Development of peak load forecasting system using neural networks and fuzzy theory

This paper presents a peak load forecasting system using multilayer neural networks and fuzzy theory. Electric load forecasting in power systems is a very important task from the perspective of reliability and economic operation. Daily peak load forecasting is one of the basic operations of generation scheduling for the following day. Therefore, many statistical methods have been developed and used for such forecasting even though it has been difficult to construct a proper functional model. The developed system is applied by neural network and fuzzy theory to forecast for daily, weekly and monthly peak load. The system consists of an engineering workstation (EWS) and a personal computer (PC). The EWS is for learning and data-bases, and the PC is for man-machine interface such as forecasting operation. The system has been used since June 1993. The result evaluated with an absolute mean error is 1.63 percent for 10 months. From the results shown here, the system applied by neural network and fuzzy theory has high validity.     

Learning in dynamic neural networks using signal flow graphs

The paper presents the universal approach to the determination of the sensitivity functions for dynamic neural networks and its application in learning algorithms of adaptive networks. The method is based on the application of signal flow graph and specially defined graph adjoint to it. The method is equally applied to either feed‐forward or recurrent network structures. This paper is mainly concerned with neural network applications of the approach. Different kinds of dynamic neural networks are considered and discussed in the paper: the FIR dynamic multilayer perceptron (MLP), the cascade connection of dynamic MLPs as well as two non‐linear recurrent systems: the dynamic recurrent MLP network and ARMA recurrent network. The rule of sensitivity determination has been applied in practical learning of neural networks. Chosen results of numerical experiments concerning the application of this approach to the learning processes of recurrent neural networks are also given and discussed. Copyright © 1999 John Wiley & Sons, Ltd.     

一种模糊神经控制系统及其应用

将模糊逻辑与神经网络相结合,对一种模糊神经控制系统模型进行研究,提出了该模糊神经控制系统的混合学习算法,并将其用于１０５组稻米香数据的数值实验,仿真结果表明,该模型的性能优于一般模糊系统,从而表明了这一模型的有效性。     

基于GIS的小波神经网络库区径流预报模型研究

提出了一种基于GIS与小波神经网络方法相结合构建而成的水库日径流预测模型(GWNNR),通过模糊C均值聚类分析将水库历史径流数据分成4类,并分别建立相应的小波神经网络预测模型,应用遗传算法(Genetic algorithm)和误差反传递(Back-propagation)算法对模型的参数进行优化,对某水库2005年日平均来流进行分类预测,结果表明,该方法具有较好的训练速度和较高的预测精度.     

共生进化免疫神经网络在电力系统短期负荷预测中的应用

为了克服传统BP神经网络在结构设计和学习算法中存在的缺陷 ,提出了一种共生进化免疫神经网络来预测电力系统短期负荷。其中利用共生进化原理设计神经网络 ,通过对神经元群体进行优化设计 ,显著地减轻了计算量。在进化过程中 ,结合免疫算法中的浓度机制和个体多样性保持策略进行免疫调节 ,有效地克服了未成熟收敛现象 ,提高了群体的多样性 ,加快了网络设计速度。算例计算表明 ,该方法具有更短的训练时间和更高的预测精度     

采用共生进化算法的模糊控制器参数寻优方法

为解决模糊控制器自动优化设计中对结构和参数的学习和寻优搜索缓慢，以及模糊规则基维数爆炸问题，采用共生进化遗传算法结合分级模糊建模的思想相结合，进行模糊控制器的自动设计。提出了模糊规则分类形成子种群、多种群并行进化的遗传算法。此方法可以极大的减小编码规模，提高参数寻优的搜索速度。仿真结果表明，该方法寻优搜索速度快，设计出的控制器控制效果好。     

进化计算在神经网络中应用

本文介绍国外关于进化计算和人工神经网络结合技术的研究现状,主要包括进化计算用于神经网络优化设计、神经网络输入数据预处理、选择性神经网络集成等方面的内容,其中优化网络设计包括三个层次:权值优化、结构优化和学习规则优化;数据预处理主要用于模式分类中进行特征提取;选择性的网络集成则能很好地提高集成后网络的泛化能力.并对研究过程中出现的主要问题及未来发展趋势进行了讨论.     

