动态电源管理超时策略与随机型策略的等效关系

为了建立动态电源管理不同类型策略优化之间的联系,研究了超时策略与随机型策略在性能与功耗均衡上的等效关系.构建了动态电源管理系统基于半Markov控制过程的随机分析模型,通过分析该系统的稳态行为,揭示了超时策略和随机型策略在性能与功耗均衡上的等效性,推导出这2种策略之间的等效关系式;证明了超时策略具有最优的动态电源管理效果,并使得2种类型策略的优化结果能够相互转换.最后通过无线通信节点动态电源管理的数值仿真验证了这种等效关系.     

动态电源管理的在线优化技术

研究离散事件动态系统中的一类随机离散动态系统—–半Markov决策过程,在动态电源管理问题中的应用.动态电源管理问题存在于很多便携式电子设备中,其主要目的是根据电子设备的状态通过电源管理策略选择关闭或休眠一些元器件,从而实现节省电子设备功耗,延长电池使用时间的目的.首先讨论了动态电源管理问题的建模,给出了一种带有禁止时间的在线优化方法,该方法通过设备自身运行数据,自主地学习并改进电源的动态管理策略,从而使每台电子设备具有个性化的动态电源管理方式,其优化过程可以在设备充电时完成,不需要通过云传输和云计算,避免了隐私数据的泄漏.最后通过仿真实验验证了算法的有效性.     

动态电源管理的随机切换模型与在线优化

考虑系统参数未知情况下的动态电源管理问题,提出一种基于强化学习的在线策略优化算法. 通过建立事件驱动的随机切换分析模型,将动态电源管理问题转化为带约束的Markov 决策过程的策略优化问题. 利用此模型的动态结构特性,结合在线学习估计梯度与随机逼近改进策略,提出动态电源管理策略的在线优化算法．随机切换模型对电源管理系统的动态特性描述精确,在线优化算法自适应性强,运算量小,精度高,具有较高的实际应用价值．     

动态电源管理的随机切换模型与策略优化

提出一种基于连续时间Markov决策过程的动态电源管理策略优化方法.通过建立动态电源管理系统的随机切换模型,将动态电源管理问题转化为带约束的策略优化问题,并给出一种基于矢量合成的策略梯度优化算法.随机切换模型对动态电源管理系统的描述精确,策略优化算法简便有效,既能离线计算,也适用于在线优化.仿真实验验证了该方法的有效性.     

嵌入式系统中的电压自适应超时策略

针对电池供电系统放电过程中输出电压不恒定的特性,在临界电压区设计电压自适应超时策略。根据工作负载的变化情况,在线动态调整超时门限值,在?V(?t)值恒定情况下,通过改变?t(?V)值达到系统性能与电池寿命间的平衡,并扩展动态电压管理自适应对象的范畴。在嵌入式系统开发平台的应用结果表明,该策略在降低系统功耗的同时,能延长电池持续使用时间。     

BUCBAT自适应动态电源管理策略

结合电池放电特性,提出一种自适应超时动态电源管理策略BUCBAT。基于电池放电过程中电压逐渐降低的特性,BUCBAT根据电池放电电压的大小动态调整超时阙值;采用两块电池以特定频率轮流供电,充分利用电池放电电压的自恢复特性。实验结果表明,与超时策略相比,BUCBAT动态电源管理策略在兼顾系统QoS性能的同时,能够合理地管理系统功耗,从而延长系统的可持续工作时间。     

事件驱动的动态服务组合策略在线自适应优化

针对复杂应用环境中网络新媒体服务系统的特点,提出一种事件驱动的动态服务组合策略及其在线优化算法,在保证各类业务服务质量（QoS）的同时,提高系统资源的利用率．通过定义不同类型的事件,驱动服务组合的动态调整,实现对各类业务Qos的保障和对业务需求变化的感知．构建基于半Markov切换空间控制过程的系统分析模型,利用模型的动态结构特点,提出一种结合随机逼近和策略迭代的在线优化算法．该算法不依赖系统参数信息,对环境具有良好的自适应性．仿真实验结果验证了算法的有效性．     

一种基于活跃态的动态电源管理预测算法

提出一种基于活跃态的动态电源管理预测算法,充分利用了活跃态和空闲时间段的关系,并且加入动态自适应调节因子,不仅对较大变化的时间段预测误差小,而且能快速调整适应工作负载的变化.实验表明该算法优于传统算法.     

