检索结果-内蒙古大学图书馆

Rare Event Detection in Imbalanced Multi-Class Datasets Using an Optimal MIP-Based Ensemble Weighting Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tertytchny, Georgios Stavrinides, Georgios L. Michael, Maria K. KIOS Research and Innovation Center of Excellence Cyprus Department of Electrical and Computer Engineering University of Cyprus Cyprus

To address the challenges of imbalanced multi-class datasets typically used for rare event detection in critical cyber-physical systems, we propose an optimal, efficient, and adaptable mixed integer programming (MIP) ensemble weighting scheme. Our approach leverages the diverse capabilities of the classifier ensemble on a granular per class basis, while optimizing the weights of classifier-class pairs using elastic net regularization for improved robustness and generalization. Additionally, it seamlessly and optimally selects a predefined number of classifiers from a given set. We evaluate and compare our MIP-based method against six well-established weighting schemes, using representative datasets and suitable metrics, under various ensemble sizes. The experimental results reveal that MIP outperforms all existing approaches, achieving an improvement in balanced accuracy ranging from 0.99% to 7.31%, with an overall average of 4.53% across all datasets and ensemble sizes. Furthermore, it attains an overall average increase of 4.63%, 4.60%, and 4.61% in macro-averaged precision, recall, and F1-score, respectively, while maintaining computational efficiency. © 2024, CC BY.

关键词： mixed-integer linear programming

Forbidden Patterns in mixed linear Layouts

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Haun, Deborah Merker, Laura Pupyrev, Sergey Karlsruhe Institute of Technology Germany Menlo Park CA United States

An ordered graph is a graph with a total order over its vertices. A linear layout of an ordered graph is a partition of the edges into sets of either non-crossing edges, called stacks, or non-nesting edges, called queues. The stack (queue) number of an ordered graph is the minimum number of required stacks (queues). mixed linear layouts combine these layouts by allowing each set of edges to form either a stack or a queue. The minimum number of stacks plus queues is called the mixed page number. It is well known that ordered graphs with small stack number are characterized, up to a function, by the absence of large twists (that is, pairwise crossing edges). Similarly, ordered graphs with small queue number are characterized by the absence of large rainbows (that is, pairwise nesting edges). However, no such characterization via forbidden patterns is known for mixed linear layouts. We address this gap by introducing patterns similar to twists and rainbows, which we call thick patterns;such patterns allow a characterization, again up to a function, of mixed linear layouts of bounded-degree graphs. That is, we show that a family of ordered graphs with bounded maximum degree has bounded mixed page number if and only if the size of the largest thick pattern is bounded. In addition, we investigate an exact characterization of ordered graphs whose mixed page number equals a fixed integer k via a finite set of forbidden patterns. We show that for every k ≥ 2, there is no such characterization, which supports the nature of our first result. © 2024, CC BY.

关键词： mixed-integer linear programming

Speedup Techniques for Switchable Temporal Plan Graph Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, He Lin, Muhan Li, Jiaoyang Carnegie Mellon University United States

Multi-Agent Path Finding (MAPF) focuses on planning collision-free paths for multiple agents. However, during the execution of a MAPF plan, agents may encounter unexpected delays, which can lead to inefficiencies, deadlocks, or even collisions. To address these issues, the Switchable Temporal Plan Graph provides a framework for finding an acyclic Temporal Plan Graph with the minimum execution cost under delays, ensuring deadlock- and collision-free execution. Unfortunately, existing optimal algorithms, such as mixed integer linear programming and Graph-Based Switchable Edge Search (GSES), are often too slow for practical use. This paper introduces Improved GSES, which significantly accelerates GSES through four speedup techniques: stronger admissible heuristics, edge grouping, prioritized branching, and incremental implementation. Experiments conducted on four different map types with varying numbers of agents demonstrate that Improved GSES consistently achieves over twice the success rate of GSES and delivers up to a 30-fold speedup on instances where both methods successfully find solutions. Copyright © 2024, The Authors. All rights reserved.

