Short term and medium term power distribution load forecasting by neural networks

Load forecasting is an important subject for power distribution systems and has been studied from different points of view. In general, load forecasts should be performed over a broad spectrum of time intervals, which could be classified into short term, medium term and long term forecasts. Several research groups have proposed various techniques for either short term load forecasting or medium term load forecasting or long term load forecasting. This paper presents a neural network (NN) model for short term peak load forecasting, short term total load forecasting and medium term monthly load forecasting in power distribution systems. The NN is used to learn the relationships among past, current and future temperatures and loads. The neural network was trained to recognize the peak load of the day, total load of the day and monthly electricity consumption. The suitability of the proposed approach is illustrated through an application to real load shapes from the Turkish Electricity Distribution Corporation (TEDAS) in Nigde. The data represents the daily and monthly electricity consumption in Nigde, Turkey.     

Support vector machines for short‐term electrical load forecasting

Short‐term electrical load forecasting plays a vital role in the electric power industries. It ensures the availability of supply of electricity, as well as providing the means of avoiding over‐ and under‐utilization of generating capacity and therefore optimizes energy prices. Several methods have been applied to short‐term load forecasting, including statistical, regression and neural networks methods. This paper introduces support vector machines, the latest neural network algorithm, to short‐term electrical load forecasting and compares its performance with the auto‐regression model. The results indicate that support vector machines compare favourably against the auto‐regressive model using the same data for building and testing both models based on the root‐mean‐square errors between the actual and the predicted data. Support vector machines allow the training data set to be increased beyond what is possible using the auto‐regressive model or other neural networks methods. Increasing the training data further improves the performance of support vector machines method. Copyright © 2002 John Wiley & Sons, Ltd.     

Electric load analysis using an artificial neural network

Load forecasting in the current, increasingly liberalized, electricity power market is of crucial importance as a means for producers to optimize and rationalize energy supply. A number of electric power companies are equipped to make forecasts with the aid of traditional statistical methods. This paper presents the use of an artificial neural net to an hourly based load forecasting application for a small electric grid on an Italian island (Lipari) not connected to the mainland. The aim was to examine the forecasting ability of a neural net in a situation where the electric load was subject to considerable seasonal variations over the year. The variations are affected by energy demand related to the tourism season as well as by climatic conditions, especially temperature. The network developed was a multi‐layer perceptron type built on three layers trained with a back‐propagation algorithm. The input layer receives all the most relevant information regarding: the class of day type, the hour in the daytime, the load and background temperature recorded at the indicated time for the months of March, August and October whilst the output layer provides the forecast value at the indicated time in December. The results obtained are encouraging; in the training phase the RMS error rate was around 2% and this rate settled at about 2.6% during testing. As both the margins of error recorded are acceptable, the use of a neural network for electric load forecasting applications can be considered an attractive option. Copyright © 2005 John Wiley & Sons, Ltd.     

A new recursive neural network algorithm to forecast electricity price for PJM day‐ahead market

This paper evaluates the usefulness of publicly available electricity market information in predicting the hourly prices in the PJM day‐ahead electricity market using recursive neural network (RNN) technique, which is based on similar days (SD) approach. RNN is a multi‐step approach based on one output node, which uses the previous prediction as input for the subsequent forecasts. Comparison of forecasting performance of the proposed RNN model is done with respect to SD method and other literatures. To evaluate the accuracy of the proposed RNN approach in forecasting short‐term electricity prices, different criteria are used. Mean absolute percentage error, mean absolute error and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination (R²) of 0.7758 between load and electricity price. Error variance, one of the important performance criteria, is also calculated in order to measure robustness of the proposed RNN model. The numerical results obtained through the simulation to forecast next 24 and 72 h electricity prices show that the forecasts generated by the proposed RNN model are significantly accurate and efficient, which confirm that the proposed algorithm performs well for short‐term price forecasting. Copyright © 2009 John Wiley & Sons, Ltd.     

Wavelet transform and neural networks for short-term electrical load forecasting

Demand forecasting is key to the efficient management of electrical energy systems. A novel approach is proposed in this paper for short term electrical load forecasting by combining the wavelet transform and neural networks. The electrical load at any particular time is usually assumed to be a linear combination of different components. From the signal analysis point of view, load can also be considered as a linear combination of different frequencies. Every component of load can be represented by one or several frequencies. The process of the proposed approach first decomposes the historical load into an approximate part associated with low frequencies and several detail parts associated with high frequencies through the wavelet transform. Then, a radial basis function neural network, trained by low frequencies and the corresponding temperature records is used to predict the approximate part of the future load. Finally, the short term load is forecasted by summing the predicted approximate part and the weighted detail parts. The approach has been tested by the 1997 data of a practical system. The results show the application of the wavelet transform in short term load forecasting is encouraging.     

