Analysis of energy consumption of elevator group supervisory control system based on genetic network programming

Elevator Group Supervisory Control System (EGSCS) is a traffic system, which provides the transportation services for passengers in modern buildings. As the elevator systems include uncertainty due to the future arrival of the passengers, it difficult to model, analyze, and optimize the elevator group supervisory control system. Recently, artificial intelligence technology has been used in such complex systems. Genetic Network Programming(GNP), a graph‐based evolutionary method extended from genetic algorithm and genetic programming, has been already applied to EGSCS. On the other hand, since energy consumption is becoming one of the greatest challenges in the society, it should be taken as one of the criteria of the elevator operations. The elevators with maximum energy efficiency are therefore required. In this paper, the GNP is used to solve EGSCS with energy consumption (EC). Moreover, the idle car assignment has been embedded in the proposed method. Finally, the simulations show that some factors should be introduced into GNP in order to deal with the higher EC in the light traffic of the elevator systems. © 2011 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

基于关联规则数据挖掘技术的电网故障诊断

在实际的电网故障诊断中,面临如何从海量数据找到真正对于诊断结果有帮助的关键数据以及当故障信息存在不完整或不确定性,甚至关键信息丢失时,会导致故障诊断难以得出正确结论的问题。针对此问题,将关联规则数据挖掘DLG(Direct Large temsests Generation）算法引入到电网故障诊断中。首先以保护、断路器作为条件属性,故障区域作为决策属性,考察各种故障情况并建立原始决策表,然后利用关联规则挖掘进行属性约简,通过修改阈值进行交互式挖掘,直接提取最佳属性约简组合,然后利用最佳属性约简组合形成的约简决策表和关联规则交互式挖掘,针对各种情况的故障信息进行诊断推理。运用C编写了基于该方法的故障诊断软件, 采用四母线配电网系统作为仿真对象,算例结果表明该算法在一定电网规模和保护动作信息不完备的情况下,故障诊断正确性高、容错性好,实用性强。     

基于关联规则数据挖掘技术的电网故障诊断

在实际的电网故障诊断中,面临如何从海量数据找到真正对于诊断结果有帮助的关键数据以及当故障信息存在不完整或不确定性,甚至关键信息丢失时,会导致故障诊断难以得出正确结论的问题.针对此问题,将关联规则数据挖掘DLG(Direct Large temsests Generation)算法引入到电网故障诊断中.首先以保护、断路器作为条件属性,故障区域作为决策属性,考察各种故障情况并建立原始决策表,然后利用关联规则挖掘进行属性约简,通过修改阈值进行交互式挖掘,直接提取最佳属性约简组合,然后利用最佳属性约简组合形成的约简决策表和关联规则交互式挖掘,针对各种情况的故障信息进行诊断推理.运用C编写了基于该方法的故障诊断软件, 采用四母线配电网系统作为仿真对象,算例结果表明该算法在一定电网规模和保护动作信息不完备的情况下,故障诊断正确性高、容错性好,实用性强.     

A rule based comprehensive approach for reconfiguration of electrical distribution network

This paper proposes a rule based comprehensive approach to study distribution network reconfiguration (DNRC). The DNRC model with line power constraints is set up, in which the objective is to minimize the system power loss. In order to get the precise branch current and system power loss, a power summation based radiation distribution network load flow (PSRDNLF) method is applied in the study. The rules that are used to select the optimal reconfiguration of distribution network are formed based on the system operation experiences. The proposed rule based comprehensive approach is implemented in distribution network in Guiyang South Power Supply Bureau. For the purpose of illustrating the proposed approach, two distribution network systems are tested and analyzed in the paper.     

An improved distribution network reconfiguration method based on minimum spanning tree algorithm and heuristic rules

This paper presents an improved distribution network reconfiguration method with the goal to minimize active power loss. The proposed method combines the minimum spanning tree (MST) algorithm and improved heuristic rules. It consists of three procedures. The first procedure calculates the branch (edge) weights with bus (vertex) voltages, and then carries out preliminary optimization with MST algorithm to get a local optimal solution. The second procedure gets alternative optimal solution based on the improved heuristic rules. Then during the third procedure, the optimal solution can generally be obtained through correcting the results. The algorithm does not rely on the initial network topology. The local optimal solution, solved by MST algorithm, provides a favorable initial condition for the subsequent optimization procedures. Further with the improved heuristic rules, the amount of the candidate switches can be significantly reduced. Two typical test systems, 33-bus system and 69-bus system, and a real 210-bus MV utility distribution system verified the feasibility and effectiveness of the proposed method. The method has higher efficiency and can be used to the large distribution systems.     

基于改进遗传算法的配电网无功优化

对配电网无功优化问题进行了研究.针对无功优化问题的特点,提出了一种应用于电力系统无功优化问题的改进遗传算法.该算法将迭代群体分为一般组和精英组,对一般组进行交叉和变异操作,而对精英组只进行变异操作,实现分组进化.在该算法中利用整数和浮点数混合编码,并对遗传算法的选择,交叉、变异算子进行改进,采用自适应罚因子、交叉率和变...     

