检索结果-内蒙古大学图书馆

An error-corrected deep Autoformer model via bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction

引用

APPLIED ENERGY 2025年 377卷

作者： Chen, Jie Peng, Tian Qian, Shijie Ge, Yida Wang, Zheng Nazir, Muhammad Shahzad Zhang, Chu 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

Accurate PV power prediction is crucial for stable grid operation and rational dispatch. However, due to the instability of PV power generation, PV power prediction still has great challenges. Therefore, an Autoformer model based on secondary decomposition, bayesian optimization and error correction for PV power prediction. In order to reduce the complexity of the data and fully extract the features, two decomposition methods are employed. First, empirical mode decomposition (EMD) is applied to decompose the PV power series at the first level. Then, the sample entropy (SE) is introduced to measure the complexity of each component, and the variational mode decomposition (VMD) is employed to implement secondary decomposition of the component with the highest complexity. Secondly, a bayesian optimization algorithm enhanced Autoformer model is developed for predicting each component, and the predicted component results are aggregated to obtain preliminary PV power prediction results. Finally, the preliminary prediction results are error corrected using a least squares support vector machine. A four-month PV dataset from a PV power plant in Hangzhou, China is utilized to validate the effectiveness of the proposed model. The experimental results show that the model after primary decomposition is superior to the single model, and the prediction accuracy is substantially improved after secondary decomposition. The proposed model has the best prediction performance in predicting the PV power for different seasons, which shows good robustness.

关键词： Photovoltaic power prediction Autoformer Secondary decomposition Error correction bayesian optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

An online adaptive ROP prediction model using GBDT and bayesian optimization algorithm in drilling

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2025年 246卷

作者： Hao, Jiasheng Xu, Haomin Peng, Zhinan Cao, Zhen Univ Elect Sci & Technol China Sch Automat Engn Chengdu 611731 Sichuan Peoples R China

As global energy demand continues to grow, improving drilling efficiency and reducing costs become pivotal factors in the advancement of oil and gas industry. As a core component of drilling optimization, measuring the rate of penetration (ROP) is crucial for enhancing the efficiency and profitability of the extraction process. Employing machine learning techniques to predict ROP represents an effective strategy. However, accurately predicting ROP within the diverse and dynamic stratigraphic environments remains a critical challenge. This paper proposes a novel approach for adaptive drilling optimization based on online machine learning, aimed at improving adaptability to varying stratigraphic conditions. This approach consists of two components: a learning model using Gradient Boosting Decision Trees (GBDT) and an optimal drilling parameters selector based on bayesian optimization. Specifically, GBDT is adopted to construct the ROP prediction model, which is continuously updated by integrating newly acquired information while drilling and removing outdated data. The parameters selector identifies the optimal combination of drilling parameters through the online bayesian algorithm, thereby facilitating ROP predictions. Experimental data from multiple horizontal wells in southwestern China demonstrate that this method significantly enhances the performance of the ROP prediction model by 10%-20%, with each optimization process requiring only approximately 2 s. This improvement is consistent across various formation depths and regions.

关键词： bayesian optimization algorithm Gradient boosting decision tree (GBDT) Rate of penetration Online update

来源：评论

学校读者我要写书评

暂无评论

Enhanced K-NN with bayesian optimization algorithm for predicting energy efficiency of smart grids in IoT

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2024年第9期27卷 12311-12322页

作者： Zhao, Wenlong Hu, Yuanchao Yan, Xiaopeng Liu, Xiaowei Ding, Rixian Dai, Chaofeng Cao, Ying Beijing Inst Technol Beijing Peoples R China Shandong Univ Technol Zibo Peoples R China Air Force Engn Univ Air Def & Missile Def Coll Xian Peoples R China Inspur Grp Co Ltd Jinan Peoples R China Henan Shenghuang Power Equipment Co Ltd Nanyang Peoples R China

With the increasing a huge amount of end users using electricity in modern cities, smart grids have some critical problems for energy efficiency and managing renewable energy resources. Therefore, electricity load forecasting is an important strategy to avoid power disconnection and power communication damages in smart grids. On the other hand, the Internet of Things (IoT) devices can collect appropriate data from end users with smart metering. In addition, smart devices can gather critical data from power stations using smart sensors and actuators to provide the quality of service (QoS) factors and energy efficiency of electricity transmission in the smart girds. Due to the huge amount of data transmission, machine learning is useful for evaluating electricity load forecasting and power stability in smart grids. For detecting electric load forecasting and energy consumption factors, this paper develops bayesian optimization for K-nearest neighbor (BOKNN) with the hyper-parameters function to detect the electricity load forecasting and estimated power consumption factors in smart grids. The proposed technique optimizes the performance of electricity load forecasting and enhances the structure of the machine learning efficiency with high accuracy. Two real-data sets as our case studies for short-term electricity load forecasting are applied to evaluate the proposed BOKNN as existing experimental testbeds. The simulation results illustrate that the proposed BOKNN provides optimized high accuracy with 88.33% and 98.13% of correlation coefficient and minimum mean absolute error with 0.04% for existing datasets. The experimental results show that the suggested BOKNN model greatly outperforms other prediction algorithms.

