检索结果-内蒙古大学图书馆

Structured threshold policies for dynamic sensor scheduling - A partially observed Markov decision process approach

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2007年第10期55卷 4938-4957页

作者： Krishnamurthy, Vikram Djonin, Dejan V. Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada Univ British Columbia Dyaptive Syst Inc Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada

We consider the optimal sensor scheduling problem formulated as a partially observed Markov decision process (POMDP). Due to operational constraints, at each time instant, the scheduler can dynamically select one out of a finite number of sensors and record a noisy measurement of an underlying Markov chain. The aim is to compute the optimal measurement scheduling policy, so as to minimize a cost function comprising of estimation errors and measurement costs. The formulation results in a nonstandard POMDP that is nonlinear in the information state. We give sufficient conditions on the cost function, dynamics of the Markov chain and observation probabilities so that the optimal scheduling policy has a threshold structure with respect to a monotone likelihood ratio (MLR) ordering. As a result, the computational complexity of implementing the optimal scheduling policy is inexpensive. We then present stochastic approximation algorithms for estimating the best linear MLR order threshold policy.

关键词： bayesian filtering monotone likelihood ratio (MLR) ordering partially observed Markov decision processes (POMDPs) sensor scheduling stochastic approximation algorithms stochastic dynamic programming threshold policies

来源：评论

学校读者我要写书评

暂无评论

Can culling a threatened species increase its chance of persisting?

引用

ECOLOGICAL MODELLING 2007年第1期201卷 11-18页

作者： Bode, Michael Possingham, Hugh P. Univ Queensland Ctr Ecol St Lucia Qld 4072 Australia

Many interacting predator-prey populations have a natural tendency to exhibit persistent limit-cycles or damped oscillations, especially in the presence of environmental stochasticity. The restriction of populations into small conservation reserves reduces the scale of ecosystems, and can induce cycling in previously stable predator-prey relationships. During the course of these cycles, the abundance of both predator and prey regularly decrease to low levels. At these times, environmental and demographic stochasticity may cause the extinction of one of the populations. Could culling one or both species at critical times reduce their probability of extinction? we use stochastic dynamic programming to determine the optimal management strategy for oscillation-prone species pairs. Remarkably, if the interventions are enacted at the appropriate time, infrequent culling of a small number of individuals significantly reduces the probability of extinction of the predator. Our approach can be applied to many different ecosystems, and can incorporate more complex system dynamics without a significant increase in computational time. (c) 2006 Elsevier B.V. All rights reserved.

关键词： predator-prey relationships stochastic dynamic programming culling optimal control

来源：评论

学校读者我要写书评

暂无评论

Minimise long-term loss or maximise short-term gain? Optimal translocation strategies for threatened species

引用

ECOLOGICAL MODELLING 2007年第1期201卷 67-74页

作者： Rout, T. M. Hauser, C. E. Possingham, H. P. Univ Queensland Ctr Ecol St Lucia Qld 4072 Australia

Translocation is a useful management option for conservation of threatened animal species. It can be used to increase the range of a species, augment the numbers in a critical population, or establish new populations and hence spread the risk of extinction through local catastrophes. As it is an important and expensive conservation tool, translocation management decisions must be carefully considered, with the objective of the translocation project in mind. By analysing the translocation problem within a decision-theory framework, we find optimal management decisions that are rational and transparent. We illustrate our approach using a case study of the bridled nailtail wallaby (Onychoyalea fraenata). Our particular translocation question is: if we have a set number of wallabies to translocate in each time period and two translocation sites, how many wallabies should we put at each site given the state of each population to maximise the benefit to the species? We model the translocated populations with first-order Markov chain stochastic population models, and use stochastic dynamic programming to determine the optimal management decisions. We look at two sites with different growth rates - one increasing and one decreasing - and compare the optimal strategies for two different objective functions. The first is a long-term persistence objective function, which maximises the persistence of translocated populations a large number of time steps after the end of the translocation program. The second maximises total population size at the end of the translocation program. Although these objective functions are similar, they generate surprisingly different optimal translocation strategies. When maximising the long-term persistence of the translocated populations, translocation decisions are not important as long as an increasing population is established. This indicates that site quality - rather than the number and timing of translocations - primarily determines the long

关键词： threatened and endangered species wildlife management translocation decision theory stochastic dynamic programming

来源：评论

学校读者我要写书评

暂无评论

dynamic reserve site selection under contagion risk of deforestation

引用

ECOLOGICAL MODELLING 2007年第1期201卷 75-81页

作者： Sabbadin, R. Spring, D. Rabier, C. -E. [a]INRA de Toulouse Unité de Biométrie et Intelligence Artificielle BP 52627-31326 Castanet-Tolosan Cedex Castanet-Tolosan France[b]Australian Centre for Biodiversity School of Biological Sciences PO Box 18 Monash University Clayton Vic. 3800 Australia