Reconfiguration of distribution network for loss reduction and reliability improvement based on an enhanced genetic algorithm

Electrical distribution network reconfiguration is a complex combinatorial optimization process aimed at finding a radial operating structure that minimizes the system power loss or/and maximizes the system reliability while satisfying operating constraints. In this paper, a distribution network reconfiguration method is presented for both the indices of power loss reduction and reliability improvement. The enhanced genetic optimization algorithm is used to handle the reconfiguration problem so as to determine the switch operation schemes. Based on the information of a single loop caused by closing a normally open switch, we improve the algorithm on crossover and mutation operations of original Genetic Algorithms. The effectiveness of the proposed method is demonstrated on 33-bus, 69-bus, and 136-bus radial distribution systems.     

基于粗糙集的关联规则挖掘方法的研究与应用

基于粗糙集理论知识,对关联规则挖掘算法作出一定的改进。该算法的主要思想是把集合的近似质量作为迭代准则,初始约简集是所有的条件属性集合,在保证近似质量不变的前提下通过逐步缩减的方式来求取约简集,保证了所求的约简不会减弱对问题的分类决策能力。约简后得到新的决策表,在此基础上应用基于贪心思想的Apriori算法挖掘关联规则。算法的主要优势是在不影响对问题分类决策能力的前提下,以较小的属性和候选项集数目以及有限的扫描次数生成决策规则。通过应用实例和实验分析验证了算法的有效性。     

A new dynamic security enhancement method via genetic algorithms integrated with neural network based tools

In this paper, a new dynamic security assessment and generation rescheduling method utilizing genetic algorithms (GAs) which are integrated with probabilistic neural networks (PNNs) and adaptive neuro fuzzy inference systems (ANFISs) is proposed for the preventive control of large power systems against transient instabilities. By the proposed approach, PNNs are employed in a feasible manner to calculate the security regions accurately during the assessment and control. The security constrained generation rescheduling is implemented through a GA which optimizes the total fuel cost or the generation shifting during the preventive control. The steady-state solutions of the variables required for the GA are smoothly performed by the use of an ANFIS. The proposed methods are demonstrated on the 17-generator 163-bus Iowa power system and on the 50-generator 145-bus IEEE test system successfully and the effectiveness of the approaches is discussed.     

基于语义相似度及命名实体识别的主观题自动评分方法

人工智能技术目前已运用于诸多领域,其中在教育行业的一个重要应用为主观题评分系统。文本相似度计算是主观题评分的一大难点,目前采用的基于同义词词林的词语相似度计算方法已经了取得较好的效果,但文本过长会导致传统词语相似度计算方法性能下降。该文采用拓展的命名实体识别方法将主观题的候选答案中部分关键词提取出来,采用改进的同义词林词语相似度计算方法将候选关键词与主观题标准答案中目标关键词进行相似度计算。所提方法能有效提升词语匹配效率,在原同义词林词语相似度算法基础上,提升了性能,有效缩短了计算时间。     

基于隔离信息相似度的配电网故障仿真培训评价方法

为解决配电网调度员故障仿真培训自动评价问题,提出了一种基于隔离信息相似度的配电网故障仿真培训评价方法。该方法通过主动隔离范围集、被动隔离范围集、失电负荷量及负荷数、误操作步骤数等构建隔离信息阵以描述调度员及教练员故障仿真培训处理的信息模型。基于人工智能推理思想,通过相似度理论描述实时和标准隔离信息阵之间的相似度以实现调度员故障仿真培训的评价。通过主动隔离范围纵向相似度、被动隔离范围纵向相似度、重要指标纵向相似度、防误操作纵向相似度实现实时和标准隔离信息阵单点元素的相似度分析。通过单点元素的相似度及欧几里德距离实现故障馈线的整体横向相似度,并结合多馈线故障及海明距离实现隔离信息阵综合相似度计算。实例分析表明该方法能较为全面的反映调度员故障隔离及转供操作对配电网运行的影响,能有效的区分不同隔离操作之间的评价档次,方法简便,具有较好的实用价值。     

基于遗传算法和BP神经网络的电力客户信用评价模型

对电力客户的信用进行分析评估对于供电企业将电力输送给可靠的电力用户、提高企业经济效益具有重要意义。在分析影响电力客户信用影响因素的基础上,构建了电力客户信用评价指标体系,将遗传算法和神经网络原理引入电力客户信用评价领域,提出了基于遗传算法和神经网络的电力客户信用评价模型。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。     

基于遗传单纯形神经网络的大坝变形监控模型

本文针对遗传算法局部搜索能力差的缺陷,把单纯形法嵌入到遗传算法中构成复合遗传算法,建立了基于遗传单纯形神经网络的大坝变形监控模型。实例研究表明,该模型较遗传神经网络模型、BP模型收敛性能好,具有较高的预报精度、较快的训练速度和较强的泛化能力,用于大坝变形预测有效可行,具有良好的应用前景。     