关键词： mixed-integer linear programming

Multi-objective robust optimization for multi-stage-multi-product agile closed-loop supply chain under uncertainty in the context of circular economy

学校读者我要写书评

暂无评论

JOURNAL OF ENTERPRISE INFORMATION MANAGEMENT 2021年第1期38卷 94-126页

作者： Ghoushchi, Saeid Jafarzadeh Hushyar, Iman Sabri-Laghaie, Kamyar Urmia Univ Technol Fac Ind Engn Orumiyeh Iran

Purpose A circular economy (CE) is an economic system that tries to eliminate waste and continually use resources. Due to growing environmental concerns, supply chain (SC) design should be based on the CE considerations. In addition, responding and satisfying customers are the challenges managers constantly encounter. This study aims to improve the design of an agile closed-loop supply chain (CLSC) from the CE point of view. Design/methodology/approach In this research, a new multi-stage, multi-product and multi-period design of a CLSC network under uncertainty is proposed that aligns with the goals of CE and SC participants. Recycling of goods is an important part of the CLSC. Therefore, a multi-objective mixed-integer linear programming model (MILP) is proposed to formulate the problem. Besides, a robust counterpart of multi-objective MILP is offered based on robust optimization to cope with the uncertainty of parameters. Finally, the proposed model is solved using the e-constraint method. Findings The proposed model aims to provide the strategic choice of economic order to the suppliers and third-party logistic companies. The present study, which is carried out using a numerical example and sensitivity analysis, provides a robust model and solution methodology that are effective and applicable in CE-related problems. Practical implications This study shows how all upstream and downstream units of the SC network must work integrated to meet customer needs considering the CE context. Originality/value The main goal of the CE is to optimize resources, reduce the use of raw materials, and revitalize waste by recycling. In this study, a comprehensive model that can consider both SC design and CE necessities is developed that considers all SC participants.

关键词： Closed-loop supply chain Robust optimization mixed-integer linear programming Circular economy Sustainable development

EXDBN: EXACT LEARNING OF DYNAMIC BAYESIAN NETWORKS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rytíř, Pavel Wodecki, Aleš Korpas, Georgios Mareček, Jakub Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic HSBC Lab Emerging Technologies Innovation & Ventures Singapore Faculty of Electrical Engineering Czech Technical University in Prague and Archimedes Research Unit on AI Data Science and Algorithms Greece

Causal learning from data has received much attention in recent years. One way of capturing causal relationships is by utilizing Bayesian networks. There, one recovers a weighted directed acyclic graph, in which random variables are represented by vertices, and the weights associated with each edge represent the strengths of the causal relationships between them. This concept is extended to capture dynamic effects by introducing a dependency on past data, which may be captured by the structural equation model, which is utilized in the present contribution to formulate a score-based learning approach. A mixed-integer quadratic program is formulated and an algorithmic solution proposed, in which the pre-generation of exponentially many acyclicity constraints is avoided by utilizing the so-called branch-and-cut ("lazy constraint") method. Comparing the novel approach to the state of the art, we show that the proposed approach turns out to produce excellent results when applied to small and medium-sized synthetic instances of up to 25 time-series. Lastly, two interesting applications in bio-science and finance, to which the method is directly applied, further stress the opportunities in developing highly accurate, globally convergent solvers that can handle modest instances. Copyright © 2024, The Authors. All rights reserved.

关键词： mixed-integer linear programming

An Optimal Energy Management System Using Day-ahead Prediction Algorithm 11

学校读者我要写书评

暂无评论

An Optimal Energy Management System Using Day-ahead Predicti...

11th IEEE-PES Innovative Smart Grid Technologies Europe (IEEE-PES ISGT Europe)

作者： Venkateswaran, Rogith Balaji Tomar, Anuradha Phuong Nguyen Suma, Alexander Univ Technol Eindhoven Dept Elect Engn NL-5300 MB Eindhoven Netherlands Netaji Subhas Univ Technol Dept Inst & Control Sec 3Dwarka 78 Delhi India IBIS Power NL-5617 AB Eindhoven Netherlands

ISBN: (纸本)9781665448758

y Renewable energy sources (RES) are currently being deployed worldwide with the focus to reduce grid load, secure tax incentives, and promote RES. Meanwhile, the Dutch government has introduced a new regulation for net-metering policy and nearly zero energy building (n-ZEB). To combat these new regulations, wind turbines and photovoltaics (PV) panels along with a battery energy storage (BES) are placed to improve the tuning possibilities of RES and load demand. An energy management system (EMS) is required to optimize the performance and lifecycle of the BES and simultaneously reducing the electricity bill. In this paper, a mixed-integer linear programming (MILP) optimization problem is formulated to schedule energy profile for the BES considering the day-ahead predicted RES and load demand. Henceforth, a prediction algorithm is designed to forecast the day-ahead prediction of RES and load demand from the day-ahead weather forecast. A case study has been performed for 130 house apartment building in Alkmaar, the Netherlands. The simulation results show at least 90% correlation between the weather parameters, RES, and load demand. Further, results demonstrate the effectiveness of the proposed EMS for different seasons throughout the year.