Stability analysis of delayed fuzzy Cohen-Grossberg neural networks with discontinuous activations

In this article, we investigate the dynamical behavior of a class of delayed fuzzy Cohen-Grossberg neural networks (FCGNNs) with discontinuous activation functions subject to time delays and fuzzy terms. By using the inequality analysis technique and the M-matrix theory, sufficient and proper conditions are given in order to establish the existence, convergence, and global exponential stability of equilibrium point of the system. In particular, we discuss the impact of discontinuous neuron activations on the existence and exponential stability of equilibrium point for FCGNNs. Two numerical examples are provided to substantiate the theoretical results.     

Transmission lines distance protection using artificial neural networks

This work presents the development and implementation of an artificial neural network based algorithm for transmission lines distance protection. This algorithm was developed to be used in any transmission line regardless of its configuration or voltage level. The described ANN-based algorithm does not need any topology adaptation or ANN parameters adjustment when applied to different electrical systems. This feature makes this solution unique since all ANN-based solutions presented until now were developed for particular transmission lines, which means that those solutions cannot be implemented in commercial relays.     

基于神经网络的非线性最优滑动模态设计

针对具有简约形式的非线性系统,提出了神经网络最优滑动模态控制策略。首先基于最优控制理论设计变结构控制的滑动模态,然后利用多层神经网络给出了变结构控制切换函数的设计方法,并依此设计控制律,使得所设计的变结构控制系统具有最优滑动模态。     

Power-system stabilizing control by SMES using fuzzy techniques and neural networks

It has been clarified that a superconducting magnetic energy storage (SMES) is very effective for power system stabilization. The control methods proposed for power system stabilization by SMES include the pole assignment, the optimum control, and so on, each of which, however, has its drawbacks. The application of fuzzy control is considered to overcome these drawbacks. This paper considers the power system stabilization by fuzzy control of the active and reactive power of SMES. First, the adequate fuzzy control rules of an SMES for the model power system is derived. Then, to alleviate the dependence of the fuzzy control on the operating condition and the fault, a method is proposed which adjusts the fuzzy parameter according to the operating condition and the fault using a neural network. The validity of the proposed method is examined by computer simulations.     

Twisted quaternary neural networks

The quaternary neural network (QNN) proposed by Nitta is a high‐dimensional neural network. Nitta showed that its learning is faster than that of ordinary neural networks and the number of required parameters is almost one‐third of that of real‐valued neural networks by computer simulations. In this paper, we propose the twisted quaternary neural network (TQNN) which modifies the directions of multiplications of the QNN. Since quaternions are noncommutative on multiplication, we can get another neural network. When the activation function is linear, multilayered neural networks can be expressed by single‐layered neural networks. But the TQNN cannot be expressed by a single‐layered QNN even if the activation function is linear. Therefore, the TQNN is expected to produce a variety of signal‐processing systems. We performed computer simulations to compare the QNN and the TQNN. Then we found that the latter's learning is a little faster. Moreover, computer simulation showed that the QNN tended to be trapped in local minima or plateaus but the TQNN did not. It is said that reducibility causes local minima and plateaus. We discuss the differences of reducibility between the QNN and the TQNN as well. © 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于神经网络非线性系统的故障诊断研究

提出了一种关于变工作点非线性系统故障诊断研究的新方法。将此类非线性系统用变参数线性系统表示,其中模型参数为可测量工作点及故障的函数。基于Hopfield神经网络,估计系统模型参数,引入“参考工作点”这一新概念,根据模糊聚类分析方法,确定故障种类。最后,在某位置伺服系统故障诊断研究中证实了这种方法的有效性。     

电力系统负荷频率控制LFC的小波神经网络辨识

建立了非线性的电力系统负荷频率控制LFC模型,利用递归NARMA模型的小波网络的实现方法对LFC模型进行了辨识,利用Akaike's的最终预测误差准则FPE和信息准则AIC,进行了隐层节点数目和反馈阶次的计算,理论和仿真表明辨识模型可取得较好效果。     

