检索结果-内蒙古大学图书馆

parallel dynamic programming on clusters of workstations

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED SYSTEMS 2005年第9期16卷 785-798页

作者： Canto, SD de Madrid, AP Bencomo, SD Univ Nacl Educ Distancia Dept Comp Sci & Automat Control Madrid 28040 Spain

The standard DP ( dynamic programming) algorithms are limited by the substantial computational demands they put on contemporary serial computers. In this work, the theory behind the solution to serial monadic dynamic programming problems highlights the theory and application of parallel dynamic programming on a general-purpose architecture ( Cluster or Network Of Workstations). A simple and well-known technique, message passing, is considered. Several parallel serial monadic DP algorithms are proposed, based on the parallelization in the state variables and the parallelization in the decision variables. Algorithms with no interpolation are also proposed. It is demonstrated how constraints introduce load unbalance which affect scalability and how this problem is inherent to DP.

关键词： parallel dynamic programming constrained optimization combinatorial algorithms networked workstations performance evaluation NOWs

来源：评论

学校读者我要写书评

暂无评论

parallel dynamic programming Based on Stage ReConstruction and its Application in Reservoir Operation 13

Parallel Dynamic Programming Based on Stage ReConstruction a...

引用

13th IEEE/ACIS International Conference on Computer and Information Science (ICIS)

作者： Zheng, Huitao Mei, Yadong Duan, Kai Lin, Yuru Wuhan Univ Wuhan Peoples R China Wuhan Donghu Dist Management Comm Wuhan Peoples R China Yangtze River Sci Res Inst Wuhan Peoples R China

ISBN: (纸本)9781479948604

dynamic programming is a classic method to solve reservoir optimized operation. However, with the increasing number of reservoir power stations, computation amount is increasing exponentially, resulting in a dramatic decrease in the timeliness of solving and even causing "curse of dimensionality". In response to this, we improved the serial recursion calculation process of dynamic programming and introduced parallel dynamic programming based on stage reconstruction. Through the proposed algorithm a multistage decision problem can be repeatedly reconstructed in a parallel environment and gradually transferred to a single stage issue. This algorithm was then applied to solve the optimized operation of cascade reservoirs in the lower reach of Yalong River in China. Analog computation was carried out to evaluate the effects of parameter control on the parallel calculation performance of the algorithm. Results indicate that the calculating efficiency, compared with serial dynamic programming, can be significantly improved without sacrificing the accuracy with parallel dynamic programming based on stage reconstruction.

关键词： parallel computing optimized operation of cascade reservoir parallel dynamic programming stage reconstruction

来源：评论

学校读者我要写书评

暂无评论

parallel dynamic programming based on stage reconstruction and its application in reservoir operation

引用

INTERNATIONAL JOURNAL OF NETWORKED AND DISTRIBUTED COMPUTING 2015年第1期3卷 31-41页

作者： Zheng, Huitao Mei, Yadong Duan, Kai Lin, Yuru Wuhan Univ State Key Lab Water Resources & Hydropower Engn S Donghunan Rd 8 Wuhan 430072 Hubei Peoples R China Yangtze River Sci Res Inst Wuhan 430010 Hubei Peoples R China

We improved the serial recursion calculation process of dynamic programming and introduced parallel dynamic programming based on stage reconstruction. Through the proposed algorithm a multistage decision problem can be repeatedly reconstructed and gradually transferred to a single stage issue. This algorithm was applied to solve the optimized operation of cascade reservoirs in the lower reach of Yalong River in China. Results indicate that the calculating efficiency, compared with serial dynamic programming, can be significantly improved without sacrificing accuracy.

关键词： parallel computing optimized operation of cascade reservoir parallel dynamic programming stage reconstruction

来源：评论

学校读者我要写书评

暂无评论

Asynchronous analysis of parallel dynamic programming algorithms

引用

IEEE TRANSACTIONS ON parallel AND DISTRIBUTED SYSTEMS 1996年第4期7卷 425-438页

作者： Lewandowski, G Condon, A Bach, E UNIV WISCONSIN MADISON WI 53706 USA

We examine a very simple asynchronous model of parallel computation that assumes the time to compute a task is random, following some probability distribution. The goal of this model is to capture the effects of unpredictable delays on processors, due to communication delays or cache misses, for example. Using techniques from queueing theory and occupancy problems, we use this model to analyze two parallel dynamic programming algorithms. We show that this model is simple to analyze and correctly predicts which algorithm will perform better in practice. The algorithms we consider are a pipeline algorithm, where each processor i computes in order the entries of rows i, i + p, and so on, where p is the number of processors;and a diagonal algorithm, where entries along each diagonal extending from the left to the top of the table are computed in turn. It is likely that the techniques used here can be useful in the analysis of other algorithms that use barriers or pipelining techniques.