关键词： Smart grids Internet of things (IoT) bayesian optimization algorithm Power load forecasting Energy management Machine learning Accuracy

来源：评论

学校读者我要写书评

暂无评论

Lithium-ion battery equivalent thermal conductivity testing method based on bayesian optimization algorithm

引用

JOURNAL OF THERMAL ANALYSIS AND CALORIMETRY 2024年第24期149卷 15073-15083页

作者： Wang, Fang Liu, Ruihao Ma, Xiaole Zhang, Yuxuan Bai, Guangli Ma, Biao Li, Danhua Wei, Zhen Liu, Shiqiang Zhu, Yueying China Automot Technol & Res Ctr Co Ltd Tianjin 300162 Peoples R China Tianjin Univ Sci & Technol Sch Mech Engn Tianjin 300457 Peoples R China

The thermal conductivity is one of the key thermal property's parameters in the design, modeling, and simulation of lithium-ion battery thermal management systems. Accurate measurement of thermal conductivity allows for a deep understanding of the heat transfer behavior inside lithium-ion batteries, providing essential insights for optimizing battery design, enhancing energy density, and improving safety. In this study, the surface temperature variation data of lithium-ion batteries were obtained by externally heating the batteries using a constant pressure source in an accelerating rate calorimeter enhanced system (ARC). Based on the Fourier one-dimensional heat conduction model, the average specific heat capacity and vertical thermal conductivity of the lithium-ion batteries were calculated. Additionally, the bayesian optimization algorithm was employed to significantly reduce the number of iterations and rapidly invert the in-plane thermal conductivity of the batteries. The accuracy of the thermal conductivity measurement results was verified by comparing the consistency between experimental and simulation data. The results indicate that the transient deviation between experimental and simulation data at each temperature measurement point does not exceed 0.2 degrees C, demonstrating the high accuracy of the proposed method. Furthermore, the thermal conductivity of the lithium-ion battery was measured using the Hot Disk method for comparative validation. The results show that the maximum transient deviation of the Hot Disk data is 0.4 degrees C, indicating that compared to the Hot Disk method, the proposed method exhibits higher accuracy.

关键词： Lithium-ion battery Equivalent thermal conductivity Quasi-steady state bayesian optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

On Hyperparameter optimization of Machine Learning Methods Using a bayesian optimization algorithm to Predict Work Travel Mode Choice

引用

IEEE ACCESS 2023年 11卷 19762-19774页

作者： Aghaabbasi, Mahdi Ali, Mujahid Jasinski, Michal Leonowicz, Zbigniew Novak, Tomas Chulalongkorn Univ Transportat Inst Bangkok 10330 Thailand Silesian Tech Univ Fac Transport & Aviat Engn Dept Transport Syst Traff Engn & Logist PL-40019 Katowice Poland Wroclaw Univ Sci & Technol Fac Elect Engn Dept Elect Engn Fundamentals PL-50370 Wroclaw Poland VSB Tech Univ Ostrava Fac Elect Engn & Comp Sci Dept Elect Power Engn Ostrava 70800 Czech Republic

Prediction of work Travel mode choice is one of the most important parts of travel demand forecasting. Planners can achieve sustainability goals by accurately forecasting how people will get to and from work. In the prediction of travel mode selection, machine learning methods are commonly employed. To fit a machine-learning model to various challenges, the hyperparameters must be tweaked. Choosing the optimal hyperparameter configuration for machine learning models has an immediate effect on the performance of the model. In this paper, optimizing the hyperparameters of common machine learning models, including support vector machines, k-nearest neighbor, single decision trees, ensemble decision trees, and Naive Bayes, is studied using the bayesian optimization algorithm. These models were developed and optimized using two datasets from the 2017 National Household Travel Survey. Using several criteria, including average accuracy (%), average area under the receiver operating characteristics, and a simple ranking system, the performance of the optimized models was investigated. The findings of this study show that the BO is an effective model for improving the performance of the k-nearest neighbor model more than other models. This research lays the groundwork for using optimized machine learning methods to mitigate the negative consequences of automobile use.

