Research on entropy weight variation evaluation method for wind power clusters based on dynamic layered sorting

This paper presents an evaluation method for the entropy-weighting of wind power clusters that comprehensively evaluates the allocation problems of wind power clusters by considering the correlation between indicators and the dynamic performance of weight changes.A dynamic layered sorting allocation method is also proposed.The proposed evaluation method considers the power-limiting degree of the last cycle,the adjustment margin,and volatility.It uses the theory of weight variation to update the entropy weight coefficients of each indicator in real time,and then performs a fuzzy evaluation based on the membership function to obtain intuitive comprehensive evaluation results.A case study of a large-scale wind power base in Northwest China was conducted.The proposed evaluation method is compared with fixed-weight entropy and principal component analysis methods.The results show that the three scoring trends are the same,and that the proposed evaluation method is closer to the average level of the latter two,demonstrating higher accuracy.The proposed allocation method can reduce the number of adjustments made to wind farms,which is significant for the allocation and evaluation of wind power clusters.

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proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel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.

Extreme scenario extraction of a grid with large scale wind power integration by combined entropy-weighted clustering method

Large-scale integration of wind power into a power system introduces uncertainties to its operation and planning,making the power system operation scenario highly diversified and variable.In conventional power system planning,some key operation modes and most critical scenarios are typically analyzed to identify the weak and high-risk points in grid operation.While these scenarios may not follow traditional empirical patterns due to the introduction of large-scale wind power.In this paper,we propose a weighted clustering method to quickly identify a system’s extreme operation scenarios by considering the temporal variations and correlations between wind power and load to evaluate the stability and security for system planning.Specifically,based on an annual time-series data of wind power and load,a combined weighted clustering method is used to pick the typical scenarios of power grid operation,and the edge operation points far from the clustering center are extracted as the extreme scenarios.The contribution of fluctuations and capacities of different wind farms and loads to extreme scenarios are considered in the clustering process,to further improve the efficiency and rationality of the extreme-scenario extraction.A set of case studies was used to verify the performance of the method,providing an intuitive understanding of the extreme scenario variety under wind power integration.

Research on typical operating conditions of hydrogen production system with off-grid wind power considering the characteristics of proton exchange membrane electrolysis cell

Hydrogen energy,with its abundant reserves,green and low-carbon characteristic,high energy density,diverse sources,and wide applications,is gradually becoming an important carrier in the global energy transformation and development.In this paper,the off-grid wind power hydrogen production system is considered as the research object,and the operating characteristics of a proton exchange membrane(PEM)electrolysis cell,including underload,overload,variable load,and start-stop are analyzed.On this basis,the characteristic extraction of wind power output data after noise reduction is carried out,and then the self-organizing mapping neural network algorithm is used for clustering to extract typical wind power output scenarios and perform weight distribution based on the statistical probability.The trend and fluctuation components are superimposed to generate the typical operating conditions of an off-grid PEM electrolytic hydrogen production system.The historical output data of an actual wind farm are used for the case study,and the results confirm the feasibility of the method proposed in this study for obtaining the typical conditions of off-grid wind power hydrogen production.The results provide a basis for studying the dynamic operation characteristics of PEM electrolytic hydrogen production systems,and the performance degradation mechanism of PEM electrolysis cells under fluctuating inputs.

Three-Level Optimal Scheduling and Power Allocation Strategy for Power System ContainingWind-Storage Combined Unit

To mitigate the impact of wind power volatility on power system scheduling,this paper adopts the wind-storage combined unit to improve the dispatchability of wind energy.And a three-level optimal scheduling and power allocation strategy is proposed for the system containing the wind-storage combined unit.The strategy takes smoothing power output as themain objectives.The first level is the wind-storage joint scheduling,and the second and third levels carry out the unit combination optimization of thermal power and the power allocation of wind power cluster(WPC),respectively,according to the scheduling power of WPC and ESS obtained from the first level.This can ensure the stability,economy and environmental friendliness of the whole power system.Based on the roles of peak shaving-valley filling and fluctuation smoothing of the energy storage system(ESS),this paper decides the charging and discharging intervals of ESS,so that the energy storage and wind power output can be further coordinated.Considering the prediction error and the output uncertainty of wind power,the planned scheduling output of wind farms(WFs)is first optimized on a long timescale,and then the rolling correction optimization of the scheduling output of WFs is carried out on a short timescale.Finally,the effectiveness of the proposed optimal scheduling and power allocation strategy is verified through case analysis.

Short-Term Wind Power Prediction Using Fuzzy Clustering and Support Vector Regression

A sustainable production of electricity is essential for low carbon green growth in South Korea. The generation of wind power as renewable energy has been rapidly growing around the world. Undoubtedly, wind energy is unlimited in potential. However due to its own intermittency and volatility, there are difficulties in the effective harvesting of wind energy and the integration of wind power into the current electric power grid. To cope with this, many works have been done for wind speed and power forecasting. In this paper, an SVR （support vector regression） using FCM （Fuzzy C-Means） is proposed for wind speed forecasting. This paper describes the design of an FCM based SVR to increase the prediction accuracy. Proposed model was compared with ordinary SVR model using balanced and unbalanced test data. Also, multi-step ahead forecasting result was compared. Kernel parameters in SVR are adaptively determined in order to improve forecasting accuracy. An illustrative example is given by using real-world wind farm dataset. According to the experimental results, it is shown that the proposed method provides better forecasts of wind power.

