Short-Term Household Load Forecasting Based on Attention Mechanism and CNN-ICPSO-LSTM

Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.

A hybrid model for short-term rainstorm forecasting based on a back-propagation neural network and synoptic diagnosis

Rainstorms are one of the most important types of natural disaster in China.In order to enhance the ability to forecast rainstorms in the short term,this paper explores how to combine a back-propagation neural network(BPNN)with synoptic diagnosis for predicting rainstorms,and analyzes the hit rates of rainstorms for the above two methods using the county of Tianquan as a case study.Results showed that the traditional synoptic diagnosis method still has an important referential meaning for most rainstorm types through synoptic typing and statistics of physical quantities based on historical cases,and the threat score(TS)of rainstorms was more than 0.75.However,the accuracy for two rainstorm types influenced by low-level easterly inverted troughs was less than 40%.The BPNN method efficiently forecasted these two rainstorm types;the TS and equitable threat score(ETS)of rainstorms were 0.80 and 0.79,respectively.The TS and ETS of the hybrid model that combined the BPNN and synoptic diagnosis methods exceeded the forecast score of multi-numerical simulations over the Sichuan Basin without exception.This kind of hybrid model enhanced the forecasting accuracy of rainstorms.The findings of this study provide certain reference value for the future development of refined forecast models with local features.

Hybrid partial least squares and neural network approach for short-term electrical load forecasting

Intelligent systems and methods such as the neural network （NN） are usually used in electric power systems for short-term electrical load forecasting. However, a vast amount of electrical load data is often redundant, and linearly or nonlinearly correlated with each other. Highly correlated input data can result in erroneous prediction results given out by an NN model. Besides this, the determination of the topological structure of an NN model has always been a problem for designers. This paper presents a new artificial intelligence hybrid procedure for next day electric load forecasting based on partial least squares （PLS） and NN. PLS is used for the compression of data input space, and helps to determine the structure of the NN model. The hybrid PLS-NN model can be used to predict hourly electric load on weekdays and weekends. The advantage of this methodology is that the hybrid model can provide faster convergence and more precise prediction results in comparison with abductive networks algorithm. Extensive testing on the electrical load data of the Puget power utility in the USA confirms the validity of the proposed approach.

Load-forecasting method for IES based on LSTM and dynamic similar days with multi-features

To fully exploit the rich characteristic variation laws of an integrated energy system(IES)and further improve the short-term load-forecasting accuracy,a load-forecasting method is proposed for an IES based on LSTM and dynamic similar days with multi-features.Feature expansion was performed to construct a comprehensive load day covering the load and meteorological information with coarse and fine time granularity,far and near time periods.The Gaussian mixture model(GMM)was used to divide the scene of the comprehensive load day,and gray correlation analysis was used to match the scene with the coarse time granularity characteristics of the day to be forecasted.Five typical days with the highest correlation with the day to be predicted in the scene were selected to construct a“dynamic similar day”by weighting.The key features of adjacent days and dynamic similar days were used to forecast multi-loads with fine time granularity using LSTM.Comparing the static features as input and the selection method of similar days based on non-extended single features,the effectiveness of the proposed prediction method was verified.

A SELF-SIMILAR LOCAL NEURO-FUZZY MODEL FOR SHORT-TERM DEMAND FORECASTING

This paper proposes a selfsimilar local neurofuzzy （SSLNF） model with mutual informati onbased input selection algorithm for the shortterm electricity demand forecasting. The proposed self similar model is composed of a number of local models, each being a local linear neurofuzzy （LLNF） model, and their associated validity functions and can be interpreted itself as an LLNF model. The proposed model is trained by a nested local liner model tree （NLOLIMOT） learning algorithm which partitions the input space into axisorthogonal subdomains and then fits an LLNF model and its associated validity function on each subdomain. Furthermore, the proposed approach allows different input spaces for rule premises （validity functions） and consequents （local models）. This appealing property is employed to assign the candidate input variables （i.e., previous load and temperature） which influence shortterm electricity demand in linear and nonlinear ways to local models and validity functions, respectively. Numerical results from shortterm load forecasting in the New England in 2002 demonstrated the accuracy of the SSLNF model for the STLF applications.

