Forecast of solar irradiance using recurrent neural networks combined with wavelet analysis

In this paper, artificial neural network is combined with wavelet analysis for the forecast of solar irradiance. This method is characteristic of the preprocessing of sample data using wavelet transformation for the forecast, i.e., the data sequence of solar irradiance as the sample is first mapped into several time-frequency domains, and then a recurrent BP network is established for each domain. The forecasted solar irradiance is exactly the algebraic sum of all the forecasted components obtained by the respective networks, which correspond respectively the time-frequency domains. Discount coefficients are applied to take account of different effect of different time-step on the accuracy of the ultimate forecast when updating the weights and biases of the networks in network training. On the basis of combination of recurrent BP networks and wavelet analysis, a model is developed for more accurate forecasts of solar irradiance. An example of the forecast of day-by-day solar irradiance is presented in the paper, the historical day-by-day records of solar irradiance in Shanghai constituting the data sample. The results of the example show that the accuracy of the method is more satisfactory than that of the methods reported before.     

Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks

An accurate forecast of solar irradiation is required for various solar energy applications and environmental impact analyses in recent years. Comparatively, various irradiation forecast models based on artificial neural networks (ANN) perform much better in accuracy than many conventional prediction models. However, the forecast precision of most existing ANN based forecast models has not been satisfactory to researchers and engineers so far, and the generalization capability of these networks needs further improving. Combining the prominent dynamic properties of a recurrent neural network (RNN) with the enhanced ability of a wavelet neural network (WNN) in mapping nonlinear functions, a diagonal recurrent wavelet neural network (DRWNN) is newly established in this paper to perform fine forecasting of hourly and daily global solar irradiance. Some additional steps, e.g. applying historical information of cloud cover to sample data sets and the cloud cover from the weather forecast to network input, are adopted to help enhance the forecast precision. Besides, a specially scheduled two phase training algorithm is adopted. As examples, both hourly and daily irradiance forecasts are completed using sample data sets in Shanghai and Macau, and comparisons between irradiation models show that the DRWNN models are definitely more accurate.     

Short term solar irradiance forecasting using a mixed wavelet neural network

In modern smart grids and deregulated electricity markets, accurate forecasting of solar irradiance is critical for determining the total energy generated by PV systems. We propose a mixed wavelet neural network (WNN) in this paper for short-term solar irradiance forecasting, with initial application in tropical Singapore. The key advantage of using wavelet transform (WT) based methods is the high signal compression ability of wavelets, making them suitable for modeling of nonstationary environmental parameters with high information content, such as short timescale solar irradiance. In this WNN, a combination of the commonly known Morlet and Mexican hat wavelets is used as the activation function for hidden-layer neurons of a feed forward artificial neural network (ANN). To demonstrate the effectiveness of the proposed approach, hourly predictions of solar irradiance, which is an aggregate sum of irradiance value observed using 25 sensors across Singapore, are considered. The forecasted results show that WNN delivers better prediction skill when compared with other forecasting techniques.     

Online 24-h solar power forecasting based on weather type classification using artificial neural network

Power forecasting is an important factor for planning the operations of photovoltaic (PV) system. This paper presents an advanced statistical method for solar power forecasting based on artificial intelligence techniques. The method requires as input past power measurements and meteorological forecasts of solar irradiance, relative humidity and temperature at the site of the photovoltaic power system. A self-organized map (SOM) is trained to classify the local weather type of 24 h ahead provided by the online meteorological services. A unique feature of the method is that following a preliminary weather type classification, the neural networks can be well trained to improve the forecast accuracy. The proposed method is suitable for operational planning of transmission system operator, i.e. forecasting horizon of 24 h ahead and for PV power system operators trading in electricity markets. Application of the forecasting method on the power production of an actual PV power system shows the validity of the method.     

