Neural network load forecasting with weather ensemble predictions

In recent years, a large amount of literature has evolved on the use of artificial neural networks (ANNs) for electric load forecasting. ANNs are particularly appealing because of their ability to model an unspecified nonlinear relationship between load and weather variables. Weather forecasts are a key input when the ANN is used for forecasting. This paper investigates the use of weather ensemble predictions in the application of ANNs to load forecasting for lead times from one to ten days ahead. A weather ensemble prediction consists of multiple scenarios for a weather variable. We use these scenarios to produce multiple scenarios for load. The results show that the average of the load scenarios is a more accurate load forecast than that produced using traditional weather forecasts. We use the load scenarios to estimate the uncertainty in the ANN load forecast. This compares favorably with estimates based solely on historical load forecast errors.     

基于模糊粗糙集和神经网络的短期负荷预测方法

针对采用神经网络进行电力系统短期负荷预测时其网络输入变量的选择是影响预测效果的关键问题，该文提出使用模糊粗糙集理论解决这一问题：对采集到的信息进行特征提取、形成决策表；利用模糊粗糙集理论进行属性约简、去除冗余信息；用得到的属性作为BP网络的输入进行训练预测。该方法既全面考虑了影响负荷预测的历史时间序列、气象等各种因素，为合理地选择神经网络的输入变量提供了一种新的方法，又避免了由于输入变量过多而导致神经网络拓扑结构复杂、训练时间长等不足。计算实例表明，文中提出的方法是有效且可行的。     

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%。     

基于人工鱼群算法神经网络的电力系统短期负荷预测

人工鱼群算法是一种新型的寻优策略,文中将人工鱼群算法用于RBF神经网络的训练过程,建立了相应的优化模型.依据人工鱼群算法的神经网络,提出一种短期负荷预测的新方法,实践表明:该方法具有预测精度高、误差小的优点,是值得广泛推广的好方法.     

One-hour-ahead load forecasting using neural network

Load forecasting has always been the essential part of an efficient power system planning and operation. Several electric power companies are now forecasting load power based on conventional methods. However, since the relationship between load power and factors influencing load power is nonlinear, it is difficult to identify its nonlinearity by using conventional methods. Most of papers deal with 24-hour-ahead load forecasting or next day peak load forecasting. These methods forecast the demand power by using forecasted temperature as forecast information. But, when the temperature curves changes rapidly on the forecast day, load power changes greatly and forecast error would going to increase. In conventional methods neural networks uses all similar day's data to learn the trend of similarity. However, learning of all similar day's data is very complex, and it does not suit learning of neural network. Therefore, it is necessary to reduce the neural network structure and learning time. To overcome these problems, we propose a one-hour-ahead load forecasting method using the correction of similar day data. In the proposed prediction method, the forecasted load power is obtained by adding a correction to the selected similar day data     

基于支持向量机混合模型的短期负荷预测方法

将支持向量机专家系统混合模型应用于短期负荷预测采用方法分为2个阶段:应用神经网络中的聚类算法将历史数据分割成不相连的数据域;对每个数据域选择最佳核函数预测单个SVMs。实际数据验证表明,该方法与单个多项式核、高斯核和3次样条核的SVMs预测相比具有预测精度高、支持向量少和计算量小等优点。     

Short term load forecasting using a multilayer neural network withan adaptive learning algorithm

A multilayer feedforward neural network is proposed for short-term load forecasting. To speed up the training process, a learning algorithm for the adaptive training of neural networks is presented. The effectiveness of the neural network with the proposed adaptive learning algorithm is demonstrated by short-term load forecasting of the Taiwan power system. It is found that, once trained by the proposed learning algorithm, the neural network can yield the desired hourly load forecast efficiently and accurately. The proposed adaptive learning algorithm converges much faster than the conventional backpropagation-momentum learning method     

Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks

The paper addresses the problem of predicting hourly load demand using adaptive artificial neural networks (ANNs). A particle swarm optimization (PSO) algorithm is employed to adjust the network's weights in the training phase of the ANNs. The advantage of using a PSO algorithm over other conventional training algorithms such as the back-propagation (BP) is that potential solutions will be flown through the problem hyperspace with accelerated movement towards the best solution. Thus the training phase should result in obtaining the weights configuration associated with the minimum output error. Data are wavelet transformed during the preprocessing stage and then inserted into the neural network to extract redundant information from the load curve. This results in better load characterization which creates a more reliable forecasting model. The transformed data of historical load and weather information were trained and tested over various periods of time. The generalized error estimation is done by using the reverse part of the data as a ldquotestrdquo set. The results were compared with traditional BP algorithm and offered a high forecasting precision.     

Neural networks' power

Neural networks (NNs) are effective systems for learning pattern discriminants from a body of examples. Artificial neural networks (ANNs) have been developed in a wide variety of configurations with some common underlying characteristics. All ANNs attempt to achieve good performance via massive interconnection of simple computational elements. Neural networks are characterized by the model of their neurons, the connections among them and the methods used to train them to do specific tasks. The author describes multi-layer neural networks and Kohonen neural networks. The author then discusses how they are used in electric load forecasting and power system security assessment     

采用谱分析建模和基于人工神经网络的短期负荷预测方案

提出了一种基于谱分析法进行建模的短期负荷预测方案,该方案利用负荷历史数据的谱分析结果进行人工神经网络(ANN)模式分类和选择输入变量.方案采用快速傅立叶变换(FFT)进行负荷数据预处理,运用滤波算法及小时负荷曲线的频谱分析来研究电网负荷的周期特性,所得结果表明四季负荷的谱特性具有明显差异,应采用不同的模型和方案进行预测.谱分析有助于各时段预测方案提取输入变量.利用该思路构造的基于人工神经网络的负荷预测方案被用于预测广东省网的负荷,与其他普遍采用的输入变量预测结果的对比表明,所提方案在短期负荷预测中的性能良好.     

