一种基于贝叶斯网络的电力负荷峰值预测方法

近年来,我国电力负荷峰值增长速度较快,尤其是华东地区,负荷峰值不断刷新。文章研究负荷峰值特性分布,基于向前逐步选择正则化提出两阶段法进行模型因素选择,并以实例验证选择出6个最佳影响因素组合。在两阶段法模型因素选择研究基础上,结合k-means聚类降低计算工作量,设计了基于贝叶斯网络的电力负荷峰值预测模型和分类预测算法,并以上海市浦东区为例进行验证,预测结果精度较高,验证了该方法的可行性及有效性。     

基于自组织映射网络和遗传算法优化Elman神经网络的全网短期负荷预测模型

电网数据具有海量、高维的特点,现有的短期电力负荷预测模型无法提取用户的用电习惯.提出一种基于负荷聚类的全网短期负荷预测模型,首先采用自组织映射网络对全网负荷进行聚类,将不同特性的用户负荷曲线作为子网;然后引入遗传算法对Elman神经网络的参数进行寻优,得到针对不同子网负荷特性的差异化预测网络;最后基于负荷综合稳定度得到全网负荷预测结果.将该集成模型用于某市电网进行算例仿真,预测结果表明,所提方法比传统预测方法的准确率更高,同时适用于部分子网数据缺失而需要得到全网结果的情况.     

基于XGBoost的配电网线路峰值负荷预测方法

为实现电网平稳迎峰度夏,需要在夏季负荷高峰前提前1～2个月对配电网线路进行峰值负荷预测,为设备部门有计划地制订和实施增容和改扩建方案提供数据支撑.提出一种基于XGBoost的配电网线路峰值负荷预测方法.该方法综合考虑气象因素、时间因素、春季基础负荷因素,分析各类因素与夏季负荷高峰的相关性,确定预测样本特征值.通过K-m...     

基于自组织映射神经网络的电力用户负荷曲线聚类

电力用户负荷曲线的聚类是形成合理电价体系和实施负荷管理措施的基础。文中基于自组织映射（SOM）神经网络进行低压终端用户的负荷曲线聚类研究。首先定义并提取功率曲线、分时功率、功率频谱3类向量,分别作为SOM神经网络的输入进行可视化聚类。采用相对量化误差和拓扑误差2个指标表征聚类质量,选取聚类结果最好的SOM输出层结合 k均值法进行用户负荷曲线划分。根据Davies指标将所研究的131条曲线划分为8类,对每类曲线进行描述。最后进行新用户的识别,结果表明聚类方法有效、可靠。     

基于自组织映射神经网络的市场清算电价预测

市场清算电价预测是电力市场中交易决策的基础.人工神经网络是电价预测较为理想的方法,但依然存在一些问题,如样本训练有时需要很长时间,存在收敛问题,特别是当样本特征量不明显的时候,这种现象更为突出.针对这一问题,利用自组织映射的聚类特性将历史数据进行特征分类和筛选处理,处理后形成的新数据用于训练三层BP神经网络,仿真结果表明,经过这种数据处理后,网络的收敛速度得到了显著提高,且预测效果良好.     

基于自组织映射神经网络的市场清算电价预测

市场清算电价预测是电力市场中交易决策的基础。人工神经网络是电价预测较为理想的方法,但依然存在一些问题,如样本训练有时需要很长时间,存在收敛问题,特别是当样本特征量不明显的时候,这种现象更为突出。针对这一问题,利用自组织映射的聚类特性将历史数据进行特征分类和筛选处理,处理后形成的新数据用于训练三层BP神经网络,仿真结果表明,经过这种数据处理后,网络的收敛速度得到了显著提高,且预测效果良好。     

基于自组织映射支持向量机的日前电价预测

针对电力市场中日前24点电价特性差异较大、采用单一模型很难描述的特点,建立多个模型分别对其进行预测,将数据空间按时点划分成24个子空间,然后根据这些子空间的相似性通过自组织映射对其进行自动聚类,并在不同类别的子空间分别建立支持向量机模型进行训练和预测。应用上述方法对PJM电力市场2005年8月的31天日前24点电价进行预测,结果表明该方法能够有效提高预测精度。     

