Application of chaotic ant swarm optimization in electric load forecasting

Support vector regression (SVR) had revealed strong potential in accurate electric load forecasting, particularly by employing effective evolutionary algorithms to determine suitable values of its three parameters. Based on previous research results, however, these employed evolutionary algorithms themselves have several drawbacks, such as converging prematurely, reaching slowly the global optimal solution, and trapping into a local optimum. This investigation presents an SVR-based electric load forecasting model that applied a novel algorithm, namely chaotic ant swarm optimization (CAS), to improve the forecasting performance by searching its suitable parameters combination. The proposed CAS combines with the chaotic behavior of single ant and self-organization behavior of ant colony in the foraging process to overcome premature local optimum. The empirical results indicate that the SVR model with CAS (SVRCAS) results in better forecasting performance than the other alternative methods, namely SVRCPSO (SVR with chaotic PSO), SVRCGA (SVR with chaotic GA), regression model, and ANN model.     

An adaptive fuzzy combination model based on self-organizing map and support vector regression for electric load forecasting

Electric load forecasting is an important task in the daily operations of a power utility associated with energy transfer scheduling, unit commitment and load dispatch. Inspired by the various non-linearity of electric load data and the strong learning capacity of support vector regression (SVR) for small sample and balanced data, this paper presents an adaptive fuzzy combination model based on the self-organizing map (SOM), the SVR and the fuzzy inference method. The adaptive fuzzy combination model can effectively count for electric load forecasting with good accuracy and interpretability at the same time. The key idea behind the combination is to build a human-understandable knowledge base by constructing a fuzzy membership function for each homogeneous sub-population. The comparison of different mathematical models and the effectiveness of the presented model are shown by the real data of New South Wales electricity market. The obtained results confirm the validity of the developed model.     

Combined modeling for electric load forecasting with adaptive particle swarm optimization

Electric load forecasting is crucial for managing electric power systems economically and safely. This paper presents a new combined model for electric load forecasting based on the seasonal ARIMA forecasting model, the seasonal exponential smoothing model and the weighted support vector machines. The combined model can effectively count for the seasonality and nonlinearity shown in the electric load data and give more accurate forecasting results. The adaptive particle swarm optimization is employed to optimize the weight coefficients in the combined forecasting model. The proposed combined model has been compared with the individual models and the other combined model reported in the literature and its results are promising.     

基于加权最小二乘支持向量机的月度负荷预测

考虑到实际电力负荷预测中各数据的重要程度并不相同,在标准最小二乘支持向量机回归算法的训练样本中设置权值系数,建立了加权最小二乘支持向量机模型,以实现样本的优化选择,达到历史数据"重近轻远"的学习效果;同时考虑到粒子群优化算法收敛速度快和混沌运动遍历性、随机性等特点,提出了一种基于混沌思想的粒子群优化算法对模型参数进行优化,引入优势粒子和劣势粒子的权重自适应调节机制,使算法具有动态适应性。将改进的模型应用于江西省萍乡市月度负荷预测中,结果表明本文方法与常规方法相比降低了预测误差,且速度较快。     

奇异谱分析-支持向量回归机耦合模型在月降水量预测中的应用

降水通常是一个地区水资源的主要补给来源,其准确预测对于水资源量的预测等十分重要。为提高降水量的预测精度,以吉林省西部某气象站为例,采用奇异谱分析对月降水量数据进行预处理,提取出多个独立的子序列,再利用支持向量回归机对不同子序列单独建立预测模型,对不同子序列预测模型的输出值求和即可得到该耦合模型的预测值,并利用该耦合模型(SSA-SVR)与小波分析-支持向量回归机耦合模型(WA-SVR)以及在原始降水量数据基础上建立的支持回归机预测模型(SVR)对其月降水量进行步长为1个月、3个月以及6个月的预测。结果表明,三种模型中,SSA-SVR模型的预测值与实测值最为接近,预测精度更高。     

基于灰色关联分析与随机森林回归模型的短期负荷预测

针对人工神经网络和支持向量机存在的泛化误差大、具有局部最优以及参数选取困难等缺点,将随机森林回归模型引入电力系统短期负荷预测,提出了一种基于相似日与随机森林回归模型的短期负荷预测方法。利用灰色关联分析法计算原始训练样本与预测日各影响因素间的关联系数,选取相似度较高的历史样本构成相似日样本集,对随机森林回归模型进行训练。将预测日的特征向量输入训练好的模型中,取所有回归树输出结果的平均值作为最终的负荷预测结果。实际算例表明,与常规支持向量机法和常规随机森林回归法相比,该组合方法可以有效地提高短期负荷预测的精度。     

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.     