Real-time prediction intervals for intra-hour DNI forecasts

We develop a hybrid, real-time solar forecasting computational model to construct prediction intervals (PIs) of one-minute averaged direct normal irradiance for four intra-hour forecasting horizons: five, ten, fifteen, and 20 min. This hybrid model, which integrates sky imaging techniques, support vector machine and artificial neural network sub-models, is developed using one year of co-located, high-quality irradiance and sky image recording in Folsom, California. We validate the proposed model using six-month of measured irradiance and sky image data, and apply it to construct operational PI forecasts in real-time at the same observatory. In the real-time scenario, the hybrid model significantly outperforms the reference persistence model and provides high performance PIs regardless of forecast horizon and weather condition.     

虹吸井对尾矿坝地震液化的影响分析

针对河套灌区地下水位预测问题,结合小波变换的时频局部特性和神经网络的逼近功能,构建了两种不同耦合方式下小波和BP神经网络相结合的小波网络模型,比较了不同耦合方式下小波网络模型与单纯神经网络模型的预测效果。两种耦合方式下的小波网络模型模拟结果均比单纯使用人工神经网络模型更接近实测值,对低频信号序列及高频信号序列分别进行神经网络模型预测后再进行重构的预测方式比直接将小波分解的多级信号与神经网络结合的预测方式具有更好的预测效果。     

小波网络耦合模型在地下水位动态预测中的应用

针对河套灌区地下水位预测问题,结合小波变换的时频局部特性和神经网络的逼近功能,构建了两种不同耦合方式下小波和BP神经网络相结合的小波网络模型,比较了不同耦合方式下小波网络模型与单纯神经网络模型的预测效果。两种耦合方式下的小波网络模型模拟结果均比单纯使用人工神经网络模型更接近实测值,对低频信号序列及高频信号序列分别进行神经网络模型预测后再进行重构的预测方式比直接将小波分解的多级信号与神经网络结合的预测方式具有更好的预测效果。     

应用小波-人工神经网络组合模型研究电力负荷预报

针对负荷时间序列的非线性和多时间尺度特性．提出了将小波分析与人工神经网络相结合进行负荷预报的方法——小波-人工神经网络组合模型。该模型吸取了小波分析的多分辨功能和人工神经网络的非线性逼近能力。以月、日平均负荷预报为例对模型进行验证．结果表明：该模型的拟合、检验精度较高。     

Hourly solar irradiance time series forecasting using cloud cover index

We apply time series analysis to forecast next hour solar irradiance including cloud cover effects. Three forecasting methods are proposed using different types of meteorological data as input parameters, namely, global horizontal irradiance (GHI), diffuse horizontal irradiance (DHI), direct normal irradiance (DNI) and cloud cover. The first method directly uses GHI to forecast next hour GHI through additive seasonal decomposition followed by an Auto-Regressive Integrated Moving Average (ARIMA) model. The second method forecasts DHI and DNI separately using additive seasonal decomposition followed by an ARIMA model and then combines the two forecasts to predict GHI using an atmospheric model. The third method considers cloud cover effects. An ARIMA model is used to predict cloud transients. GHI at different zenith angles and under different cloud cover conditions is constructed using nonlinear regression, i.e., we create a look-up table of GHI regression models for different cloud cover conditions. All three methods are tested using data from two weather stations in the USA: Miami and Orlando. It is found that forecasts using cloud cover information can improve the forecast accuracy.     

太阳逐时总辐射混沌优化神经网络预测模型研究

根据影响太阳逐时总辐射的气象、地理等方面因素的分析以及对太阳逐时总辐射历史数据的相关性分析,确定了建立太阳逐时总辐射的神经网络预测模型输入因素项。根据全年最大可照时数统一了太阳逐时总辐射各天的历史数据,并对宝山气象站的太阳逐时总辐射建立了混沌优化神经网络预测模型(CONN),编制了计算机程序。模型输出反映了太阳逐时总辐射的变化规律,预测结果也足够准确。     

Bayesian adaptive combination of short-term wind speed forecasts from neural network models

