检索结果-内蒙古大学图书馆

IEEE URUCON Conference (IEEE URUCON)

作者： Chaer, Ruben Camacho, Vanina Caporale, Ximena Palacio, Juan Felipe Soubes, Pablo Vallejo, Damian Ramirez, Ignacio Univ Republica Fac Ingn Montevideo Uruguay Adm Mercado Elect Montevideo Uruguay

ISBN: (纸本)9781665424431

This work shows different strategies for a Robot to learn the optimal operation of a diverse electrical energy generation system including resources such as thermal, hydroelectric, wind, solar generators and energy accumulators. The large number of variables in these systems results in a huge state space. Thus, computing an explicit representation of the cost function over said space, which is at the heart of most current optimization methods, becomes infeasible. The strategies presented here aim at solving the aforementioned problem by learning an implicit representation of the cost function over the state space. Another key idea is to keep the complexity of the representation at a minimum, in order to obtain a solution which captures the most relevant characteristics of the cost-to-go of the system, with the least possible parameters.

关键词： Energy Optimization Dispatch approximate dynamic programming Optimal Policy Learning

来源：评论

学校读者我要写书评

暂无评论

Learning-based Optimal Control of Constrained Switched Linear Systems using Neural Networks 18

Learning-based Optimal Control of Constrained Switched Linea...

引用

18th International Conference on Informatics in Control, Automation and Robotics (ICINCO)

作者： Markolf, Lukas Stursberg, Olaf Univ Kassel Dept Elect Engn & Comp Sci Control & Syst Theory Wilhelmshoher Allee 73 D-34121 Kassel Germany

ISBN: (纸本)9789897585227

This work considers (deep) artificial feed-forward neural networks as parametric approximators in optimal control of discrete-time switched linear systems with controlled switching. The proposed approach is based on approximate dynamic programming and allows the fast computation of (sub-)optimal discrete and continuous control inputs, either by approximating the optimal cost-to-go functions or by approximating the optimal discrete and continuous input policies. An important property of the approach is the satisfaction of polytopic state and input constraints, which is crucial for ensuring safety, as required in many control applications. A numeric example is provided for illustration and evaluation of the approaches.

关键词： Neural Networks Intelligent Control Hybrid Systems approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Anticipative dynamic Slotting for Attended Home Deliveries

引用

Operations Research Forum 2021年第4期2卷 70页

作者： Lang, Magdalena A. K. Cleophas, Catherine Ehmke, Jan Fabian RWTH Aachen University Templergraben 55 Aachen 52062 Germany Christian-Albrechts-Universität zu Kiel Christian-Albrechts-Platz 4 Kiel 24118 Germany University of Vienna Oskar-Morgenstern-Platz 1 Wien 1010 Austria

Attended home delivery requires offering narrow delivery time slots for online booking. Given a fixed fleet of delivery vehicles and uncertainty about the value of potential future customers, retailers have to decide about the offered delivery time slots for each individual order. To this end, dynamic slotting techniques compare the reward from accepting an order to the opportunity cost of not reserving the required delivery capacity for later orders. However, exactly computing this opportunity cost means solving a complex vehicle routing and scheduling problem. In this paper, we propose and evaluate several dynamic slotting approaches that rely on an anticipatory, simulation-based preparation phase ahead of the order horizon to approximate opportunity cost. Our approaches differ in their reliance on outcomes from the preparation phase (anticipation) versus decision making on request arrival (flexibility). For the preparation phase, we create anticipatory schedules by solving the Team Orienteering Problem with Multiple Time Windows. From stochastic demand streams and problem instance characteristics, we apply learning models to flexibly estimate the effort of accepting and delivering an order request. In an extensive computational study, we explore the behavior of the proposed solution approaches. Simulating scenarios of different sizes shows that all approaches require only negligible run times within the order horizon. Finally, an empirical scenario demonstrates the concept of estimating demand model parameters from sales observations and highlights the applicability of the proposed approaches in practice. © 2021, The Author(s).

关键词： approximate dynamic programming Attended home delivery Revenue management Routing Team orienteering problem

来源：评论

学校读者我要写书评

暂无评论

Optimal Trading of a Fixed Quantity of Power in an Illiquid Continuous Intraday Market

Optimal Trading of a Fixed Quantity of Power in an Illiquid ...

引用

14th IEEE Madrid PowerTech Conference (IEEE POWERTECH)

作者： Bertrand, Gilles Papavasiliou, Anthony CORE UCLouvain Louvain La Neuve Belgium

ISBN: (纸本)9781665435970

The recent integration of renewable resources in electricity markets has increased the need for producers to correct their trading position close to real time in order to avoid volatile real-time prices. The last market to close before delivery is the Continuous Intraday Market. Therefore, this market is an interesting outlet for renewable units that aim at covering their forecast errors. As a starting point for tackling this problem, we characterize an optimal policy for trading a fixed quantity in a simplified market model. We use this analytical solution as a basis for developing an approximate dynamic programming algorithm and an alternative Stochastic Dual dynamic programming that can trade under a more realistic set of assumptions.

