检索结果-内蒙古大学图书馆

Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches

EXPERT SYSTEMS WITH APPLICATIONS 2024年 241卷

作者： Zhang, Lijie Janosik, Dominik Changchun Univ Sci & Technol Sch Comp Sci Changchun 130000 Peoples R China Slovak Univ Technol Bratislava Radlinskeho 11 Bratislava 81368 Slovakia

The focus of this paper is to improve short-term load forecasting for electric power. To achieve this goal, the study explores and evaluates hybrid models, specifically using the CatBoost and XGBoost algorithms, which are optimized with different optimizers. The study incorporates hourly electricity load data and also includes tem-perature data to enhance the precision of the forecasting models. Statistical metrics are then used to assess the performance of these models. The study evaluates the performance of the hybrid models on both training and testing datasets. It finds that the CatBoost-arithmetic optimization algorithm hybrid model outperforms the other models in the training dataset. However, in the testing dataset, the XGBoost-arithmetic optimization algorithm hybrid model demonstrates superior performance compared to the CatBoost models. The study con-ducts an importance and sensitivity analysis to understand which variables have the most significant impact on the target variable, which is likely electricity load. The results of this analysis reveal that temperature is the most influential variable affecting the target variable. Additionally, the month variable is identified as having a notable impact on load forecasting. These findings suggest that employing hybrid models, particularly those optimized with appropriate algorithms, can significantly improve the accuracy of short-term load forecasting. Moreover, the study highlights the importance of incorporating temperature data into these models, as temperature is a key driver of electricity load patterns.

关键词： Short-term load forecasting Hybrid machine learning models CatBoost and XGBoost models arithmetic optimization algorithm Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Assessing groundwater behavior and future trends in the Ardabil Aquifer: A comparative study of groundwater modeling system and categorical gradient boosting hybrid model

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期255卷

作者： Bairami, Milad Khajavi, Hamed Rastgoo, Amir K N Toosi Univ Technol Dept Civil Engn Tehran Iran

Rapid population growth and rising demand have led to increased groundwater extraction, underscoring the importance of effective water resource management. While groundwater models are practical tools, their reliance on extensive hydrogeological and hydrological data can pose challenges when such data is unavailable or inaccessible. In this study, two modeling approaches were employed for the prediction and characterization of groundwater behavior in Ardabil Plain from October 2010 to March 2021. Initially, groundwater behavior was modeled using Modflow. Subsequently, the groundwater behavior was modeled within the same time frame using the hybrid CatBoost-AOA model. Groundwater levels were then determined using these two models until the year 2031. The CatBoost-AOA hybrid method showed the highest agreement (correlation coefficient: 0.9977). Modflow and CatBoost models predicted a decline of 0.77 and 0.85 m, respectively, until 2031. This study aims to guide sustainable development planning, with CatBoost-AOA providing a simplified and efficient alternative for accurately forecasting groundwater fluctuations.

关键词： Groundwater Modeling system Categorical Gradient Boosting Ardabil plain Groundwater level Modflow arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of SVR models built with AOA and Chaos mapping for predicting tunnel crown displacement induced by blasting excavation

引用

APPLIED SOFT COMPUTING 2023年 147卷

作者： Li, Chuanqi Mei, Xiancheng Grenoble Alpes Univ CNRS UMR 5521 Lab 3SR F-38000 Grenoble France Chinese Acad Sci Inst Rock & Soil Mech Wuhan 430071 Peoples R China

This study utilizes the support vector regression (SVR) model to predict the tunnel crown displacement (TCD) induced by the blasting excavation. 95 blasting operations considering the tunnel shape parameters, the blasting parameters, the explosive parameters, and the rock mass properties are used to train and test models. To enhance the model prediction performance, a novel combination of the arithmetic optimization algorithm (AOA) with the chaos mapping (CM) called CMAOA, is proposed to select the optimal hyperparameters of the SVR model with advantages of the computing speed and the optimization ability. Sixteen benchmark functions are adopted to verify the authenticity of the prediction performance improvement of the CMAOA, and six statistical indices are used to evaluate the performance of the proposed hybrid models for predicting the TCD. The evaluation results show that the SVR optimized by the AOA with Circle map (CirAOA-SVR) model has the best prediction accuracy among all models. The results of parameter analysis indicate that the degree of bonding of bedding surface is the most important input parameter for predicting the TCD, but the blasting and explosive parameters with fine importance scores cannot be ignored either. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Tunnel crown displacement Blasting excavation Support vector regression arithmetic optimization algorithm Chaos mapping