关键词： parallel dynamic programming asynchronous algorithms parallel models of computation queueing theory analysis of algorithms

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Multidimensional parallel dynamic programming Algorithm for a Cascade Hydropower System

引用

WATER RESOURCES MANAGEMENT 2021年第9期35卷 2705-2721页

作者： Ma, Yufei Zhong, Ping-an Xu, Bin Zhu, Feilin Li, Jieyu Wang, Han Lu, Qingwen Hohai Univ Coll Hydrol & Water Resources 1 Xikang Rd Nanjing 210098 Peoples R China Nanjing Hydraul Res Inst State Key Lab Hydrol Water Resources & Hydraul En 223 Guangzhou Rd Nanjing 210029 Peoples R China

The joint optimal operation of cascade reservoir system can greatly improve the utilization of water resources. However, the complex high-dimensional and non-linear features and calculated costs often hinder the refined operation and management of reservoirs. Recently, the local parallel computing has become an effective way to alleviate the "curse of dimensionality". Current local parallel computing has hardware limitations, which is difficult to adapt to large-scale computing. This study proposes a novel parallel dynamic programming algorithm based on Spark (PDPoS) via cloud computing. The simulation experiments are carried out for a comparative analysis of the solution efficiency, influence factors and stability of cloud computing. The results are as follows: (1) The efficiency of the cloud-based PDPoS is related to some factors;the number of CPU cores is the main influencing factor, followed by the operator, and the architecture has the least influence. (2) The runtime variance of cloud computing is 2.03, indicating cloud computing has high stability. (3) Under the same configuration (i.e., CPU and memory), the runtime of cloud computing is 41.5% similar to 110.3% longer than that of physical machines. However, cloud computing has rich resources, good scalability, and good portability of online operations, which is an attractive alternative for optimal operation of large-scale reservoir system.

关键词： Hydropower system Joint operation Curse of dimensionality parallel dynamic programming Cloud computing Spark

来源：评论

学校读者我要写书评

暂无评论

Heuristics for work distribution of a homogeneous parallel dynamic programming scheme on heterogeneous systems

引用

parallel COMPUTING 2005年第7期31卷 711-735页

作者： Cuenca, J Giménez, D Martínez, JP Univ Murcia Dept Informat & Sistemas Murcia Spain Univ Murcia Dept Ingn & Tecnol Computadores Murcia Spain Univ Miguel Hernandez Dept Estadist & Matemat Aplicada Alicante Spain

in this paper the possibility of including automatic optimization techniques in the design of parallel dynamic programming algorithms in heterogeneous systems is analyzed. The main idea is to automatically approach the optimum values of a number of algorithmic parameters (number of processes, number of processors, processes per processor), and thus obtain low execution times. Hence, users could be provided with routines which execute efficiently, and independently of the experience of the user in heterogeneous computing and dynamic programming, and which can adapt automatically to a new network of processors or a new network configuration. (c) 2005 Elsevier B.V. All rights reserved.

关键词： auto-tuning heterogeneous computing parallel dynamic programming parameter optimization performance modelling scheduling load-balancing

来源：评论

学校读者我要写书评

暂无评论

Heuristics for work distribution of a homogeneous parallel dynamic programming scheme on heterogeneous systems

Heuristics for work distribution of a homogeneous parallel d...

引用

3rd International Symposium on parallel and Distributed Computing (ISPDC 2004)/3rd International Workshop on Algorithms, Models and Tools for parallel Computing on Heterogeneous Networks (HeteroPar 04)

ISBN: (纸本)0769522106

关键词： auto-tuning heterogeneous computing parallel dynamic programming parameter optimization performance modelling scheduling load-balancing

来源：评论

学校读者我要写书评

暂无评论

An efficient optimum energy management strategy using parallel dynamic programming for a hybrid train powered by Fuel-Cells and batteries

An efficient optimum energy management strategy using Parall...