Recently, dynamic reserve site selection models based on stochastic dynamic programming (SDP) have been proposed. The models consider a random development pattern in which the probability that a site will be developed is independent of the development status of other sites. However, development often takes the form of a contagion process in which the sites most likely to be developed are near sites that already have been developed. To consider site selections in such cases, we propose improved algorithms that make use of a graph representation of the sites network. The first formulation is an exact, dynamic programming algorithm, with which theoretical and experimental complexities are evaluated. The exact method can be applied only to small problems (less than 10 sites), but real-world problems may have hundreds or thousands of sites, implying that heuristic selection methods must be used. We provide a general framework for describing such heuristic solution methods, and propose a new heuristic method based on a parameterised reinforcement learning algorithm. The method allows us to compute a heuristic function by performing and exploiting many simulations of the deforestation process. We show that the method can be applied to problems with hundreds of sites, and demonstrate experimentally that it outperforms previously proposed heuristic methods in terms of the average number of species conserved. [Copyright &y& Elsevier]

关键词： Reserve selection Uncertainty Contagion process stochastic dynamic programming Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A new approach to modelling, control and simulation of knowledgeable manufacturing cell

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2007年第17期45卷 3779-3808页

作者： Yan, H. S. Dong, H. Southeast Univ Res Inst Automat Nanjing 210096 Peoples R China

The running of the knowledgeable manufacturing cell (KMC) is a typical discrete event dynamic process. Methods used to model and analyse discrete event dynamic systems (DEDS) include Petri net and automata theory. In this paper, a new matrix-automaton is proposed to model the KMC and solve the task control problems existing in the KMC. The automaton is of structured property and can be used to analyse the dynamic performance of the KMC. stochastic dynamic programming is used to derive the optimal task control strategy of the automaton, and a simulation method and program are proposed to simulate the running of the KMC. The matrix-automaton model of an experimental KMC including m manufacturing agents and n classes of workpieces is built and solved by the methods in this paper. Compared with the random control principle, the objective function value of the control strategy in this paper is obviously lower, which testifies the validity and feasibility of the control strategy.

关键词： knowledgeable manufacturing cell matrix-automaton stochastic dynamic programming control strategy simulation

来源：评论

学校读者我要写书评

暂无评论

Mining and modeling for a metropolitan Atlanta ozone pollution decision-making framework

引用

IIE TRANSACTIONS 2007年第6期39卷 607-615页

作者： Yang, Zehua Chen, Victoria C. P. Chang, Michael E. Murphy, Terrence E. Tsai, Julia C. C. Univ Texas Dept Ind & Mfg Syst Engn Arlington TX 76019 USA Abbott Labs Irving TX 75038 USA Georgia Inst Technol Sch Earth & Atmospher Sci Atlanta GA 30332 USA Joy You Ind Corp Chicago IL 60610 USA

In this paper, we present a Decision-Making Framework (DMF) for reducing ozone pollution in the metropolitan Atlanta region. High ground-level concentrations of ozone continue to be a serious problem in several US cities, and Atlanta is one of the most serious of these cases. In contrast to the "trial and error" approach utilized by state government decision-makers, our DMF searches for dynamic and focused control strategies that require a lower total reduction of emissions than current control strategies. Our DMF utilizes a rigorous stochastic dynamic programming formulation and includes an Atmospheric Chemistry Module to represent how ozone concentrations change over time. This paper focuses on the procedures within the Atmospheric Chemistry Module. Using the US EPA's Urban Airshed Model for Atlanta, we use mining and metamodeling tools to develop a computationally efficient representation of the relevant ozone air chemistry. The proposed approach is able to effectively model changes in ozone concentrations over a 24-hour period.

关键词： data mining metamodeling decision-making ozone pollution stochastic dynamic programming urban airshed model

来源：评论

学校读者我要写书评

暂无评论

An alternative approach to the operation of multinational reservoir systems:: Application to the Amistad & Falcon system (Lower Rio Grande Rio Bravo)

引用

WATER RESOURCES MANAGEMENT 2007年第4期21卷 677-698页

作者： Serrat-Capdevila, Aleix Valdes, Juan B. Univ Arizona Dept Hydrol & Water Resources Tucson AZ 85721 USA Univ Arizona SAHRA Sustainabil Semiarid Hydrol & Riparian Area Tucson AZ 85721 USA Univ Arizona Dept Civil Engn & Engn Mech Tucson AZ 85721 USA

An optimization approach for the operation of international multi-reservoir systems is presented. The approach uses stochastic dynamic programming (SDP) algorithms - both steady-state and real-time - to develop two models. In the first model, the reservoirs and flows of the system are aggregated to yield an equivalent reservoir, and the obtained operating policies are disaggregated using a non-linear optimization procedure for each reservoir and for each nation's water balance. In the second model a multi-reservoir approach is applied, disaggregating the releases for each country's water share in each reservoir. The non-linear disaggregation algorithm uses SDP-derived operating policies as boundary conditions for a local time-step optimization. Finally, the performance of the different approaches and methods is compared. These models are applied to the Amistad-Falcon International Reservoir System as part of a binational dynamic modeling effort to develop a decision support system tool for a better management of the water resources in the Lower Rio Grande Basin, currently enduring a severe drought.

