混合系统——智能技术的建成

将各种智能技术以集成是通向下一代智能技术的重要途径。本文介绍了某些混合技术，包括模糊神经网络、基于神经网络的遗传算法和模糊遗传算法，并简要地介绍了它们在电力系统中的应用。     

电力系统自动化与智能技术

自动控制从线性开环发展到闭环,使电力系统控制提高到了一个新的水平 。自从计算机的应用迅速发展以 来,电力系统控制更迈上了一个新台阶。近年来, 模糊技术、神经网络、演化遗传算法等技术的发展又开 拓了软计算即智能技术的新道路。 文中 结合1997年第15届欧洲智能技术会议上报道的最新研究成果,介绍 了模糊技术利用人们的经 验对控制技术的改进,着重介绍了模糊PID技术、神经模糊控制和多种智能技术。     

遗传模糊神经网络在交流伺服系统中的应用

为了满足交流伺服系统高精度、快响应的要求，提出了基于遗传算法的模糊神经网络控制方案。该方案把神经网络与模糊逻辑控制结合起来，采用遗传算法（GA）对模糊神经网络控制器中的参数进行搜索和优化，给出了设计方法和优化步骤。实验结果表明：该控制方法用于交流伺服系统，具有精度高、无超调、收敛性好以及较强的鲁棒性和抗干扰性等优点。     

模糊神经网络及其在电力系统中的应用研究

阐述了神经网络、模糊理论、模糊神经网络、遗传算法等分支的技术发展,优、缺点及它们相互之间的结合,接着论述了模糊神经网络在电力系统中电厂的过程控制、电力系统稳定器、励磁控制、重合闸、继电保护及灵活交流输电系统等领域的应用研究的现状及前景。     

模糊神经网络及其在电力系统中的应用研究

阐述了神经网络、模糊理论、模糊神经网络、遗传算法等分支的技术发展,优、缺点及它们相互之间的结合,接着论述了模糊神经网络在电力系统中电厂的过程控制、电力系统稳定器、励磁控制、重合闸、继电保护及灵活交流输电系统等领域的应用研究的现状及前景.     

基于遗传算法的模糊神经网络在动态系统辨识中的应用

复杂不规则系统的语言建模构成了许多控制／决策系统的核心问题,模糊逻辑是进行语言建模最有效的方法之一。本文介绍了一种基于模糊逻辑、神经网络和遗传算法的语言建模方法,并给出了新型的混合学习算法,即：首先由自组织算法确定出模糊神经网络的初始隶属度函数;其次由最大匹配因子学习算法完成模糊规则确定;最后提出了一种改进的遗传算法用来优化调节已经获得的隶属度函数。通过具体的仿真实例说明了所提出的建模方法在动态系     

基于递阶遗传算法优化的交通流预测

及时准确地进行短时交通流预测是智能交通系统研究的关键内容之一。基于小波分析和模糊神经网络的相关知识,本文提出模糊小波神经网络的控制方法。将小波函数作为模糊隶属函数,利用神经网络实现模糊推理,从而完成对下一周期交通流量的预测,同时采用递阶遗传算法实现网络结构和参数的优化。经实测数据验证,本文的方法预测精度高,运行稳定,适应性强。     

遗传算法在水轮发电机模糊神经网络励磁控制器设计中的应用研究

本文在分析了模糊神经网络(FNN)控制器的工作原理及设计方法的基础上,提出了一种采用遗传算法优化设计水轮发电机模糊神经网络励磁控制器的方法。其基本过程是利用遗传算法得到初始模糊控制规则,并对初始规则进行过滤,在此基础上利用遗传算法结合模拟退火对得到的模糊神经网络进行训练。仿真结果表明与根据专家经验获得模糊规则和BP算法进行学习的常规FNN比较,采用遗传算法优化设计的模糊神经网络励磁控制器所构成的励磁系统具有更好的动态性能。     

模糊神经网络在噪声消除中的应用

提出了一种基于改进模糊聚类算法的训练模糊神经网络的算法,该方法采用遗传算法改进传统的模糊聚类算法,并给出了一个衡量聚类有效性的函数以确定聚类算法中的聚类总数,从而确定模糊神经网络结构,仿结果表明神经网络可成功的应用于噪声消除。     

