检索结果-内蒙古大学图书馆

Shape Constraints in Economics and Operations Research

STATISTICAL SCIENCE 2018年第4期33卷 527-546页

作者： Johnson, Andrew L. Jiang, Daniel R. Texas A&M Univ Dept Ind & Syst Engn College Stn TX 77840 USA Osaka Univ Sch Informat Sci & Technol Suita Osaka 5650871 Japan Univ Pittsburgh Dept Ind Engn Pittsburgh PA 15261 USA

Shape constraints, motivated by either application-specific assumptions or existing theory, can be imposed during model estimation to restrict the feasible region of the parameters. Although such restrictions may not provide any benefits in an asymptotic analysis, they often improve finite sample performance of statistical estimators and the computational efficiency of finding near-optimal control policies. This paper briefly reviews an illustrative set of research utilizing shape constraints in the economics and operations research literature. We highlight the methodological innovations and applications, with a particular emphasis on utility functions, production economics and sequential decision making applications.

关键词： Shape constraints multivariate convex regression nonparametric regression production economics consumer preferences revealed preferences approximate dynamic programming reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automated Feature Synthesis From Relational Database For Data Science Related Problems 16

Automated Feature Synthesis From Relational Database For Dat...

引用

16th International Conference on Frontiers of Information Technology (FIT)

作者： Fatima, Afifa Khan, Faizan Ali Raza, Aneeq Kamran, Abdul Basit Sir Syed CASE Inst Technol Comp Sci Islamabad Pakistan

ISBN: (纸本)9781538693551

Feature Synthesis is the most important aspect of Data Science. This process requires domain knowledge of the data to produce meaningful features that support decision-making algorithms. The biggest technical obstacle which a data scientist must subdue is the synthesis of such features that would assist AI algorithms to predict the target variable with the least error. Feature synthesis is a crucial step toward the application of machine learning which consumes time and resources. Automated Feature Synthesis obviates the tedious task of data scientists. Data Science Machine and One Button Machine are pioneering researches that explored the possibility of feature synthesis from raw relational data by applying linear exploratory algorithms which increase the dimensionality of the feature matrix exponentially, and hence, they consume a lot of time and memory. Our research revolves around the process of feature synthesis from the structured and unstructured data types for relational data which will provide an effective automation of a hectic manual task for the non-experts consuming a reasonable amount of resources. We devised a solution to reduce the time complexity of the operation by reducing dimensionality while considering the target variable by using approximate dynamic programming. The model is designed utilizing the concept of sparse reward setting, and it tries to achieve maximum reward as it explores the feature set. The target variable plays its part to compute the reward eventually leading to an optimum feature set. This process reduces data exploration time, cost and effort for both data scientists and non-experts.

关键词： approximate dynamic programming Automated Feature Synthesis

来源：评论

学校读者我要写书评

暂无评论

ADP-based Home Energy Management System: A Case Study using DYNAMO

ADP-based Home Energy Management System: A Case Study using ...

引用

IEEE-Power-and-Energy-Society General Meeting (PESGM)

作者： Faqiry, M. N. Wang, L. Wu, H. Krishnamurthy, D. Palmintier, B. Kansas State Univ Dept Elect & Comp Engn Manhattan KS 66506 USA Natl Renewable Energy Lab Power Syst Engn Ctr Golden CO 80401 USA

ISBN: (纸本)9781538677032

This paper explores Home Energy Management System (HEMS) algorithms to minimize household cost while maintaining comfort when faced with uncertain weather, and demand. Specifically, we consider a HEMS that optimizes forward looking schedules for a home's heating, ventilation, and air conditioning (HVAC);water heater (WH);and electric vehicle (EV) charging while considering uncertainty in outside temperature, hot water usage, and non-controllable load (NCL). We adopt a dynamic programming (DP) formulation and utilize the dynamic programming for Adaptive Modeling and Optimization (DYNAMO) toolkit to implement DP and approximate dynamic programming (ADP) algorithms. Simulation results under a single tariff plan compare the quality of the solution generated by ADP to that of DP, and show significant improvement in computation time while maintaining acceptable solution accuracy.

关键词： approximate dynamic programming demand response electric vehicle home energy management system stochastic mixed-integer programming

来源：评论

学校读者我要写书评

暂无评论

The Military Inventory Routing Problem: Utilizing Heuristics Within a Least Squares Temporal Differences Algorithm to Solve a Multiclass Stochastic Inventory Routing Problem with Vehicle Loss

The Military Inventory Routing Problem: Utilizing Heuristics...