来源：评论

学校读者我要写书评

暂无评论

Enhanced conditional random field-long short-term memory for name entity recognition in English texts

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2023年第9期35卷

作者： Bhumireddypalli, Veera Sekhar Reddy Koppula, Srinivas Rao Koppula, Neeraja MLR Inst Technol Dept Comp Sci & Engn Hyderabad India Geethanjali Coll Engn & Technol Dept Comp Sci & Engn Hyderabad India MLR Inst Technol Dept Comp Sci & Engn Hyderabad India

Named entity recognition (NER) is an essential topic in the real world during the advanced development of technologies. Hence, in this article, develop enhanced conditional random field-long short-term memory (ECRF-LSTM) for NER in the English language. The proposed ECRF-LSTM is the combination of conditional random field-long short-term memory (ECRF-LSTM) and chaotic arithmetic optimization algorithm (CAOA). The proposed research concentrated to perform NER for Indian names from the given input database for Indian digital database management and processing. The Chaotic AOA leads to fast convergence and helps to avoid the local optima. The proposed method is working with three phases preprocessing phase, the feature extraction phase, and the NER phase. In the initial stage, the datasets are collected from the online system. In the preprocessing phase, the removal of the URL, removal of special symbol, username removal, tokenization, and stop word removal are done. After that, the essential features such as domain weight, event weight, textual similarity, spatial similarity, temporal similarity, and relative document-term frequency difference are extracted and then applied to train the proposed model. To empower the training phase of the CRF-LSTM method, CAOA is utilized to select optimal weight parameter coefficients of CRF-LSTM for training the model parameters. The proposed method is validated by statistical measurements and compared with the conventional methods such as convolutional neural network-particle swarm optimization and convolutional neural network respectively. The proposed method achieves 98.91 accuracy, 97.36 sensitivity, 97.19 specificity, 97.54 precision, and 97.63 recall which is better than the existing methodologies.

关键词： arithmetic optimization algorithm feature extraction long short-term memory named entity recognition preprocessing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid AOSAOA Scheme Based on the Optimal Location for Electric Vehicle Parking Lots and Capacitors in a Grid to Care of Voltage Profile and Power Loss

引用

ENERGIES 2022年第12期15卷 4202-4202页

作者： Rao, Ch. S. V. Prasad Pandian, A. Reddy, Ch. Rami Prasad, A. Giri Alahmadi, Ahmad Alharbi, Yasser Koneru Lakshmaiah Educ Fdn Dept Elect & Elect Engn Guntur 522302 Andhra Pradesh India Malla Reddy Engn Coll A Dept Elect & Elect Engn Secunderabad 500100 India VNR Vignana Jyothi Inst Engn & Technol Dept Elect & Elect Engn Secunderabad 500090 India Taif Univ Dept Elect Engn Coll Engn POB 11099 Taif 21944 Saudi Arabia

In this manuscript, a hybrid system depending on the optimal location of electric vehicle parking lots (PL) and capacitors under voltage profile care and power loss is proposed. The proposed hybrid scheme is the joint execution of both the atomic orbital search (AOS) and arithmetic optimization algorithm (AOA). Commonly it is called the AOSAOA technique. In the paper, the allocation of the parking lot and capacitor is introduced to congestion management with reactive power compensation. To optimally regulate that parking lot size, the AOSAOA technique is adopted. Furthermore, parking lot and capacitor allocation are introduced to congestion management and reactive power compensation. With this proper control, the perfect sitting of capacitor and EV parking lots under the grid, including the deterioration of real and reactive power loss and voltage profiles are optimally chosen. Furthermore, the implementation of the proposed AOSAOA model is developed by the MATLAB/Simulink platform, and the efficiency of the proposed model is likened to other techniques.