Machine learning based switching model for electricity load forecasting

In deregulated power markets, forecasting electricity loads is one of the most essential tasks for system planning, operation and decision making. Based on an integration of two machine learning techniques: Bayesian clustering by dynamics (BCD) and support vector regression (SVR), this paper proposes a novel forecasting model for day ahead electricity load forecasting. The proposed model adopts an integrated architecture to handle the non-stationarity of time series. Firstly, a BCD classifier is applied to cluster the input data set into several subsets by the dynamics of the time series in an unsupervised manner. Then, groups of SVRs are used to fit the training data of each subset in a supervised way. The effectiveness of the proposed model is demonstrated with actual data taken from the New York ISO and the Western Farmers Electric Cooperative in Oklahoma.     

Short‐term load forecasting based on support vector regression and load profiling

The article proposes a methodology to forecast the electric load for the 24 h of the following day based on support vector regression. The study considers 24 distinct models, one for each predicted hour, where each individual model is treated independently. Its objective is to find the optimal combination of support vector machine parameters that could generalize low forecasting errors, using simulated annealing as a metaheuristic. The adopted methodology is compared to concurrent methods based on neural networks when applied to a simulated load diagram (to illustrate a distribution feeder supplying a sample of 740 consumers). The results have proven its effectiveness with mean absolute percentage errors being less than 5% for testing samples. The study also focuses on evaluating the potential benefits of adopting load profiling information as input in support vector regression, giving a consistent proof of its importance. Copyright © 2013 John Wiley & Sons, Ltd.     

基于小波分析的并行膜混合核支持向量机月度负荷预测

针对现代电力系统月负荷数据的趋势增长性和波动性的非线性特征,提出了一种基于小波变换的混合支持向量机负荷预测模型。通过小波变换将负荷序列分解为不同尺度的子序列,考虑负荷的季节波动性,将温度因素作为输入变量,构建混合核函数LWPSO-LSSVM。将负荷子序列分别放入膜系统的基本膜中进行并行预测,然后对子序列预测数据进行重构得到预测结果。利用四川省某地区电网负荷数据进行应用研究,结果表明所提出的模型较传统核函数支持向量机预测精度和效率有明显提高。     

基于分位回归鲁棒极限学习机的短时负荷预测方法

针对短期负荷预测对电力系统运行管理和优化调度的影响,提出一种基于分位回归鲁棒极限学习机的短时负荷预测方法,即先对所收集的历史负荷数据进行归一化处理,然后利用自相关分析提取最相关的历史负荷数据作为模型的输入变量,再融合鲁棒极限学习机和分位回归建立负荷预测基本模型,最后利用某电力公司2016年采样频率为30min的数据进行实例分析,试验数据表明相比极限学习机(ELM)、分位回归(QR)和分位回归支持向量机(QR-SVM),所提模型预测精度更高,验证了所提模型和算法的可行性和有效性。     

A multi-granularity heterogeneous combination approach to crude oil price forecasting

Crude oil price forecasting has attracted much attention due to its significance on commodities market as well as nonlinear complexity in prediction task. Combining forecasts in different granular spaces, we propose a multi-granularity heterogeneous combination approach to enhance forecasting accuracy in the study. Firstly, we introduce various feature selection techniques including filter, wrapper and embedded methods, to identify key factors that affect crude oil price and construct different granular spaces. Secondly, distinct feature subsets distinguished by different feature selection methods are incorporated to generate individual forecasts using three popular forecasting models including Linear regression (LR), Artificial neural network (ANN) and Support vector machine (SVR). Finally, the final forecasts are obtained by combining the forecasts from individual forecasting model in each granular space and the optimal weighting vector is achieved by artificial bee colony (ABC) techniques. The experimental results demonstrate that the proposed multi-granularity heterogeneous combination approach based on ABC can outperform not only individual competitive benchmarks but also single-granularity heterogeneous and multi-granularity homogenous approaches.     

基于能量熵重构与支持向量回归的水电机组状态趋势预测

针对水电机组运行状态趋势预测的问题,提出了一种基于能量熵重构(EER)与支持向量回归(SVR)的混合预测模型。先针对复杂非平稳监测信号,利用快速集成经验模态分解(FEEMD)算法将其分解为多个本征模态函数(IMFs)分量和单个残余分量;然后基于能量熵(EE)理论对各分量进行重构,以有效降低分量的复杂度;最后,将生成的重构本征模态函数(RIMFs)作为SVR的输入,训练模型参数得到最优的SVR,用于预测机组状态发展趋势。与实例对比分析表明,所提混合预测模型具有较高的预测精度,为机组运维策略的制定提供了一定的指导。     

A novel seasonal decomposition based least squares support vector regression ensemble learning approach for hydropower consumption forecasting in China

Due to the distinct seasonal characteristics of hydropower, this study tries to propose a seasonal decomposition (SD) based least squares support vector regression (LSSVR) ensemble learning model for Chinese hydropower consumption forecasting. In the formulation of ensemble learning model, the original hydropower consumption series are first decomposed into trend cycle, seasonal factor and irregular component. Then the LSSVR with the radial basis function (RBF) kernel is used to predict the three different components independently. Finally, these prediction results of the three components are combined with another LSSVR to formulate an ensemble result for the original hydropower consumption series. In terms of error measurements and statistic test on the forecasting performance, the proposed approach outperforms all the other benchmark methods listed in this study in both level accuracy and directional accuracy. Experimental results reveal that the proposed SD-based LSSVR ensemble learning paradigm is a very promising approach for complex time series forecasting with seasonality.     