Short term wind speed forecasting in La Venta,Oaxaca, México,using artificial neural networks

In this paper the short term wind speed forecasting in the region of La Venta, Oaxaca, Mexico, applying the technique of artificial neural network (ANN) to the hourly time series representative of the site is presented. The data were collected by the Comisión Federal de Electricidad (CFE) during 7 years through a network of measurement stations located in the place of interest. Diverse configurations of ANN were generated and compared through error measures, guaranteeing the performance and accuracy of the chosen models. First a model with three layers and seven neurons was chosen, according to the recommendations of diverse authors, nevertheless, the results were not sufficiently satisfactory so other three models were developed, consisting of three layers and six neurons, two layers and four neurons and two layers and three neurons. The simplest model of two layers, with two input neurons and one output neuron, was the best for the short term wind speed forecasting, with mean squared error and mean absolute error values of 0.0016 and 0.0399, respectively. The developed model for short term wind speed forecasting showed a very good accuracy to be used by the Electric Utility Control Centre in Oaxaca for the energy supply.     

基于PSO聚类分析与BP网络的短期电力负荷预测

针对短期负荷预测特点, 提出一种基于PSO聚类分析和BP网络的短期负荷预测方法, 通过PSO聚类分析将负荷历史数据分成若干类对输入数据预处理,建立了相应BP网络模型,采用附加动量和变学习速率法预测每小时负荷.以华东某地区实际负荷预测为例,分析结果表明,该方法适应性强、预测精度高、结果满意.     

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。     

西北电网短期负荷预测软件系统的设计与实现

本文介绍了西北电网短期负荷预测软件系统。该系统包含相似日、时间序列、人工神经网络和偏最小二乘回归分析四种短期负荷预测方法。预测结果表明该系统能够满足西北电网短期负荷预测的需要,预测结果合理,界面友好、操作方便,在很大程度上提高了调度人员的劳动效率。     

基于BP神经网络灰色回归组合模型的年最大负荷预测

为克服单一电力负荷预测模型的局限性,改善预测结果,提出了一种基于BP神经网络灰色回归组合模型的年最大负荷预测方法。在BP神经网络预测模型中,采用Levenberg-Marquardt算法对参数迭代过程进行优化;在灰色预测模型中,采用加政策因子处理法对原始数列进行改造以强化数列的递增趋势;在回归预测模型中,采用逐步线性回归法剔除对因变量影响较小的自变量。最后利用方差-协方差法对三种预测模型进行加权组合。以广州市2007—2016年实际数据对组合预测模型进行验证,并对广州市2017—2019年的年最大负荷进行预测。结果表明:所提方法预测精度较高且误差在工程允许范围之内,具有一定的工程实用价值。     

Medium-term electric load forecasting using singular value decomposition

Medium-term load forecasting is an important stage in electric power system planning and operation. It is used in maintenance scheduling, and to plan for outages and major works in the power system. A new technique is proposed which uses hourly loads of successive years to predict hourly loads and peak load for the next selected time span. The proposed method implements a new combination of some existing and well established techniques. This is done by first filtering out the load trend, then applying the SVD (singular value decomposition) technique to de-noise the resulting signal. Hourly load is thus divided to three main components: a) a load trend-following component, b) a random component, and c) a de-noised component. Results of applying the technique to the Jordanian power system showed that good forecasting accuracies are attained. In addition, the proposed method outperforms the traditional exponential curve fitting method. The peak load error was found to be less than 5% using the proposed methodology. It was also found that a lag period of 4 years suits the load forecasting purposes of the Jordanian power system. The proposed method is generic and can be implemented to the hourly loads of any power system.     

基于长短期记忆神经网络的饱和负荷预测方法及应用

为充分分析关联因素对饱和负荷水平的影响,针对饱和负荷预测不确定性强、时间相关性大的特点,利用长短期记忆神经网络的长期记忆单元与可遗忘机制保存和更新历史用电信息,构建了多输入的长短期记忆神经网络饱和负荷预测模型。首先提取出人口、经济等6个影响因素作为网络模型输入量,采用Adam优化方法训练网络模型,并在多场景下,运用优化后的模型进行饱和负荷预测,结合饱和判据得到最终的饱和时间与用电规模。某省电网的饱和负荷预测结果表明,所建模型及预测方法合理、有效。     

A computer program for 24-hour electric utility load forecasting

A computerized statistical model is described which makes twenty-four hourly forecasts of the total load supplied by an electric utility company. Weather forecasts are included in the load-forecasting process. The root-mean-square hourly forecasting error was less than 2% of the typical daily peak load in three weeks of testing.     

Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method

Wind speed is the major factor that affects the wind generation, and in turn the forecasting accuracy of wind speed is the key to wind power prediction. In this paper, a wind speed forecasting method based on improved empirical mode decomposition (EMD) and GA-BP neural network is proposed. EMD has been applied extensively for analyzing nonlinear stochastic signals. Ensemble empirical mode decomposition (EEMD) is an improved method of EMD, which can effectively handle the mode-mixing problem and decompose the original data into more stationary signals with different frequencies. Each signal is taken as an input data to the GA-BP neural network model. The final forecasted wind speed data is obtained by aggregating the predicted data of individual signals. Cases study of a wind farm in Inner Mongolia, China, shows that the proposed hybrid method is much more accurate than the traditional GA-BP forecasting approach and GA-BP with EMD and wavelet neural network method. By the sensitivity analysis of parameters, it can be seen that appropriate settings on parameters can improve the forecasting result. The simulation with MATLAB shows that the proposed method can improve the forecasting accuracy and computational efficiency, which make it suitable for on-line ultra-short term (10 min) and short term (1 h) wind speed forecasting.     

