检索结果-内蒙古大学图书馆

Embedding a state space model into a Markov decision process

ANNALS OF OPERATIONS RESEARCH 2011年第1期190卷 289-309页

作者： Nielsen, Lars Relund Jorgensen, Erik Hojsgaard, Soren Univ Aarhus Dept Genet & Biotechnol Fac Agr Sci Res Unit Bioinformat Genet & Stat DK-8830 Tjele Denmark

In agriculture Markov decision processes (MDPs) with finite state and action space are often used to model sequential decision making over time. For instance, states in the process represent possible levels of traits of the animal and transition probabilities are based on biological models estimated from data collected from the animal or herd. State space models (SSMs) are a general tool for modeling repeated measurements over time where the model parameters can evolve dynamically. In this paper we consider methods for embedding an SSM into an MDP with finite state and action space. Different ways of discretizing an SSM are discussed and methods for reducing the state space of the MDP are presented. An example from dairy production is given.

关键词： State space model Markov decision process Sequential decision making stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Inventory Management of Platelets in Hospitals: Optimal Inventory Policy for Perishable Products with Regular and Optional Expedited Replenishments

引用

M&SOM-MANUFACTURING & SERVICE OPERATIONS MANAGEMENT 2011年第4期13卷 420-438页

作者： Zhou, Deming Leung, Lawrence C. Pierskalla, William P. Chinese Univ Hong Kong Dept Decis Sci & Managerial Econ Shatin Hong Kong Peoples R China Univ Calif Los Angeles Anderson Sch Management Los Angeles CA 90095 USA

Platelets are short-life blood components used in hospital blood transfusion centers. Excluding time for transportation, testing, and arrangement, clinically transfusable platelets have a mere three-day life span. This paper analyzes a periodic review inventory system for such a perishable product under two replenishment modes. Regular orders are placed at the beginning of a cycle. Within the cycle, the manager has an option of placing an additional order, referred to as an expedited order, characterized by an order-up-to level policy. For this platelet inventory problem, we prove the existence and uniqueness of an optimal policy that minimizes the expected cost. We then derive the necessary and sufficient conditions for the policy, based on which an algorithm is developed. Using real-life data, we provide a numerical illustration and a sensitivity analysis followed by extensive simulation experiments to examine the dynamics of platelet inventory management. It is shown that the optimal cost is significantly affected by demand uncertainty, lead times, seasonality, and vintage of expedited orders. Given a hospital's demand profile and the cost parameters, we are able to determine whether the hospital should order daily or every other day (i.e., adopting a combined use of regular and optional expedited orders). We also show that the analytical solution is a good approximation of the optimal policy obtained from simulation experiments, where more realistic features are incorporated. This inventory research problem can be classified as a fixed-lifetime perishable problem with dual modes of replenishments.

关键词： perishable inventory management dual sourcing stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Fuzzy rule-based model for hydropower reservoirs operation

引用

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2011年第2期33卷 171-178页

作者： Moeini, R. Afshar, A. Afshar, M. H. Iran Univ Sci & Technol Sch Civil Engn Tehran Iran

Real-time hydropower reservoir operation is a continuous decision-making process of determining the water level of a reservoir or the volume of water released from it. The hydropower operation is usually based on operating policies and rules defined and decided upon in strategic planning. This paper presents a fuzzy rule-based model for the operation of hydropower reservoirs. The proposed fuzzy rule-based model presents a set of suitable operating rules for release from the reservoir based on ideal or target storage levels. The model operates on an 'if-then' principle, in which the 'if' is a vector of fuzzy premises and the 'then' is a vector of fuzzy consequences. In this paper, reservoir storage, inflow, and period are used as premises and the release as the consequence. The steps involved in the development of the model include, construction of membership functions for the inflow, storage and the release, formulation of fuzzy rules, implication, aggregation and defuzzification. The required knowledge bases for the formulation of the fuzzy rules is obtained form a stochastic dynamic programming (SDP) model with a steady state policy. The proposed model is applied to the hydropower operation of "Dez" reservoir in Iran and the results are presented and compared with those of the SDP model. The results indicate the ability of the method to solve hydropower reservoir operation problems. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Fuzzy rules-based model stochastic dynamic programming Hydropower reservoir operation

来源：评论

学校读者我要写书评

暂无评论

Suitability of short or long conservation contracts under ecological and socio-economic uncertainty

引用

ECOLOGICAL MODELLING 2011年第15期222卷 2856-2866页

作者： Lennox, Gareth D. Armsworth, Paul R. Univ Sheffield Dept Anim & Plant Sci Sheffield S10 2TN S Yorkshire England Univ Tennessee Dept Ecol & Evolutionary Biol Knoxville TN USA

