一种基于SARIMA-LSTM模型的电网主机负载预测方法

随着智能电网的不断发展,如何提高对信息设备运行状态的预测准确率以及设置适应数据变化的动态阈值区间是电网IT运维面临的巨大挑战。为了解决这些问题,提出了组合时间序列预测模型(SARIMA-LSTM),即在传统周期性ARIMA模型(SARIMA)的基础上,引入深度学习领域的LSTM模型,并摒弃了过去精度低、效果差的误差拟合方法,使用误差自回归方法来补偿预测结果。该模型可以学习到传统ARIMA模型无法捕捉到的误差波动规律,解决其无法预测非线性数据的问题。实验结果表明,在实际预测电网内存负载数据时,与ARIMA模型和SAIRIMA模型相比,SARIMA-LSTM模型可以实现更高的预测精度。     

Implementation of hybrid short-term load forecasting system with analysis of temperature sensitivities

Load forecasting is necessary for economic generation of power, economic allocation between plants (unit commitment scheduling), maintenance scheduling, and for system security such as peak load shaving by power interchange with interconnected utilities. A novel hybrid load forecasting algorithm, which combines the fuzzy support vector regression method and the linear extrapolation based on similar days method with the analysis of temperature sensitivities is presented in this paper. The fuzzy support vector regression method is used to consider the lower load-demands in weekends and Monday than on other weekdays. The normal load in weekdays is forecasted by the linear extrapolation based on similar days method. Moreover, the temperature sensitivities are used to improve the accuracy of the load forecasting in relation to the daily load and temperature. The result demonstrated the accuracy of the proposed load forecasting scheme.     

A SOM-based hybrid linear-neural model for short-term load forecasting

In this paper, a short-term load forecasting method is considered, which is based upon a flexible smooth transition autoregressive (STAR) model. The described model is a linear model with time varying coefficients, which are the outputs of a single hidden layer feedforward neural network. The hidden layer is responsible for partitioning the input space into multiple sub-spaces through multivariate thresholds and smooth transition between the sub-spaces. In this paper, we propose a new method to smartly initialize the weights of the hidden layer of the neural network before its training. A self-organizing map (SOM) network is applied to split the historical data dynamics into clusters, and the Ho-Kashyap algorithm is then used to obtain the separating planes' equations. Applied to the electricity markets, the proposed method is better able to model the smooth transitions between the different regimes, which are present in the load demand series because of market effects and season effects. We use data from three electricity markets to compare the prediction accuracy of the proposed method with traditional benchmarks and other recent models, and find our results to be competitive.     

基于动态双组粒子群的短期负荷预测

为提高电网短期负荷预测的精度,提出一种有效的优化支持向量机参数的算法。该算法首先将初始粒子群适应度排序,然后根据适应度的大小将初始粒子群划分为两组,并同时运用不同的权重进行全局搜索和局部搜索。前期,全局搜索的粒子群数量远多于局部搜索,且使用全局搜索能力强的较大的惯性权重;局部搜索的粒子群使用较小的惯性权重。随着迭代次数的增加,全局搜索的粒子群数量不断减少,局部搜索不断增多,两组粒子数量动态变化。并且引入平均粒距和适应度方差解决粒子群容易陷入局部最优这一问题,最后用改进的动态双组粒子群算法优化最小二乘支持向量机的参数用于短期负荷预测,实验结果表明该方法预测精度更高,可行且有效。     

ARIMA和RBF神经网络相融合的股票价格预测研究

针对股票价格的突变性、非线性和随机性,单一预测方法仅能描述股票价格片断信息等缺陷,提出一种股票价格组合预测模型。采用自回归移动平均模型（ARIMA）对股票价格进行预测,捕捉股票价格线性变化趋势。采用RBF神经网络对非线性、随机变化规律进行预测。将两者结果组合得到股票价格预测结果。采用组合模型对包钢股份（600010）股票收盘价进行仿真实验,结果表明,相对于单一预测模型,组合预测模型更加全面、准确刻画了股票价格的变化规律,提高了股票价格预测精度。     

蚁群神经网络在短期负荷预测的应用

为了进一步提高BP神经网络的性能,实现准确、快速预测电力系统负荷的目的,将蚁群算法(ACA)作为BP神经网络的学习算法,建立了一种新的蚁群神经网络(AcAN)预测模型.对某电力系统短期负荷预测的计算实例表明,基于蚁群神经网络的负荷预测方法与传统的BP神经网络预测方法相比,具有较强的自适应能力和较好的效果.     

