共查询到19条相似文献,搜索用时 62 毫秒
1.
本文提出了一种改进的层划分算法.该算法充分考虑了划分块的最小执行延迟和尽可能充分利用可重构资源,能够跟踪层划分算法节点分配过程并进行调整,消除了经典层划分算法不能动态更新就绪节点列表选取节点进行划分的缺陷.实验结果表明,与层划分算法相比,所提出的改进层划分算法在模块数、执行延迟和跨模块间的I/O边数等三个方面均获得了改进.与现有的簇划分、增强静态列表、多目标时域划分、簇层次敏感等四种划分算法相比,新算法能获得最少的执行延迟,并且随着可重构处理单元面积的增大,模块数的均值也是最小的. 相似文献
2.
针对多约束下的行流水粗粒度可重构体系结构的硬件任务划分映射问题,提出了一种多目标优化映射算法.该算法根据运算节点执行时延、依赖度等因素构造了累加概率权值函数,在满足可重构单元面积和互连等约束下,通过该函数值动态调整就绪节点的映射调度次序,当一块可重构单元阵列当前行映射完毕后,就自动换行,当一块阵列被填满,就切换到下一块,当一个数据流图映射完毕后,就自动计算划分块数等参数.实验结果表明,与层贪婪映射算法相比,文中算法平均执行总周期降低了8.4%(RCA4×4)和5.3%(RCA6×6),与分裂压缩内核映射算法相比,文中算法平均执行总周期降低了20.6%(RCA4×4)和21.0%(RCA6×6),从而验证了文中提出算法的有效性. 相似文献
3.
4.
《电子技术与软件工程》2015,(16)
本文提出了一种用于解决约束多目标优化问题的方法。本算法在进化算法的基础上加入了邻里竞争与邻里合作算子,并通过引入agent-based模型的设计理念,更加注重个体变化对整个群体的影响。本算法首先使用约束偏离值的方法将约束多目标优化问题简化为多目标优化问题;然后使用自我更新算子,当新产生的个体优于原先的个体时予以替换;之后通过邻里竞争与邻里合作加快种群内部的信息交流;最后加入量子加速算子,通过使用量子旋转门来扩大计算搜寻范围提高程序计算速度。本文最后与两种已有算法进行对比,实验结果表明,本算法完成了设计目标。在运行时间和输出结果精度方面都有不错的表现。 相似文献
5.
6.
7.
8.
9.
针对杂波环境下多扩展目标量测集难以划分,且时间代价高的问题,该文引入近邻传播聚类技术,提出一种新的多扩展目标量测集划分算法.该算法先采用密度分析技术对量测集进行预处理,滤除部分杂波量测,然后引入近邻传播聚类技术,通过量测间的相互竞争,初步确定扩展目标的数目和质心位置,然后通过扩展目标PHD滤波方法估计目标数目和状态.该方法可有效避免量测集聚类过程中扩展目标质心初始化的干扰,能够准确地划分杂波环境下多扩展目标量测集.与传统的距离划分,K-means++划分方法相比,所提算法能够自适应地确定目标数目,降低时间成本,提高多扩展目标的跟踪性能. 相似文献
10.
为提高约束多目标优化问题所求解集的分布性和收敛性,该文提出基于自适应截断策略的约束多目标优化算法。首先,自适应截断选择策略能够保留Pareto最优解和约束违反度及目标函数值均较优的不可行解,不仅提高了种群多样性,而且能够较好地兼顾多样性和收敛性;其次,为增强算法的局部开发能力,在变异操作和交叉操作之后进行指数变异;最后,改进的拥挤密度估计方式只选择一部分Pareto最优解和距离较近的个体参与计算,不仅更加准确地反映解集的分布性,而且降低了计算量。通过在标准测试问题(CTP系列)上与其他4种优秀算法的对比结果可以得出,该算法所求解集的分布性和收敛性均得到一定提高,而且相较于对比算法在求解性能上具备一定的优势。 相似文献
11.
For the problem of coexistence of different resource utility objectives and mutual influence of resource selection strategies in the complex structure of software-defined network (SDN),an SDN based network resource selection multi-objective optimization algorithm was proposed.The optimization goals of resource providers and clients were taken into account in the algorithm,and a resource selection multi-objective optimization model was constructed.The model was further solved by the reference vector based multi-objective optimization algorithm.Simulation results show that compared with other algorithms,the proposed algorithm could quickly converge to the uniformly distributed non-inferior solution set,and balance the optimization objects of multi-party in SDN based resource access management. 相似文献
12.
Aiming at previous research primarily focused on constructing service paths with a single objective,for exam-ple,latency minimization,cost minimization or load balance,which ignored the overall performance of constructed ser-vice paths,a multi-objective service path constructing algorithm based on discrete particle swarm optimization (MOPSO) was proposed.To promote the convergence rate and improve constructing performance,the criterions for selecting can-didate physical nodes and paths were explored,and a particle position initialization and update strategy (PIFC) was de-signed.Simulation experiments show that the proposed algorithms can improve the overall quality of service paths and increase the success rate and long-term average revenue. 相似文献
13.
