检索结果-内蒙古大学图书馆

13th IEEE International Conference on Signal Processing and Communication Systems (ICSPCS)

作者： Chen, Xiang Chen, Shuangwu Ullah, Amin Yu, Chaojie Yang, Jian Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China

ISBN: (纸本)9781728121949

Video streaming traffic over Internet has rapidly risen to be the main killer of network bandwidth. In order to accommodate the time-varying network conditions, Scalable video coding (SVC) provides a flexible way to transmit a video in different qualities and bit rates. Limited by current best-efforts Internet, video bitrate adaptivity can only conducted on the end side. Recently, the emerging software-defined networking (SDN) technology makes it possible to view the in-network states and control data forwarding. This motivates us to consider the SVC layer selection and multipath routing (video layers go along different path) jointly. The optimization problem is formulated as a Markov Decision Process (MDP) problem. To solve the issue of dimensionality disaster which is common in traditional MDP problem when the state space or action space is large, a kernel based feature extraction is used to transform state-action space to feature space with lower dimensionality. Based on the network features, we construct an approximate value function of long term reward via approximate dynamic programming (ADP) method. Then the optimal policy is derived directly by maximizing the value function. The experiment results show the proposed algorithm achieves a better video quality while keeping a higher convergence speed.

关键词： Scalable video coding Software defined networking Markov decision process approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Multiperiod Stochastic Resource Planning in Professional Services Organizations

引用

DECISION SCIENCES 2019年第6期50卷 1281-1318页

作者： Solomon, Stanislaus Li, Haitao Womer, Keith Santos, Cipriano Southern Illinois Univ Edwardsville Management & Mkt Dept Sch Business Edwardsville IL 62025 USA Univ Missouri St Louis Supply Chain & Analyt Dept Coll Business Adm St Louis MO 63121 USA Gurobi Optimizat Beaverton OR 97008 USA

Resource planning (RP) in a professional service organization matches workforce resources with project tasks while considering a myriad of factors such as skill requirements, service delivery role, skill type, workforce proficiency level, and geographical location. The multiperiod stochastic resource planning studied in this article extends the one-period deterministic resource planning by explicitly coping with both internal resource attrition and project demand uncertainty in a sequential decision-making framework. It allows resource managers to make effective use of their internal resources and identify the need to outsource to external contingent resources. We model the multiperiod stochastic resource planning as a Markov decision process and implement an approximate dynamic programming algorithm to obtain dynamic and adaptive solutions in reasonable computation times. A comprehensive computational study shows that our approximate dynamic programming algorithm achieves higher profitability and internal resource utilization compared to the rolling horizon approach used as a benchmark.

关键词： approximate dynamic programming Markov Decision Process Project Management Resource Planning Uncertainty Workforce Optimization

来源：评论

学校读者我要写书评

暂无评论

Learning nonlinear robust control as a data-driven zero-sum two-player game for an active suspension system

引用

IFAC-PapersOnLine 2020年第2期53卷 8057-8062页

作者： Mircea-Bogdan Radac Timotei Lala Department of Automation and Applied Informatics Politehnica University of Timisoara Bd. V. Parvan 2 RO-300223 Timisoara Romania

An optimal robust control data-driven learning solution is proposed for an active suspension system. The problem is formulated as a zero-sum two-player differential game (ZS-TP-DG), where the optimal control law and the worst-case disturbance control law must be searched for. The distinctive features of the proposed solution are: a Q-learning-like data-driven model-free (with unknown process dynamics) algorithm relying on collected input-state data from the process; neural networks being used as generic function approximators; validation on an active suspension system that is easily amenable to artificial road profile disturbance generation. The superiority of the ZS-TP-DG controller over another optimal controller learned in a disturbance-free context is validated and proven.

关键词： active suspension system hydraulic actuator neural networks optimal control approximate dynamic programming reinforcement learning two-player zero-sum games

来源：评论

学校读者我要写书评

暂无评论

approximate dynamic programming solutions with a single network adaptive critic for a class of nonlinear systems

引用

控制理论与应用（英文版） 2011年第3期9卷 370-380页

作者： S.N.BALAKRISHNAN Department of Mechanical and Aerospace Engineering Missouri University of Science and Technology

approximate dynamic programming(ADP) formulation implemented with an adaptive critic(AC)-based neural network(NN) structure has evolved as a powerful technique for solving the Hamilton-Jacobi-Bellman(HJB) *** interest in ADP and the AC solutions are escalating with time,there is a dire need to consider possible enabling factors for their implementations.A typical AC structure consists of two interacting NNs,which is computationally *** this paper,a new architecture,called the ’cost-function-based single network adaptive critic(J-SNAC)’ is presented,which eliminates one of the networks in a typical AC *** approach is applicable to a wide class of nonlinear systems in *** order to demonstrate the benefits and the control synthesis with the J-SNAC,two problems have been solved with the AC and the J-SNAC *** are presented,which show savings of about 50% of the computational costs by J-SNAC while having the same accuracy levels of the dual network structure in solving for optimal ***,convergence of the J-SNAC iterations,which reduces to a least-squares problem,is discussed;for linear systems,the iterative process is shown to reduce to solving the familiar algebraic Ricatti equation.