关键词： stochastic dynamic programming multinational reservoir systems multi-reservoir modeling approach country water budgets quantitative model comparison

来源：评论

学校读者我要写书评

暂无评论

Neuro-dynamic programming for designing water reservoir network management policies

引用

CONTROL ENGINEERING PRACTICE 2007年第8期15卷 1031-1038页

作者： Castelletti, A. de Rigo, D. Rizzoli, A. E. Soncini-Sessa, R. Weber, E. Politecn Milan Dipartimento Elettron & Informat I-20133 Milan Italy IDSIA CH-6928 Manno Lugano Switzerland

stochastic dynamic programming (SDP) can improve the management of a multipurpose water reservoir by generating management policies which are efficient with respect to the management objectives (flood protection, water supply for irrigation, hydropower generation, etc.). The improvement in efficiency is even more remarkable for networks of reservoirs. Unfortunately, SDP is affected by the well-known 'curse of dimensionality', i.e. computational time and computer memory occupation increase exponentially with the dimension of the problem (number of reservoirs), and the problem rapidly becomes intractable. Neuro-dynamic programming (NDP) can sensibly mitigate this limitation by approximating Bellman functions with artificial neural networks (ANNs). In this paper the application of NDP to the problem of the management of reservoir networks is introduced. Results obtained in a real-world case study are finally presented. (c) 2006 Elsevier Ltd. All rights reserved.

关键词： water reservoir network reservoir management stochastic dynamic programming neuro-dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Supply chain operations in the presence of a spot market:: a review with discussion

引用

JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY 2007年第11期58卷 1412-1429页

作者： Haksoz, C. Seshadri, S. City Univ London CASS Business Sch Fac Management London EC1Y 8TZ England NYU New York NY USA

We survey the recent literature on the use of spot market operations to manage procurement in supply chains. We present results in two categories: work that deals with optimal procurement strategies and work related to the valuation of procurement contracts. As an example of the latter, we provide new results on valuation of a supply contract with abandonment option. Based on our review, we also discuss the scope for doing further work.

关键词： supply chain contracts stochastic dynamic programming risk real options practice of OR

来源：评论

学校读者我要写书评

暂无评论

Take a risk: Preferring prevention over control of biological invaders

引用

ECOLOGICAL ECONOMICS 2007年第2期62卷 216-222页

作者： Finnoff, David Shogren, Jason F. Leung, Brian Lodge, David Univ Wyoming Dept Econ & Finance Dept 3985 Laramie WY 82071 USA McGill Univ Dept Biol Montreal PQ H3A 1B1 Canada McGill Univ Sch Environm Montreal PQ H3A 1B1 Canada Univ Notre Dame Dept Biol Sci Notre Dame IN 46556 USA

Scientists have argued that invasive species can be managed most cost effectively with greater investments in prevention. Further, under ideas like the precautionary principle it is reasonable to expect that a cautious manager would use more prevention relative to control because it keeps more invaders out. Yet, this is not typically done. In many cases, private and public resources are invested primarily to control existing invaders rather than to prevent new invasions. Managers frequently wait until after invaders have arrived and then scramble to limit the damages. We believe these paradoxical decisions can be understood by recognizing the link between typical human preferences for risk bearing and the technology of risk reduction. We demonstrate quantitatively how managers perceived to be cautious or averse to risk tend to shy away from prevention relative to control. This counterintuitive result arises because control is a safer choice than prevention because its productivity is relatively less risky: it works to remove existing invaders from the system. In contrast, the productivity of prevention is more uncertain because prevention only reduces the chance of invasion, it does not eliminate it, and invasion may not occur even in the absence of prevention. Managers' averse to risk will inherently avoid as much uncertainty as possible, whether the source of uncertainty regards ecological outcomes or economic productivity. implications for environmental decision making are clear. In invasive species management, if managers act as though they are risk averse, their caution can backfire when it leads to more control rather than prevention. The social consequences of this choice are a greater probability of future invasions and lower social welfare. Our results suggest that social welfare is highest when managers were willing to "take a risk" with prevention. (c) 2006 Elsevier B.V. All rights reserved.

关键词： biological invasions risk preferences 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：