Typical load profile-supported convolutional neural network for short-term load forecasting in the industrial sector

This paper investigates how existing forecasting models can be enhanced to accurately forecast the electric load at factory level,enabling industrial companies to shift consumption to times of low energy costs.The model architecture must outperform state-of-the-art models and be sufficiently robust for use in multiple factories with low effort for specific applications.Moreover,this work focuses on the processing of high-resolution input data available almost in real time from multiple submeters after the main meters.The theory of load forecasting and related works are summarized in a first step including the requirements of forecasting models applied at factory level.Based on existing models,a new hybrid machine-learning model is proposed,combining a decision tree-based typical load profiler with a convolutional neural network that extracts features from multidimensional endogenous inputs with measurements of the preceding two weeks for multi-step-ahead load forecasts updated almost in real time.Furthermore,a multi-model approach is presented for calculating bottom-up forecasts with submeter data aggregated to a main-meter forecast.In a case study,the forecasting accuracy of the hybrid model is compared to both base models and a seasonal naïve model calculating the load forecasts for three factories.The results indicate that the proposed typical-load-profile-supported convolutional neural network for all three factories achieves the lowest forecasting error.Furthermore,it is validated that a reduction in data transfer delay leads to better forecasts,as the forecasting accuracy is higher with near real time data than with a data transfer delay of one day.Thus,a model architecture is proposed for robust forecasting in digitalized factories.

基于CNN-BiGRU-Attention的短期电力负荷预测

针对目前电力负荷数据随机性强,影响因素复杂,传统单一预测模型精度低的问题,结合卷积神经网络(Convolutional neural network,CNN)、双向门控循环单元(Bi-directional gated recurrent unit,BiGRU)以及注意力机制(Attention)在短期电力负荷预测上的不同优点,提出一种基于CNN-BiGRU-Attention的混合预测模型。该方法首先通过CNN对历史负荷和气象数据进行初步特征提取,然后利用BiGRU进一步挖掘特征数据间时序关联,再引入注意力机制,对BiGRU输出状态给与不同权重,强化关键特征,最后完成负荷预测。试验结果表明,该模型的平均绝对百分比误差(Mean absolute percentage error,MAPE)、均方根误差(Root mean square error,RMSE)、判定系数(R-square,R~2)分别为0.167%、0.057%、0.993,三项指标明显优于其他模型,具有更高的预测精度和稳定性,验证了模型在短期负荷预测中的优势。

基于CNN-LSTM电力消耗预测模型及系统开发

有效预测电能负荷,对提高电力负荷时间序列测量准确度及合理制定用电能管理措施具有重要意义。针对传统预测模型在电能负荷预测中无法充分挖掘时间序列数据中隐藏特征的问题,基于电能数据时间序列的趋势,融合数值信息提出一种卷积神经网络(convolutional neuralnetwork,CNN)与长期短期记忆循环神经网络(long short-term memory network,LSTM)相结合的混合多隐层CNN-LSTM电力能耗预测模型。首先,通过设定最小目标函数作为优化目标,Adam优化算法更新神经网络的权重,并对网络层和批大小进行自适应调优以确定最佳层数和批大小。其次,构建混合多隐层模型并进行隐层组合优化与讨论,确定最佳时间维度的参数,进行时间维度的特征学习进而预测下一时间序列的耗电量。然后以某公司的电力负荷数据为例进行验证,并与LSTM、CNN、RNN等模型的预测结果分析比较。结果表明上述混合多隐层模型预测准确度达98.94%,平均绝对误差(MAE)达到0.0066,均优于其他相关模型,证明以上混合预测模型在电力负荷预测精度方面具有更好的性能。基于上述理论,开发了能耗监控决策系统,实现设备状态实时监控和能耗智能预测功能,为解决传统制造业能耗需求不精确和能源库存浪费问题提供参考和指导。