引用

16th IEEE Vehicle Power and Propulsion Conference (VPPC)

作者： Peng, Hujun Li, Jianxiang Deng, Kai Thul, Andreas Li, Weihan Loewenstein, Lars Sauer, Dirk Uwe Hameyer, Kay Rhein Westfal TH Aachen Inst Elect Machines IEM Aachen Germany Rhein Westfal TH Aachen Inst Power Elect & Elect Drives ISEA ESS Aachen Germany Siemens Mobil GmbH Vienna Austria

ISBN: (纸本)9781728112497

A parallel dynamic programming algorithm, basing on the matrix calculation, is used to develop the optimum energy management strategy for a fuel cell and lithium-ion battery hybrid train. In this paper, besides the state of charge of the battery, the power from the fuel cell is defined as the other state variable. Then, the control variable is the power change rate in the fuel cell system. With the help of this problem formulation, an efficient parallel dynamic programming is easy to implement. The parallel calculation requires only one loop over the time stages. To make the parallel dynamic programming basing on the matriculated calculation successful, a semi-physical soft constraints mechanism is developed to initialize the cost function at the end time stage properly. With this parallel dynamic programming, the effect of a weighting factor between maximizing the fuel economy and avoiding high dynamic power change of fuel cell, on the total hydrogen consumption is investigated time efficiently.

关键词： fuel cell hybrid train optimum energy management parallel dynamic programming soft constraints fuel economy weighting factor

来源：评论

学校读者我要写书评

暂无评论

Optimal impoundment operation for cascade reservoirs coupling parallel dynamic programming with importance sampling and successive approximation

引用

ADVANCES IN WATER RESOURCES 2019年 131卷 103375-000页

作者： He, Shaokun Guo, Shenglian Chen, Kebing Deng, Lele Liao, Zhen Xiong, Feng Yin, Jiabo Wuhan Univ State Key Lab Water Resources & Hydropower Engn S Wuhan 430072 Hubei Peoples R China

The optimal impoundment operation of cascade reservoirs can dramatically improve the utilization of water resources. However, their complex non-convexity and computational costs pose challenges to optimal hydroelectricity output and limit further development of joint operation within larger-scale cascade reservoirs. In recent decades, parallel dynamic programming (PDP) has emerged as a means of alleviating the 'curse of dimensionally' in the mid-long term reservoir operation with more involved computing processors. But it still can't effectively solve the daily impoundment operation of more than three reservoirs. Here, we propose a novel method called importance sampling-PDP (IS-PDP) algorithm in which the merits of PDP are integrated with importance sampling and successive approximation strategy. Importance sampling is first used to construct the state vectors of each period by introducing 'Manhattan distance' in the discrete state space. Then the PDP recursive equation is used to find an improved solution during the iteration. The IS-PDP method is tested to optimize hydropower output for the joint operation of an 11-reservoir system located in the upper Yangtze River basin of China after establishing impoundment operation by advancing impoundment timings and rising water levels. We find that our methodology could effectively deal with the 'curse of dimensionally' for such mega reservoir systems and make better use of water resources in comparison to the Standard Operation Policy (SOP). Given its computational efficiency and robust convergence, the methodology is an attractive alternative for non-convex operation of large-scale cascade reservoirs.

关键词： Joint impoundment operation Cascade reservoir Curse of dimensionality parallel dynamic programming Importance sampling Successive approximation

来源：评论

学校读者我要写书评

暂无评论

Dataset for reservoir impoundment operation coupling parallel dynamic programming with importance sampling and successive approximation

引用

DATA IN BRIEF 2019年 26卷 104440-104440页

作者： He, Shaokun Guo, Shenglian Chen, Kebing Deng, Lele Liao, Zhen Xiong, Feng Yin, Jiabo Wuhan Univ State Key Lab Water Resources & Hydropower Engn S Wuhan 430072 Hubei Peoples R China

The dataset contains reservoir characteristic parameters, stream-flow series of reservoirs in the upper Yangtze River, the standard operating rules (SORs) and the seasonal top of buffer pools (seasonal TBPs) for these reservoirs, which were provided by the Yangtze River Commission. Moreover, annual hydropower of these reservoirs is tested to evaluate operation performance. These research materials are related to the research article in Advances in Water Resources, entitled 'Optimal impoundment operation for cascade reservoirs coupling parallel dynamic programming with importance sampling and successive approximation' (He et al., 2019). The dataset could be used to derive optimal operating rules to explore the potential benefits of water resources via our proposed algorithm (importance sampling - parallel dynamic programming, IS-PDP) in different runoff scenarios. It can also be further applied for water resources management and other potential users. (C) 2019 The Authors. Published by Elsevier Inc.

关键词： Cascade reservoirs Impoundment operation Yangtze river basin Streamflow observation parallel dynamic programming Importance sampling Seasonal top of buffer pools

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

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

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：