高效的调度方法促使云计算更快更好地服务,一般采用优化算法来解决云计算中的调度问题。将布谷鸟搜索(CS)和粒子群优化(PSO)两种算法相结合,提出多目标布谷鸟粒子群优化算法(MO-CPSO),主要目的是提高云计算的服务质量。使用Cloudsim仿真工具对MO-CPSO算法的性能进行了评估。仿真结果表明,与CS、ACO和Min-Min算法相比,MO-CPSO算法使makespan、开销和截止时间违背率均最小。 相似文献
14.
15.
密集异构网络(Dense Heterogeneous Network, DHN)通过部署小基站可以提升网络容量和用户速率,但小基站的密集部署会产生巨大的能耗和严重的干扰,进而影响系统的能量效率(Energy Efficiency, EE)和频谱效率(Spectral Efficiency, SE)。在保证用户服务质量(Quality of Service, QoS)需求的前提下,为了联合优化系统的能量效率和频谱效率,研究了密集异构网络中下行链路的资源分配(Resource Allocation, RA)问题。首先,将频谱和小基站发射功率分配问题建模为联合优化系统能量效率和频谱效率的多目标优化问题;其次,提出了基于单策略多目标强化学习(Single-strategy Multi-objective Reinforcement Learning, SMRL)的资源分配算法求解所建立的多目标优化问题。仿真结果表明,与基于单目标强化学习的资源分配算法相比,所提算法可以实现系统能量效率和频谱效率的联合优化,与基于群体智能算法的资源分配算法相比,所提算法的系统能量效率提高了1%~1.5%,频谱效率... 相似文献
16.
Most existing researches of resource allocation in data center did not take into full consideration how to decrease energy consumption.The energy efficiency virtual resource allocation for cloud computing as a multi-objective optimization problem was formulated,which was then solved by intelligent optimization algorithm.The simulation results reveal that the strategy can successfully generate schedule scheme of different numbers of servers-VM with diverse characteristics and decrease the total operating energy of data center effectively. 相似文献
17.
由于高光谱图像的丰度特性,盲源分离算法 不能直接用于高光谱图像解混。同时,在解混过程中用 梯度算法对目标函数进行优化时易陷入局部最优。为此,本文提出了一种基于多目标蝙蝠优 化算法的高光谱图 像解混算法。该算法将高光谱图像模型中存在的丰度非负约束及丰度和 为一约束作为解混的两个目标函数, 将解混问题转化为对目标函数的优化问题,同时引入多目标蝙蝠优化算法来求解,从而实现高光谱图像解 混。实验结果表明,本文算法能有效解决上述问题,并且当改变图像的信噪比 、像元纯度和像素数时,观察光 谱角距离与均方根误差值的变化情况,与其它解混算 法相比,本文算法具有更高的解混精度和很好的抗噪性,在像元纯度很低的情况下也有很好 的性能。 相似文献
18.
The Internet of Things (IoT) is a recent wireless telecommunications platform, which contains a set of sensor nodes linked by wireless sensor networks (WSNs). These approaches split the sensor nodes into clusters, in which each cluster consists of an exclusive cluster head (CH) node. The major scope of this task is to introduce a novel CH selection in WSN applicable to IoT using the self-adaptive meta-heuristic algorithm. This paper aids in providing the optimal routing in the network based on direct node (DN) selection, CH selection, and clone cluster head (CCH) selection. DNs are located near the base station, and it is chosen to avoid the load of CH. The adoption of the novel self-adaptive coyote optimization algorithm (SA-COA) is used for the DN selection and CCH selection. When the nodes are assigned in the network, DN and CCH selection is performed by the proposed SA-COA. Then, the computation of residual energy helps to select the CH, by correlating with the threshold energy. CCH is proposed to copy the data from the CH to avoid the loss of data in transmitting. By forming the CCH, the next CH can be easily elected with the optimal CCH using SA-COA. From the simulation findings, the best value of the designed SA-COA-LEACH model is secured at 1.14%, 3.17%, 1.18%, and 7.33% progressed than self-adaptive whale optimization algorithm (SAWOA), cyclic rider optimization algorithm (C-ROA), krill herd algorithm (KHA), and COA while taking several nodes 50. The proposed routing of sensor networks specifies better performance than the existing methods. 相似文献
19.
针对航天测控资源配置优化问题这类约束条件繁杂且数量众多的组合优化问题,提出了可用于资源动态预留的航天测控资源配置优化算法。具体来讲,考虑测控设备和航天器执行任务的唯一性约束以及时间窗口冲突约束,建立了基于原子型任务调度的0-1整数规划模型;设计了能将实际需求和求解算法进行解耦的求解框架,并基于最大化利用测控资源的思想获得了可回溯的并行最佳优先搜索算法。仿真结果表明,所提算法达到了能在国内东部、西部、南部和北部四大测控区域中更加均衡地动态预留出更多、更重要测控设备的资源配置优化效果。 相似文献