Acquisition of land rights has become a primary tool used to protect terrestrial biodiversity. Fixed length contracts are often used when trying to secure conservation benefits on private land in agri-environment schemes and payment for environmental services schemes, but the duration of the conservation contracts used in different programmes varies. To date, very little research has been undertaken to determine the situations in which contracts of differing lengths are optimal or when conservation agencies or groups should use a portfolio of different contract lengths rather than relying on a single type. Using stochastic dynamic programming and related heuristic methods, we investigate how the choice between short or long conservation contracts is affected by uncertainty regarding the future availability of sites and their ecological condition. We also examine the benefits offered by using a portfolio of different contract lengths. Conservation agencies must pay private landowners a premium to secure longer agreements and because of this, shorter contracts are advantageous if sites are likely to remain available for conservation in the future. Long contracts are preferred when future site availability becomes more unlikely. In contrast to uncertainty over site availability, uncertainty over future ecological conditions has little effect on contract selection and only markedly influences the choice between short and long contracts when there is heterogeneity across sites in expected conservation outcomes and future availability of sites is also uncertain. Finally, when future site availability is unlikely, the use of a portfolio of short and long contracts would offer greater conservation gains than using either type in isolation, even though this option is not yet one that is commonly found in conservation practice. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Conservation contract stochastic dynamic programming Private land Site selection Agri-environment scheme Payment for environmental services

来源：评论

学校读者我要写书评

暂无评论

Discounted dynamic programming with unbounded returns: Application to economic models

引用

JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS 2011年第2期378卷 450-462页

作者： Jaskiewicz, Anna Nowak, Andrzej S. Wroclaw Univ Technol Inst Math & Comp Sci PL-50370 Wroclaw Poland Univ Zielona Gora Fac Math Comp Sci & Econometr PL-65246 Zielona Gora Poland

In this paper, we study discounted Markov decision processes on an uncountable state space. We allow a utility (reward) function to be unbounded both from above and below. A new feature in our approach is an easily verifiable rate of growth condition introduced for a positive part of the utility function. This assumption, in turn, enables us to prove the convergence of a value iteration algorithm to a solution to the Bellman equation. Moreover, by virtue of the optimality equation we show the existence of an optimal stationary policy. (C) 2010 Elsevier Inc. All rights reserved.

关键词： stochastic dynamic programming Bellman equation stochastic optimal growth

来源：评论

学校读者我要写书评

暂无评论

Optimal management of an ecosystem with an unknown threshold

引用

ECOLOGICAL ECONOMICS 2011年第4期70卷 627-640页

作者： Brozovic, Nicholas Schlenker, Wolfram Columbia Univ New York NY 10027 USA Univ Illinois Urbana IL 61801 USA NBER New York NY 10027 USA

We consider an ecosystem with two distinct equations of motion that are separated by a threshold value of the state variable. We find that increasing uncertainty (both uncertainty embedded in the natural system and uncertainty of the decisionmaker about the location of the threshold) can lead to nonmonotonic changes in precaution: a reduction in uncertainty can first increase and then decrease optimal precautionary activity. This nonmonotonicity can help to explain why regulators often give conflicting arguments about optimal abatement policies in the face of uncertainty. For example, some regulators argue for an immediate reduction in pollutant loading until uncertainty about the underlying process is reduced while others call for no costly reductions in pollutant loading until the same uncertainty is reduced. These statements can be consistent even if both sides agree on both economic objectives and the system dynamics, but have different priors on the uncertainty involved. (C) 2010 Elsevier B.V. All rights reserved.

关键词： Ecosystem management Threshold stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Managing and learning with multiple models: Objectives and optimization algorithms

引用

BIOLOGICAL CONSERVATION 2011年第4期144卷 1237-1245页

作者： Probert, William J. M. Hauser, Cindy E. McDonald-Madden, Eve Runge, Michael C. Baxter, Peter W. J. Possingham, Hugh P. Univ Queensland Ctr Appl Environm Decis Anal Sch Biol Sci St Lucia Qld 4069 Australia Univ Queensland Dept Math St Lucia Qld 4069 Australia Univ Melbourne Australian Ctr Excellence Risk Anal Parkville Vic 3010 Australia Univ Melbourne Ctr Appl Environm Decis Anal Sch Bot Parkville Vic 3010 Australia CSIRO Sustainable Ecosyst St Lucia Qld 4069 Australia US Geol Survey Patuxent Wildlife Res Ctr Laurel MD 20708 USA

The quality of environmental decisions should be gauged according to managers' objectives. Management objectives generally seek to maximize quantifiable measures of system benefit, for instance population growth rate. Reaching these goals often requires a certain degree of learning about the system. Learning can occur by using management action in combination with a monitoring system. Furthermore, actions can be chosen strategically to obtain specific kinds of information. Formal decision making tools can choose actions to favor such learning in two ways: implicitly via the optimization algorithm that is used when there is a management objective (for instance, when using adaptive management), or explicitly by quantifying knowledge and using it as the fundamental project objective, an approach new to conservation. This paper outlines three conservation project objectives - a pure management objective, a pure learning objective, and an objective that is a weighted mixture of these two. We use eight optimization algorithms to choose actions that meet project objectives and illustrate them in a simulated conservation project. The algorithms provide a taxonomy of decision making tools in conservation management when there is uncertainty surrounding competing models of system function. The algorithms build upon each other such that their differences are highlighted and practitioners may see where their decision making tools can be improved. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Adaptive management Conservation biology Decision theory Uncertainty Optimization stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Maintenance/production planning with interactive feedback of product quality