关键词： electric vehicles parking lot voltage and power loss atomic orbital search arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing short-term wind speed prediction based on an outlier-robust ensemble deep random vector functional link network with AOA-optimized VMD

引用

ENERGY 2024年 296卷

作者： Zhang, Chu Li, Zhengbo Ge, Yida Liu, Qianlong Suo, Leiming Song, Shihao Peng, Tian Huaiyin Inst Technol Fac Automat Huaian 223003 Peoples R China Huaiyin Inst Technol Jiangsu Permanent Magnet Motor Engn Res Ctr Huaian 223003 Peoples R China

Wind speed prediction is a crucial aspect in the utilization of wind energy. In this paper, a wind speed prediction model based on an outlier-robust ensemble deep random vector functional link network (ORedRVFL) and arithmetic optimization algorithm-optimized variational mode decomposition (AOA-VMD) is designed. First, the penalty factor and the number of mode decompositions of VMD are optimized using the AOA algorithm and the original data are decomposed using the optimized VMD. Then the decomposed data is predicted using the ensemble deep random vector functional link network (edRVFL) model. The edRVFL uses rich intermediate features for the final decision, which can make the final result closer to the real data. In order to strengthen the anti-interference ability to the outliers, this paper robustly improves the edRVFL model, and the improved model is called ORedRVFL. ORedRVFL reduces the impact of outliers by introducing regularization and norm to balance the relationship between training error and weights. The experiments have proved that the model proposed in this paper outperforms other models in terms of anti-interference ability and prediction accuracy.

关键词： Ensemble deep random vector functional link network Anti-interference ability Wind speed prediction arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Sizing and Energy Management of Parking Lots of Electric Vehicles Based on Battery Storage with Wind Resources in Distribution Network

引用

ENERGIES 2021年第20期14卷 6755页

作者： Shahrokhi, Saman El-Shahat, Adel Masoudinia, Fatemeh Gandoman, Foad H. Aleem, Shady H. E. Abdel Islamic Azad Univ Dept Elect Engn Sanandaj Branch Sanandaj *** Iran Purdue Univ Energy Technol Program Sch Engn Technol W Lafayette IN 47907 USA Islamic Azad Univ Dept Elect Engn Sofian Branch Sofian *** Iran Vrije Univ Brussel VUB ETEC Dept Pl Laan 2 B-1050 Brussels Belgium Vrije Univ Brussel VUB MOBI Res Grp Pl Laan 2 B-1050 Brussels Belgium Sci Valley Acad Valley Higher Inst Engn & Technol Dept Elect Engn Al Qalyubia 44971 Egypt

In this paper, an optimal sizing and placement framework (OSPF) is performed for electric parking lots integrated with wind turbines in a 33-bus distribution network. The total objective function is defined as minimizing the total cost including the cost of grid power, cost of power losses, cost of charge and discharge of parking lots, cost of wind turbines as well as voltage deviations reduction. In the OSPF, optimization variables are selected as electric parking size and wind turbines, which have been determined optimally using an intelligent method named arithmetic optimization algorithm (AOA) inspired by arithmetic operators in mathematics. The load following strategy (LFS) is used for energy management in the OSPF. The OSPF is evaluated in three cases of the objective function such as minimizing the cost of power losses, minimizing the network voltage deviations, and minimizing the total objective function using the AOA. The capability of the AOA is compared with the well-known particle swarm optimization (PSO) and artificial bee colony (ABC) algorithms for solving the OSPF in the last case. The findings show that the power loss, voltage deviations, and power purchased from the grid are reduced considerably based on the OSPF using the AOA. The results show the lowest total cost of energy and also minimum network voltage deviation (third case) by the AOA in comparison with the PSO and ABC with a higher convergence rate, which confirms the better capability of the proposed method. The results of the first and second cases show the high cost of power purchased from the main grid as well as the high total cost. Therefore, the comparison of different cases confirms that considering the cost index along with losses and voltage deviations causes a compromise between different objectives, and thus the cost of purchasing power from the main network is significantly reduced. Moreover, the voltage profile of the network improves, and also the minimum voltage of the netwo

关键词： distribution network optimal sizing and placement framework parking lots cost arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Bi-directional Long-term Short-term Memory Classification Method of Diabetes Datasets

引用

ENGINEERING LETTERS 2022年第4期30卷 1603页

作者： Li, Xu-Dong Wang, Jie-Sheng Hao, Wen-Kuo Zhao, Xiao-Rui Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan 114051 Peoples R China