引用

作者： Ethan L. Salgado AIR FORCE INSTITUTE OF TECHNOLOGY

学位级别：博士

Military commanders currently resupply forward operating bases (FOBs) from a central location within an area of operations mainly via convoy operations in a way that closely resembles vendor managed inventory practices. Commanders must decide when and how much inventory to distribute throughout their area of operations while minimizing soldier risk. Technology currently exists that makes utilizing unmanned cargo aerial vehicles (CUAVs) for resupply an attractive alternative due to the dan– gers of utilizing convoy operations. Enemy actions in wartime environments pose a significant risk to a CUAV's ability to safely deliver supplies to a FOB. This dis– sertation develops a Markov decision process (MDP) model to examine this military inventory routing problem (MILIRP). The first paper examines the structure of the MILIRP by considering a small problem instance and prove value function monotonicity when a sufficient penalty is applied. Moreover, this paper develops a monotone least squares temporal differ– ences (MLSTD) algorithm that exploits this structure and demonstrate its efficacy for approximately solving this problem class. This work compares MLSTD to least squares temporal differences (LSTD), a similar ADP algorithm that does not ex– ploit monotonicity. MLSTD attains a 3.05% optimality gap for a baseline scenario and outperforms LSTD by 31.86% on average in our computational experiments. The second paper expands the problem complexity with additional FOBs. This work gen– erates two new algorithms, Index and Rollout, for the routing portion and implement an LSTD algorithm that utilized these to produce solutions 22% better than myopic generated solutions on average. The third paper greatly increases problem complex– ity with the addition of supply classes. This research formulates an MDP model to handle the increased complexity and implement our LSTD-Index and LSTD-Rollout algorithms to solve this larger problem instance and perform 21% better on average than

关键词： stochastic inventory routing approximate dynamic programming Markov decision process vendor managed inventory least squares temporal differences

来源：评论

学校读者我要写书评

暂无评论

Stochastic dynamic programming approach to managing power system uncertainty with distributed storage

引用

COMPUTATIONAL MANAGEMENT SCIENCE 2018年第1期15卷 87-110页

作者： Zephyr, Luckny Anderson, C. Lindsay Cornell Univ Dept Biol & Environm Engn Riley Robb Hall Ithaca NY 14853 USA

Wind integration in power grids is challenging because of the uncertain nature of wind speed. Forecasting errors may have costly consequences. Indeed, power might be purchased at highest prices to meet the load, and in case of surplus, power may be wasted. Energy storage may provide some recourse against the uncertainty of wind generation. Because of their sequential nature, in theory, power scheduling problems may be solved via stochastic dynamic programming. However, this scheme is limited to small networks by the so-called curse of dimensionality. This paper analyzes the management of a network composed of conventional power units and wind turbines through approximate dynamic programming, more precisely stochastic dual dynamic programming. A general power network model with ramping constraints on the conventional generators is considered. The approximate method is tested on several networks of different sizes. The numerical experiments also include comparisons with classical dynamic programming on a small network. The results show that the combination of approximation techniques enables to solve the problem in reasonable time.

关键词： Power grid management Energy storage Stochastic dynamic programming Stochastic dual dynamic programming approximate dynamic programming Generalized linear programming

来源：评论

学校读者我要写书评

暂无评论

Simulation-based approximate policy iteration for dynamic patient scheduling for radiation therapy

引用

HEALTH CARE MANAGEMENT SCIENCE 2018年第3期21卷 317-325页

作者： Gocgun, Yasin Istanbul Kemerburgaz Univ Dept Ind Engn Istanbul Turkey

We study radiation therapy scheduling problem where dynamically and stochastically arriving patients of different types are scheduled to future days. Unlike similar models in the literature, we consider cancellation of treatments. We formulate this dynamic multi-appointment patient scheduling problem as a Markov Decision Process (MDP). Since the MDP is intractable due to large state and action spaces, we employ a simulation-based approximate dynamic programming (ADP) approach to approximately solve our model. In particular, we develop Least-square based approximate policy iteration for solving our model. The performance of the ADP approach is compared with that of a myopic heuristic decision rule.

关键词： Patient scheduling Markov decision processes approximate dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning based finite-horizon optimal tracking control for nonlinear system

Deep reinforcement learning based finite-horizon optimal tra...

