Optimization of support vector machine power load forecasting model based on data mining and Lyapunov exponents

According to the chaotic and non-linear characters of power load data,the time series matrix is established with the theory of phase-space reconstruction,and then Lyapunov exponents with chaotic time series are computed to determine the time delay and the embedding dimension.Due to different features of the data,data mining algorithm is conducted to classify the data into different groups.Redundant information is eliminated by the advantage of data mining technology,and the historical loads that have highly similar features with the forecasting day are searched by the system.As a result,the training data can be decreased and the computing speed can also be improved when constructing support vector machine(SVM) model.Then,SVM algorithm is used to predict power load with parameters that get in pretreatment.In order to prove the effectiveness of the new model,the calculation with data mining SVM algorithm is compared with that of single SVM and back propagation network.It can be seen that the new DSVM algorithm effectively improves the forecast accuracy by 0.75%,1.10% and 1.73% compared with SVM for two random dimensions of 11-dimension,14-dimension and BP network,respectively.This indicates that the DSVM gains perfect improvement effect in the short-term power load forecasting.

Short-Term Power Load Forecasting with Hybrid TPA-BiLSTM Prediction Model Based on CSSA

Since the existing prediction methods have encountered difficulties in processing themultiple influencing factors in short-term power load forecasting,we propose a bidirectional long short-term memory(BiLSTM)neural network model based on the temporal pattern attention(TPA)mechanism.Firstly,based on the grey relational analysis,datasets similar to forecast day are obtained.Secondly,thebidirectional LSTM layermodels the data of thehistorical load,temperature,humidity,and date-type and extracts complex relationships between data from the hidden row vectors obtained by the BiLSTM network,so that the influencing factors(with different characteristics)can select relevant information from different time steps to reduce the prediction error of the model.Simultaneously,the complex and nonlinear dependencies between time steps and sequences are extracted by the TPA mechanism,so the attention weight vector is constructed for the hidden layer output of BiLSTM and the relevant variables at different time steps are weighted to influence the input.Finally,the chaotic sparrow search algorithm(CSSA)is used to optimize the hyperparameter selection of the model.The short-term power load forecasting on different data sets shows that the average absolute errors of short-termpower load forecasting based on our method are 0.876 and 4.238,respectively,which is lower than other forecastingmethods,demonstrating the accuracy and stability of our model.

A Weighted Combination Forecasting Model for Power Load Based on Forecasting Model Selection and Fuzzy Scale Joint Evaluation

To solve the medium and long term power load forecasting problem,the combination forecasting method is further expanded and a weighted combination forecasting model for power load is put forward.This model is divided into two stages which are forecasting model selection and weighted combination forecasting.Based on Markov chain conversion and cloud model,the forecasting model selection is implanted and several outstanding models are selected for the combination forecasting.For the weighted combination forecasting,a fuzzy scale joint evaluation method is proposed to determine the weight of selected forecasting model.The percentage error and mean absolute percentage error of weighted combination forecasting result of the power consumption in a certain area of China are 0.7439%and 0.3198%,respectively,while the maximum values of these two indexes of single forecasting models are 5.2278%and 1.9497%.It shows that the forecasting indexes of proposed model are improved significantly compared with the single forecasting models.

Theory Study and Application of the BP-ANN Method for Power Grid Short-Term Load Forecasting

Aiming at the low accuracy problem of power system short-term load forecasting by traditional methods, a back-propagation artificial neural network （BP-ANN） based method for short-term load forecasting is presented in this paper. The forecast points are related to prophase adjacent data as well as the periodical long-term historical load data. Then the short-term load forecasting model of Shanxi Power Grid （China） based on BP-ANN method and correlation analysis is established. The simulation model matches well with practical power system load, indicating the BP-ANN method is simple and with higher precision and practicality.