关键词： approximate dynamic programming Optimal control Nonlinear control Adaptive critic Cost-functionbased single network adaptive critic J-SNAC architecture

来源：评论

学校读者我要写书评

暂无评论

Beyond Biomass: Valuing Genetic Diversity in Natural Resource Management

引用

AMERICAN JOURNAL OF AGRICULTURAL ECONOMICS 2020年第2期102卷 607-624页

作者： Springborn, Michael R. Faig, Amanda Dedrick, Allison Baskett, Marissa L. Univ Calif Davis Dept Environm Sci & Policy Davis CA 95616 USA Univ Washington Sch Aquat Fisheries & Sci Seattle WA 98195 USA Natl Marine Fisheries Serv Alaska Fisheries Sci Ctr Seattle WA USA Ctr Ocean Solut Stanford CA USA

Strategies for increasing production of goods from working and natural systems have raised concerns that the diversity of species on which these services depend may be eroding. This loss of natural capital threatens to homogenize global food supplies and compromise the stability of human welfare. We assess the trade off between artificial augmentation of biomass and degradation of biodiversity underlying a populations' ability to adapt to shocks. Our application involves the augmentation of wild stocks of salmon. Practices in this system have generated warnings that genetic erosion may lead to a loss of the "portfolio effect" and the value of this loss is not accounted for in decision making. We construct an integrated bioeconomic model of salmon biomass and genetic diversity. Our results show how practices that homogenize natural systems can still generate positive returns. However, the substitution of more physical capital and labor for natural capital must be maintained for gains to persist, weakens the capacity for adaptation should this investment cease, and can cause substantial loss of population wildness. We apply an emerging optimization method-approximate dynamic programming-to solve the model without simplifying restrictions imposed previously.

关键词： approximate dynamic programming biodiversity dynamic optimization genetic erosion homogenization portfolio effect quantitative genetic-bioeconomic

来源：评论

学校读者我要写书评

暂无评论

CONTROLLED SEQUENTIAL MONTE CARLO

引用

ANNALS OF STATISTICS 2020年第5期48卷 2904-2929页

作者： Heng, Jeremy Bishop, Adrian N. Deligiannidis, George Doucet, Arnaud ESSEC Business Sch Cergy France CSIRO Canberra ACT Australia Univ Oxford Oxford England

Sequential Monte Carlo methods, also known as particle methods, are a popular set of techniques for approximating high-dimensional probability distributions and their normalizing constants. These methods have found numerous applications in statistics and related fields;for example, for inference in nonlinear non-Gaussian state space models, and in complex static models. Like many Monte Carlo sampling schemes, they rely on proposal distributions which crucially impact their performance. We introduce here a class of controlled sequential Monte Carlo algorithms, where the proposal distributions are determined by approximating the solution to an associated optimal control problem using an iterative scheme. This method builds upon a number of existing algorithms in econometrics, physics and statistics for inference in state space models, and generalizes these methods so as to accommodate complex static models. We provide a theoretical analysis concerning the fluctuation and stability of this methodology that also provides insight into the properties of related algorithms. We demonstrate significant gains over state-of-the-art methods at a fixed computational complexity on a variety of applications.

关键词： State space models annealed importance sampling normalizing constants optimal control approximate dynamic programming reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal Control via Continuous-Time Q-Learning for Unknown Nonlinear Affine Systems 58

Adaptive Optimal Control via Continuous-Time Q-Learning for ...

引用

58th IEEE Conference on Decision and Control (CDC)

作者： Chen, Anthony Siming Herrmann, Guido Univ Bristol Dept Mech Engn Bristol BS8 1QU Avon England Univ Manchester Dept Elect & Elect Engn Manchester M13 9PL Lancs England

ISBN: (数字)9781728113982

ISBN: (纸本)9781728113982

This paper proposes two novel adaptive optimal control algorithms for continuous-time nonlinear affine systems based on reinforcement learning: i) generalised policy iteration (GPI) and ii) Q-learning. As a result, the a priori knowledge of the system drift f(x) is not needed via GPI, which gives us a partially model-free and online solution. We then for the first time extend the idea of Q-learning to the nonlinear continuous time optimal control problem in a noniterative manner. This leads to a completely model-free method where neither the system drift f(x) nor the input gain g(x) is needed. For both methods, the adaptive critic and actor are continuously and simultaneously updating each other without iterative steps, which effectively avoids the hybrid structure and the need for an initial stabilising control policy. Moreover, finite-time convergence is guaranteed by using a sliding mode technique in the new adaptive approach, where the persistent excitation (PE) condition can be directly verified online. We also prove the overall Lyapunov stability and demonstrate the effectiveness of the proposed algorithms using numerical examples.

