电力线通信系统中基于改进NSGA-II的自适应资源分配

 分析电力线通信系统在各种约束下,多用户多业务在多子载波上自适应资源分配的多层多目标模型。基于快速的非支配分类遗传算法II,提出改进的功率或速率自适应的资源分配多目标和单目标优化遗传算法。在使用多目标遗传算法获得实时用户资源分配的所有Pareto非劣解后,由每个Pareto解计算系统的剩余资源,再采用单目标遗传算法把剩余资源分给非实时用户,最后从所有的资源分配方案中寻找全局最优方案。在典型电力线信道环境下仿真结果表明,本文算法其性能更好且能更好地满足多用户资源分配的多目标要求。     

基于改进遗传算法的油田配电网无功优化

遗传算法是一种模拟生物进化过程的优化算法,可用来求解包含离散化变量的复杂优化问题。将遗传算法应用于油田配电网无功优化,并对常规遗传算法的编码方式、遗传算子以及终止判据等方面进行改进,提高了计算效率和全局寻优能力。通过对油田配电网的分析和计算,结果表明该改进遗传算法应用于油田无功优化是合理可行的,其优化效果优于传统遗传算法。     

基于BP算法的信息化厂商评价模型研究

信息化厂商质量评价是供电企业信息系统运维的重要工作,其中关键的一项就是对信息化厂商质量进行分析评估,这对于信息系统运行可靠具有重要意义。将遗传算法神经网络原理引入信息化厂商质量评价领域,构建了基于遗传算法和神经网络的信息化厂商质量评价模型,为供电企业的信息化厂商质量评估研究提供模型和方法的支撑。实证结果表明,模型具有较强的自组织、自学习和自适应能力,模型评估结果比较客观合理。     

An online power allocation algorithm based on deep reinforcement learning in multibeam satellite systems

Dynamic power allocation (DPA) is the key technique to improve the system throughput by matching the offered capacity with that required among distributed beams in multibeam satellite systems. Existing power allocation studies tend to adopt the metaheuristic optimization algorithms such as the genetic algorithm. The achieved DPA cannot adapt to the dynamic environments due to the varying traffic demands and the channel conditions. To solve this problem, an online algorithm named deep reinforcement learning‐based dynamic power allocation (DRL‐DPA) algorithm is proposed in this paper. The key idea of the proposed DRL‐DPA lies in the online power allocation decision making other than the offline way of the traditional metaheuristic methods. Simulation results show that the proposed DRL‐DPA algorithm can improve the system performance in terms of system throughput and power consumption in multibeam satellite systems.     

MIMO系统一种新的功率分配算法及容量分析

在不额外增加发射功率和带宽消耗的情况下,注水功率分配算法能够获得最大的多输入多输出(MIMO)系统容量.基于拉格朗日乘数法,推导给出了MIMO系统注水功率分配算法的显式解.利用信道冲激响应矩阵的奇异值分解(SVD)算法,推导给出了注水功率分配算法MIMO系统的容量分析公式.利用数字波束形成(DBF)技术,提出了一种新的功率分配算法,推导给出了该算法MIMO系统的容量分析公式.仿真结果表明,提出的功率分配算法的系统容量虽然略低于注水功率分配算法的系统容量,但它的计算复杂度较低.     

基于免疫克隆算法的最优M序列搜索

二相编码脉冲压缩信号例如巴克码和M序列已经广泛应用于现代雷达系统中。二相编码波形设计中初始移位寄存器的选择是个关键技术，它直接决定了信号波形在满足最小峰值功率下能否具有最大脉压比。基于免疫学中的抗体克隆选择，提出了用免疫克隆算法（ICSA）来搜索M序列最优初始移位寄存器值。与标准遗传算法（SGA）和一种混合遗传算法（HGA）相比，文中提出的方法有效地战胜了早熟现象，得到了更优的搜索结果。实验结果证明了此算法的可行性和有效性。     

Test Generation Algorithm for Linear Systems Based on Genetic Algorithm

This paper proposes a test generation algorithm combining genetic algorithm for fault diagnosis on linear systems. Most test generation algorithms just used a single value fault model. This test generation algorithm is based on a continuous fault model. This algorithm can improve the treatment of the tolerance problem, including the tolerances of both normal and fault parameters, and enhance the fault coverage rate. The genetic algorithm can be used to choose the characteristic values. The genetic algorithm can enhance precision of test generation algorithm especially for complex fitness functions derived from complex systems under test. The genetic algorithm can also further improve the fault coverage rate by reducing the loop number of divisions of the initial fault range. The experiments are carried out to show this test generation algorithm with a linear system and an integrated circuit.     