基于TVF-EMD-SVM-GRU混合模型的短期电网负荷预测

短期电网负荷表现出非规律的波动性和非稳定的周期性,对其进行准确预测是一项挑战。采用时变滤波的经验模态分解,对一维观测信号进行分解,得到具有不同尺度特征的固有模态函数。通过随机重构构造一个新的观测值,形成二维矩阵。引入支持向量机来替代门控循环单元最终输出层中的归一化指数函数,并将交叉熵函数替换为基于边缘的函数,从而进行基于混合模型的短期电网负荷预测。试验结果表明,与大间隔最近邻算法、卷积神经网络以及融合门控循环单元的支持向量机相比,混合模型的计算成本虽然稍高,但均方根误差和平均绝对误差都是最小的。因此,混合模型具有最好的预测性能,可用于短期电网负荷预测。

Forecasting Daily Electric Load by Applying Artificial Neural Network with Fourier Transformation and Principal Component Analysis Technique

In this paper,we propose a hybrid forecasting model(HFM)for the short-term electric load forecasting using artificial neural network(ANN),discrete Fourier transformation(DFT)and principal component analysis(PCA)techniques in order to attain higher prediction accuracy.Firstly,we estimate Fourier coefficients by the DFT for predicting the next-day load curve with an ANN and obtain approximate load curves by applying the inverse discrete Fourier transformation.Approximate curves,together with other input variables,are given to the ANN to predict the next-day hourly load curves.Furthermore,we predict PCA scores to obtain approximate load curves in the first step,which are then given to the ANN again in the second step.Both DFT and PCA models use input variables such as calendrical and meteorological data as well as past electric loads.Applying those models for forecasting hourly electric load in the metropolitan area of Japan for January and May in 2018,we train our models using historical data since January 2008.The forecast results show that the HFM consisting of“ANN with DFT”and“ANN with PCA”predicts next-day hourly loads more accurately than the conventional three-layered ANN approach.Their corresponding mean average absolute errors show 2.7%for ANN with DFT,2.6%for ANN with PCA and 3.0%for the conventional ANN approach.We also find that in May,when electric demand is smaller with smaller fluctuations,forecasting errors are much smaller than January for all the models.Thus,we can conclude that the HFM would contribute to attaining significantly higher forecasting accuracy.

最小信息损失综合短期负荷预测(二):算法和算例

该文引入信息理论分析电力系统的负荷预测以及可再生能源出力预测,将其描述为信息决策过程,并提出了短期负荷预测中的最小信息损失(minimization of information loss,MIL)综合模型,利用历史负荷与预测误差的分布情况在信息损失最小的原则下求解最可能的负荷取值。针对MIL综合模型中概率分布的估计问题,文中应用了正态分布参数估计和Parzen窗估计2种不同的方法,给出了各自的算法和实现方案。算例部分通过用实际电网负荷数据和实际风力发电出力数据进行测试,研究了MIL综合模型结构与参数对预测结果的影响,并在与传统综合模型的比较中显示了新模型的优越性。

最小信息损失综合短期负荷预测(一)—理论

该文引入信息理论分析电力系统的负荷预测,将其描述为信息决策过程,并提出了短期负荷预测中的最小信息损失(minimization of information loss,MIL)综合模型,利用历史负荷与预测误差的分布情况在信息损失最小的原则下求解最可能的负荷取值。针对MIL综合模型中概率分布的估计问题,文中应用了正态分布参数估计和Parzen窗估计2种不同的方法,给出了各自的算法。

混合模型神经网络在短期负荷预测中的应用

提出了可应用于电力系统负荷预测的混合模型神经网络方法 ,该方法同时具有电力系统负荷预测的传统方法的优点及人工神经网络方法的优点 .该方法中 ,不同的负荷分量采用不同类型的预测方法 ,并采用基本频率的谐振分量作神经网络的输入 ,神经网络的训练采用快速的学习算法进行 .该方法具有很强的实时性和适应性 ,适用于没有气象资料的应用场合 .仿真计算的结果表明 ,预测精度较传统方法来得高 .