用遗传算法优化模糊控制器的隶属度参数

介绍了遗传算法的基本原理和执行步骤，并用遗传算法优化模糊控制器的隶属度参数，在倒立摆的仿真实验中取得了很好的结果。     

Review on application and comparison of metaheuristic techniques to multi-area economic dispatch problem

This paper presents both application and comparison of the metaheuristic techniques to multi-area economic dispatch (MAED) problem with tie line constraints considering transmission losses, multiple fuels, valve-point loading and prohibited operating zones. The metaheuristic techniques such as differential evolution, evolutionary programming, genetic algorithm and simulated annealing are applied to solve MAED problem. These metaheuristic techniques for MAED problem are evaluated on three different test systems, both small and large, involving varying degree of complexity and the results are compared against each other     

Optimal reactive power dispatch using self-adaptive real coded genetic algorithm

In this paper, self-adaptive real coded genetic algorithm (SARGA) is used as one of the techniques to solve optimal reactive power dispatch (ORPD) problem. The self-adaptation in real coded genetic algorithm (RGA) is introduced by applying the simulated binary crossover (SBX) operator. The binary tournament selection and polynomial mutation are also introduced in real coded genetic algorithm. The problem formulation involves continuous (generator voltages), discrete (transformer tap ratios) and binary (var sources) decision variables. The stochastic based SARGA approach can handle all types of decision variables and produce near optimal solutions. The IEEE 14- and 30-bus systems were used as test systems to demonstrate the applicability and efficiency of the proposed method. The performance of the proposed method is compared with evolutionary programming (EP) and previous approaches reported in the literature. The results show that SARGA solves the ORPD problem efficiently.     

Fuzzy Genetic Algorithm Approach for the Optimal Placement of Flexible AC Transmission Systems Devices in a Power System

Abstract—This article presents a novel approach for optimal flexible AC transmission systems devices planning in an interconnected power system under different loading conditions. The static VAR compensator and thyristor-controlled series capacitor are two types of flexible AC transmission systems devices considered for optimal power system operation. In the proposed approach, a fuzzy membership function is used to determine weak nodes in the power system for the placement of static VAR compensators as a flexible AC transmission systems device. The thyristor-controlled series capacitor is the other type of flexible AC transmission systems devices for which its positions are determined by the reactive power flow in lines. The genetic algorithm is used for the optimal setting of the power system variables, including flexible AC transmission systems devices. The proposed technique is compared with other optimization methods using different globally accepted evolutionary algorithms where the nodes or point of VAR compensation is determined by eigenvalue analysis, and the amount of flexible AC transmission systems devices is determined by evolutionary techniques, such as the genetic algorithm, differential evolution, and particle swarm optimization. The superiority of the proposed fuzzy-based optimization approach is established by the results and comparative analysis with other methods.     

Oppositional krill herd algorithm for optimal location of capacitor with reconfiguration in radial distribution system

The delivery of power from sources to the consumer points is always accompanied of power losses. Basically, active losses in distribution systems can be reduced by optimal reconfigurations of the network. Optimal capacitor allocation problem in reconfigured distribution network is a challenge of researchers for several decades. This paper presents a computationally efficient methodology namely, krill herd (KH) algorithm to find optimal location of capacitor and optimal reconfiguration in order to minimize real power loss of radial distribution systems. Moreover, the opposition based learning (OBL) concept is integrated with KH algorithm for improving the convergence speed and simulation results. In order to show the usefulness and supremacy, the conventional KH and proposed oppositional KH (OKH) algorithms are tested on 33-bus and 69-bus radial distribution networks. The simulation results of the proposed methods are compared with fuzzy multi-objective approach and non dominated sorting genetic algorithm (NSGA). The solution results show that OKH technique could generate better quality solutions and better convergence characteristics than those obtained by conventional KH algorithm and other existing optimization techniques available in the literature. Results also show the robustness of the proposed methodology to solve reconfigured distribution network (RDN) problems.     