关键词： optimization Support vector machines Transportation Machine learning Predictive models Bayes methods Decision trees bayesian optimization algorithm hyperparameters sustainable mode choice decision work travel mode choice

来源：评论

学校读者我要写书评

暂无评论

Automatic SWMM Parameter Calibration Method Based on the Differential Evolution and bayesian optimization algorithm

引用

WATER 2023年第20期15卷 3582-3582页

作者： Gao, Jiawei Liang, Ji Lu, Yu Zhou, Ruilong Lu, Xin Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Sichuan Hydraul Res Inst Chengdu 610072 Peoples R China

In response to the low accuracy exhibited by the Storm Water Management Model (SWMM), we propose an enhanced Differential Evolution and bayesian optimization algorithm (DE-BOA). This algorithm integrates the global search capability of the differential evolution algorithm with the local search capability of the bayesian optimization algorithm, which enables a more comprehensive exploration of the vector solution space. A comparative analysis of various types of rainfall events is conducted. For model calibration and validation, a drainage subzone in Jinshazhou, Guangzhou City, is selected as the research subject. In total, 20 specific rainfall events are selected, and the DE-BOA algorithm outperforms the manual calibration, the differential evolution algorithm, and the bayesian optimization algorithm regarding model calibration accuracy. Furthermore, the DE-BOA algorithm exhibits robust adaptability to rainfall events characterized by multiple peaks and higher precipitation levels, with the Nash-Sutcliffe efficiency coefficient values surpassing 0.90. This study's findings could hold significant reference value for dynamically updating model parameters, thereby enhancing the model simulation performance and improving the accuracy of the urban intelligent water management platform.

关键词： SWMM differential evolution algorithm bayesian optimization algorithm automatic parameter calibration urban drainage

来源：评论

学校读者我要写书评

暂无评论

A novel model for rainfall prediction using hybrid stochastic-based bayesian optimization algorithm

引用

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH 2023年第40期30卷 92555-92567页

作者： Lathika, P. Singh, D. Sheeba Noorul Islam Ctr Higher Educ Dept Math Thuckalay Tamil Nadu India

Rainfall forecasting is considered one of the key concerns in the meteorological department because it is related strongly to social as well as economic factors. But, because of modern context of climatic conditions and the intense activities of humans, the forecasting procedure of rainfall patterns becomes more problematic. Therefore, this paper proposes a novel timely and reliable rainfall prediction model using a hybrid stochastic bayesian optimization approach (HS-BOA). The weather dataset containing different meteorological geographical features is provided as input to the introduced prediction method. Hybrid stochastic (HS) specifications are tuned by the bayesian optimization algorithm (BOA) to upgrade the prediction accuracy. The weather data are initially preprocessed through the pipelines, namely, data separation, missing value prediction, weather condition cod separation, and normalization. After preprocessing, the highly correlated features are removed by correlation matrix using the Pearson correlation coefficient. Then, the most significant features which contribute more to predicting rainfall are selected through the feature selection process. At last, the suggested rainfall forecasting model accurately predicts rainfall using optimized parameters. The experimental analysis is performed, and for the proposed HS-BOA, MAE, RMSE, and COD, values attained for rainfall prediction are 0.513 mm, 59.90 mm, and 40.56 mm respectively. As a result, the proposed HS-BOA approach achieves minimum error rates with increased prediction accuracy than other existing approaches.

关键词： Rainfall Prediction Hybrid stochastic bayesian optimization algorithm Weather dataset

来源：评论

学校读者我要写书评

暂无评论

Performance optimization of Web Front-end Frameworks: Automatic Adjustment Strategies Based on bayesian optimization algorithm 24

Performance Optimization of Web Front-end Frameworks: Automa...

引用

International Conference on Machine Intelligence and Digital Applications (MIDA)

作者： Chen, Cuiqin Meng, Qing Huang, Junze Hainan Vocat Univ Haikou 570216 Hainan Peoples R China

ISBN: (纸本)9798400718144

In modern web development, performance optimization of front-end frameworks has become a key issue in improving user experience and system efficiency. The existing manual adjustment methods are often time-consuming and have unstable effects. This article proposes an automatic adjustment strategy based on bayesian optimization algorithm to achieve efficient optimization of front-end framework performance. After using bayesian optimization algorithm, the average time of Largest Contentful Paint (LCP) is reduced to 2052 milliseconds. In terms of response speed indicators, the optimized time to interactive (TTI) decreases to 2923 milliseconds. Users are also very satisfied with the optimized experience. After using bayesian optimization algorithm, the CPU (Central Processing Unit) utilization rate decreases to 65.9% and the memory usage decreases to 324.4MB. From the data conclusion, it can be seen that the automatic adjustment strategy based on bayesian optimization algorithm has shown significant advantages in improving the performance, response speed, user experience, and resource utilization efficiency of web front-end frameworks.

