词： Feature selection Metaheuristic algorithm evolutionary mating algorithm Artificial neural networks Chiller power consumption prediction Energy management system HVAC systems

来源：评论

学校读者我要写书评

暂无评论

Investigating the potential of EMA-embedded feature selection method for ESVR and LSTM to enhance the robustness of monthly streamflow forecasting from local meteorological information

引用

JOURNAL OF HYDROLOGY 2024年 636卷

作者： Xu, Lei Shi, Peng Wu, Hongshi Qu, Simin Li, Qiongfang Sun, Yiqun Yang, Xiaoqiang Jiang, Peng Qiu, Chao Hohai Univ Coll Hydrol & Water Resources Nanjing 210098 Peoples R China Cooperat Innovat Ctr Water Safety & Hydro Sci Nanjing 210098 Peoples R China Hohai Univ Yangtze Inst Conservat & Dev Nanjing 210098 Peoples R China Zhejiang Hydrol Management Ctr Hangzhou 310009 Peoples R China

Accurate forecast of monthly streamflow is helpful to improve the social capability in risk management. Diverse input features are crucial to the accuracy of machine learning -based monthly streamflow forecast models. The embedded feature selection (EFS) method based on binary-coded metaheuristic algorithm is adept at parallel optimization of feature selection and model hyperparameter. It has been rarely studied coupled with deep learning models in monthly streamflow forecasting. This study further investigated the potential of EFS method using the well-known Long short-term memory network (LSTM) and a state-of-the-art model named Extreme support vector regression (ESVR), with the evolutionary mating algorithm (EMA) as the search algorithm. The benchmark models were established using EMA for hyperparameter optimization without feature selection. Ten basins with distinct hydroclimate characteristics minimally impacted by human activities from the Catchment Attributes and Meteorology for Large -sample Studies (CAMELS) data set were used to comprehensively examine the proposed models. Nonparametric approaches including the Friedman test and Wilcoxon signed ranks test were utilized to rank the models and detect the significance of the performance variation brought by EFS. The kernel ESVR model coupled with EFS-EMA (EFS-KESVREMA) ranked the first in the 1 -month -ahead experiment with NSE = 0.734 - 0.944. EFS-ESVREMA and EFS-LSTMEMA ranked second and third, with NSE = 0.746 - 0.94 and NSE = 0.701 - 0.94 respectively. The results also demonstrated that EFS-EMA helps the benchmark models improve prediction accuracy at a confidence level of 95 % but it has no obvious effect on the standard SVR. As the forecast horizon increased to 3- and 5 -month -ahead, EFS-ESVREMA maintained a reliable performance. Whereas EFS-LSTMEMA experienced a significant accuracy decrease in the 5 -month -ahead experiment. The proposed models and relevant findings in this study have certain referenc

关键词： Monthly streamflow forecasting Embedded feature selection evolutionary mating algorithm Extreme support vector regression LSTM CAMELS

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：