Rural Power System Load Forecast Based on Principal Component Analysis

Power load forecasting accuracy related to the development of the power system. There were so many factors influencing the power load, but their effects were not the same and what factors played a leading role could not be determined empirically. Based on the analysis of the principal component, the paper forecasted the demands of power load with the method of the multivariate linear regression model prediction. Took the rural power grid load for example, the paper analyzed the impacts of different factors on power load, selected the forecast methods which were appropriate for using in this area, forecasted its 2014-2018 electricity load, and provided a reliable basis for grid planning.

Grid Power Optimization Based on Adapting Load Forecasting and Weather Forecasting for System Which Involves Wind Power Systems

This paper describes the performance, generated power flow distribution and redistribution for each power plant on the grid based on adapting load and weather forecasting data. Both load forecasting and weather forecasting are used for collecting predicting data which are required for optimizing the performance of the grid. The stability of each power systems on the grid highly affected by load varying, and with the presence of the wind power systems on the grid, the grid will be more exposed to lowering its performance and increase the instability to other power systems on the gird. This is because of the intermittence behavior of the generated power from wind turbines as they depend on the wind speed which is varying all the time. However, with a good prediction of the wind speed, a close to the actual power of the wind can be determined. Furthermore, with knowing the load characteristics in advance, the new load curve can be determined after being subtracted from the wind power. Thus, with having the knowledge of the new load curve, and data that collected from SACADA system of the status of all power plants, the power optimization, load distribution and redistribution of the power flows between power plants can be successfully achieved. That is, the improvement of performance, more reliable, and more stable power grid.

Day-Ahead Probabilistic Load Flow Analysis Considering Wind Power Forecast Error Correlation

Short-term power flow analysis has a significant influence on day-ahead generation schedule. This paper proposes a time series model and prediction error distribution model of wind power output. With the consideration of wind speed and wind power output forecast error’s correlation, the probabilistic distributions of transmission line flows during tomorrow’s 96 time intervals are obtained using cumulants combined Gram-Charlier expansion method. The probability density function and cumulative distribution function of transmission lines on each time interval could provide scheduling planners with more accurate and comprehensive information. Simulation in IEEE 39-bus system demonstrates effectiveness of the proposed model and algorithm.

Short-Term Load Forecasting Using Radial Basis Function Neural Network

An accurate short-term forecasting method for load of electric power system can help the electric power system’s operator to reduce the risk of unreliability of electricity supply. This paper proposed a radial basis function (RBF) neural network method to forecast the short-term load of electric power system. To demonstrate the effectiveness of the proposed method, the method is tested on the practical load data information of the Tai power system. The good agreements between the realistic values and forecasting values are obtained;the numerical results show that the proposed forecasting method is accurate and reliable.

计及相似日和时间相关性的深度学习短期电力负荷预测

针对特征提取不足、负荷数据噪声大等问题,提出一种基于多因素相似日聚类、时间相关性分析、两层分解降噪的多分支组合负荷预测方法。首先,利用皮尔逊相关系数和最大互信息系数综合分析日负荷影响因素的线性相关性和非线性相关性,增强对重要特征的筛选。将筛选出的高相关性气象因素、日期因素和24 h日负荷数据通过主成分分析方法降维后,进行K-medoids相似日聚类。然后,对各聚类相似日的负荷、气象和日期等数据进行多维分析、多特征提取,构建多特征提取矩阵块以增强数据的周期性规律和时空特性,并结合变分模态分解及经验小波变换提取原始数据的多尺度波动规律、增加数据细节特征,同时降低数据的非线性程度。利用组合预测模型中不同输入分支的门控残差卷积模块充分挖掘数据间的局部相关性,提取局部短时依赖、获取高维特征;利用输入分支并联的双向长短期记忆网络提取数据间的时序特征、挖掘长期依赖关系。最后,对不同类型的特征进行综合集成、强化,实现短期电力负荷预测。实验结果表明:在短期电力负荷单步预测中,用所提的多特征提取、多模型组合方法可获得较高的预测精度;在多步预测中,用所提策略能大幅提升预测精度。所提方法整体预测效果优异。

