Research on the IL-Bagging-DHKELM Short-Term Wind Power Prediction Algorithm Based on Error AP Clustering Analysis

With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.

A physical approach of the short-term wind power prediction based on CFD pre-calculated flow fields

A physical approach of the wind power prediction based on the CFD pre-calculated flow fields is proposed in this paper. The flow fields are obtained based on a steady CFD model with the discrete inflow wind conditions as the boundary conditions, and a database is established containing the important parameters including the inflow wind conditions, the flow fields and the corresponding wind power for each wind turbine. The power is predicted via the database by taking the Numerical Weather Prediction （NWP） wind as the input data. In order to evaluate the approach, the short-term wind power prediction for an actual wind farm is conducted as an example during the period of the year 2010. Compared with the measured power, the predicted results enjoy a high accuracy with the annual Root Mean Square Error （RMSE） of 15.2% and the annual MAE of 10.80%. A good performance is shown in predicting the wind power＇s changing trend. This approach is independent of the historical data and can be widely used for all kinds of wind farms including the newly-built wind farms. At the same time, it does not take much computation time while it captures the local air flows more precisely by the CFD model. So it is especially practical for engineering projects.

Ultra-short-term Interval Prediction of Wind Power Based on Graph Neural Network and Improved Bootstrap Technique

Reliable and accurate ultra-short-term prediction of wind power is vital for the operation and optimization of power systems.However,the volatility and intermittence of wind power pose uncertainties to traditional point prediction,resulting in an increased risk of power system operation.To represent the uncertainty of wind power,this paper proposes a new method for ultra-short-term interval prediction of wind power based on a graph neural network(GNN)and an improved Bootstrap technique.Specifically,adjacent wind farms and local meteorological factors are modeled as the new form of a graph from the graph-theoretic perspective.Then,the graph convolutional network(GCN)and bi-directional long short-term memory(Bi-LSTM)are proposed to capture spatiotemporal features between nodes in the graph.To obtain highquality prediction intervals(PIs),an improved Bootstrap technique is designed to increase coverage percentage and narrow PIs effectively.Numerical simulations demonstrate that the proposed method can capture the spatiotemporal correlations from the graph,and the prediction results outperform popular baselines on two real-world datasets,which implies a high potential for practical applications in power systems.

Wind Power Potential in Interior Alaska from a Micrometeorological Perspective

The wind power potential in Interior Alaska is evaluated from a micrometeorological perspective. Based on the local balance equation of momentum and the equation of continuity we derive the local balance equation of kinetic energy for macroscopic and turbulent systems, and in a further step, Bernoulli’s equation and integral equations that customarily serve as the key equations in momentum theory and blade-element analysis, where the Lanchester-Betz-Joukowsky limit, Glauert’s optimum actuator disk, and the results of the blade-element analysis by Okulov and Sorensen are exemplarily illustrated. The wind power potential at three different sites in Interior Alaska (Delta Junction, Eva Creek, and Poker Flat) is assessed by considering the results of wind field predictions for the winter period from October 1, 2008, to April 1, 2009 provided by the Weather Research and Forecasting (WRF) model to avoid time-consuming and expensive tall-tower observations in Interior Alaska which is characterized by a relatively low degree of infrastructure outside of the city of Fairbanks. To predict the average power output we use the Weibull distributions derived from the predicted wind fields for these three different sites and the power curves of five different propeller-type wind turbines with rated powers ranging from 2 MW to 2.5 MW. These power curves are represented by general logistic functions. The predicted power capacity for the Eva Creek site is compared with that of the Eva Creek wind farm established in 2012. The results of our predictions for the winter period 2008/2009 are nearly 20 percent lower than those of the Eva Creek wind farm for the period from January to September 2013.