基于稀疏自编码非线性自回归网络的负荷电价预测方法

准确的电价和负荷预测对现代电力系统至关重要,但由于电价与负荷之间存在较强的相关性,若不考虑其相互影响,将导致预测的精度下降。为了提高现有方法的预测准确性,在考虑价格与负荷关系的前提下,提出了一种基于深度递归神经网络的价格与负荷预测模型,即基于外部输入的稀疏自编码器的非线性自回归网络,其功能包括特征提取和预测。首先针对特征提取环节,对原有方法进行改进,提出了稀疏自编码器,可以大大提高特征提取的有效性。其次,利用非线性自回归网络进行电价和负荷预测。使用电力市场大数据ISONE和PJM进行仿真验证,与级联Elam网络相比,ESAENARX在负荷预测方面将平均绝对误差降低了16%,在价格预测方面降低了7%。     

基于泛函网络的电力负荷预测研究

介绍了电力系统负荷预测的概念,并结合泛函中的线性算子介绍了负荷预测的基本模型.回顾了负荷预测方法的发展历程,给出了适用于电力负荷预测的多元非线性泛函回归预测模型.最后通过算例验证了使用泛函网络进行电力负荷预测的有效性.     

基于子集自回归模型的短期负荷预测

介绍了自回归时间序列模型的一种特殊形式--子集自回归模型及其辨识方法,并研究该模型在电力负荷短期预报中的应用.由于子集自回归模型的自激响应可形成伪极限环,因此可复现电力负荷短期变化的主要特征--季节性趋势.实例分析结果表明,该模型用于负荷短期预测时具有较高的预测精度.     

Electricity peak load forecasting with self‐organizing map and support vector regression

This paper aims to study the short‐term peak load forecasting (PLF) by using Kohonen self‐organizing maps (SOM) and support vector regression (SVR). We first adopt a SOM network to cluster the input data set into several subsets in an unsupervised learning strategy. Then, several SVRs for the next day's peak load are used to fit the training data of each subset in the second stage. In the numerical experiments, data of electricity demand from the New York Independent System Operator (ISO) are used to verify the effectiveness of the prediction for the proposed method. The simulation results show that the proposed model can predict the next day's peak load with a considerably high accuracy compared with the ISO forecasts. © 2006 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Peak load forecasting using multiple-year data with trend data processing techniques

This paper presents a regression-based daily peak load forecasting method using multiple-year data with trend cancellation and trend estimation techniques. Daily peak load heavily depends on daytime temperature and is influenced by the other weather factors such as humidity. Since the characteristic of the load is varying, peak loads just before a forecasting day are more significant for the forecasting. The regression model can represent relationships between these weather factors and peak loads. However, the forecasting model is sometimes not adequate for precise load forecasting. The regression model is well matched with the late data, but the model causes large forecasting errors in transitional seasons because of seasonal change of load characteristics. In order to forecast precisely through a year, a method of using seasonal or whole year data from past years is proposed. In this paper, two kinds of trend data processing techniques are described. The first is trend cancellation. The second is trend estimation. The trend cancellation technique removes annual load growth by means of division or subtraction processes with morning load on the forecasting day. The trend estimation technique estimates the trend between the forecasting year's load and the past year's load by using the variable transformation techniques. The performance of both techniques, verified with simulations on actual load data, is also described. © 1998 Scripta Technica, Electr Eng Jpn, 124(1): 7–16, 1998     

夏季日峰荷特性分析与预测

在分析夏季日峰荷特性的基础上,利用小波变换对负荷序列进行分解和单支重构．得到不同频段上的近似序列和细节序列,用相关性分析方法分别分析其早晚高峰值与气温的关系,根据分析的结果,使用RBF神经网络建立相应模型预测,将各序列的预测值相加得到日峰荷值。根据江苏省实际负荷运行数据,对方法进行了检验。     

基于模糊推理的节假日负荷预测

由于节假日负荷成分与正常日有较大差异,加之样本较少,节假日短期负荷预测难度较大.而准确预测可以提高系统运行的可靠性和经济性.为了提高节假日负荷预测的精度,针对节假日负荷特点,利用相似日方法获得待预测日负荷归一化曲线,利用模糊推理方法对负荷水平年增长率进行调整.通过对实际负荷进行预报计算,结果表明预报精度较高,建议用于节假日短期负荷预测.     