On the use of reactive power as an endogenous variable in short‐term load forecasting

In the last decades, short‐term load forecasting(STLF) has been the object of particular attention in the power systems field. STLF has been applied almost exclusively to the generation sector, based on variables, which are transversal to most models. Among the most significant variables we can find load, expressed as active power (MW), as well as exogenous variables, such as weather and economy‐related ones; although the latter are applied in larger forecasting horizons than STLF. In this paper, the application of STLF to the distribution sector is suggested including inductive reactive power as a forecasting endogenous variable. The inclusion of this additional variable is mainly due to the evidence that correlations between load and weather variables are tenuous, due to the mild climate of the actual case‐study system and the consequent feeble penetration of electrical heating ventilation and air conditioning loads. Artificial neural networks (ANN) have been chosen as the forecasting methodology, with standard feed forward back propagation algorithm, because it is a largely used method with generally considered satisfactory results. Usually the input vector to ANN applied to load forecasting is defined in a discretionary way, mainly based on experience, on engineering judgement criteria and on concern about the ANN dimension, always taking into consideration the apparent (or actually evaluated) correlations within the available data. The approach referred in the paper includes pre‐processing the data in order to influence the composition of the input vector in such a way as to reduce the margin of discretion in its definition. A relative entropy analysis has been performed to the time series of each variable. The paper also includes an illustrative case study. Copyright © 2003 John Wiley & Sons, Ltd.     

基于逆推理论改进模糊均生函数的短期负荷预测

为提高短期电力负荷预测精度,针对电力负荷序列的周期性、随机波动性等特点,提出一种基于逆推理论改进模糊均生函数的短期负荷预测模型。该模型先将模糊均生函数算法引入负荷预测领域,同时应用逆推理论改进模糊均生函数的构造过程,然后将其与最优子集回归算法相结合,建立短期负荷预测模型,最后使用该模型进行预测。以山东电网某市的负荷数据为例,对该模型进行了验证,并与实际负荷数据及传统均生函数模型的预测结果进行对比。结果表明,所提模型能有效提高短期负荷预测的精度,具有很好的实用性。     

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.     

基于RBF神经网络与模糊控制的短期负荷预测

针对电力系统短期负荷预测,综合考虑温度、日期类型和天气等因素对短期电力负荷的影响,建立了径向基函数（Radial?Basis?Function,RBF）神经网络和模糊控制相结合的短期负荷预测模型。该模型利用RBF神经网络的非线性逼近能力对预测日负荷进行了预测,并采用在线自调整因子的模糊控制对预测误差进行在线智能修正。实际算例表明RBF神经网络与模糊控制相结合提高了预测精度。     

Combined use of unsupervised and supervised learning for daily peak load forecasting

In this paper, we have aimed to present a hybrid neural network model for daily electrical peak load forecasting (PLF). Since peak loads usually follow similar patterns, classification of data improves the accuracy of the forecasts. Several factors in peak load, e.g. weather temperature, relative humidity, wind speed and cloud cover, were introduced into the model in order to enhance forecast quality. Most classification attempts in the literature have been intuitive and empty of justification. In this paper, we have proposed a novel approach for clustering data by using a self-organizing map. The Davies–Bouldin validity index was introduced to determine the best clusters. A feed forward neural network (FFNN) has been developed for each cluster to provide the PLF. Eight training algorithms have also been used in order to train the proposed FFNNs. Applying principal component analysis (PCA) decreased the dimensions of the network’s inputs and led to simpler architecture. To evaluate the effectiveness of the proposed hybrid model (PHM), forecasting has been performed by developing a FFNN that uses the un-clustered data. The results proved the superiority and effectiveness of the PHM. Linear regression (LR) models have also been developed for PLF, and the results indicated that the PHM produces considerably better forecasts than those of LR models. Furthermore, the results show that the suggested clustering approach significantly improves the forecasting results on regression analysis too.     

An efficient approach for electric load forecasting using distributed ART (adaptive resonance theory) & HS-ARTMAP (Hyper-spherical ARTMAP network) neural network

This paper presents a neural network based on adaptive resonance theory, named distributed ART (adaptive resonance theory) & HS-ARTMAP (Hyper-spherical ARTMAP network), applied to the electric load forecasting problem. The distributed ART combines the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multi-layer perceptions. The HS-ARTMAP, a hybrid of an RBF (Radial Basis Function)-network-like module which uses hyper-sphere basis function substitute the Gaussian basis function and an ART-like module, performs incremental learning capabilities in function approximation problem. The HS-ARTMAP only receives the compressed distributed coding processed by distributed ART to deal with the proliferation problem which ARTMAP (adaptive resonance theory map) architecture often encounters and still performs well in electric load forecasting. To demonstrate the performance of the methodology, data from New South Wales and Victoria in Australia are illustrated. Results show that the developed method is much better than the traditional BP and single HS-ARTMAP neural network.