计及SOC自恢复的混合储能平抑风电功率波动控制

混合储能系统能够较好地应对复杂的风电波动,有效地提高电网的稳定性和安全性。在混合储能平抑风电功率波动的典型应用场景下,该文首先提出一种计及荷电状态(SOC)自恢复的混合储能平抑风电功率波动控制方法,在满足风电平抑需求的情况下,通过模型预测控制快速调节储能在平抑功率过程中的荷电状态,提高储能持续稳定运行能力;然后,为提高混合储能系统协调运行能力,设计了加权滑动平均(WMA)-模糊控制策略对超级电容和蓄电池功率进行动态分配;最后,结合实际风电功率数据,通过仿真验证了所提策略能有效平衡储能寿命和平抑风电波动的矛盾,能充分考虑两种储能设备的特性差异并提高功率分配的合理性。

Wind power prediction based on variational mode decomposition multi-frequency combinations

Because of the uncertainty and randomness of wind speed, wind power has characteristics such as nonlinearity and multiple frequencies. Accurate prediction of wind power is one effective means of improving wind power integration. Because the traditional single model cannot fully characterize the fluctuating characteristics of wind power, scholars have attempted to build other prediction models based on empirical mode decomposition(EMD) or ensemble empirical mode decomposition(EEMD) to tackle this problem. However, the prediction accuracy of these models is affected by modal aliasing and illusive components. Aimed at these defects, this paper proposes a multi-frequency combination prediction model based on variational mode decomposition(VMD). We use a back propagation neural network(BPNN),autoregressive moving average(ARMA)model, and least square support vector machine(LS-SVM) to predict high, intermediate,and low frequency components,respectively. Based on the predicted values of each component, the BPNN is applied to combine them into a final wind power prediction value.Finally,the prediction performance of the single prediction models(ARMA,BPNN and LS-SVM)and the decomposition prediction models(EMD and EEMD) are used to compare with the proposed VMD model according to the evaluation indices such as average absolute error, mean square error,and root mean square error to validate its feasibility and accuracy. The results show that the prediction accuracy of the proposed VMD model is higher.

基于改进SABO-BP算法的电网谐波预测

针对日趋严重的电网谐波污染亟需大量谐波数据支撑分析和治理及电网谐波监测能力不足的问题,提出一种改进减法平均优化(subtraction average based optimizer, SABO)算法优化反向传播(back-propagation, BP)神经网络实现谐波预测,以缓解当前谐波数据匮乏的问题。为了克服现有SABO算法易于陷入局部最优解,初始化时使用Logistic混沌映射替代随机数,同时迭代搜索中利用黄金正弦优化算法辅助SABO跳出局部最优,从而提高BP神经网络预测准确率。最后,以某省实际运行数据验证所提改进SABAO-BP模型在谐波电压畸变率及单次谐波电压含有率预测中均具有较高准确性。

Time series models in prediction of severe fever with thrombocytopenia syndrome cases in Shandong province,China

Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease caused by the SFTS virus (SFTSV). Predicting the incidence of this disease in advance is crucial for policymakers to develop prevention and control strategies. In this study, we utilized historical incidence data of SFTS (2013–2020) in Shandong Province, China to establish three univariate prediction models based on two time-series forecasting algorithms Autoregressive Integrated Moving Average (ARIMA) and Prophet, as well as a special type of recurrent neural network Long Short-Term Memory (LSTM) algorithm. We then evaluated and compared the performance of these models. All three models demonstrated good predictive capabilities for SFTS cases, with the predicted results closely aligning with the actual cases. Among the models, the LSTM model exhibited the best fitting and prediction performance. It achieved the lowest values for mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE). The number of SFTS cases in the subsequent 5 years in this area were also generated using this model. The LSTM model, being simple and practical, provides valuable information and data for assessing the potential risk of SFTS in advance. This information is crucial for the development of early warning systems and the formulation of effective prevention and control measures for SFTS.

Analysis and Modeling of Time Output Characteristics for Distributed Photovoltaic and Energy Storage

Due to the unpredictable output characteristics of distributed photovoltaics,their integration into the grid can lead to voltage fluctuations within the regional power grid.Therefore,the development of spatial-temporal coordination and optimization control methods for distributed photovoltaics and energy storage systems is of utmost importance in various scenarios.This paper approaches the issue from the perspective of spatiotemporal forecasting of distributed photovoltaic(PV)generation and proposes a Temporal Convolutional-Long Short-Term Memory prediction model that combines Temporal Convolutional Networks(TCN)and Long Short-Term Memory(LSTM).To begin with,an analysis of the spatiotemporal distribution patterns of PV generation is conducted,and outlier data is handled using the 3σ rule.Subsequently,a novel approach that combines temporal convolution and LSTM networks is introduced,with TCN extracting spatial features and LSTM capturing temporal features.Finally,a real spatiotemporal dataset from Gansu,China,is established to compare the performance of the proposed network against other models.The results demonstrate that the model presented in this paper exhibits the highest predictive accuracy,with a single-step Mean Absolute Error(MAE)of 1.782 and an average Root Mean Square Error(RMSE)of 3.72 for multi-step predictions.