The application of seasonal latent variable in forecasting electricity demand as an alternative method

In this study, we used ARIMA, seasonal ARIMA (SARIMA) and alternatively the regression model with seasonal latent variable in forecasting electricity demand by using data that belongs to “Kayseri and Vicinity Electricity Joint-Stock Company” over the 1997:1–2005:12 periods. This study tries to examine the advantages of forecasting with ARIMA, SARIMA methods and with the model has seasonal latent variable to each other. The results support that ARIMA and SARIMA models are unsuccessful in forecasting electricity demand. The regression model with seasonal latent variable used in this study gives more successful results than ARIMA and SARIMA models because also this model can consider seasonal fluctuations and structural breaks.     

基于H-P滤波预测技术的年用电量预测模型研究

针对电力市场预测电力负荷受众多因素影响及各类预测模型模拟预测误差较大的问题,为提高负荷预测精度,基于H-P滤波预测法将等维信息法、指数回归模型及分布滞后回归模型引入年用电量预测中,通过双层预测降低预测误差,并结合实例比较。对比结果,滤波滞后回归模型的预测综合得分高于滤波指数回归模型。     

Using machine learning tools for forecasting natural gas consumption in the province of Istanbul

Commensurate with unprecedented increases in energy demand, a well-constructed forecasting model is vital to managing energy policies effectively by providing energy diversity and energy requirements that adapt to the dynamic structure of the country. In this study, we employ three alternative popular machine learning tools for rigorous projection of natural gas consumption in the province of Istanbul, Turkey's largest natural gas-consuming mega-city. These tools include multiple linear regression (MLR), an artificial neural network approach (ANN) and support vector regression (SVR). The results indicate that the SVR is much superior to ANN technique, providing more reliable and accurate results in terms of lower prediction errors for time series forecasting of natural gas consumption. This study could well serve a useful benchmarking study for many emerging countries due to the data structure, consumption frequency, and consumption behavior of consumers in various time-periods.     

Nonlinear multivariable modeling of locomotive proton exchange membrane fuel cell system

A nonlinear multivariable model of a locomotive proton exchange membrane fuel cell (PEMFC) system based on a support vector regression (SVR) is proposed to study the effect of different operating conditions on dynamic behavior of a locomotive PEMFC power unit. Furthermore, an effective informed adaptive particle swarm optimization (EIA-PSO) algorithm which is an adaptive swarm intelligence optimization with preferable search ability and search rate is utilized to tune the hyper-parameters of the SVR model for the improvement of model performance. The comparisons with the experimental data demonstrate that the SVR model based on EIA-PSO can efficiently approximate the dynamic behaviors of locomotive PEMFC power unit and is capable of predicting dynamic performance in terms of the output voltage and power with a high accuracy.     

Biohydrogen from food waste: Modeling and estimation by machine learning based super learner approach

This study demonstrated the application of a hybrid Bayesian algorithm (BA) and support vector regression (SVR) as a potential super-learner tool (BA-SVR) to predict biohydrogen production from food waste-originated feedstocks. The novelty of the present approach, as compared to the existing response surface methodology (RSM), includes (i) hybridization of BA with SVR for modeling of biohydrogen production and minimization of biomethane formation, (ii) performance evaluation and comparison of the developed BA-SVR models with the existing RSM models based on the several indicators such as coefficient of determination (R²), relative error (RE), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE), (iii) analysis of the robustness of the model and (iv) testing generalization ability. The calculated values of these indicators suggested that the proposed super leaner models demonstrated better performance predicting the biohydrogen and biomethane (products) responses than those using the existing RSM models - as reported in Rafieenia et al. 2019 [45]. The estimated low errors for biohydrogen: MAE = 0.5919, RMSE = 0.592, MAPE = 11.1387; for biomethane: MAE = 0.2681, RMSE = 0.2688, MAPE = 0.3708, signifie the reliable model predictions. The BA-SVR model also provided high adj R² (>0.99 for both biohydrogen and biomethane), indicating an excellent fitting of the model. Concerning the MAPE, the proposed BA-SVR models for both the biohydrogen and biomethane responses showed superior performances (as compared to the RSM models) with a performance enhancement of 64.16% and 98.81%, respectively.     

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.