Short-term wind speed forecasting is of great importance for wind farm operations and the integration of wind energy into the power grid system. Adaptive and reliable methods and techniques of wind speed forecasts are urgently needed in view of the stochastic nature of wind resource varying from time to time and from site to site. This paper presents a robust two-step methodology for accurate wind speed forecasting based on Bayesian combination algorithm, and three neural network models, namely, adaptive linear element network (ADALINE), backpropagation (BP) network, and radial basis function (RBF) network. The hourly average wind speed data from two North Dakota sites are used to demonstrate the effectiveness of the proposed approach. The results indicate that, while the performances of the neural networks are not consistent in forecasting 1-h-ahead wind speed for the two sites or under different evaluation metrics, the Bayesian combination method can always provide adaptive, reliable and comparatively accurate forecast results. The proposed methodology provides a unified approach to tackle the challenging model selection issue in wind speed forecasting.     

基于改进遗传算法优化的小波神经网络短期负荷预测模型

针对传统小波神经网络在电力系统短期负荷预测中存在预测结果的精确度依赖初始网络参数的问题,提出了一种基于改进遗传算法优化的小波神经网络短期负荷预测模型。为了保证神经网络在训练过程中,各个层的权值和阈值按最优方向变化,将遗传算法引入小波神经网络,利用遗传算法寻优能力指导权值和阈值进行优化。将概率分布策略用于遗传算法的种群交叉和变异过程,解决遗传算法在中后期搜索精度差,收敛速度慢等问题。应用结果表明,与基本的小波神经网络的预测模型相比,在只考虑短期负荷历史数据的情况下,通过均方根误差计算比较,基于改进遗传算法优化的小波神经网络短期负荷预测模型具有更高的预测精度。     

应用盲分离神经网络预测逐日太阳辐射能

提出一种应用盲分离神经网络预测逐日太阳辐射能的方法。首先在卷积混合基础上,应用最大化负熵准则分离原始太阳辐射时间序列,从观测数据中剔除不可靠信息;考虑到太阳负荷的特点,将分离后的样本输入到径向基函数神经网络(RBFN)中,通过调整参数训练网络直到满足约束条件为止,由此恢复盲分离所带来的幅值和排列顺序变化;最后分别比较盲分离神经网络、RBFN和BP网络的预测误差值,结果说明本文建立的模型提高了预测的准确度。     

基于小波变换与Elman神经网络的短期风速组合预测

风速的准确预测对风电场发电系统的经济和安全运行有着重要的作用。为了克服风速随机性强的缺点,提高短期风速预测的精度,提出了一种将小波变换与Elman神经网络相结合的短期风速组合预测模型。该模型由小波预处理模块和神经网络预测模块组成。首先利用小波预处理模块将风速序列作多尺度分解,重构得到不同频段的子序列,然后利用Elman神经网络模块分别对其训练和预测。实际风速预测结果表明,与单一的Elman和ARMA法相比,该组合预测模型的预测精度有较大的改善,可以用于风电场短期风速的预测。     

A regime-dependent artificial neural network technique for short-range solar irradiance forecasting

Solar power can provide substantial power supply to the grid; however, it is also a highly variable energy source due to changes in weather conditions, i.e. clouds, that can cause rapid changes in solar power output. Independent systems operators (ISOs) and regional transmission organizations (RTOs) monitor the demand load and direct power generation from utilities, define operating limits and create contingency plans to balance the load with the available power generation resources. ISOs, RTOs, and utilities will require solar irradiance forecasts to effectively and efficiently balance the energy grid as the penetration of solar power increases. This study presents a cloud regime-dependent short-range solar irradiance forecasting system to provide 15-min average clearness index forecasts for 15-min, 60-min, 120-min and 180-min lead-times. A k-means algorithm identifies the cloud regime based on surface weather observations and irradiance observations. Then, Artificial Neural Networks (ANNs) are trained to predict the clearness index. This regime-dependent system makes a more accurate deterministic forecast than a global ANN or clearness index persistence and produces more accurate predictions of expected irradiance variability than assuming climatological average variability.     