基于Attention-LSTM的短期电力负荷预测

电力负荷预测的准确性受到多种因素的干扰,如气候变化、经济发展以及区域差异等,这些因素使得电力负荷呈现出显著的不稳定性和复杂的非线性特征,从而增加了提高预测精度的难度。为了应对这一挑战,本文创新性地引入了一种结合自注意力机制与长短期记忆网络(LSTM)的预测方法。通过在美国某一地区的实际用电负荷数据验证模型,实验结果表明,该方法的决定系数(R2)为0.96,平均绝对误差(MAE)为0.023,均方根误差(RMSE)为0.029,提升了预测的准确性。这不仅证明了所提模型在提高电力负荷预测精度方面的有效性,也为其在船舶电力负荷预测的应用奠定了一定的基础。

Research on Short-Term Electric Load Forecasting Using IWOA CNN-BiLSTM-TPA Model

Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.

基于CNN-SAEDN-Res的短期电力负荷预测方法

基于深度学习的序列模型难以处理混有非时序因素的负荷数据,这导致预测精度不足。提出一种基于卷积神经网络(CNN)、自注意力编码解码网络(SAEDN)和残差优化(Res)的短期电力负荷预测方法。特征提取模块由二维卷积神经网络组成,用于挖掘数据间的局部相关性,获取高维特征。初始负荷预测模块由自注意力编码解码网络和前馈神经网络构成,利用自注意力机制对高维特征进行自注意力编码,获取数据间的全局相关性,从而模型能根据数据间的耦合关系保留混有非时序因素数据中的重要信息,通过解码模块进行自注意力解码,并利用前馈神经网络回归初始负荷。引入残差机制构建负荷优化模块,生成负荷残差,优化初始负荷。算例结果表明,所提方法在预测精度和预测稳定性方面具有优势。

基于多维气象信息时空融合和MPA-VMD的短期电力负荷组合预测模型

为提高电力负荷预测精度,需考虑区域内不同地区多维气象信息对电力负荷影响的差异性。在空间维度上,提出多维气象信息时空融合的方法,利用Copula理论将多座气象站的风速、降雨量、温度、日照强度等气象信息与电力负荷进行非线性耦合分析并实现时空融合。在时间维度上,采用海洋捕食者算法(MPA)实现变分模态分解(VMD)核心参数的自动寻优,并采用加权排列熵构造MPA-VMD适应度函数,实现负荷序列的自适应分解。通过将时间维度各分量与空间维度各气象信息进行融合构造长短期记忆(LSTM)网络模型与海洋捕食者算法-最小二乘支持向量机(MPA-LSSVM)模型的输入集,得到各分量预测结果,根据评价指标选择各分量对应的预测模型,重构得到整体预测结果。算例分析结果表明,所提预测模型优于传统预测模型,有效提高了电力负荷预测精度。

Some Views about Recent Electric Power Supply Shortage in Shenzhen

Since the beginning of the year 2000, the power demands in Guangdong, Zhejiang provinces and Beijing Tianjin-Tangshan district have been increasing dramatically, power supply shortages have appeared again. This paper analyzes the reasons for the current power supply shortages in Shenzhen district and the problems existing presently in Shenzhen power system. It indicates that, to strengthen power demand forecast, to speed up power construction steps and with ’to develop power ahead of the rest’ as a fundamental target, are the precondition to the long term, steady development of power industry.

