检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pangia, Andrew Sudjianto, Agus Zhang, Aijun Khan, Taufiquar UNC Charlotte United States H2O.ai United States Wells Fargo United States

Fair lending practices and model interpretability are crucial concerns in the financial industry, especially given the increasing use of complex machine learning models. In response to the Consumer Financial Protection Bureau’s (CFPB) requirement to protect consumers against unlawful discrimination, we introduce LDA-XGB1, a novel less discriminatory alternative (LDA) machine learning model for fair and interpretable binary classification. LDA-XGB1 is developed through biobjective optimization that balances accuracy and fairness, with both objectives formulated using binning and information value. It leverages the predictive power and computational efficiency of XGBoost while ensuring inherent model interpretability, including the enforcement of monotonic constraints. We evaluate LDA-XGB1 on two datasets: SimuCredit, a simulated credit approval dataset, and COMPAS, a real-world recidivism prediction dataset. Our results demonstrate that LDA-XGB1 achieves an effective balance between predictive accuracy, fairness, and interpretability, often outperforming traditional fair lending models. This approach equips financial institutions with a powerful tool to meet regulatory requirements for fair lending while maintaining the advantages of advanced machine learning techniques. © 2024, CC BY.

关键词： mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

STATISTICAL INFERENCE FOR FOUR-REGIME SEGMENTED REGRESSION MODELS

arXiv

引用

arXiv 2024年

作者： Yan, Han Chen, Song Xi Guanghua School of Management Peking University China Department of Statistics and Data Science Tsinghua University China

Segmented regression models offer model flexibility and interpretability as compared to the global parametric and the nonparametric models, and yet are challenging in both estimation and inference. We consider a four-regime segmented model for temporally dependent data with segmenting boundaries depending on multivariate covariates with non-diminishing boundary effects. A mixed integer quadratic programming algorithm is formulated to facilitate the least square estimation of the regression and the boundary parameters. The rates of convergence and the asymptotic distributions of the least square estimators are obtained for the regression and the boundary coefficients, respectively. We propose a smoothed regression bootstrap to facilitate inference on the parameters and a model selection procedure to select the most suitable model within the model class with at most four segments. Numerical simulations and a case study on air pollution in Beijing are conducted to demonstrate the proposed approach, which shows that the segmented models with three or four regimes are suitable for the modeling of the meteorological effects on the PM2.5 concentration. © 2024, CC BY.

关键词： mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Computing Optimal Resilience-Oriented Operation of Distribution Systems Considering Heterogenous Consumer-Side Microgrids

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Bai, Ziyi Xu, Da Zhou, Bin Yang, Xiaodong Yang, Hanyu Liu, Ju Hubei University of Technology Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Wuhan430068 China Hubei University of Technology School of Electrical and Electronic Engineering Wuhan430068 China University of Macau State Key Laboratory of Internet of Things for Smart City Macao999078 China China University of Geosciences School of Automation Wuhan430074 China Hunan University College of Electrical and Information Engineering Changsha410082 China Hefei University of Technology State Key Laboratory of High Efficiency and High Quality Electric Energy Conversion Hefei230009 China Nanjing Tech University College of Electrical Engineering and Control Science Nanjing211816 China SGCC Jingmen Power Supply Company Jingmen448000 China

Mobile battery energy storage systems (MBESs), also called power-to-mobility, have been field-validated as backup generation resources. However, the role of multi-energy coordination towards resilient distribution systems (DSs) against large area disasters is still not yet involved. To cope with such challenges, this paper proposes a computing optimal resilient operation model for post-disaster microgrid-penetrated DS recovery based on the energy-to-mobility approach. In this model, mobile multi-energy storages (MMESs) are invested and routed based on their different transportation mobility, while DS with consumer-side biogas-solar-wind multi-energy microgrids are topologized by network reconfiguration. The coordinated resilient operation of different recovery actions of DS, MMESs, and consumer-side microgrids is a difficult optimization problem as results of its inherent nonconvexities, temporal-spatial mobility and strong multi-energy couplings. The original mixed-integer non-linear programming (MINLP) problem is thus equivalently linearized and reformulated into a mixed-integer linear programming (MILP) for computation performance improvement. The proposed methodology is benchmarked and performed on a modified radial DS with three consumer-side microgrids. Numerical studies demonstrate the effectiveness and superiority of the energy-to-mobility scheme over MBESs on system resilient level and economy. © 1975-2011 IEEE.