舰船网络通信接口数据传输功耗预测模型

针对舰船网络环境复杂,通信接口数据传输功耗预测精度过低的问题,设计舰船网络通信接口数据传输功耗预测模型。由传输层、网络层、数据链路层等组成舰船网络通信数据传输模型,舰船网络通信接口位于数据链路层作为光导纤维媒介,进行舰船网络的数据传输。舰船网络通信接口数据传输的总功耗,由动态功耗、空闲功耗以及泄露功耗组成。利用指数平均预测算法,引入微分调节因子,构建数据传输功耗预测模型。利用权重系数衡量通信接口功耗预测真实值与预测值的偏离程度,实现舰船网络通信接口功耗的精准预测。模型测试结果表明,该模型能够有效预测舰船网络通信接口数据传输功耗,数据传输功耗预测的均方误差低于0.04。

基于改进灰色模型的光伏发电预测输入数据计算方法

人工神经网络是光功率预测的主要模型之一,其输入数据的准确性是影响光功率预测精度的主要因素。该文使用实际测量的、准确的天气历史数据,采用灰色模型GM(1,1)来预测当前的天气数据,并选择多个长度的历史数据序列来进行预测,用相对误差平均值来评估对历史数据的拟合效果,然后选择对历史数据拟合效果最好的序列预测的天气数据,将其与天气预报的天气数据进行加权平均来得到人工神经网络的输入数据,而相应的权重根据灰色模型对历史数据的拟合效果来动态调整。最后,对现有光伏电站数据的仿真验证了该文算法的有效性。

A Power Load Prediction by LSTM Model Based on the Double Attention Mechanism for Hospital Building

This work proposed a LSTM(long short-term memory)model based on the double attention mechanism for power load prediction,to further improve the energy-saving potential and accurately control the distribution of power load into each department of the hospital.Firstly,the key influencing factors of the power loads were screened based on the grey relational degree analysis.Secondly,in view of the characteristics of the power loads affected by various factors and time series changes,the feature attention mechanism and sequential attention mechanism were introduced on the basis of LSTM network.The former was used to analyze the relationship between the historical information and input variables autonomously to extract important features,and the latter was used to select the historical information at critical moments of LSTM network to improve the stability of long-term prediction effects.In the end,the experimental results from the power loads of Shanxi Eye Hospital show that the LSTM model based on the double attention mechanism has the higher forecasting accuracy and stability than the conventional LSTM,CNN-LSTM and attention-LSTM models.

基于自回归滑动平均模型的风力发电容量预测

利用时间序列分析法对富锦风电场风电机组发电容量时间序列进行分析,通过长自回归模型法建立了基于这些数据的自回归模型(AR)和自回归滑动平均模型(ARMA)。在建模过程中,采用3种定阶方法分别建立了不同的ARMA模型,并在对比分析了不同模型的优缺点之后对其进行加权平均综合处理,最终得到较理想的预测模型,使风力发电容量短期预测的归一化平均绝对误差降到7%以内。

某型通信装备带内多频电磁环境生存能力预测

针对复杂电磁环境下用频装备战场生存能力研究的不足,对某型通信装备在带内多频电磁环境下的生存能力进行了研究。通过对通信装备带内干扰效应原理分析,分别从不同的敏感参数角度出发,建立了2种通信装备带内多频电磁环境生存能力预测模型;并通过某型通信装备带内单频、双频、三频连续波电磁辐射效应试验,研究了受试装备在不同频率组合、不同强度组合下电磁辐射效应的变化规律。试验结果表明:受试装备的带内双频、三频电磁辐射效应试验的验证结果(即平均功率比值之和)基本都在1上下浮动,与平均功率敏感的模型十分相符;电场强度幅值敏感模型的验证结果(即电场强度幅值比值之和)双频电磁辐射为1.4左右,而三频达到了1.6。因此,受试装备带内电磁效应由干扰信号平均功率决定,第2种预测模型能够有效预测带内多频电磁环境下通信装备生存能力。