Temporal,spatial, and constraint handling in the Conceptual Programming environment,CP

Abstract

The Conceptual Programming environment, CP, being developed at New Mexico State University (NMSU), is a complete knowledge representation programming environment for use with both dynamic, open-world, problem solving (weak) applications and static, closed-world, scientific analysis (strong) applications. CP is based upon a graphical methodology of visualization derived from John Sowa's conceptual graph theory. In this paper, we describe the formal basis for the internal CP representation and explain the mechanisms for the operators relating to the processing of time, space and constraints within the CP environment. The CP environment is a ‘working’ representation system, and makes a good foundation for suitable applications     

利用PSO-SA混合优化支持向量回归的径流预报模型研究

为了有效提高径流预报的准确度,提出一种有效的融合优化策略,采用基于粒子群和模拟退火算法相结合的混合方法同时优化支持向量回归核函数类型和内核参数,以此建立一种有效的混合优化支持向量回归径流预报模型。提出的方法为核函数选择和参数优化提供了一种有效途径。通过对广西柳州柳江径流实例分析,并与纯粹的支持向量回归模型对比,研究结果表明,该模型预测稳定,具有较高泛化性能和预测准确度,为径流预报提供了一种有效预测方法。     

基于组合预测模型的云计算资源负载预测研究

随着云计算技术的不断发展,云计算资源负载变化呈现出越来越复杂的特征。针对云计算资源的负载预测问题,综合考虑云计算环境中资源负载时间序列的线性与非线性特性,提出了一种基于自回归移动平均模型ARIMA与长短期记忆网络LSTM的组合预测模型LACL。使用公开数据集与传统负载预测模型进行了对比实验,实验结果表明,该云计算资源组合预测模型预测精度明显高于其他预测模型,显著 降低了云环境中对资源负载的实时预测误差。     

基于PSO-BP混合算法的短期电力负荷预测

将粒子群优化算法和BP神经网络算法相结合,形成粒子群一神经网络（PSO—BP）混合算法,建立了涉及各种影响因素的短期负荷预测模型。运用所建立的PSO-BP混合算法和BP算法的负荷预测模型进行短期负荷预测,比较所得结果可知,PSO-BP混合算法预测精度较高,效果较好。     

A novel combined model based on hybrid optimization algorithm for electrical load forecasting

Accurate electrical load forecasting always plays a vital role in power system administration and energy dispatch, which are the foundation of the smooth operation of the national economy and people’s daily life. Thinking from this vision, many scholars have made great efforts to seek suitable optimization algorithms to improve the performance of existing forecasting algorithm. However, most of the studies ignore the inherent disadvantages of single optimization algorithm, which leads to sub-optimal forecasting performance. Therefore, a novel electric load forecasting system was successfully proposed in this paper by the combination of data preprocessing, hybrid optimization algorithms, and several single classical forecasting methods, which successfully overcomes the defects of single traditional forecasting models and achieves higher forecasting accuracy than that of single model optimization. Besides, the 30 min interval data of Queensland, Australia from March to April is used as illustrative examples to evaluate the performance of the developed model. The results of tests demonstrate that the proposed hybrid model can better approximate the actual value, and it can also be employed as a useful tool for smart grids dispatching planning.     

基于相似日负荷修正算法的短期负荷预测

为实现准确、快速预测电力系统短期负荷的目的,综合考虑气象、日类型和时间对负荷的影响,提出了基于相似日负荷修正算法的预测模型.首先建立相似度量化模型,具体用灰色关联分析法计算气象相似度,兼顾"近大远小"和"周期性"原则来量化时间相似度,二者乘积作为总体相似度,依此选取若干相似日;然后基于"日类型"和"时间跨度"修正相似日负荷;最后用加权平均法预测负荷.短期负荷预测的实例结果表明了该算法的可行性.     

改进GA-BPNN在短期电力负荷预测中的应用

为了避免传统方法预测短期电力负荷建模复杂性,将改进遗传算法（GA）和误差反向传播（BP）算法相结合构成的混合算法用于训练人工神经网络,结合电力负荷历史数据,对短期电力负荷进行仿真预测。仿真结果表明,该混合算法有效地解决了常规BP算法学习网络权值收敛速度慢、易陷入局部极小和GA算法独立训练神经网络速度缓慢等问题,具有较快的收敛速度和较高的预测精度。     

基于多重核学习支持向量机短期负荷预测研究

近年来,支持向量机（SVM）方法在电力系统负荷预测领域的应用研究成为了热点,鉴于传统的标准支持向量机方法在预测时间和预测精度方面的不足,首次将多重核支持向量回归方法（Multiple Kernel Learning,MKL）应用于电力系统短期负荷预测领域。通过在混合核空间求解二次约束下的二次规划问题实现多重核支持向量回归算法。该方法较标准的支持向量回归算法,不仅可以提高预测性能,而且能够减少支持向量的个数。实际算例表明,该方法能够有效地提高预测精度,缩短预测时间,具有良好的泛化性能。     

