针对热力站供热量与需求量不匹配的现象,提出一种基于深度确定性策略梯度(DDPG)的热力站一次侧优化控制方法。采用LSTM(long short term memory)算法对热力站进行建模,然后结合集中供热系统运行机理,使用DDPG控制算法对热力站一次侧供...针对热力站供热量与需求量不匹配的现象,提出一种基于深度确定性策略梯度(DDPG)的热力站一次侧优化控制方法。采用LSTM(long short term memory)算法对热力站进行建模,然后结合集中供热系统运行机理,使用DDPG控制算法对热力站一次侧供水流量序列求解。运用包头某热力站的大量历史工况数据,进行仿真实验,结果表明该方法的有效性,一定程度上实现了热力站的按需供热,提高热量的利用率。展开更多
In this paper,we focus on the compiling implementation of parallel logic language PARLOG and functional language ML on distributed memory multiprocessors.Under the graph rewriting framework, a Heterogeneous Parallel G...In this paper,we focus on the compiling implementation of parallel logic language PARLOG and functional language ML on distributed memory multiprocessors.Under the graph rewriting framework, a Heterogeneous Parallel Graph Rewriting Execution Model(HPGREM)is presented firstly.Then based on HPGREM,a parallel abstract machine PAM/TGR is described.Furthermore,several optimizing compilation schemes for executing declarative programs on transputer array are proposed. The performance statistics on a transputer array demonstrate the effectiveness of our model,parallel ab- stract machine,optimizing compilation strategies and compiler.展开更多
The knapsack problem is well known to be NP-complete. Due to its importance in cryptosystem and in number theory, in the past two decades, much effort has been made in order to find techniques that could lead to pract...The knapsack problem is well known to be NP-complete. Due to its importance in cryptosystem and in number theory, in the past two decades, much effort has been made in order to find techniques that could lead to practical algorithms with reasonable running time. This paper proposes a new parallel algorithm for the knapsack problem where the optimal merging algorithm is adopted. The proposed algorithm is based on anEREW-SIMD machine with shared memory. It is proved that the proposed algorithm is both optimal and the first without memory conflicts algorithm for the knapsack problem. The comparisons of algorithm performance show that it is an improvement over the past researches. Keywords knapsack problem - NP-complete - parallel algorithm - optimal algorithm - memory conflict Supported by the National Natural Science Foundation of China under Grant No.60273075, the National High Technology Development 863 Program of China under Grant No.863-306-ZD-11-01-06.Ken-Li Li received his B.S. and M.S. degrees in mathematics from National University of Defense Technology and Central South University in 1995 and 2000 respectively and he is now a Ph.D. candidate in computer software and theory at Huazhong University of Science and Technology. His main research interests include parallel computing and combinatorial optimization.Ren-Fa Li received his Ph.D. degree in computer software and theory at Huazhong University of Science and Technology, and he is concurrently a professor and Ph.D. supervisor in School of Computer and Communication, Human University. His main research interests include network computing.Qing-Hua Li received his M.S. degree in computer science from Huazhong University of Science and Technology in 1981, and he is concurrently a professor and Ph.D. supervisor in School of Computer Science and Technology, Huazhong University of Science and Technology. His current research interests include parallel processing, combinatorial optimization, and grid computing.展开更多
文摘针对热力站供热量与需求量不匹配的现象,提出一种基于深度确定性策略梯度(DDPG)的热力站一次侧优化控制方法。采用LSTM(long short term memory)算法对热力站进行建模,然后结合集中供热系统运行机理,使用DDPG控制算法对热力站一次侧供水流量序列求解。运用包头某热力站的大量历史工况数据,进行仿真实验,结果表明该方法的有效性,一定程度上实现了热力站的按需供热,提高热量的利用率。
基金This work was partially supported by the National 863 High Technical Grant 863-306-101the National Doctoral Subject Foundation Grant 0249136.
文摘In this paper,we focus on the compiling implementation of parallel logic language PARLOG and functional language ML on distributed memory multiprocessors.Under the graph rewriting framework, a Heterogeneous Parallel Graph Rewriting Execution Model(HPGREM)is presented firstly.Then based on HPGREM,a parallel abstract machine PAM/TGR is described.Furthermore,several optimizing compilation schemes for executing declarative programs on transputer array are proposed. The performance statistics on a transputer array demonstrate the effectiveness of our model,parallel ab- stract machine,optimizing compilation strategies and compiler.
文摘The knapsack problem is well known to be NP-complete. Due to its importance in cryptosystem and in number theory, in the past two decades, much effort has been made in order to find techniques that could lead to practical algorithms with reasonable running time. This paper proposes a new parallel algorithm for the knapsack problem where the optimal merging algorithm is adopted. The proposed algorithm is based on anEREW-SIMD machine with shared memory. It is proved that the proposed algorithm is both optimal and the first without memory conflicts algorithm for the knapsack problem. The comparisons of algorithm performance show that it is an improvement over the past researches. Keywords knapsack problem - NP-complete - parallel algorithm - optimal algorithm - memory conflict Supported by the National Natural Science Foundation of China under Grant No.60273075, the National High Technology Development 863 Program of China under Grant No.863-306-ZD-11-01-06.Ken-Li Li received his B.S. and M.S. degrees in mathematics from National University of Defense Technology and Central South University in 1995 and 2000 respectively and he is now a Ph.D. candidate in computer software and theory at Huazhong University of Science and Technology. His main research interests include parallel computing and combinatorial optimization.Ren-Fa Li received his Ph.D. degree in computer software and theory at Huazhong University of Science and Technology, and he is concurrently a professor and Ph.D. supervisor in School of Computer and Communication, Human University. His main research interests include network computing.Qing-Hua Li received his M.S. degree in computer science from Huazhong University of Science and Technology in 1981, and he is concurrently a professor and Ph.D. supervisor in School of Computer Science and Technology, Huazhong University of Science and Technology. His current research interests include parallel processing, combinatorial optimization, and grid computing.