关键词： mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Solving data envelopment analysis models with sum-of-fractional objectives: a global optimal approach based on the multiparametric disaggregation technique

引用

ANNALS OF OPERATIONS RESEARCH 2021年第1-2期304卷 453-480页

作者： Xie, Jianhui Xie, Qiwei Li, Yongjun Liang, Liang Sun Yat Sen Univ Int Sch Business & Finance Zhuhai 519082 Guangdong Peoples R China Beijing Univ Technol Res Base Beijing Modern Mfg Dev Beijing 100124 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Univ Sci & Technol China Sch Management Hefei 230026 Anhui Peoples R China Hefei Univ Technol Sch Management 193 TunXi Rd Hefei 230009 Anhui Peoples R China

The majority of data envelopment analysis (DEA) models can be linearized via the classical Charnes-Cooper transformation. Nevertheless, this transformation does not apply to sum-of-fractional DEA efficiencies models, such as the secondary goal I (SG-I) cross efficiency model and the arithmetic mean two-stage network DEA model. To solve a sum-of-fractional DEA efficiencies model, we convert it into bilinear programming. Then, the obtained bilinear programming is relaxed to mixed-integer linear programming (MILP) by using a multiparametric disaggregation technique. We reveal the hidden mathematical structures of sum-of-fractional DEA efficiencies models, and propose corresponding discretization strategies to make the models more easily to be solved. Discretization of the multipliers of inputs or the DEA efficiencies in the objective function depends on the number of multipliers and decision-making units. The obtained MILP provides an upper bound for the solution and can be tightened as desired by adding binary variables. Finally, an algorithm based on MILP is developed to search for the global optimal solution. The effectiveness of the proposed method is verified by using it to solve the SG-I cross efficiency model and the arithmetic mean two-stage network DEA model. Results of the numerical applications show that the proposed approach can solve the SG-I cross efficiency model with 100 decision-making units, 3 inputs, and 3 outputs in 329.6 s. Moreover, the proposed approach obtains more accurate solutions in less time than the heuristic search procedure when solving the arithmetic mean two-stage network DEA model.

关键词： Data envelopment analysis mixed-integer linear programming Global optimal solution Fractional programming

来源：评论

学校读者我要写书评

暂无评论

Towards renewable energy projects under sustainable watersheds principles for forest biomass supply

引用

BIOMASS & BIOENERGY 2023年第1期176卷

作者： Franca, Luciano Cavalcante de Jesus Silva, Carolina Souza Jarochinski e Mucida, Danielle Piuzana da Costa, Jaqueline Severino Gomide, Lucas Rezende Fed Univ Uberlandia UFU Inst Agr Sci Monte Carmelo MG Brazil Fed Univ Lavras UFLA Dept Forestry Sci Lavras MG Brazil Fed Univ Jequitinhonha & Mucuri Valleys UFVJM Dept Forest Engn Diamantina MG Brazil Fed Univ Lavras UFLA Dept Agribusiness Management Lavras MG Brazil

The transition in the global energy matrix to sources of renewable electric generation has been the main demand of countries in the face of a state of climatic emergency. Forest biomass is a potential alternative to meet the growing demand. The expansion of thermoelectric projects based on forest residues highlights the need to assess raw materials' availability and land suitability. This is usually a problem of spatial decision and geographic intelligence under a holistic perspective since, in planning these projects, it is essential to understand the economic, environmental, and social feasibility. In this article, we propose a decision support system based on multicriteria modeling on a GIS structure associated with a mathematical optimization model for zoning the suitability and availability of land for constructing thermoelectric power plants. The geospatial model for determining priority sites integrated various environmental, social, and economic criteria and constraints. The AHP method was used to weigh and estimate the relative importance weights of the criteria for modeling territorial aptitude. The results of the GIS stage formed the basis of a mixed-integer linear programming model that incorporated technical and economic aspects for a better allocation of financial resources. The minimized cost function included transport costs, harvesting, forestry, purchasing land/leasing land/forest outgrower schemes, and purchasing wood from the market to supply the biomass. We used a sizeable hydrographic basin in southeastern Brazil as a case study for the demonstration. The mapping of suitability and constrained zones identified the classes of preference and availability of land. The proposed mathematical model recognized sets of supply locations (new plantations or existing areas) and minimized the project's final cost to supply biomass to meet the demand of potential thermoelectric plants that are candidates for implementation. Despite the problem's large scale

关键词： Forest planning Land-use planning Green industry Multi-criteria decision analysis mixed-integer linear programming Bioeconomy