基于混合神经网络和遗传算法的故障诊断系统

故障诊断对于事故后快速恢复具有重要意义。多种人工智能技术在其中得以应用, 然而快速、准确的故障诊断仍是一个悬而未决的难题, 尤其在保护和断路器不正常动作或多重故障的情况下, 故障诊断更为困难。提出了一种基于神经网络 (ANN) 和遗传算法 (GA) 的故障诊断方法, 它采用三层前向神经网络执行诊断功能, 双重 GA循环优化该神经网络的结构和连接权重。第一重 GA循环用于优化神经网络结构, 第二重 GA循环进一步优化神经网络的连接权重。两重 GA循环可以搜索确定用于故障诊断的最优神经网络。有关的数学模型和算法流程在文中作了详细介绍。以4-母线简单电力系统为例, 进行了计算机仿真计算。结果表明, 基于混合神经网络和遗传算法的故障诊断系统优于传统的BP神经网络, 可以较好地解决故障诊断问题。     

Parameter optimization of multimachine power system stabilizers using genetic local search

A genetic local search (GLS) algorithm for optimal design of multimachine power system stabilizers (PSSs) is presented in this paper. The proposed approach hybridizes the genetic algorithm (GA) with a heuristic local search in order to combine their strengths and overcome their shortcomings. The potential of the proposed approach for optimal parameter settings of the widely used conventional lead–lag PSSs has been investigated. Unlike the conventional optimization techniques, the proposed approach is robust to the initial guess. The performance of the proposed GLS-based PSS (GLSPSS) under different disturbances, loading conditions, and system configurations is investigated for different multimachine power systems. Eigenvalue analysis and simulation results show the effectiveness and robustness of the proposed GLSPSS to damp out local as well as interarea modes of oscillations and work effectively over a wide range of loading conditions and system configurations.     

Reactive power dispatch considering voltage stability with seeker optimization algorithm

Optimal reactive power dispatch (ORPD) has a growing impact on secure and economical operation of power systems. This issue is well known as a non-linear, multi-modal and multi-objective optimization problem where global optimization techniques are required in order to avoid local minima. In the last decades, computation intelligence-based techniques such as genetic algorithms (GAs), differential evolution (DE) algorithms and particle swarm optimization (PSO) algorithms, etc., have often been used for this aim. In this work, a seeker optimization algorithm (SOA) based method is proposed for ORPD considering static voltage stability and voltage deviation. The SOA is based on the concept of simulating the act of human searching where search direction is based on the empirical gradient by evaluating the response to the position changes and step length is based on uncertainty reasoning by using a simple Fuzzy rule. The algorithm's performance is studied with comparisons of two versions of GAs, three versions of DE algorithms and four versions of PSO algorithms on the IEEE 57 and 118-bus power systems. The simulation results show that the proposed approach performed better than the other listed algorithms and can be efficiently used for the ORPD problem.     

遗传算法在无功优化应用中的改进

将遗传算法应用于电力系统无功优化的同时,针对无功优化的实际,文章提出了在不同优化阶段,对目标函数各项罚因子采用不同权重,并且构造出分阶段适应性函数,以及提出了选择式杂交方式等改进措施。通过典型算例和实际系统的测试,证明了这些改进方法对遗传算法应用于无功优化计算的寻优速度和收敛特性都有明显提高。     

基于免疫遗传算法优化的神经网络配电网网损计算

提出了一种基于免疫遗传算法(IGA)的BP神经网络方法计算配电网的理论线损。该算法在遗传算法(GA)的基础上引入生物免疫系统中的多样性保持机制和抗体浓度调节机制,有效地克服了GA算法的搜索效率低、个体多样性差及早熟现象,提高了算法的收敛性能。为了解决BP神经网络权值随机初始化带来的问题,用多样性模拟退火算法(SAND)进行神经网络权值初始化,并给出了算法详细的设计步骤。仿真结果表明,同混合遗传算法相比,该算法设计的BP神经网络具有较快的收敛速度和较强的全局收敛性能, 比现有其它计算配电网理论线损的方法更为     

遗传算法搜索优化及其在机组启停中的应用

提出了一种遗传算法应用于机组启停的新思路。针对机组启停问题的特点,设计了一些启发式技术,使得遗传算法初始种群中的所有个体都是可行解。针对遗传操作生成的不可行解,建立了一种从不可行域到可行域的是映射关系,大大减少了搜索中的无效操作。对过度满足约束条件的解,给出了一种有效减冗余的手段。并提出了一种边界搜索方法,可以更容易得到更优的解。这些措施起到了优化搜索路径的作用,有效地提高了遗传算法求解的效率和质量。