关键词： Battery energy storage day-ahead prediction energy management system feedforward neural network mixed-integer linear programming

Day-ahead transactive market operations with smart distribution power systems 52

学校读者我要写书评

暂无评论

Day-ahead transactive market operations with smart distribut...

52nd North American Power Symposium (NAPS)

作者： Erudiel Santos-Gonzalez, Erik Gutierrez-Alcaraz, Guillermo Tecnol Nacl Mexico IT Morelia Dept Elect Engn Morelia Michoacan Mexico

ISBN: (纸本)9781728181929

With the increase of distributed energy resources (DER) and renewable energy sources (RES) in distribution power systems, distribution system operators requires new tools to coordinate the transactive dispatch of supply and demand at the distribution level. Interest in harnessing the potential of demand response, energy storage systems motivates the design of new retail energy market structures. Transactive energy is emerging as one of the most innovative and effective approaches to the smart grid. In this paper, a day-ahead transactive energy market model is proposed. The model is formulated as a mixed-integer linear programming. Distribution losses are included using piecewise linear expressions. The model is applied to a case study of a 16-bus system.

关键词： transactive energy demand response mixed-integer linear programming

SCHEDULING MAINTENANCE TECHNICIANS IN A RAILWAY DEPOT

学校读者我要写书评

暂无评论

SCHEDULING MAINTENANCE TECHNICIANS IN A RAILWAY DEPOT

100th Joint Rail Conference (JRC)

作者： Alves, Tiago Andrade, Antonio R. Univ Lisbon IDMEC Inst Super Tecn Lisbon Portugal

ISBN: (纸本)9780791884775

This paper presents a mathematical programming model that optimizes the daily schedule of maintenance technicians in a railway depot. The aim of the model is the minimization of the associated labor costs, while assigning the different technicians and skills required for each maintenance task. A case study of a Portuguese frain operating company is explored, including many technical constraints imposed by the company. A mixed-integer linear programming model is formulated and applied to the case study, while observing the rolling stock schedule and the maintenance tactical plan. The optimized solution shows that the maintenance team could be shortened, as some workers are not necessary to carry out all maintenance actions, suggesting the need for more flexible maintenance crew scheduling and associated labor conditions. The present model is integrated within a tactical maintenance planning model, which finds a feasible annual maintenance plan for the entire fleet, and an operational maintenance scheduling model, which assigns frain units to service tasks and schedules the maintenance tasks within the rolling stock. Together, the three models provide a decision framework that can support maintenance planning and scheduling decisions. Finally, the present maintenance crew scheduling model adds a key aspect to the literature: the skills of maintenance technicians.

关键词： Railway Maintenance Maintenance Crew Scheduling mixed-integer linear programming Maintenance planning Maintenance scheduling

Sensing Resource Allocation Against Data-Poisoning Attacks in Traffic Routing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yu, Yue Thorpe, Adam J. Milzman, Jesse Fridovich-Keil, David Topcu, Ufuk The Department of Aerospace Engineering and Mechanics The University of Minnesota Twin Cities MinneapolisMN United States The Oden Institute for Computational Engineering and Sciences The Department of Aerospace Engineering and Engineering Mechanics The University of Texas at Austin AustinTX United States DEVCOM Army Research Laboratory 2800 Powder Mill Rd AdelphiMD United States

Data-poisoning attacks can disrupt the efficient operations of transportation systems by misdirecting traffic flows via falsified data. One challenge in countering these attacks is to reduce the uncertainties on the types of attacks, such as the distribution of their targets and intensities. We introduce a resource allocation method in transportation networks to detect and distinguish different types of attacks and facilitate efficient traffic routing. The idea is to first cluster different types of attacks based on the corresponding optimal routing strategies, then allocate sensing resources to a subset of network links to distinguish attacks from different clusters via lexicographical mixed-integer programming. We illustrate the application of the proposed method using the Anaheim network, a benchmark model in traffic routing that contains more than 400 nodes and 900 links. © 2024, CC BY.

关键词： mixed-integer linear programming