Application of switched adaptive system to load forecasting

In this paper, we propose an approach for next day peak load forecasting for electrical companies. First a nonlinear model for the peak load is proposed taking into account the historical load and the temperature. Based on this model time-varying local models are obtained for some temperature intervals. The peak load forecasting system is constructed based on these local models which parameters are estimated using an on-line recursive algorithm. We remark that in this methodology it is not necessary to know precisely the temperature of the days since the proposed system is based on an interval for the future temperature instead of a number. An application example illustrates the proposed approach.     

Long-term load forecasting using improved recurrent neural network

In general, electric power companies must prepare power supply capability for maximum electric load demand because it is very difficult at present to store electric power. It takes several years and requires a great amount of money to construct power generation and transmission facilities. Therefore, it is necessary to forecast long-term load demand exactly in order to plan or operate power systems efficiently. Several methods have been investigated so far for the long-term load forecasting. However, because the electric loads consist of many complex factors, good forecasting has been very difficult. This paper proposes a long-term load forecasting method using a recurrent neural network (RNN). This is a mutually connected network that has the ability of learning patterns and past records. In general, when interpolation is used for unlearned data sets, the neural network provides reasonably good outputs. However, when extrapolation is used, such as in long-term load forecasting, some kind of tunings have been necessary to obtain good results. Therefore, to solve the problem, a method is proposed in which growth rates are used as input and output data. Using the proposed method, successful results have been obtained and comparisons have been made with the conventional methods.     

多级负荷预测的基础问题分析

围绕多级负荷预测及其协调问题,首先剖析了多级负荷预测的基础---负荷预测的分类方式,通过拓展不同的分类角度,提出了基于雷达图的负荷预测的分类方法,从而清晰地表征负荷预测的“多级”特性。从供应侧和需求侧的角度分析了相关因素对预测对象的影响途径,提出了多级负荷预测中不同级别电网对相关因素的处理策略;研究了多级负荷预测体系下母线负荷预测与系统负荷预测的关系,提出了“虚拟母线”的概念和应用方法;最后总结了多级负荷预测的分析思路和研究内容。该文的研究为建立多级负荷预测理论提供了广阔的空间。     

基于灰色神经网络法的高峰负荷预测

针对多个相关序列预测的问题,提出了灰色神经网络模型。考虑各序列数据之间的关系及各序列之间的关系,能一次得到多个预测值。利用神经网络对预测值进行校正,得到最终的预测值。实例表明,此种模型具有预测精度高、所需样本少、计算简便等优点,取得了满意的结果。     

A neural-net based short term load forecasting using moving window procedure

An improved neural-net approach based on a combined unsupervised/supervised learning concept is proposed. A ‘moving window’ procedure is applied to the most recent load and weather information for creating training set data base. A forecasting lead time that varies from 16 hours to 88 hours is introduced to produce the short term electric load forecasting that meets requirements of real electric utility operating practice. The unsupervised learning (UL) is used to identify days with similar daily load patterns. A feed forward three-layer neural net is designed to predict 24-hour loads within the supervised learning (SL) phase. The effectiveness of proposed methods is demonstrated by comparison of forecasted hourly loads in every single day during 1991 with data realized in the same period in the Electric Power Utility of Serbia (EPS). A better choice of input features and more appropriate training set selection procedure allow significant improvement in forecasting results comparing with our previous UL/SL concept characterized by a fixed neural-net structure and absence of re-training procedure. The improvement is illustrated by reduction of average error in daily energy forecasting for 0.83% and reduction of 90th percentile of 2.04%.