基于EMD和SVR的混合智能预测模型及实证研究

针对非平稳、非线性时间序列变化复杂、难以用单一智能方法进行有效预测的问题,提出一种新的基于经验模式分解和支持向量回归的混合智能预测模型。经验模式分解能将非平稳时间序列按其内在的时间特征尺度自适应地分解为多个基本模式分量,根据这些分量各自趋势变化的剧烈程度选择不同的核函数进行支持向量回归预测,对各预测分量进行加权组合,得到原始序列的准确预测值。实证研究表明对于非平稳、非线性时间序列的预测,不论是单步预测还是多步预测,该模型均能取得很好的预测效果。     

基于包容性检验和证据理论的短期负荷预测

为了提高短期负荷的预测精度,提出一种包容性检验和证据理论的短期负荷组合预测模型(ET-DS).分别采用多个单一模型对短期负荷进行预测,采用包容性检验选择最合适的单一模型,利用证据理论获取单一模型的权值,实现短期负荷的组合预测,并采用短期负荷数据对模型性能进行仿真测试.仿真结果表明,相对单一模型及其它组合模型,ET-DS组合模型更加准确刻画了短期负荷变化趋势,提高了短期负荷预测精度,预测结果可为电力规划提供有价值参考意见.     

A methodology for short-term electric load forecasting based on specialized recursive digital filters

In this paper we propose a methodology for short-term electric load forecasting, which is adaptive and based on signal processing theory. The main interest here is to construct a next day predictor for the peak and hourly load. To this end the load data are organized into profiles according to day type and temperature interval. For each load profile, we use a specialized adaptive recursive digital filter, for which parameters are estimated on-line by using a recursive algorithm. As a result, the complete forecasting system is nonlinear and the prediction is computed based on the type and on the temperature interval of the next day. The effectiveness of the proposed methodology is illustrated by a numerical example, in which we compare performance of the proposed approach to a non-specialized and a naïve predictors, by using the Mean Absolute Percentage Error (MAPE) of the forecasting errors.     

基于ACS优化BP神经网络的交通流量短时预测方法

交通流量预测是智能交通系统中非常重要的研究领域,因为交通流量的复杂性,传统的预测方法不能很好地预测。提出一种基于[t]分布自适应变异优化的布谷鸟算法,通过动态变异控制尺度和设置多个自由度来构造自适应变异算法,可以获得优于高斯变异和柯西变异的整体优化效果。在此基础上,提出改进布谷鸟搜索算法优化神经网络的交通流量预测模型（ACS-BPNN）,通过优化BP神经网络的初始权值和阈值参数,以提高短时交通流量预测精度。仿真结果表明,该方法取得比较好的预测结果。     

Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression

BackgroundShort-term load forecasting is an important issue that has been widely explored and examined with respect to the operation of power systems and commercial transactions in electricity markets. Of the existing forecasting models, support vector regression (SVR) has attracted much attention. While model selection, including feature selection and parameter optimization, plays an important role in short-term load forecasting using SVR, most previous studies have considered feature selection and parameter optimization as two separate tasks, which is detrimental to prediction performance.ObjectiveBy evolving feature selection and parameter optimization simultaneously, the main aims of this study are to make practitioners aware of the benefits of applying unified model selection in STLF using SVR and to provide one solution for model selection in the framework of memetic algorithm (MA).MethodsThis study proposes a comprehensive learning particle swarm optimization (CLPSO)-based memetic algorithm (CLPSO-MA) that evolves feature selection and parameter optimization simultaneously. In the proposed CLPSO-MA algorithm, CLPSO is applied to explore the solution space, while a problem-specific local search is proposed for conducting individual learning, thereby enhancing the exploitation of CLPSO.ResultsCompared with other well-established counterparts, benefits of the proposed unified model selection problem and the proposed CLPSO-MA for model selection are verified using two real-world electricity load datasets, which indicates the SVR equipped with CLPSO-MA can be a promising alternative for short-term load forecasting.     

基于CS-HRVM的网络流量预测

为了获得更加理想的网络流量预测结果,准确刻画网络流量的变化趋势,提出一种基于布谷鸟搜索算法优化组合核相关向量机的网络流量预测模型（CS-HRVM）。首先针对网络流量的混沌特性,采用相空间理论建立网络流量的多维学习样本,并采用组合核函数构建相关向量机,然后将学习样本输入到相关向量机中进行训练,并采用布谷鸟搜索算法对模型参数进行优化,从而建立网络流量预测模型,最后采用仿真实验对模型性能进行仿真对比实验。结果表明,CS-HRVM获得了比其他网络流量预模型更高的预测精度,而且可以对含噪网络流量进行准确预测。