As a underlying disease, diabetes has become more and more common worldwide. The patients presented with persistent and long-term hyperglycemia. If the cause of diabetes is not identified and not treated in time, many complications will occur. Because the identification process is complicated, patients choose a medical center to visit a diagnostic center to consult a doctor. This study will focus on how to design a classification model to accurately determine whether a patient has diabetes. Therefore, this paper combines the trigonometric function pedigree arithmetic optimization algorithm (AOA) with the bi-directional long short-term memory (Bi-LSTM) neural network. Based on two kinds of neural networks, 10 diabetes classification methods based on heuristic algorithm training network parameters are designed. Simulation experimental results demonstrate that the trigonometric function pedigree arithmetic optimization algorithm to improve the parameters of the Bi-LSTM network can significantly improve the classification accuracy. Finally, the Bi-LSTM classification model based on tanAOA has the best classification utility, and the classification accuracy is better than other classification methods.

关键词： diabetes data classification arithmetic optimization algorithm bi-directional long-term short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Multiple Indefinite Kernel Learning Framework for Disease Classification from Gene Expression Data

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第6期14卷 844-855页

作者： Swetha, S. Srinivasan, G. N. Dayananda, P. RV Coll Engn Dept Informat Sci & Engn Bengaluru 560059 Karnataka India Manipal Acad Higher Educ Manipal Inst Technol Bengaluru Dept Informat Technol Manipal India

In recent years, Machine Learning (ML) techniques have been used by several researchers to classify diseases using gene expression data. Disease categorization using heterogeneous gene expression data is often used for defining critical problems such as cancer analysis. A variety of evaluated factors known as genes are used to characterize the gene expression data gathered from DNA microarrays. Accurate classification of genetic data is essential to provide accurate treatments to sick people. A large number of genes can be viewed simultaneously from the collected data. However, processing this data has some limitations due to noises, redundant data, frequent errors, increased complexity, smaller samples with high dimensionality, difficult interpretation, etc. A model must be able to distinguish the features in such heterogeneous data with high accuracy to make accurate predictions. So this paper presents an innovative model to overcome these issues. The proposed model includes an effective multiple indefinite kernel learning based model for analyze the gene expression microarray data, then an optimized kernel principal component analysis (OKPCA) to select best features , hybrid flow-directed arithmetic support vector machine (SVM)-based multiple infinite kernel learning (FDASVM-MIKL) model for classification. Flow direction and arithmetic optimization algorithms are combined with SVM to increase classification accuracy. The proposed technique has an accuracy of 99.95%, 99.63%, 99.60%, 99.51% , 99.79% using the datasets including colon, Isolet, ALLAML, Lung_cancer, and Snp2 graph.

关键词： Gene expression optimized kernel principle component analysis multiple indefinite kernel learning flow direction algorithm based support vector machine arithmetic optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel decomposition integration model for power coal price forecasting

引用

RESOURCES POLICY 2023年 80卷

作者： Wu, Siping Xia, Guilin Liu, Lang East China Jiaotong Univ Sch Econ & Management Nanchang 330013 Peoples R China Guizhou Univ Finance & Econ Sch Business Adm Guiyang 550000 Peoples R China

Accurate prediction of steam coal prices is important for stabilizing the coal trading market and formulating coal use strategies scientifically. In this paper, a new decomposition integration model (VADM) is proposed to predict coal prices by combining the variational modal decomposition (VMD), arithmetic optimization algorithm (AOA), deep temporal convolutional network (DeepTCN), and mean impact value algorithm (MIV). Firstly, the AOA optimization algorithm is used to improve the VMD, AOA-VMD was obtained. It is used to decompose the steam coal price series. Then, the decomposed subsequences are predicted for the prediction of steam coal prices by using DeepTCN. Finally, the MIV algorithm is applied to analyze the impact of different factors on the price of steam coal. It is found that: the steam coal price sub-series decomposed by AOA-VMD are smoother and more linear compared with the original series;the errors in forecasting steam coal prices are significantly reduced after considering newly proposed factors, interest rates, such as the overnight Shanghai interbank offered rate and the six-month treasury bond yield;the MAPE, MASE and SMAPE of the VADM model all show different degrees of decline compared with benchmark models. The forecasting effect of VADM model is better than the benchmark model in terms of stability and accuracy, and can be used for short-term forecasting of coal prices.

关键词： arithmetic optimization algorithm Variational modal decomposition Deep temporal convolutional network Mean impact value algorithm Steam coal price forecasting

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：