关键词： Stochastic optimal control continuous intraday market approximate dynamic programming stochastic dual dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Optimization of cyclic air braking strategy for heavy haul trains: an ADP approach

Optimization of cyclic air braking strategy for heavy haul t...

引用

IEEE Intelligent Transportation Systems Conference (ITSC)

作者： Su, S. Liu, W. Huang, Y. Tang, T. Beijing Jiaotong Univ State Key Lab Traff Control & Safety Frontiers Sci Ctr Smart High Speed Railway Syst Beijing Peoples R China

ISBN: (纸本)9781728191423

The cyclic air braking strategy on the long steep downward slopes is one of the main challenges to the heavy haul train control in China. To overcome this dilemma, this paper proposes an optimization method of cyclic air braking strategy based on the approximate dynamic programming (ADP) algorithm which can achieve low maintenance costs and high running efficiency on the premise of safe operation. The optimization problem is described considering the characteristics of the heavy haul railways in China. Then the cyclic air braking strategy on the long steep downward slopes is formalized as a Markov decision process (MDP) and the critical elements in the ADP methodology are introduced according to the constraints and optimization objectives. Further, the value-iteration based ADP approach is proposed to solve the optimization problem of cyclic air braking strategy. The simulation experiments are carried out with the real-world data of the Shuohuang Line to illustrate the effectiveness of the proposed approach.

关键词： Heavy haul railway Cyclic air braking strategy approximate dynamic programming Driving strategy

来源：评论

学校读者我要写书评

暂无评论

Solving Finite-Horizon HJB for Optimal Control of Continuous-Time Systems

Solving Finite-Horizon HJB for Optimal Control of Continuous...

引用

International Conference on Computer, Control and Robotics (ICCCR)

作者： Lin, Ziyu Duan, Jingliang Li, Shengbo Eben Li, Jie Ma, Haitong Sun, Qi Chen, Jianyu Cheng, Bo Tsinghua Univ Sch Vehicle & Mobil Beijing Peoples R China Tsinghua Univ Inst Interdisciplinary Informat Sci Beijing Peoples R China

ISBN: (纸本)9781728190358

Hamilton-Jacobi-Bellman (HJB) equation is the sufficient and necessary condition for continuous-time optimal control problem (OCP). Different from HJB equation in infinite horizon, finite-horizon HJB equation contains a time-dependent value function, whose partial derivative with respect to time is an intractable unknown term. My study has found that the partial derivative exactly equals the terminal-time utility function by analyzing the initial-time equivalency between fixed time horizon OCP and fixed terminal time OCP. We also provide another proof, which uses the definition of partial derivative. This finding allows reusing traditional approximate dynamic programming (ADP) algorithm to approximate optimal policy with a parameterized function like neural network, thus solving the continuous-time finite-horizon OCP. The correctness of our finding is evaluated by analyzing a linear quadratic problem.

关键词： finite-horizon HJB equation approximate dynamic programming continuous-time optimal control

来源：评论

学校读者我要写书评

暂无评论

Solving the Top-percentile traffic routing problem by approximate dynamic programming

引用

IMA JOURNAL OF MANAGEMENT MATHEMATICS 2012年第4期23卷 413-434页

作者： Yang, Xinan Grothey, Andreas Univ Edinburgh Coll Sci & Engn Sch Math Operat Res & Optimizat Grp Edinburgh EH9 3JZ Midlothian Scotland

Internet Service Providers (ISPs) have the ability to route their traffic over different network providers. This study investigates the optimal routing strategy under multihoming in the case where network providers charge ISPs according to top-percentile pricing (i.e. based on the theta th highest volume of traffic shipped). We call this problem the Top-percentile Traffic Routing Problem (TpTRP). The TpTRP is a multistage stochastic optimization problem. Routing decision for every time period should be made before knowing the amount of traffic that is to be sent. The stochastic nature of the problem forms the critical difficulty of this study. Solution approaches based on Stochastic Integer programming or Stochastic dynamic programming (SDP) suffer from the curse of dimensionality, which restricts their applicability. To overcome this, we suggest to use approximate dynamic programming, which exploits the structure of the problem to construct continuous approximations of the value functions in SDP. Thus, the curse of dimensionality is largely avoided.

关键词： top-percentile pricing multihoming stochastic routing policy approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A Real-time Energy Management Strategy of HEVs Based on Velocity Prediction 60

A Real-time Energy Management Strategy of HEVs Based on Velo...

