An optimization planning technique for Suez Canal Network in Egypt

This paper introduces a proposed optimization technique POT for predicting the peak load demand and planning of transmission line systems. Many of traditional methods have been presented for long-term load forecasting of electrical power systems. But, the results of these methods are approximated. Therefore, the artificial neural network (ANN) technique for long-term peak load forecasting is modified and discussed as a modern technique in long-term load forecasting. The modified technique is applied on the Egyptian electrical network dependent on its historical data to predict the electrical peak load demand forecasting up to year 2017. This technique is compared with extrapolation of trend curves as a traditional method. The POT is applied also to obtain the optimal planning of transmission lines for the 220 kV of Suez Canal Network (SCN) using the ANN technique. The minimization of the transmission network costs are considered as an objective function, while the transmission lines (TL) planning constraints are satisfied. Zafarana site on the Red Sea coast is considered as an optimal site for installing big wind farm (WF) units in Egypt. So, the POT is applied to plan both the peak load and the electrical transmission of SCN with and without considering WF to develop the impact of WF units on the electrical transmission system of Egypt, considering the reliability constraints which were taken as a separate model in the previous techniques. The application on SCN shows the capability and the efficiently of the proposed techniques to obtain the predicting peak load demand and the optimal planning of transmission lines of SCN up to year 2017.     

Confidence intervals for neural network based short-term loadforecasting

Using traditional statistical models, like ARMA and multilinear regression, confidence intervals can be computed for the short-term electric load forecasting, assuming that the forecast errors are independent and Gaussian distributed. In this paper, the 1 to 24 steps ahead load forecasts are obtained through multilayer perceptrons trained by the backpropagation algorithm. Three techniques for the computation of confidence intervals for this neural network based short-term load forecasting are presented: (1) error output; (2) resampling; and (3) multilinear regression adapted to neural networks. A comparison of the three techniques is performed through simulations of online forecasting     

基于粗糙集理论和动态时序模型的日负荷曲线预测新方法

作者提出了一种短期日负荷曲线预测新方法.该方法首先采用日最小负荷对日负荷曲线进行规范化,再将日负荷曲线预测转化为对日最小负荷的预测和对日规范化负荷曲线的预测.对日最小负荷预测应用动态时序模型;对日规范负荷曲线应用专家系统进行推理预测,专家系统中的推理规则应用粗糙集理论从历史数据中获取.采用上海电网数据对该预测方法进行了测试,结果表明该方法便于对各种影响因素进行分析处理,能够更有效地利用历史数据所包含的信息.     

基于EMD和ELM的短期负荷预测

为了快速、准确预测具有随机性的电力负荷,引入经验模式分解和极限学习机组合负荷预测算法。首先,利用EMD将非平稳负荷序列分解成一系列相对平稳的分量,减少不同负荷影响因素间的相互影响;然后针对各分量的不同特性,利用ELM具有预测能力强、计算时间短、计算准确性高等特点建立不同的预测模型,分别预测各分量值;最后组合ELM预测的各分量值,得到最终预测结果。仿真算例表明,EMD和ELM组合预测方法较传统单一神经网络方法在短期负荷预测精度和运算时间方面具有其独特的优势。     

考虑多重周期性的短期电价预测

考虑到电价各时段变化以及周末与工作日变化的差异,提出了区分周末的分时段短期电价预测模型。该模型首先将各日中同一时段的电价形成该时段的电价序列,再将各时段电价序列分为工作日电价序列和周末电价序列。这样形成了多个消除了日周期性和星期周期性的子电价序列,分别对各子电价序列进行预测以得到预测日电价。采用基于小波分析的广义回归神经网络对这些子电价序列分别进行提前一天的预测,各子电价序列的预测电价就形成了下一天的预测电价。采用该方法对西班牙电力市场电价进行了长时间的连续预测,并与已有的预测方法进行了详细的比较分析,研究表明该方法能够提供更准确的预测电价。     

基于功率谱分解和实时气象因素的短期负荷预测

提出了基于功率谱分解和实时气象因素的短期负荷预测方法,采用快速傅里叶变换(fast Fourier transform,FFT)对负荷序列进行变换得到功率谱,依据变换结果分析功率谱得出负荷基频、低频和高频分量的频率范围,采用有限脉冲响应(finite impulse response,FIR)滤波器从负荷中分离出各 个负荷分量。分析各个负荷分量的特点,针对各个负荷分量分别设计预测模型,对基频分量采用Elman回归神经网络进行预测,这部分较好地反映出基频分量的时间序列特性;对低频和高频分量分别采用自适应线性回归神经网络进行预测,在对这部分分量的预测中重点引入实时气象因素,以利用最新的气象信息提高预测精度。通过在某地区的实际应用证明了所提出方法的有效性。     