On global asymptotic stability for a class of delayed neural networks

This paper deals with the problem of stability analysis for a class of delayed neural networks described by nonlinear delay differential equations of the neutral type. A new and simple sufficient condition guaranteeing the existence, uniqueness and global asymptotic stability of an equilibrium point of such a kind of delayed neural networks is developed by the Lyapunov–Krasovskii method. The condition is expressed in terms of a linear matrix inequality, and thus can be checked easily by recently developed standard algorithms. When the stability condition is applied to the more commonly encountered delayed neural networks, it is shown that our result can be less conservative. Examples are provided to demonstrate the effectiveness of the proposed criteria. Copyright © 2011 John Wiley & Sons, Ltd.     

Global robust stability of interval delayed neural networks: Modified approach

A criterion for the global robust stability of Hopfield‐type delayed neural networks with the intervalized network parameters is presented. The criterion, which is derived by utilizing the idea of splitting the given interval into two intervals, is in the form of linear matrix inequality and, hence, computationally tractable. The criterion yields a less conservative condition compared with many recently reported criteria, as is demonstrated with an example. Copyright © 2008 John Wiley & Sons, Ltd.     

Electricity price forecasting using artificial neural networks

Electricity price forecasting in deregulated open power markets using neural networks is presented. Forecasting electricity price is a challenging task for on-line trading and e-commerce. Bidding competition is one of the main transaction approaches after deregulation. Forecasting the hourly market-clearing prices (MCP) in daily power markets is the most essential task and basis for any decision making in order to maximize the benefits. Artificial neural networks are found to be most suitable tool as they can map the complex interdependencies between electricity price, historical load and other factors. The neural network approach is used to predict the market behaviors based on the historical prices, quantities and other information to forecast the future prices and quantities. The basic idea is to use history and other estimated factors in the future to “fit” and “extrapolate” the prices and quantities. A neural network method to forecast the market-clearing prices (MCPs) for day-ahead energy markets is developed. The structure of the neural network is a three-layer back propagation (BP) network. The price forecasting results using the neural network model shows that the electricity price in the deregulated markets is dependent strongly on the trend in load demand and clearing price.     

基于模糊小波网络的电力系统短期负荷预测方法

提出一种基于模糊小波网络的短期负荷预测模型。模糊小波网络结合了小波变换良好的时频局域化性质、模糊推理和神经网络的学习能力,因此函数逼近能力大大提高。模糊小波网络由一组模糊推理规则和若干小波子网络组成,其中模糊规则的结论部分与某一特定尺度的小波子网络相对应。在学习过程中通过同时调整小波基函数的平移因子和隶属度函数的形状,使得模糊小波网络的精度和泛化能力大大提高。实例计算表明,这种模型是切实可行的。     

基于模糊神经网络的水轮机调速器故障诊断

分析了水轮机调速器调节过程的故障机理,得到专家经验的故障诊断推理规则,利用模糊逻辑在表达专家知识方面的优势及神经网络的自学习能力,建立模糊神经网络,利用有限的推理规则对模糊神经网络进行训练,得到的模糊神经网络作为专家系统用于水轮机调速器的故障诊断,解决了故障样本获取困难、专家经验获取不足及模糊规则＂组合爆炸＂的问题,仿真实验证明该网络诊断结果正确,实用性较强。     

A solution method using neural networks for the generator commitment problem

This paper studies the feasibility of applying the Hopfield-type neural network to unit commitment problems in a large power system. The unit commitment problem is to determine an optimal schedule of what thermal generation units must be started or shut off to meet the anticipated demand; it can be formulated as a complicated mixed integer programming problem with a number of equality and inequality constraints. In our approach, the neural network gives the on/off states of thermal units at each period and then the output power of each unit is adjusted to meet the total demand. Another feature of our approach is that an ad hoc neural network is installed to satisfy inequality constraints which take into account standby reserve constraints and minimum up/down time constraints. The proposed neural network approach has been applied to solve a generator scheduling problem involving 30 units and 24 time periods; results obtained were close to those obtained using the Lagrange relaxation method.