来源：评论

学校读者我要写书评

暂无评论

Technology portfolios optimization to deliver cost-effective shale gas development: Using CO2 versus water

引用

FUEL 2023年第1期335卷

作者： Ji, Tiancheng Jiang, Peixue Xu, Ruina Tsinghua Univ Dept Energy & Power Engn Key Lab CO2 Utilizat & Reduct Technol Beijing Beijing 100084 Peoples R China Tsinghua Univ Dept Energy & Power Engn Key Lab Thermal Sci & Power Engn Minist Educ Beijing 100084 Peoples R China

Hydraulic fracturing is widely used in shale gas development, while it could cause decline in production in water -sensitive formations. Using CO2 for reservoir fracturing, injection to enhance gas recovery, and sequestration in depleted shale reservoirs can solve this problem, increase shale gas production, and store CO2 underground. Given the high expense of these CO2 techniques, the trade-off between the rising cost of deploying CO2 tech-niques and the benefit of increased shale gas production influences the technology portfolios for shale gas development. Financial incentives for carbon credits can provide compensation for the cost of CO2 techniques, further influencing the technology portfolios. Currently, questions remain regarding the optimal technology portfolios for achieving cost-effective shale gas development under different reservoir conditions and the impacts of the carbon price incentive. Here, we propose a novel optimization model that simultaneously integrates the hydraulic fracturing, CO2 fracturing, CO2 injection, and CO2 sequestration techniques to investigate the optimal technology mix for cost-effective shale gas development. We select the non-water sensitive formations and water sensitive formations as two representative scenarios. The results show that to cost-effectively develop shale gas, hydraulic fracturing is preferred in the non-water sensitive scenario whereas CO2 fracturing and CO2 injection are preferred in the water sensitive scenario. The synergistic deployment of CO2 fracturing and CO2 injection techniques can not only improve economic performance but also sequestrate more CO2. Our findings provide policy makers with critical insights into achieving cost-effective shale gas development while curbing carbon emissions.

关键词： Hydraulic fracturing CO2 fracturing CO2 injection for enhanced gas recovery CO2 sequestration Shale gas development mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Optimal decarbonization strategies for existing districts considering energy systems and retrofits

引用

APPLIED ENERGY 2023年 352卷

作者： Lerbinger, Alicia Petkov, Ivalin Mavromatidis, Georgios Knoeri, Christof Swiss Fed Inst Technol Grp Sustainabil & Technol CH-8092 Zurich Switzerland OPTIML AG CH-8003 Zurich Switzerland

Integrated energy system planning at the district level can contribute towards the sustainable transformation of the building sector by unlocking solutions beyond individual buildings. This is particularly true for existing districts, whose older buildings have a low energy performance and for which measures to reduce the energy demand and ensure a low-emission energy supply must be implemented. In the urban context, district heating networks (DHN) are a promising way of doing the latter, especially with carbon capture and storage (CCS) on the horizon. However, investment decisions for both types of measures - energy supply and demand reduction - must consider individual buildings as part of district-scale considerations as building-level demand-side interventions affect energy demand patterns and densities. These can in turn affect energy supply decisions at the district-level. This study presents a comprehensive methodology for determining optimal decarbonization strategies for existing districts while considering building-level energy supply and retrofitting investment decisions and the expansion of existing DHN. We do so by extending the MANGOret (Multi-stAge eNerGy Optimization -retrofitting) optimization framework for the long-term investment planning of building-level multi-energy systems and envelope retrofits. In addition, the study presents an approach for modeling CCS as an emission -reduction technology for the waste incinerator supplying the marginal expansion of the district heating network. The developed optimization model considers a long-term time horizon with multiple investment stages, allowing it to represent economic and technological developments over the model time horizon. It incorporates a multi-objective perspective, capturing the trade-offs between the total system costs and emissions. The model is applied to two existing case study neighborhoods in the city of Chur, Switzerland. The long-term energy system design and operation for the two

关键词： Decentralized and renewable multi-energy systems District heating networks Urban decarbonization Renewable energy Building retrofitting Multi-stage optimization mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Stochastic Optimization-Based hosting capacity estimation with volatile net load deviation in distribution grids

引用

APPLIED ENERGY 2023年第1期341卷

作者： Cho, Yongjun Lee, Eunjung Baek, Keon Kim, Jinho Gwangju Inst Sci & Technol Sch Integrated Technol Gwangju South Korea