基于因子和趋势分析反馈的多元回归负荷预测

提出一种基于因子和趋势分析反馈的考虑气象因素的多元回归预测模型,降低预测算法精度验证的计算负担。首先通过因子分析对气象和负荷指标进行相关性计算;其次,通过趋势分析量化历史负荷数据在时间尺度上的变化;然后,通过多元非线性回归模型,将气象指标作为自变量,负荷数据作为因变量进行函数拟合;最后,通过拟合出的历史预测数据与气象指标进行因子分析和趋势分析,并与第一步得到的数据进行动态相对误差计算,将动态误差反馈给多元回归预测模型。以某地区的实际负荷为例进行验证,结果表明该方法得到的预测精度高,且计算时间短。     

Reconstructing clusters for preconditioned short‐term load forecasting

This paper presents a new preconditioned method for short‐term load forecasting that focuses on more accurate predicted value. In recent years, the deregulated and competitive power market increases the degree of uncertainty. As a result, more sophisticated short‐term load forecasting techniques are required to deal with more complicated load behavior. To alleviate the complexity of load behavior, this paper presents a new preconditioned model. In this paper, clustering results are reconstructed to equalize the number of learning data after clustering with the Kohonen‐based neural network. That enhances a short‐term load forecasting model at each reconstructed cluster. The proposed method is successfully applied to real data of one‐step ahead daily maximum load forecasting. © 2007 Wiley Periodicals, Inc. Electr Eng Jpn, 161(1): 26–33, 2007; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.20300     

An adaptable automated procedure for short-term electricity loadforecasting

The Irish Electricity Supply Board requires forecasts of system demand or electrical load for: (a) one day ahead; and (b) 7-10 days ahead. Here, the authors concentrate on and give results only for one day ahead forecasts although the method is also applicable for 7-10 days ahead. A forecasting model has been developed which identifies a `normal' or weather-insensitive load component and a weather-sensitive load component. Linear regression analysis of past load and weather data is used to identify the normal load model. The weather-sensitive component of the load is estimated using the parameters of regression analysis. Certain design features of the short-term load forecasting system are important for its successful operation over time. These include adaptability to changing operational conditions, computational economy and robustness. An automated load forecasting system is presented here that includes these design features. A fully automated algorithm for updating the model is described in detail as are the techniques employed in both the identification and treatment of influential points in the data base and the selection of predictors for the weather-load model. Monthly error statistics of forecast load for only one day ahead are presented for recorded weather conditions     

基于混沌理论的短期负荷局域多步预测法

分析了目前对短期负荷时间序列进行预测的加权一阶局域一步预测方法,针对其用于多步预测会产生累计误差并且计算量很大的缺点,提出了将加权一阶局域法多步预测模型用于短期负荷预测。在分析电力系统历史短期负荷时间序列混沌特性的基础上,通过将多步预测模型应用于负荷的预测,验证了该方法相对于一步预测法在计算速度和精度方面都有明显提高。     

基于元学习的时变非线性负荷预测组合算法

单一的预测算法或多或少存在着归纳偏置,由此导致了系统偏差的普遍性。提出了一种基于元学习的时变非线性组合预测算法,该算法在进行组合预测时将序列的特征属性和基预测器预测的结果形成元知识,作为元预测器的输入,从而发现并且纠正基预测器的系统偏差。在元预测器中,通过门控网络确定各基预测器的权重,保证了权重的时变性和非负性。将该算法应用于电力负荷超短期预测,预测结果表明,该算法的预测精度高于单一预测算法和常用的线性和非线性组合算法。     

Innovations-based Neural Network Seasonal Day-ahead Marginal Price Forecasting

Successful bidding and operational strategies of electric power generators (GENCO) depend highly on the availability of accurate and timely load and price forecasts. Several techniques have been proposed and applied over the past few years to predict the marginal price of electricity in deregulated markets. To improve accuracy, these techniques apply time-consuming, complex, and hybrid methods requiring multiple inputs and large databases. This article introduces the first application of the method of “innovations” and a single artificial neural network to provide accurate forecasting results with mean absolute percentage error comparable to more complex and hybrid artificial neural network forecasting methods. The proposed model is applied to data of two seasons of Spain's power market operator (OMEL) marginal price data. The technique provided average accuracy improvement of 26% with overall mean absolute percentage error of 6.5%, which is reasonable considering the number of inputs and the simplicity of this model compared to other proposed models.     

一种多变量时间序列的短期负荷预测方法研究

针对短期负荷影响因素多的特点提出了电力短期负荷的多变量时间序列预测方法,并根据单变量时间序列的延时重构对由历史负荷序列及其相关因素序列所构成的多变量时间序列进行了相空间重构,采用互信息法计算了各子序列的延迟时间,各子序列的嵌入维数则运用平均一步绝对误差和最小一步绝对误差进行选取,然后通过RBF神经网络的非线性映射能力进行电力短期负荷预测.研究结果表明多变量时间序列的预测效果相对于单变量序列有较大提高.     