电力系统短期负荷预测的混合模型神经元网络方法

提出一种将线性模型方法和神经元网络方法相结合的负荷预测方法——混合模型神经元网络方法。该方法将一部分线性变化的负荷分量用线性模型描述，其它负荷分量用神经元网络建立，因而同时具有线性模型的优点和神经元网络的优点。将这一方法用于江苏省连云港市超前２４ｈ 负荷预测，取得了比单纯的神经元网络模型高的预测精度。

用自适应模糊推理系统预测电力短期负荷

为寻求有效的电力系统负荷预测方法以提高预测结果的准确度,提出了基于Takagi-Sugeno(T-S)模型的自适应神经模糊推理系统(ANFIS)。该系统采用减法聚类初始化模糊推理,把神经网络学习机制引入到逻辑推理中,并用混合学习算法调整前件参数和结论参数,自动产生模糊规则。考虑气象、日期类型等因素后将学习样本分为3组进行训练和检测。该方法对于受天气影响较明显的电网,能有效防止不合理预测结果的出现。对于武汉地区实际负荷的预测结果的分析表明该方法有较高的预测准确度,取得了令人满意的结果。

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。

基于CNN-BIGRU-ATTENTION的短期电力负荷预测

电价的实时波动,会对负荷预测精度产生一定影响,增加预测的复杂性。针对这一问题,本文构建基于注意力(ATTENTION)机制的卷积神经网络(CNN)和双向门控循环单元(BIGRU)混合模型对短期电力负荷进行预测。首先用CNN对负荷及电价数据特征进行抽取;其次,利用BIGRU对潜藏的时序规律进行提取;最后结合ATTENTION机制,突出关键特征。仿真结果表明,与BP网络、CNN-GRU、CNN-BIGRU和CNN-GRU-ATTENTION混合模型的预测结果相比,上述模型具有更高的预测精度,是一种有效的短期负荷预测方法。

基于两重门限GARCH模型的短期负荷预测

针对负荷时间序列的非线性和波动性特征,在研究负荷时间序列波动性门限特征的基础上,引入冲量门限的概念,提出了一种基于两重门限GARCH模型的短期负荷预测新方法.利用条件极大似然估计方法,估计了模型参数.同时,考虑到负荷时间序列波动的厚尾效应,将模型推广为服从非高斯分布假设下的情形,建立了2种基于厚尾假设的两重门限GARCH类负荷预测模型.利用所提出的混合信息冲击曲面,分析了不同性质的冲击和冲量对负荷时间序列波动性的影响.实际算例基于南京地区日用电量数据进行了短期负荷预测,验证了模型及方法的可行性和有效性.算例结果表明,服从广义误差分布的两重门限GARCH模型预测效果满意.

基于集合经验模态分解和ARIMA-GRNN的负荷预测方法

针对传统负荷预测方法难以兼顾电力负荷内在线性特征量与非线性特征量的问题,文中提出一种基于EEMD和ARIMA-GRNN的混合负荷预测模型方法。该方法采用EEMD法,将负荷数据分解成不存在模态混叠的IMF分量和余项。运用ARIMA模型算法对每个IMF分量进行线性预测,得到时间序列预测分量,并将其与原始数据相减得到其中的非线性分量。通过GRNN神经网络算法对非线性分量进行预测得到非线性分量的预测值,并将求得的线性预测分量和非线性预测分量相加得到最终的预测值。仿真实验表明,文中提出的基于EEMD和ARIMA-GRNN的混合预测模型在预测精度和性能上均优于采用单一算法的负荷预测方法。

基于EMD-CNN-LSTM混合模型的短期电力负荷预测

为了更有效地提取电力负荷数据中的潜藏特征与隐藏信息,提高电力负荷预测精度,针对负荷具有较强非线性、非平稳性和时序性特点,提出一种基于经验模态分解(empirical mode decomposition,EMD)、卷积神经网络(convolutional neural network,CNN)和长短期记忆网络(long-term and short-term memory network,LSTM)的混合模型短期电力负荷预测方法,将海量过往负荷数据、温度和历史电价信息以滑动窗口方式构造串联特征向量作为输入,先利用EMD将数据重构成多个分量,将高、中和低频分量各自叠加组合,再运用CNN提取高、中分量的潜藏特征,减少权值数量,并以特征向量的方式输入LSTM网络进行负荷预测,最后叠加各分量预测结果得到最终负荷预测值。实验结果表明,相对于BP神经网络(Back Propagation Neural Network)、支持向量机(support vector machine,SVM)、LSTM模型和EMD-LSTM模型,此模型具有更高的负荷预测精度。