一种时频尺度下的多元短期电力负荷组合预测方法

随机因素的增加导致电力负荷数据成分日渐复杂,使短期负荷预测的难度逐渐增大。针对该问题,提出一种时频尺度下的时间卷积网络与多元线性回归相融合的组合预测模型。利用自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)在时频域上将负荷数据分解为若干个频率特征不同的本征模态分量,在模糊熵准则下聚类为随机项和趋势项。采用皮尔逊系数从诸多影响因素中筛选出与电力负荷高度相关的特征,鉴于小时间尺度分析更易于挖掘局部细节特征,分别构建了随机项与趋势项的细颗粒度特征集。利用具有强非线性处理能力的时间卷积网络(temporal convolutional network,TCN)去预测随机项,利用结构简单及线性拟合效果好的多元线性回归(multiplelinearregression,MLR)去预测趋势项,将二者的预测结果进行叠加重构后获得最终预测值。在新加坡和比利时两组数据集上的实验结果证明:所提模型具有较高的预测精度、较好的泛化性能及鲁棒性。

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。

基于集群辨识和卷积神经网络-双向长短期记忆-时序模式注意力机制的区域级短期负荷预测

为了解决区域级短期电力负荷预测时输入特征过多和负荷时序性较强的问题,提出一种基于集群辨识和卷积神经网络(convolutional neural networks,CNN)-双向长短期记忆网络(bi-directional long short-term memory,BiLSTM)-时序模式注意力机制(temporal pattern attention,TPA)的预测方法。首先,将用电模式和天气作为影响因素,基于二阶聚类算法对区域内的负荷节点进行集群辨识,再从每个集群中挑选代表特征作为深度学习模型的输入,这样既能减少输入特征维度,降低计算复杂度,又能综合考虑预测区域的整体特征,提升预测精度。然后,针对区域电力负荷时序性的特点,用CNN-BiLSTM-TPA模型完成训练和预测,该模型能提取输入数据的双向信息生成隐状态矩阵,并对隐状态矩阵的重要特征加权,从多时间步上捕获双向时序信息用于预测。最后,在美国加利福尼亚州实例上分析验证了所提方法的有效性。

基于极限学习机的短期电力负荷在线预测

为满足智能电网对电力负荷实时预测的需求,提出基于稀疏递归最小二乘法的极限学习机(SRLS-ELM)在线学习算法,用于短期电力负荷的在线预测.相比在线序列ELM, SRLS-ELM算法无需选择离线样本初始化网络输出权重,将网络学习的平方误差与输出权值的稀疏正则化项相结合,用l1-范数稀疏化网络隐藏层节点,用次梯度策略解决求解过程中代价函数无法处处可微的问题,以递归最小二乘的训练方法完成在线学习,根据估计误差自适应寻找最优正则化参数.仿真结果表明,基于SRLS-ELM的算法能有效简化网络结构,且与ELM、堆叠核ELM批量、在线序列ELM半在线以及精确在线支持向量机回归模型相比,对短期电力负荷在线预测时具有更高的预测精度和学习效率,且鲁棒性强.

基于改进Transformer的电力负载预测

针对电力负载预测任务,提出了一种改进的Transformer模型。使用全连接层替换原来的解码器结构,在降低模型复杂度的同时使模型更加契合电力负载数据,使用AdamW方法优化了深度学习中普遍存在的权重衰减处理上的缺陷。实验结果表明,在洛杉矶、纽约和萨克拉门托三个城市的真实电力负载数据集上,相较于ELM、RNN、LSTM和传统的Transformer模型,改进的Transformer模型可以更准确地进行电力负载预测。

基于IGWO-Attention-GRU的短期电力负荷预测模型

为了提高短期电力负荷的预测精度,针对电力负荷序列波动性强、复杂性高的特点,综合考虑气象因素及日期类型的影响,文中提出一种基于改进灰狼优化算法(IGWO)优化Attention-GRU网络的短期电力负荷预测模型。首先,构建Attention-GRU网络;其次,对灰狼优化算法(GWO)进行改进,并利用IGWO寻找Attention-GRU网络的超参数;最后,使用IGWO-Attention-GRU模型在电力负荷数据集上进行实验,并与多种预测模型进行比较。实验结果表明,IGWO-Attention-GRU模型的MAPE、RMSE和MAE值均为各种预测模型中最低,验证了IGWO-Attention-GRU模型的优越性。