Multistate series-parallel system expansion-scheduling subject toavailability constraints

This paper addresses the multistage expansion problem for multistate series-parallel systems. The study period is divided into several stages. At each stage the demand distribution is predicted in the form of a cumulative demand curve. The additional elements chosen from a list of available products can be included into any system-component at any stage to increase the total system capacity and/or reliability. Each element is characterized by its capacity (productivity), availability, and cost. The objective is to minimize the sum of costs of the investments over the study period while satisfying reliability constraints at each stage. To solve the problem, a genetic algorithm is used as an optimization tool. The solution encoding technique allows the genetic algorithm to manipulate integer strings representing multistage expansion planes. A solution quality index comprises both reliability and cost estimations. The procedure based on the universal generating function is used for evaluating the availability of multistate series-parallel systems. An example illustrates finding the optimal expansion plan for a coal-transportation system of a power station     

PMGA and its application in area and power optimization for ternary FPRM circuit

Based on the research of population migration algorithms (PMAs), a population migration genetic algorithm (PMGA) is proposed, combining a PMA with a genetic algorithm. A scheme of area and power optimization for a ternary FPRM circuit is proposed by using the PMGA. Firstly, according to the ternary FPRM logic function expression, area and power estimation models are established. Secondly, the PMGA is used to search for the best area and power polarity. Finally, 10 MCNC Benchmark circuits are used to verify the effectiveness of the proposed method. The results show that the ternary FPRM circuits optimized by the PMGA saved 13.33% area and 20.00% power on average than the corresponding FPRM circuits optimized by a whole annealing genetic algorithm.     

基于改进序列模式挖掘算法的告警关联模型

在电力故障发生时,会产生大量的电力故障告警信息数据,如何从电力故障告警信息中挖掘出可靠的关联规则,对后续电力的调度运维有着重要的影响。广义序列模式（Generalized Sequential Pattern,GSP）算法通过增加时间上的约束条件提高算法的效率,适合应用于电力故障告警信息挖掘的场景。针对GSP算法中的关键参数多和不同的参数组合影响算法的准确性和可靠性的问题,将遗传算法与GSP算法相结合,自适应地得到一组较好的参数,将参数代入GSP算法,从而得到更加可靠的关联规则,以此来解决在电力故障告警信息应用中很难为不同的数据集找到合适的参数组合的问题。通过实例验证,电力故障告警信息数据应用遗传算法结合GSP算法能够有效地得到更加准确和可靠的计算结果。     

基于改进遗传算法的配电网无功优化研究

有效降低配电网有功损失是配电网安全、经济运行的重要课题。为解决局部地区网损偏大的问题,文中将改进的遗传算法用于无功补偿优化。在考虑配电网拓扑结构的同时,设计了自适应遗传算子并构造了指数型适应度函数来提升遗传算法收敛速度和精度,充分发挥了遗传算法的全局随机快速搜索能力。优化某16节点算例的结果表明,配电网有功网损由6.76%下降到5.16%,电压达标率从70.61%提高到92.86%,表明该方法能够提高全局寻优精度,改善区域网络电压质量,同时也证明了该改进遗传算法用于无功优化的可行性和实用性。     

一种新的智能天线波束形成算法

在DS/CDMA系统中采用智能天线技术可以增加系统的容量,提高抗干扰性能.智能天线技术的核心是波束形成算法,基于遗传算法提出了一种新的智能天线波束形成算法,算法采用了内插和外推两种交叉算子,克服了遗传算法的早熟收敛问题,提高了全局收敛能力.研究结果表明,提出的智能天线波束形成算法具有良好的收敛性和稳定性,可用于DS/CDMA系统抵抗干扰的影响.     

Signal optimization for UWB radio systems

This paper presents and studies three frequency-domain models for optimizing source pulses and detection templates in ultrawide-band (UWB) radio systems. The optimization aims mainly at maximizing the equivalent isotropically radiated power band efficiency in the free space and the output of correlation detection at a receiver. These models are based on the differential evolution, an improved version of the genetic algorithm, and carried out on a set of UWB signals with given mathematical forms. As examples, these models are used to optimize the UWB signals for both narrow-band thin-wire and wide-band planar antenna systems. In addition, the optimized results are validated by nonoptimization simulation.     