基于遗传算法和并行组合模拟退火算法的洪水过程缩放模型研究

针对泄洪风险和施工导流风险计算对洪水缩放的要求和传统洪水同频率放大方法中手工修匀任意性较大等方面的不足,提出采用计算机优化方法来实现洪水过程的自动放大。在满足洪峰流量约束和分时段洪量约束条件下,本文建立了以洪水过程模式尽量相似为目标的洪水过程放大优化模型,并采用具有全局搜索能力的遗传算法和并行组合模拟退火算法求解该模型。通过实例计算可以看出,这两种算法计算结果均能较好的满足洪峰洪量约束要求,并有效保持了典型洪水的模式,避免了人工修匀的任意性。     

A topology analysis and genetic algorithm combined approach for power network intentional islanding

Intentional islanding is to determine proper network splitting strategy while ensuring local power balance and transmission capacity constraints when islanding operation is unavoidable. The intentional islanding problem is very complicated in general because a combinatorial exploitation of strategy space is required. This paper apply a topology analysis and genetic algorithm combined approach for determining proper splitting strategies of large-scale power networks. Topology analysis is used to simplify the original power network into a simple equivalent network so that the splitting strategy space world be dramatically reduced; while the genetic algorithm incorporated with the breadth-first search (BFS) is employed to determine the final proper splitting strategy in the simplified power network. Two additional applications, mimicking weak connections between islands and obtaining specific pre-defined islands, of the proposed method are introduced. Simulation results on several test system show that the proposed approach can quickly provide proper splitting strategies and is effective for larger-scale power systems.     

基于PSO算法的DBN模型参数优化

针对深度置信网络模型每层神经元个数难以确立的问题,提出利用粒子群寻优确立DBN网络每层节点数,利用Kmeans聚类来决定是否需要增加隐藏层的方法来确立DBN的网络结构。该算法根据粒子群寻优算法以最小化所有样本重构误差的平方和为目标函数来确定DBN每层神经元个数,以确定DBN的初步结构,为了验证DBN结构的有效性,利用DBN提取的数据特征来进行聚类测试,进一步根据聚类结果来修正DBN,以获得DBN的最佳结构,以红酒数据集进行分类实验,实验结果表明,与传统未经改进的深度置信网络进行对比,发现该方法确立的深度置信网络分类效果更优。     

A RBF neural network model with GARCH errors: Application to electricity price forecasting

In this article, we propose a nonlinear forecasting model based on radial basis function neural networks (RBF-NNs) with Gaussian activation functions and robust clustering algorithms to model the conditional mean and a parametric generalized autoregressive conditional heteroskedasticity (GARCH) specification to model the conditional volatility. Instead of calibrating the parameters of the RBF-NNs via numerical simulations, we propose an estimation procedure by which the number of basis functions, their corresponding widths and the parameters of the GARCH model are jointly estimated via maximum likelihood along with a genetic algorithm to maximize the likelihood function. We use this model to provide multi-step-ahead point and direction-of-change forecasts of the Spanish electricity pool prices.     

基于关联规则与变权重系数的变压器状态综合评估方法

为了提高变压器诊断的准确性和适应设备检修的发展趋势,克服传统智能算法的局限性,提出一种基于关联规则和变权重系数的变压器状态综合评估的方法。根据试验和监测数据建立评估体系,通过9种综合故障和24种单项故障状态量,利用关联规则分别计算置信度和变权重系数,结合变压器的运行状态与检修对照关系,诊断变压器的整体指标。实验结果表明该方法准确率达到91%,能够准确评估电力变压器的健康状态。该方法可为运维人员做设备检修提供科学指导方案,也为其他高压设备的状态评估提供参考和借鉴。     

一种基于非线性模型的OFDM信道估计

导频辅助的信道估计方法是OFDM系统中应用最为广泛的一类信道估计方法,其中的2-D维纳滤波是最小均方误差意义下的最佳线性估计器,但是由于其计算量非常大,因而在实际中不能得到很好的应用。2×1-D的维纳滤波器利用信道相关函数的可分离性,对2-D维纳滤波器进行了简化,一定程度地降低了其复杂性,但仍然需要知道或估计信道的统计特性。文中介绍了一种基于非线性模型的信道估计方法,对其算法进行了仿真并与2×1-D维纳滤波的误比特率(BER)性能进行了比较。仿真结果表明,此方法能以较低的复杂性达到与2×1-D维纳滤波相近的性能,且无需对信道特性估计,是一种较实用的信道估计方法。     

基于遗传神经网的自适应电池荷电态预估模型

电池荷电态(SOC)是放电电流、端电压、温度等多种因素的复杂的非线性函数,而且不同类型的电池具有很大的差异,不能建立统一的模型。因此要对其做出精确的预估是一件很困难的事情,需要耗费很多的人力和时间对特定类型的电池进行大量试验然后建模。为克服这些缺点,提出一种基于遗传神经网的自适应SOC预估模型,通过遗传算法对神经网络结构及其学习算法进行优化,在较短的时间内寻找到适合特定类型电池的神经网络模型,大大缩短了人工建模需要的时间,提高了模型对SOC预估的性能。对于三种不同类型电池的数据进行建模的仿真试验结果验证了本方法的有效性。