改进自适应学习树电源管理预测策略

为了降低嵌入式设备的功耗,研究了基于自适应学习树结构模型的动态电源管理预测策略.通过在基于概率自适应学习树结构模型的基础上添加空闲时间长度结点,提出了概率统计加权空闲时间的改进自适应学习树电源管理预测策略,以空闲时间长度作为预测依据,同时采用实际状态历史概率统计的结果进行预测空闲时间长度的更新.仿真结果表明,该方法可以有效地降低设备功耗,并且提高了预测准确率.     

Markov控制过程基于单个样本轨道的在线优化算法

在Markov性能势理论基础上, 研究了Markov控制过程的性能优化算法. 不同于传统的基于计算的方法, 文中的算法是根据单个样本轨道的仿真来估计性能指标关于策略参数的梯度, 以寻找最优 (或次优 )随机平稳策略. 由于可根据不同实际系统的特征来选择适当的算法参数, 因此它能满足不同实际工程系统在线优化的需要. 最后简要分析了这些算法在一个无限长的样本轨道上以概率 1的收敛性, 并给出了一个三 状态受控Markov过程的数值实例.     

Adaptive on-line steady-state optimization of slow dynamic processes

A software package OLIOPT was developed for the on-line optimization of the steady-state behaviour of slow dynamic processes in a relatively short time period. In the starting phase, the independently variable inputs are changed according to a special test signal. A nonlinear dynamic process model is identified on-line. Based on the static part of the model and the known inputs, the gradients of the performance index are calculated. An optimization algorithm changes the inputs towards their optimal values. On-line identification of the nonlinear model continues and the prediction of the optimum improves. In the last phase, the inputs take their optimal values and the process follows, feedforward controlled, to its optimal steady-state. The method is suited for industrial processes with one or more variable inputs, where a small gain in efficiency turns out to give a relatively large financial return. Results are shown for the on-line optimization of a thermal pilot process.     

动态功耗管理算法在ucLinux中的研究和实现

嵌入式产品体积的缩小和更长使用时间的要求,使嵌入式系统对功耗管理的要求越来越高.给出了一种实时功耗管理算法,对其功耗管理效果进行了研究和分析.详细描述了ucLinux中的功耗管理机制,并结合嵌入式系统的特点,对其进行了研究和改进.以此基础,在ucLinux中实现了动态功耗管理算法,给出了具体的功能实现描述,并验证了其效果.结果表明,这种方法起到了较好的功耗管理效果,实现了对嵌入式系统外设有效的功耗管理.     

On integral generalized policy iteration for continuous-time linear quadratic regulations

This paper mathematically analyzes the integral generalized policy iteration (I-GPI) algorithms applied to a class of continuous-time linear quadratic regulation (LQR) problems with the unknown system matrix A$A$. GPI is the general idea of interacting policy evaluation and policy improvement steps of policy iteration (PI), for computing the optimal policy. We first introduce the update horizon ?$?$, and then show that (i) all of the I-GPI methods with the same ?$?$ can be considered equivalent and that (ii) the value function approximated in the policy evaluation step monotonically converges to the exact one as ?→∞$?\to \infty$. This reveals the relation between the computational complexity and the update (or time) horizon of I-GPI as well as between I-PI and I-GPI in the limit ?→∞$?\to \infty$. We also provide and discuss two modes of convergence of I-GPI; I-GPI behaves like PI in one mode, and in the other mode, it performs like value iteration for discrete-time LQR and infinitesimal GPI (?→0$?\to 0$). From these results, a new classification of the integral reinforcement learning is formed with respect to ?$?$. Two matrix inequality conditions for stability, the region of local monotone convergence, and data-driven (adaptive) implementation methods are also provided with detailed discussion. Numerical simulations are carried out for verification and further investigations.     