应用于负荷经济分配的改进差分进化算法

为了求解电力系统负荷经济分配问题,提出一种改进差分进化算法.该算法考虑机组的爬坡约束、出力限制区约束等非光滑费用函数曲线等非线性特性,采用词典排序法处理系统约束来保证算法结果严格满足约束条件,保证了系统的稳定性和安全性.在差分进化算法的交叉算子计算中引入微粒群算法中的个体最优和全局最优的概念,并采用遗传微粒群算法的多点交叉机制,将两者以一定的比率引入试验向量增强算法的局部搜索能力.此算法被应用于一个6台机组的算例,与遗传算法、微粒群算法和标准差分进化算法相比较,改进的差分进化算法的结果质量更好并且更稳定,是求解负荷经济分配问题的一种有效方法.     

基于情感神经网络的风电功率预测

风力发电功率预测对于风能并网具有重要意义.采用一种可用于复杂系统和模式建模的新型神经网络——情感神经网络,对风力发电功率进行预测.为防止ENN在训练时陷入局部最优解,提出采用遗传算法对其进行训练.采用预测误差的均方根和标准差衡量预测准确性、稳定性,对ENN性能进行了检验.结果表明,相比于人工神经网络、支持向量机和自滑动回归模型,ENN能够获得更高的预测准确率和预测可靠性.     

一种基于改进遗传算法的风光互补移动基站智能供电系统设计

针对移动基站面广量大,机房几乎无人值守,系统成本高等问题,以吐鲁番地区实际应用环境为背景,研究并设计了一种基于改进遗传算法的风光互补移动基站智能供电系统。首先,对风光互补移动基站智能供电系统进行了软硬件设计,支持远程智能控制;然后,为了解决成本最优和计算效率问题,将传统遗传算法和粒子群算法相结合,提出了基于粒子群算法的改进遗传算法,对系统优化配置,从而在满足负荷用电的前提下,使系统寿命周期成本显著降低,同时计算效率提高。实验结果表明,所设计的系统工作性能稳定可靠,系统成本降低可在吐鲁番地区及类似地域无人值守的移动通信基站中推广使用。     

Second-order power control with asymptotically fast convergence

This paper proposes a distributed power control algorithm that uses power levels of both current and previous iterations for power update. The algorithm is developed by applying the successive overrelaxation method to the power control problem. The gain from such a second-order algorithm is in faster convergence. Convergence analysis of the algorithm in case of feasible systems is provided in this paper. Using the distributed constrained power control (DCPC) as a reference algorithm, we carried out computational experiments on a DS-CDMA system. The results indicate that our algorithm significantly enhances the convergence speed of power control. A practical version of the proposed algorithm is provided and compared with the bang-bang type algorithm used in the IS-95 and the WCDMA systems. The results show that our algorithm also has a high potential for increasing the radio network capacity. Our analysis assumes that the system is feasible in the sense that we can support every active user by an optimal power control. When the system becomes infeasible because of high traffic load, it calls for other actions such as transmitter removal, which is beyond the scope of the present paper     

基于模糊进程因子的改进自适应遗传算法

首先提出了一种改进自适应遗传算法,在本算法中引入模糊进程因子,设置了最佳样本保留数、最佳基因保留数等五个可调参数,使它们随着模糊进程因子的变化而变化,从而实现算法自适应;然后给出了新算法的步骤,并用标准测试函数对该算法进行了测试,测试结果表明:该算法具有较好的在线性能,提高了收敛速度;最后,用该新算法进行了功率谱估计,该算法比LS法具有更好的谱分辨率和适应性。     

基于PSO-GA算法的多用户OFDM系统资源分配

为了最小化多用户OFDM系统的总发射功率,提出利用改进的粒子群算法与遗传算法相结合的联合算法(PSO-GA)来搜索最优的子载波和比特分配。该算法首先利用改进粒子群算法对系统的子载波和比特分配进行优化。算法运行过程中,当更新后的粒子速度大于最大粒子速度或小于最小粒子速度时,取最大粒子速度与最小粒子速度区间中的一个随机值作为更新的粒子速度。待PSO-GA算法的改进粒子群算法收敛后,将收敛后的种群作为遗传算法的初始种群,再利用遗传算法进行系统的子载波和比特优化分配,进而得出最优解。仿真结果表明,利用该算法比利用遗传算法、粒子群算法与Zhang算法的分配方案使系统需要的总发射功率降低2~10 dB。     

一个新的分散定步长功率控制算法

功率控制是CDMA蜂窝移动通信系统的关键技术之一。该文考虑CDMA蜂窝移动系统,在假设系统信道增益时变、有界的情形下,把一个时变系统功率控制问题转化为具有确定信道增益功率控制问题。提出了一个分散定步长反馈调节功率控制算法,并证明了算法的收敛性。仿真结果表明算法是可行的。