关键词： Web front-end Front-end framework bayesian optimization algorithm Performance optimization Heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Using bayesian optimization algorithm for model-based integration testing

引用

SOFT COMPUTING 2022年第7期26卷 3503-3525页

作者： Rafe, Vahid Mohammady, Somayeh Cuevas, Erik Arak Univ Fac Engn Dept Comp Engn Arak *** Iran Univ Guadalajara Dept Elect CUCEI Av Revoluc 1500 Guadalajara Jalisco Mexico

Model-based testing is an automated process in which executable tests are derived from behavioral models of a system. Model checking is a verification technique to reveal errors in which all reachable states of a system can be generated as state space. In the literature, different approaches suggest using model checkers for model-based testing. Model checker explores all possible system states, so utilizing the various paths in the state-space as test cases seems a promising solution. However, these approaches suffer from two main challenges. The first challenge is state space explosion, which prevents generating all reachable states by the model checker. The second one is generating redundant test cases. Recently, several methods using meta-heuristic and evolutionary approaches have been proposed to cope with these problems. Therefore, exploring a portion of state space using an optimization approach to detect the test objectives can be a proper way to manage the state space explosion and generate an optimal test suite with the least redundancy. In this paper, a method is proposed using a bayesian optimization algorithm (BOA), and a model checker is as a bed to generate test cases for the service-oriented systems. In the proposed approach, the test suite is a set of paths on the state space starting from an initial state and leading to the state in which all the test objectives are satisfied. In this research, we have implemented BOA with three different structures in GROOVE toolset, an open-source toolset for designing and model checking graph transformation. Experimental results show that our solution generates better results in terms of coverage and speed in different case studies than the existing approaches.

关键词： Model-based testing Graph transformation bayesian optimization algorithm Integration testing Data flow

来源：评论

学校读者我要写书评

暂无评论

bayesian optimization algorithm-Based Statistical and Machine Learning Approaches for Forecasting Short-Term Electricity Demand

引用

ENERGIES 2022年第9期15卷 3425-3425页

作者： Sultana, Nahid Hossain, S. M. Zakir Almuhaini, Salma Hamad Dustegor, Dilek Imam Abdulrahman Bin Faisal Univ Dept Comp Sci Coll Comp Sci & Informat Technol Dammam 31441 Saudi Arabia Univ Bahrain Dept Chem Engn Coll Engn Zallaq 32038 Bahrain Univ Groningen Fac Sci & Engn NL-9747 AG Groningen Netherlands

This article focuses on developing both statistical and machine learning approaches for forecasting hourly electricity demand in Ontario. The novelties of this study include (i) identifying essential factors that have a significant effect on electricity consumption, (ii) the execution of a bayesian optimization algorithm (BOA) to optimize the model hyperparameters, (iii) hybridizing the BOA with the seasonal autoregressive integrated moving average with exogenous inputs (SARIMAX) and nonlinear autoregressive networks with exogenous input (NARX) for modeling separately short-term electricity demand for the first time, (iv) comparing the model's performance using several performance indicators and computing efficiency, and (v) validation of the model performance using unseen data. Six features (viz., snow depth, cloud cover, precipitation, temperature, irradiance toa, and irradiance surface) were found to be significant. The Mean Absolute Percentage Error (MAPE) of five consecutive weekdays for all seasons in the hybrid BOA-NARX is obtained at about 3%, while a remarkable variation is observed in the hybrid BOA-SARIMAX. BOA-NARX provides an overall steady Relative Error (RE) in all seasons (1 similar to 6.56%), while BOA-SARIMAX provides unstable results (Fall: 0.73 similar to 2.98%;Summer: 8.41 similar to 14.44%). The coefficient of determination (R-2) values for both models are >0.96. Overall results indicate that both models perform well;however, the hybrid BOA-NARX reveals a stable ability to handle the day-ahead electricity load forecasts.

关键词： electricity demand short-term forecast bayesian optimization algorithm SARIMAX NARX

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

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

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：