风速数据奇异点辨识研究

保证风速数据的真实性与可靠性,可以有效地提高风电功率预测精度。针对风速信号中包含奇异点,采用基于小波模极大值的方法进行辨识。该方法将阈值判定与李氏指数相结合,首先,求出小波分解后细节系数的局部极值点,由于奇异点的高频分量很大,因此利用阈值对奇异点的位置进行初步判定;然后,寻找各尺度局部极值点的传播点并绘制模极大值线,从而求得李氏指数α,当李氏指数α<1时,判定该点为奇异点;最后利用自回归滑动平均法ARMA(p,q)对奇异点进行修正。研究实例表明,所采用的基于小波模极大值的奇异点辨识方法,能够准确的判断出信号的奇异性以及发生的时刻,并且能够有效地修正奇异点的值,从而保证风速数据的可靠性,具有一定的实际应用价值。

微电网风/光发电功率预测软件的设计与开发

风力发电和光伏发电功率的预测是进行微电网能量调度计划制定的前提。运用基于时间序列法的风/光发电功率预测模型,引用等效平均风速概念,以提高风功率预测的准确度;采取在线滚动建模的方式修正基于时间序列法的预测模型,最后运用天气预报信息修正风/光发电功率预测的误差。设计了风/光发电功率预测软件的功能组成结构,制定了包括超短期、扩展短期与短期预测模块的程序流程,应用实例验证了所开发软件的实用性与有效性。

基于滑动窗口的指数平均动态电源管理预测算法

针对动态电源管理中指数平均预测算法存在的不足,提出了一种改进的指数平均动态电源管理预测算法.该算法结合滑动窗口,加入动态自适应调节因子,充分利用设备空闲状态的历史信息对未来的空闲时间进行预测.实验结果表明该算法对工作状态平稳的系统空闲预测效果良好,预测误差率比原算法降低了8.3%,并具有对样本数量要求少,计算量小,能自适应调整预测参数的优点.

城市电网总量负荷年最大值的双向预测方法

城市电网总量负荷预测是城市电网规划的基础工作。为了充分挖掘并利用负荷历史数据的更多信息,提出一种城市电网总量负荷年最大值的双向预测方法。该方法基于历史数据分析了电力负荷与用电量的相关关系,建立了负荷-用电比模型,据此求得基于用电量数据的各月电力负荷最大值,并利用这些最大值分别运用线性回归、指数平滑、灰色理论从纵向和横向对目标年的总量负荷最大值进行预测,将所得的六个预测值加权平均作为最终预测结果。实例分析表明该方法是正确的、有效的。

灰色GM(1,1)模型及其在电力负荷预测中的应用

讨论了灰色模型GM(1,1)及其改进模型在电力负荷预测中的应用。从灰色理论建模特点出发,提出使用加权均值生成原始数据序列的数据生成方法,在进行平滑的非负电力负荷数据序列的预测中取得了较好的效果。通过后验差检验,对传统的灰色系统GM(1,1)模型和加权均值的GM(1,1)模型进行了比较分析。实例证明,加权均值生成数据的方法进行建模具有较好的精度,在实际电力预测系统中有很好的应用价值。

基于GM(2,1)模型的短期电力负荷预测

传统的灰色系统GM(1,1)模型只适用于呈近似指数增长趋势的原始数列,而GM(2,1)模型适用范围更广,被广泛应用于各个行业。但由于计算复杂,以及模型自身存在的问题,在电力负荷预测上鲜有人研究。现将GM(2,1)模型运用于短期的电力负荷预测中,详细列出参数的计算过程,并与传统的GM(1,1)模型进行对比,结果表明,GM(2,1)模型比GM(1,1)模型预测精度更高,并且G M(2,1)模型预测的精度基本不受数据的影响,使用范围更广。