关键词： adaptive optimal control Q-learning non-linear systems reinforcement learning approximate dynamic programming adaptive critic

来源：评论

学校读者我要写书评

暂无评论

A proactive transfer policy for critical patient flow management

引用

HEALTH CARE MANAGEMENT SCIENCE 2019年第2期22卷 287-303页

作者： Gonzalez, Jaime Ferrer, Juan-Carlos Cataldo, Alejandro Rojas, Luis Pontificia Univ Catolica Chile Sch Engn Vicuna Mackenna 4860 Santiago Chile Pontificia Univ Catolica Chile Sch Med Libertador Bernardo OHiggins 340 Santiago Chile

Hospital emergency departments are often overcrowded, resulting in long wait times and a public perception of poor attention. Delays in transferring patients needing further treatment increases emergency department congestion, has negative impacts on their health and may increase their mortality rates. A model built around a Markov decision process is proposed to improve the efficiency of patient flows between the emergency department and other hospital units. With each day divided into time periods, the formulation estimates bed demand for the next period as the basis for determining a proactive rather than reactive transfer decision policy. Due to the high dimensionality of the optimization problem involved, an approximate dynamic programming approach is used to derive an approximation of the optimal decision policy, which indicates that a certain number of beds should be kept free in the different units as a function of the next period demand estimate. Testing the model on two instances of different sizes demonstrates that the optimal number of patient transfers between units changes when the emergency patient arrival rate for transfer to other units changes at a single unit, but remains stable if the change is proportionally the same for all units. In a simulation using real data for a hospital in Chile, significant improvements are achieved by the model in key emergency department performance indicators such as patient wait times (reduction higher than 50%), patient capacity (21% increase) and queue abandonment (from 7% down to less than 1%).

关键词： Markov decision process approximate dynamic programming Emergency department Critical care beds Patient flow

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Home Appliances Scheduling Considering Customer Thermal Discomfort: A Multistep Look-ahead ADP-Based Approach

Multiobjective Home Appliances Scheduling Considering Custom...

引用

IEEE Milan PowerTech Conference

作者： Jeddi, Babak Mishra, Yateendra Ledwich, Gerard Queensland Univ Technol QUT Sch Elect Engn & Comp Sci Brisbane Qld Australia

ISBN: (纸本)9781538647226

This paper proposes a multiobjective home energy management unit (MO-HEMU) to balance the electricity payment and thermal discomfort of a household by properly scheduling devices in a time-varying price environment. The thermal discomfort is measured by the deviation of indoor and hot water temperature from the user's ideal temperature. The home devices include solar Photovoltaics, a battery storage system, deferrable, and thermal appliances. The proposed MO-HEMU is formulated as a dynamic program and a method based on the approximated dynamic programming is used as the scheduling algorithm. The developed method, called multistep look-ahead algorithm, is an iterative algorithm that overcomes the curse of dimensionality of the exact DP by choosing a decision based on a limited number of stages ahead. The effectiveness of the proposed model is investigated through numerical simulations. The proposed MO-HEMU enables customers to find the desired trade-off between electricity payment and a discomfort level.

关键词： Appliances scheduling approximate dynamic programming home energy management multiobjective optimization thermal discomfort

来源：评论

学校读者我要写书评

暂无评论

Strategic Location and Dispatch Management of Assets in a Military Medical Evacuation Enterprise

Strategic Location and Dispatch Management of Assets in a Mi...

引用

作者： Phillip R. Jenkins Air University

学位级别：博士

This dissertation considers the importance of optimizing deployed military med- ical evacuation (MEDEVAC) systems and utilizes operations research techniques to develop models that allow military medical planners to analyze different strategies regarding the management of MEDEVAC assets in a deployed environment. For op- timization models relating to selected subproblems of the MEDEVAC enterprise, the work herein leverages integer programming, multi-objective optimization, Markov de- cision processes (MDPs), approximate dynamic programming (ADP), and machine learning, as appropriate, to identify relevant insights for aerial MEDEVAC operations. This research is conducted in the form of three related research components: the first component develops models for optimal MEDEVAC location within an enterprise of assets, whereas the second and third components seek optimal MEDEVAC dis- patching policies for a set of established assets via a sequence of models of increasing operational complexity and corresponding solution methods. Determining where to locate mobile aeromedical staging facilities (MASFs) as well as identifying how many aeromedical helicopters to allocate to each MASF, commonly referred to as the MEDEVAC location-allocation problem, is vital to the success of a deployed MEDEVAC system. An integer mathematical programming formulation is developed to determine the location and allocation of MEDEVAC as- sets over the phases of a military deployment to support operations ranging from peacekeeping through combat to post-combat resolution. The model seeks to address the multi-objective problem of maximizing the total expected coverage of demand as a measure of solution effectiveness, minimizing the maximum number of located MASFs in any deployment phase as a measure of solution efficiency, and minimizing the total number of MASF relocations throughout the deployment as a measure of solution robustness. Moreover, the model utilizes the ε-constraint Method to assess

关键词： Military medical evacuation (MEDEVAC) integer programming multi-objective optimization Markov decision process approximate dynamic programming machine learning

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：