基于小波分解和相同尺度序列的神经网络短期电价预测

基于小波分解的短期电价预测主要是对电价样本分解后的各个子序列进行预测,并重构各个预测结果得到最终预测电价。在这一基础上,对电价和负荷样本进行多分辨率小波分解至2尺度,然后剔除噪声信号,再将其中相同制度的电价和负荷子序列相结合,并根据该尺度的时频特征设计建立神经网络模型进行预测,最后将各个子序列的预测结果重构得到预测电价。在算例分析中采用PJM市场2007年3月至2008年2月的数据,并通过绘制误差持续曲线,测试对比本文提出的预测方法和其他预测模型,证明了该方法的有效性和可行性。     

基于小波变换和长短期记忆神经网络的电力负荷预测

电力系统需要保持发电功率与用电负荷的即时平衡,而电力负荷具有非线性、时变性和不确定性等特点。针对此问题,考虑天气与日期类型的影响,构建小波变换（wavelet transform,WT）和长短期记忆（long short-term memory,LSTM）神经网络组合预测模型,对电力负荷进行短期电力负荷预测。首先,用小波变换对数据集进行特征提取、信号去噪,消除数据的波动性;其次,将预处理后的数据利用LSTM进行训练,将输出结果进行序列重构;最后,进行负荷预测,WT-LSTM组合预测模型分别与BP神经网络预测模型和LSTM预测模型进行对比数据。结果表明,WT-LSTM神经网络组合预测模型的预测效果最好,有效地提高了预测精度。     

基于改进DFNN的短期电价预测新方法

提出了一种改进的动态模糊神经网络DFNN(Dynam ic Fuzzy Neural Network)的短期电价预测方法。首先对采集到的信息进行特征提取,然后利用模糊粗糙集理论中的信息熵进行属性简化、去掉冗余信息,最后用得到的属性作为动态模糊神经网络(DFNN)的输入进行训练预测。在模糊神经网络内部引入递归环节,构成了动态模糊神经网络,并采用具有全局寻优能力的遗传算法来训练网络,克服了单纯BP算法易陷入局部最优解的困境。最后以美国加州电力市场公布的2000年数据进行了模型训练和预测,结果表明该方法所建立的预测模型具有较高的预测精度。     

一种基于模糊逻辑和神经网络的短期负荷预测的方法

应用模糊理论、人工神经网络等智能技术,确定了有效的电力系统短期负荷预测方法,其中着重考虑了天气因素对电网负荷的影响,采用了具有高度非线性映射能力的人工神经网络与具有较强结构性知识表达能力的模糊逻辑相结合的算法来预测负荷,经初步测试表明,该方法具有良好的预测精度。     

Input variable selection for ANN-based short-term load forecasting

This paper describes a novel method for input variable selection for artificial neural network (ANN) based short-term load forecasting (STLF). The method is based on the phase-space embedding of a load time-series. The accuracy of the method is enhanced by the addition of temperature and cycle variables. To test the viability of the method, real load data for two US-based electric utilities were used. Only 15 input variables were identified in both cases and used for 24-hour ahead load forecasting. Results compare favorably to the ones reported in the literature, indicating that more parsimonious set of input variables can be used in STLF without sacrificing the accuracy of the forecast. This allows more compact ANNs, smaller training sets and easier training. Consequently, the method represents a step forward in determining a general procedure for input variable selection for ANN-based STLF     

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     

动量自适应学习速率梯度下降法神经网络电力负荷预测

电力系统负荷预测的精度将直接影响电力系统的经济效益和用电的安全和稳定,是电力负荷预测的重要组成部分。利用人工神经网络可以任意逼近非线性系统的特性,将其用于短期负荷预测。在标准的BP网络中加入了动量项和自适应学习速率,预测结果表明比标准BP算法具有更好的性能。在相同的情况下,连续预测六天的负荷和一年的负荷,结果都证明了研究方法具有一定的实用性。     

基于负荷特征提取的神经网络短期负荷预测

综合考虑天气负荷类型和历史数据特征对负荷变化的影响 ,提出了一种新的短期负荷预测方法。通过ARMA、BP神经网络等提取具有特征的神经网络学习样本 ,用反向传播算法建立神经网络短期负荷预测模型。实际算例表明 :该法在负荷平稳或波动较大的季节均有预测精度高且适应性好的特点。     

基于多神经网络融合的短期负荷预测方法

为了利用不同深度神经网络的优势,提高深度学习算法对短期负荷的预测能力,提出一种基于多神经网络融合的短期负荷预测方法。以电力系统历史有功负荷、季节、日期类型和气象数据为输入特征,并行架构的深度神经网络和注意力机制网络为核心网络;以并行架构中的卷积神经网络通道提取静态特征,门控循环单元网络通道挖掘动态时序特征,采用注意力机制网络融合提取的特征并动态调整网络对不同特征的依赖程度;使用Maxout网络增强网络整体的非线性映射能力,通过全连接网络输出预测结果。与支持向量机、长短期记忆网络的算例结果对比表明,所提方法具有更高的预测平稳性和准确性。     

电力系统负荷预报的神经网络LBP算法

本文提出了一种能够反映工作日电力负荷波动性并可同时进行假日负荷预报的神经网络算法。该算法在一个神经网络中构造多个相互关联的子网络,将一周７日根据负荷特点分为四类特征日期,通过解码器根据输入的日期特征量激活对应的子网络,对基训练并作出预报。通过对实际系统的实验表明,该算法具有较高的预报精度。