引用

Joint Meeting of the 2nd IFAC Workshop on Linear Parameter Varying Systems (LPVS) / 9th IFAC Symposium on Robust Control Design (ROCOND)

作者： Kim, Jong Woo Park, Byung Jun Yoo, Haeun Lee, Jay H. Lee, Jong Min Seoul Natl Univ Inst Chem Proc Sch Chem & Biol Engn 1 Gwanak Ro Seoul 08826 South Korea Korea Adv Inst Sci & Technol Chem & Biomol Engn Dept Daejeon 3041 South Korea

Reinforcement learning (RL) can be used to obtain an approximate numerical solution to the Hamilton-Jacobi-Bellman (HJB) equation. Recent advances in machine learning community enable the use of deep neural networks (DNNs) to approximate high-dimensional nonlinear functions as those that occur in RL, accurately without any domain knowledge. In the standard RL setting, both system and cost structures are unknown, and the amount of data needed to obtain an accurate approximation can be impractically large. Meanwhile, when the structures are known, they can be used to solve the HJB equation efficiently. Herein, the model based globalized dual heuristic programming (GDHP) is proposed, in which the HJB equation is separated into value, costate, and policy functions. A particular class of interest in this research is finite horizon optimal tracking control (FHOC) problem. Additional issues that arise, such as time-varying functions, terminal constraints, and delta-input formulation, are addressed in the context of FHOC. The DNN structure and training algorithm suitable for FHOC are presented. A benchmark continuous reactor example is provided to illustrate the proposed approach. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Reinforcement learning approximate dynamic programming Deep learning Globalized dual heuristic programming Optimal control Optimal tracking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Storage Operation for a Probabilistic Locational Marginal Pricing Forecast

Optimizing Storage Operation for a Probabilistic Locational ...

引用

IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)

作者： Latif, Aadil Krishnamurthy, Dheepak Palmintier, Brian Natl Renewable Energy Lab Golden CO 80401 USA

ISBN: (纸本)9781538635964

This paper explores the applicability of using dynamic programing (DP) and approximate dynamic programming (ADP) based methods for optimal dispatch of utility scale energy storage systems (ESS). In this study, the effectiveness of these approaches have been tested using the IEEE 13 node test feeder with distributed photovoltaics (PVs) and a utility scale storage system. In this work, a co-simulation based approach has been used to setup the experiment to be able to implement detailed ESS and network models. The results obtained from DP/ADP runs have been compared with three other control strategies both myopic and intelligent. Simulations results show that DP/ADP algorithms are a good candidate for optimal EES dispatch in terms of both solution quality and execution time.

关键词： energy storage dynamic programming approximate dynamic programming co-simulation

来源：评论

学校读者我要写书评

暂无评论

Optimal forward trading and battery control under renewable electricity generation

引用

JOURNAL OF BANKING & FINANCE 2018年 95卷 244-254页

作者： Hinz, Juri Yee, Jeremy Univ Technol Sydney Sch Math & Phys Sci Sydney NSW Australia CSIRO Canberra ACT Australia

The increased market penetration of renewable energy sources and the rapid development of electric battery storage technologies yield a potential for reducing electricity price volatility while maintaining stability of the power grid. This work presents an algorithmic approach to control battery levels and forward positions to optimally manage power output fluctuations caused by intermittent renewable energy generation. This paper will also explore the effect of battery technology on the firm's optimal trading behaviour in the electricity spot market. (C) 2017 Elsevier B.V. All rights reserved.

关键词： approximate dynamic programming Battery control Distributed energy systems Energy storage Forward contracts Real options

来源：评论

学校读者我要写书评

暂无评论

Optimal Trading of a Storable Commodity via Forward Markets

Optimal Trading of a Storable Commodity via Forward Markets

引用

作者： Behzad Ghafouri University of Western Ontario

学位级别：博士

A commodity market participant trading via her inventory has access to both spot and forward markets. To liquidate her inventory, she can sell at the spot price, take a short forward position, or do a combination of both. A trade is proposed in which there is always a hedging forward contract, which can be considered a dynamic cash and carry arbitrage. The trader can adjust the maturity of the forward contract dynamically until the inventory is depleted or a time constraint is reached. In the first setup, the storage contract (to carry inventory) is assumed to have a constant cost and a flexible duration. The risk and return characteristics of an approximate dynamic programming (ADP) and a Forward dynamic Optimization solution are compared. The trade is contrasted with optimal spot sale among other alternative liquidation strategies. Independent from the underlying stochastic forward price model, it is proved and verified numerically that a partial sale strategy is not optimal. The optimally selected forward maturities are limited to the subset comprising the immediate, next, and last timesteps. Under a more realistic storage contract, which assumes a stochastic cost and a fixed duration, a new ADP approach is developed. The optimal policy shows the tanker rent decision is accompanied by a buy order since the loss from an empty tanker is more than the gain of renting it cheaply yet early. Given the nonadjustable duration of the rent contract, a longer contract generates a higher value by benefiting from a tanker refill option.

关键词： Real Options Cash and Carry Arbitrage Oil Storage Forward Trading Markov Decision Process approximate dynamic programming Least Squares Monte Carlo

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：