With the increasing penetration rates of variable renewable energies (VREs), estimating the maximum network capacity without adversely impacting the reliability or voltage quality for power system operation, that is, the hosting capacity (HC), is a significant issue. For system operators, it is challenging to secure flexible resources that can respond to the volatility of the net load resulting from the intermittent generation characteristics of VREs and the appearance of various consumers. Thus, this study proposed a hosting capacity estimation framework that considers the net load deviation. It thereby overcomes the abrupt net load deviation for the economic accommodation of VREs. To evaluate proposed framework, the qualification of the proposed net load deviation limit as a new performance index and investigation for improving HC was verified via performance violation analysis. The proposed net load filter exhibited excellent performance in capturing the net load devi-ation without distorting the conventional performance index. To consider the net load deviation magnitude and intensity effect on system operation, a multi-time stochastic optimization model was formulated. The proposed framework was tested on an IEEE 33-radial bus system to investigate the effects of the net load deviation limit on the HC, and its potential as a performance index was analyzed. Finally, as an application of the proposed model to help the system operator's precise decision making, the VRE accommodation costs was quantitatively suggested.

关键词： Distribution grid Hosting capacity mixed-integer linear programming Net-load deviation Stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

Diesel genset optimization in remote microgrids

引用

APPLIED ENERGY 2023年第1期340卷

作者： Lambert, Mathieu Hassani, Rachid Hydro Quebec 1800 Boul Lionel Boulet Varennes PQ J3X 1S1 Canada GERAD 2920 Chemin Tour Montreal PQ H3T 1J4 Canada

In this paper, a new model is proposed for the real-time diesel genset optimal dispatch and unit commitment in remote microgrids. The objective is to reduce fuel consumption, while taking into account several constraints, such as maintenance considerations and prime power ratings, specific to gensets. The model described in this work is deterministic in nature and is a mixed-integer linear programming optimization problem. In order to demonstrate the correct behavior of the model, four case studies were chosen to illustrate the activation of different constraints under certain conditions. The results show that the model properly reproduces the intended behavior, and that it could have permitted to reduce fuel consumption by 4.3 % when compared to the actual dispatch during those 2 days. Finally, it was shown that the performance of the model solved with CPLEX and Gurobi is adequate for real-time optimization in remote microgrids, and that the economic gain of using a baseload strategy instead of a load sharing strategy is negligible compared to the increase of complexity in implementing this baseload strategy.

关键词： Real-time optimization mixed-integer linear programming Deterministic unit commitment Microgrids Diesel gensets

来源：评论

学校读者我要写书评

暂无评论

Optimizing disaster relief goods distribution and transportation: a mathematical model and metaheuristic algorithms

引用

APPLIED MATHEMATICS IN SCIENCE AND ENGINEERING 2023年第1期31卷

作者： Beheshtinia, Mohammad Ali Jozi, Ali Fathi, Masood Semnan Univ Dept Ind Engn Semnan Iran Univ Skovde Sch Engn Sci Div Intelligent Prod Syst Skovde Sweden Uppsala Univ Dept Civil & Ind Engn Div Ind Engn & Management Uppsala Sweden Univ Skovde Sch Engn Sci Div Intelligent Prod Syst Hogskolevagen 1 S-54128 Skovde Sweden

The effective distribution of relief goods is critical in mitigating the impact of natural disasters and preserving human life. This study addresses a relief goods distribution problem, assuming the existence of multiple relief orders that must be delivered to various disaster-stricken regions from a network of warehouses using a fleet of diverse vehicles. The objective is to identify the most suitable warehouse for each relief order, allocate relief orders to vehicles, batch the orders in the designated vehicles, and devise routing plans to minimize the total delivery time. A mixed-integer linear programming model is formulated to tackle this problem. Owing to the problem's NP-hard nature, a metaheuristic algorithm, known as the Multiple League Championship Algorithm, is developed. Furthermore, two innovative variants of the MLCA , namely the League Base Multiple League Championship Algorithm (L- MLCA) and the Playoff Multiple League Championship Algorithm (P-MLCA), are *** results indicate that the P-MLCA outperforms the other two algorithms. The solutions derived from the P-MLCA are compared with the optimal solutions obtained by a commercial solver for small-scale problems. This comparative analysis demonstrates the promising performance of the P-MLCA in finding the optimal distribution of relief goods.

关键词： Disaster-stricken regions mixed-integer linear programming multiple league championship algorithm order batching routing planning

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：