Adaptive differential evolution algorithm for efficient reactive power management

This paper introduces a proposed procedure to solve the optimal reactive power management (ORPM) problem based on a multi-objective function using a modified differential evolution algorithm (MDEA). The proposed MDEA is investigated in order to enhance the voltage profile as well as to reduce the active power losses by solving the ORPM problem. The ORPM objective function aims to minimize transmission power losses and voltage deviation considering the system constraints. The MDEA aims to enhance the convergence characteristic of the differential evolution algorithm through updating the self-adaptive scaling factor, which can exchange information dynamically every generation. The scaling factor dynamically adopts the global and local searches to efficiently eliminate trapping in local optima. In addition, a strategy is developed to update the penalty factor for alleviating the effects of various system constraints. Numerical applications of different case studies are carried out on three standard IEEE systems, i.e., 14-bus, 30-bus and 57-bus test systems. Also, the proposed procedure is applied on Western Delta Network, which is a real part of the Egyptian main grid system. The flexibility of synchronous machines to provide controllable reactive power is proven with less dependency on the discrete reactive power controllers, such as installing the switchable devices and variations of tap changers. The obtained results show the effectiveness of the proposed enhanced optimization algorithm as an advanced optimization technique that was successively implemented with good performance characteristics.     

The optimal robust control policy for uncertain semi-Markov control processes

The optimization problems of Markov control processes (MCPs) with exact knowledge of system parameters, in the form of transition probabilities or infinitesimal transition rates, can be solved by using the concept of Markov performance potential which plays an important role in the sensitivity analysis of MCPs. In this paper, by using an equivalent infinitesimal generator, we first introduce a definition of discounted Poisson equations for semi-Markov control processes (SMCPs), which is similar to that for MCPs, and the performance potentials of SMCPs are defined as solution of the equation. Some related optimization techniques based on performance potentials for MCPs may be extended to the optimization of SMCPs if the system parameters are known with certainty. Unfortunately, exact values of the distributions of the sojourn times at some states or the transition probabilities of the embedded Markov chain for a large-scale SMCP are generally difficult or impossible to obtain, which leads to the uncertainty of the semi-Markov kernel, and thereby to the uncertainty of equivalent infinitesimal transition rates. Similar to the optimization of uncertain MCPs, a potential-based policy iteration method is proposed in this work to search for the optimal robust control policy for SMCPs with uncertain infinitesimal transition rates that are represented as compact sets. In addition, convergence of the algorithm is discussed.     

Fractional order fuzzy-PID control of a combined cycle power plant using Particle Swarm Optimization algorithm with an improved dynamic parameters selection

The effectiveness of the Particle Swarm Optimization (PSO) algorithm in solving any optimization problem is highly dependent on the right selection of tuning parameters. A better control parameter improves the flexibility and robustness of the algorithm. In this paper, a new PSO algorithm based on dynamic control parameters selection is presented in order to further enhance the algorithm's rate of convergence and the minimization of the fitness function. The powerful Dynamic PSO (DPSO) uses a new mechanism to dynamically select the best performing combinations of acceleration coefficients, inertia weight, and population size. A fractional order fuzzy-PID (fuzzy-FOPID) controller based on the DPSO algorithm is proposed to perform the optimization task of the controller gains and improve the performance of a single-shaft Combined Cycle Power Plant (CCPP). The proposed controller is used in speed control loop to improve the response during frequency drop or change in loading. The performance of the fuzzy-FOPID based DPSO is compared with those of the conventional PSO, Comprehensive Learning PSO (CLPSO), Heterogeneous CLPSO (HCLPSO), Genetic Algorithm (GA), Differential Evolution (DE), and Artificial Bee Colony (ABC) algorithm. The simulation results show the effectiveness and performance of the proposed method for frequency drop or change in loading.     

嵌入式系统动态数据结构优化的并行进化算法

为了更好地解决现代多媒体嵌入式系统动态数据结构优化问题,结合NSGA-II和SPEA2两个多目标进化算法,引入岛屿模型和多线程机制,提出了一种并行多目标进化算法--PMOEA-NS。基于多核计算机系统,使用PMOEA-NS具体的3个不同并行算法和串行NSGA-II、SPEA2,对一个实际动态嵌入式应用程序进行优化实验和计算,结果表明:与串行算法NSGA-II和SPEA2相比,并行算法不但提高了优化过程的速度,而且改善了解的质量和多样性。