引用

JOURNAL OF QUALITY IN MAINTENANCE ENGINEERING 2011年第3期17卷 281-+页

作者： Njike, Achille N. Pellerin, Robert Kenne, Jean Pierre Ecol Polytech Montreal Dept Math & Ind Engn Montreal PQ Canada Ecole Technol Super Dept Mech Engn Montreal PQ Canada Ecole Technol Montreal Dept Math & Ind Engn Montreal PQ Canada

Purpose - This paper seeks to develop an optimal stochastic control model where interactive feedback consists of the quantity of flawless and defective products. The main objective of this study is to minimize the expected discounted overall cost due to maintenance activities, inventory holding and backlogs. Design/methodology/approach - The model differs from similar research projects in that, instead of age-dependent machine failure, it considers only defective products as feedback into the optimal model for maintenance and production planning. In this paper a near optimal control policy of the system through numerical techniques is obtained. Findings - In this paper, a new model in which the system's retroaction is the quantity of defective products is presented, considering that defective products are a consequence of global manufacturing system deterioration. Instead of taking into account machine failure and human error separately, it considers a defect in product as being the consequence of a combined failure;this consideration allows one to be more realistic by merging all failure parameters into a single one. A new stochastic control model, which focuses on defective products, inventory, and backlog, has been developed. Research limitations/implications - This approach extended the concept of hedging point policy to the quantity of defective products combined with preventive and corrective maintenance strategies. The control policy obtained has a bang bang structure and is completely known for given parameters. Originality/value - The integration of maintenance and production strategies has been mainly focused on the machine. Many research projects have been focusing on the age when dealing with machine failure. It is considered as the main target of the cost reduction in maintenance engineering departments. The originality of this paper is the taking into account of all operational failures into the same optimization model. It brings a value added to high

关键词： Maintenance Quality Manufacturing systems stochastic dynamic programming Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Forest management under fire risk when forest carbon sequestration has value

引用

ECOLOGICAL ECONOMICS 2011年第11期70卷 2002-2011页

作者： Couture, Stephane Reynaud, Arnaud INRA Unite Biometrie & Intelligence Artificielle F-31326 Castanet Tolosan France Univ Toulouse 1 TSE LERNA F-31042 Toulouse France

We develop a multiple forest use model to determine the optimal harvest date for a forest stand producing both timber and carbon benefits under a risk of fire. An empirical application is provided for a forest owner producing maritime pine in Southwest of France. Our results indicate that a higher risk of fire will decrease the optimal rotation period. On the contrary, higher carbon prices increase the optimal harvesting age. To investigate the contradictory effects of fire risk and carbon price on forest rotation, we identify the set of carbon prices and fire risks that lead to a given rotation age. We also show that forest owner's willingness to pay for a risk reduction can be substantial (37.33 euros by ha and by year to reduce the annual fire risk from 1.26% to 0.07%). (C) 2011 Elsevier B.V. All rights reserved.

关键词： Forest economics Carbon sequestration Fire risk Climate change stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Adaptive optimization of crop production and nitrogen leaching abatement under yield uncertainty

引用

AGRICULTURAL SYSTEMS 2011年第8期104卷 634-644页

作者： Hyytiainen, Karl Niemi, Jarkko K. Koikkalainen, Kauko Palosuo, Taru Salo, Tapio MTT Helsinki 00790 Finland MTT Jokioinen 31600 Finland

The study develops a bio-economic crop management model that internalizes the environmental cost of nitrate pollution, accounts for stochastic weather, and includes an option for split fertilization. The integrated model is designed to indicate whether a producer can benefit from applying fertilizer several times during the growing season, in response to crop needs, rather than a single time, at sowing. The model is parameterized for the cultivation of spring malting barley (Hordeum vulgare L) in Southern Finland. The costs of negative externalities from nitrogen leaching are internalized in the landowner's decision problem through a pollution tax. The results indicate that without a pollution tax a single application of fertilizer gauged to meet the needs of the entire season is optimal. With a tax, the benefits of split application - applying varying amounts of fertilizer at selected stages of the growing season - increase significantly. In comparison to a single application of fertilizer at sowing, split fertilization improves yields, increases the total amount of fertilizer used, and reduces nitrogen leaching. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Fertilization Nitrogen Leaching Pollution tax stochastic dynamic programming

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：