基于多方法优选预报因子的天山西部山区融雪径流中长期水文预报

为实现天山西部山区喀什河流域冰川融雪区域的水资源可持续开发利用,更好地支撑所在区域工农业生产发展,有必要开展融雪径流中长期水文预报研究。基于相关系数法、主成分分析法及两种方法相结合的综合方法优选预报因子,采用BP神经网络模型和组合小波BP神经网络模型预报径流。结果表明,采用综合方法筛选出的预报因子集合可以得到更好的预报结果;组合小波BP神经网络模型在3个不同方案中的预测效果均优于BP神经网络模型的预测结果,其预报精度更高。研究成果可为该区域融雪径流模拟研究及洪水预报提供参考。     

Selection of input parameters to model direct solar irradiance by using artificial neural networks

A very important factor in the assessment of solar energy resources is the availability of direct irradiance data of high quality. However, this component of solar radiation is seldom measured and thus must be estimated from data of global solar irradiance, which is registered in most radiometric stations. In recent years, artificial neural networks (ANN) have shown to be a powerful tool for mapping complex and non-linear relationships. In this work, the Bayesian framework for ANN, named as automatic relevance determination method (ARD), was employed to obtain the relative relevance of a large set of atmospheric and radiometric variables used for estimating hourly direct solar irradiance. In addition, we analysed the viability of this novel technique applied to select the optimum input parameters to the neural network. For that, a multi-layer feedforward perceptron is trained on these data. The results reflect the relative importance of the inputs selected. Clearness index and relative air mass were found to be the more relevant input variables to the neural network, as it was expected, proving the reliability of the ARD method. Moreover, we show that this novel methodology can be used in unfavourable conditions, in terms of limited amount of available data, performing successful results.     

结合均生函数的神经网络在中长期水文预报中的应用

针对中长期径流预报在水库中长期运行方案制定及调度决策形成中的作用,基于传统和智能预报方法各自的优势,利用均生函数模型记忆时间序列的内在规律,采用偏最小二乘方法对预报因子进行降维处理,建立了结合均生函数的神经网络预报模型,并利用神经网络模型修正预报结果。实例计算表明,该模型不仅可提取径流序列的特征,且预报精度也较单一的均生函数模型和神经网络模型有所提高。     

证据理论融合蚁群神经网络的短期负荷组合预测

为提高短期负荷预测的精度,引入了证据理论融合蚁群神经网络的组合预测方法,根据重庆市负荷的实际数据,采用蚁群神经网络作为单一模型对其进行初步预测,由BP神经网络对预测误差及主要外界影响因素进行分析建模,获得了每个模型的可信度,并用证据理论对可信度进行合成得到组合权值,进而实现对短期电力负荷的组合预测。结果表明,该方法拟合误差小、预测精度高,具有一定的应用价值。     

Improved artificial neural network method for predicting photovoltaic output performance

To ensure the safety and stability of power grids with photovoltaic (PV) generation integration, it is necessary to predict the output performance of PV modules under varying operating conditions. In this paper, an improved artificial neural network (ANN) method is proposed to predict the electrical characteristics of a PV module by combining several neural networks under different environmental conditions. To study the dependence of the output performance on the solar irradiance and temperature, the proposed neural network model is composed of four neural networks, it called multi- neural network (MANN). Each neural network consists of three layers, in which the input is solar radiation, and the module temperature and output are five physical parameters of the single diode model. The experimental data were divided into four groups and used for training the neural networks. The electrical properties of PV modules, including I–V curves, P– V curves, and normalized root mean square error, were obtained and discussed. The effectiveness and accuracy of this method is verified by the experimental data for different types of PV modules. Compared with the traditional single-ANN (SANN) method, the proposed method shows better accuracy under different operating conditions.