引用

60th Annual Conference of the Society-of-Instrument-and-Control-Engineers-of-Japan (SICE)

作者： Wei, Zeyi Zhang, Yahui Yanshan Univ Coll Mech Engn Qinhuangdao Peoples R China

ISBN: (纸本)9784907764739

This paper proposes an energy management strategy (EMS) for connected power-split hybrid electric vehicles (HEVs). In detail, long short-term memory networks (LSTM) is used to predict the future velocity trajectory for a few seconds of the preceding vehicle by utilizing the information provided by vehicle to vehicle (V2V) and vehicle to infrastructure (V2I). Then consumption of fuel and electricity are chosen as the cost function of the optimization. And model predictive control (MPC) approach is adopted to optimize the cost function. In order to solve the problem of dimension explosion, the cost-to-go function is optimized through approximate dynamic programming (ADP). Finally, the effectiveness of EMS is verified on the platform of MATLAB/Simulink.

关键词： Energy management strategy hybrid electric vehicles long short-term memory networks fuel economy approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Managing Fragmented Fire-Threatened Landscapes with Spatial Externalities

引用

FOREST SCIENCE 2020年第4期66卷 443-456页

作者： Lauer, Christopher J. Montgomery, Claire A. Dietterich, Thomas G. NOAA 1315 East West Highway Silver Spring MD 20910 USA Oregon State Univ Forest Engn Resources & Management 280 Peary Hall Corvallis OR 97331 USA Oregon State Univ Elect Engn & Comp Sci 1148 Kelley Engn Ctr Corvallis OR 97331 USA

Accounting for externalities generated by fire spread is necessary for managing fire risk on landscapes with multiple owners. In this paper, we determine the optimal management of a synthetic landscape parameterized to represent the ecological conditions of Douglas-fir (Pseudotsuga menziesii) plantations in southwest Oregon. The problem is formulated as a dynamic game, where each agent maximizes their own objective without considering the welfare of the other agents. We demonstrate a method for incorporating spatial information and externalities into a dynamic optimization process. A machine-learning technique, approximate dynamic programming, is applied to determine the optimal timing and location of fuel treatments and timber harvests for each agent. The value functions we estimate explicitly account for the spatial interactions that generate fire risk. They provide a way to model the expected benefits, costs, and externalities associated with management actions that have uncertain consequences in multiple locations. The method we demonstrate is applied to analyze the effect of landscape fragmentation on landowner welfare and ecological outcomes. Study Implications: This research builds on several important ideas for forest management. Fire risk for any particular stand on a landscape is a function of vegetation conditions across the entire landscape. Landowners who wish to achieve a management objective that is affected by fire risk need to account for the risk generated by broader landscape conditions. This work expands on a tractable model to account for the spatial interactions generated by fire spread that affect the optimal timing and spatial location of timber harvest and fuel treatments. In this paper, we demonstrate that optimal behavior changes when there are multiple landowners. On a sufficiently fragmented landscape, one landowner's actions can create additional risk for their neighbors. This work suggests that policy interventions to incentivize risk

关键词： wildland fire stochastic dynamic games spatial ecological disturbance risk approximate dynamic programming multiagent reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimal stochastic dynamic scheduling for managing community recovery from natural hazards

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2020年 193卷 106627-000页

作者： Nozhati, Saeed Sarkale, Yugandhar Chong, Edwin K. P. Ellingwood, Bruce R. Colorado State Univ Dept Civil & Environm Engn Ft Collins CO 80523 USA Colorado State Univ Dept Elect & Comp Engn Ft Collins CO 80523 USA Colorado State Univ Dept Math Ft Collins CO 80523 USA

Following the occurrence of an extreme natural or man-made event, community recovery management should aim at providing optimal restoration policies for a community over a planning horizon. Calculating such optimal restoration policies in the presence of uncertainty poses significant challenges for community leaders. Stochastic scheduling for several interdependent infrastructure systems is a difficult control problem with huge decision spaces. The Markov decision process (MDP)-based optimization approach proposed in this study incorporates different sources of uncertainties to compute the restoration policies. The computation of optimal scheduling presented herein employs the rollout algorithm, which provides an effective computational tool for optimization problems dealing with real-world large-scale networks and communities. The proposed methodology is applied to a realistic community recovery problem, where different decision-making objectives are considered. The approach accommodates current restoration strategies employed in recovery management;computational results indicate that the restoration policies identified herein significantly outperform the current recovery strategies. Finally, the applicability of the method to address different risk attitudes of policymakers, which include risk-neutral and risk-averse attitudes in the community recovery management, is examined.

关键词： approximate dynamic programming Community-level decision making Community recovery management Markov decision process Optimization Rollout

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：