Multi-substation control central load area forecasting by using HP-filter and double neural networks (HP-DNNs)

Electricity load demand forecasting of Thailand using Hodrick–Prescott (HP) filters and double-neural networks (DNNs) is presented in this article by dividing whole country area into multi-substation areas. The signals of load demand in each subarea will be decomposed to trend and cycling signals by HP-filter before sent to DNNs for load demand forecast. The trend signals show close relationship with economic affecting features, while the cycling signals demonstrate strong relationship with weather features. These obvious correlations will be used for feature input selections. In the finally stage, the forecasting results from each subarea will be composed for the whole country area result. Comparing to other forecasting models, this approach not only reduce complexity of the forecasting model but also decrease mean absolute percent error (MAPE) as 1.42%. Moreover, this method can be applied to other load forecasting in power system and any application that can be separated into subarea.     

Forecasting next-day electricity prices by time series models

In the framework of competitive electricity markets, power producers and consumers need accurate price forecasting tools. Price forecasts embody crucial information for producers and consumers when planning bidding strategies in order to maximize their benefits and utilities, respectively. This paper provides two highly accurate yet efficient price forecasting tools based on time series analysis: dynamic regression and transfer function models. These techniques are explained and checked against each other. Results and discussions from real-world case studies based on the electricity markets of mainland Spain and California are presented     

Mid-term electricity market clearing price forecasting utilizing hybrid support vector machine and auto-regressive moving average with external input

Currently, there are many techniques available for short-term electricity market clearing price (MCP) forecasting, but very little has been done in the area of mid-term electricity MCP forecasting. Mid-term electricity MCP forecasting has become essential for resources reallocation, maintenance scheduling, bilateral contracting, budgeting and planning purposes. A hybrid mid-term electricity MCP forecasting model combining both support vector machine (SVM) and auto-regressive moving average with external input (ARMAX) modules is presented in this paper. The proposed hybrid model showed improved forecasting accuracy compared to forecasting models using a single SVM, a single least squares support vector machine (LSSVM) and hybrid LSSVM-ARMAX. PJM interconnection data have been utilized to illustrate the proposed model with numerical examples.     

扩展短期负荷预测方法的应用

扩展短期负荷预测方法利用最新的历史负荷数据，预测当日当前时刻以后若干小时的未知负荷，其预测精度明显高于常规的短期负荷预测。为满足电力市场实时交易对负荷预测的新要求，将这种方法应用于修改历史负荷坏数据和补足当日未知负荷数据，以协助提高短期负荷预测的准确度。文中详细介绍了这两种应用的背景和实现原理，并以实际电力系统的应用结果数据证实了这两种应用方案是有效的和实用的。     

Short-term load forecasting with local ANN predictors

A new technique for artificial neural network (ANN) based short-term load forecasting (STLF) is presented in this paper. The technique implemented active selection of training data, employing the k-nearest neighbors concept. A novel concept of pilot simulation was used to determine the number of hidden units for the ANNs. The ensemble of local ANN predictors was used to produce the final forecast, whereby the iterative forecasting procedure used a simple average of ensemble ANNs. Results obtained using data from two US utilities showed forecasting accuracy comparable to those using similar techniques. Excellent forecasts for one-hour-ahead and five-days-ahead forecasting, robust behavior for sudden and large weather changes, low maximum errors and accurate peak-load predictions are some of the findings discussed in the paper     

基于典型代表电站和改进SVM的区域光伏功率短期预测方法

准确的区域光伏功率预测作为解决光伏并网消纳和多能互补问题的技术之一受到越来越多的关注,提出一种基于典型代表电站和改进支持向量机(SVM)的区域光伏功率短期预测方法.通过K-means聚类将同一地区光伏电站划分到不同汇聚区,使用历史数据和3种数学相关系数计算得到各汇聚区典型代表电站,并通过4类光伏功率指标分析各典型代表电站与汇聚区的一致性,基于此,以改进SVM代替传统的滚动预报形成区域功率预测模型.实际算例分析表明,所提方法可提升区域光伏功率短期预测精度.     

Mid-term electricity market clearing price forecasting: A hybrid LSSVM and ARMAX approach

A hybrid mid-term electricity market clearing price (MCP) forecasting model combining both least squares support vector machine (LSSVM) and auto-regressive moving average with external input (ARMAX) modules is presented in this paper. Mid-term electricity MCP forecasting has become essential for resources reallocation, maintenance scheduling, bilateral contracting, budgeting and planning purposes. Currently, there are many techniques available for short-term electricity market clearing price (MCP) forecasting, but very little has been done in the area of mid-term electricity MCP forecasting. PJM interconnection data have been utilized to illustrate the proposed model with numerical examples. The proposed hybrid model showed improved forecasting accuracy compared to a forecasting model using a single LSSVM.