Research on Wind Power Prediction Modeling Based on Adaptive Feature Entropy Fuzzy Clustering

Wind farm power prediction is proposed based on adaptive feature weight entropy fuzzy clustering algorithm.According to the fuzzy clustering method,a large number of historical data of a wind farm in Inner Mongolia are analyzed and classified.Model of adaptive entropy weight for clustering is built.Wind power prediction model based on adaptive entropy fuzzy clustering feature weights is built.Simulation results show that the proposed method could distinguish the abnormal data and forecast more accurately and compute fastly.

Wind power time series simulation model based on typical daily output processes and Markov algorithm

The simulation of wind power time series is a key process in renewable power allocation planning,operation mode calculation,and safety assessment.Traditional single-point modeling methods discretely generate wind power at each moment;however,they ignore the daily output characteristics and are unable to consider both modeling accuracy and efficiency.To resolve this problem,a wind power time series simulation model based on typical daily output processes and Markov algorithm is proposed.First,a typical daily output process classification method based on time series similarity and modified K-means clustering algorithm is presented.Second,considering the typical daily output processes as status variables,a wind power time series simulation model based on Markov algorithm is constructed.Finally,a case is analyzed based on the measured data of a wind farm in China.The proposed model is then compared with traditional methods to verify its effectiveness and applicability.The comparison results indicate that the statistical characteristics,probability distributions,and autocorrelation characteristics of the wind power time series generated by the proposed model are better than those of the traditional methods.Moreover,modeling efficiency considerably improves.

基于HS-Clustering的风电场机组分组功率预测

为了寻求风电场功率预测精度和计算效率二者的平衡,提出了一种基于霍普金斯统计量与聚类算法(HSClustering)的风电场机组分组功率预测方法,该方法将霍普金斯统计量与聚类算法的优势有效结合,采用霍普金斯统计量确定场内机组分组个数,通过聚类算法识别不同机组的相似性将风电场分成不同的机组群,然后对每组机群分别建立功率预测模型,从而叠加得到整场输出功率;另外以实测风速、实测功率及二者组合作为机组分组模型输入,分析其对预测精度的影响程度。实例分析表明基于HSClustering的分组预测方法可以显著提高预测精度,同时保证较高的计算效率;风速是影响分组效果的主要因素,对于某些分组模型,功率又可以作为风速的重要补充。

风电租赁储能参与电能-调频市场竞价策略

风电参与市场化竞价运营,可有效激发风电的市场力及其主动租赁储能改善调频性能的积极性,在提升风电运营效益的同时,助力电网的调频调峰,但需解决风储调频性能指标优化及其电能-调频双市场竞价策略协同优化等关键问题。为此,提出了风电参与电能-调频市场竞价双层优化模型:上层为双市场多主体竞价出清模型;下层为各主体竞价策略优化模型,响应上层出清结果,优化调整竞价策略,达到各主体效益最大化。下层模型嵌套了考虑风电不确定性的储能运营商与风电集群储能租赁价格/容量主从博弈优化模型。双层模型联合求解,得出最终风电集群租赁储能容量及其双市场竞价策略。算例结果表明,所提方法能够提升风电运营效益,助力电网调频调峰。

基于CBAM-LSTM的风电集群功率短期预测方法

风电功率的精准预测对我国实现“碳达峰”、“碳中和”的目标具有重要意义。传统的风电功率预测方法往往忽视了时间序列数据中的长期依赖关系和空间相关性,导致预测结果不准确。为了解决这个问题,文中提出了了卷积块注意力机制(Convolutional Block Attention Module, CBAM)和长短时记忆网络(Long Short-Term Memory, LSTM)相结合的模型。首先,使用CBAM对风电功率时间序列数据特征和数值天气预报中蕴含的空间特性进行提取,该模块能够自适应地学习时间和空间上的重要特征;然后,将提取的特征输入到LSTM层结构中进行功率预测。为了验证所提方法的有效性,使用中国吉林省某风电场的数据集进行验证,实验结果表明,与其他功率预测方法相比,文中所提方法平均绝对误差(Mean Absolute Error, MAE)平均降低2.67%;决定系数(R-Square, R2)平均提高23%;均方根误差(Root Mean Square Error, RMSE)平均降低2.69%。

风电集群汇集的共享储能虚拟惯量补偿控制策略

针对大规模风电并网导致系统惯量削弱问题,提出风电集群汇集的共享储能虚拟惯量补偿控制策略。首先,计算风电集群惯量削弱量及共享储能电站的惯量补偿目标;然后,根据惯性响应的基本物理意义,定义储能装置的虚拟惯量;接着,探明其时变特性,求解储能虚拟惯量时域过程,确定储能电站以及各储能单元虚拟惯量补偿目标,提出各储能单元补偿目标动态设置控制参数的控制策略;最后,通过Matlab/Simulink仿真,验证了所提策略在不同储能配置容量、不同风电渗透率下均具有良好控制效果和适应性。

融合迁移学习与CGAN的风电集群功率超短期预测

针对可再生能源不确定性导致电力系统消纳能力不足的问题,提出一种基于条件生成对抗网络与迁移学习融合的风电集群功率超短期预测方法。首先,分析了风电集群功率预测样本模式的不均衡性以及导致的神经网络预测误差偏移现象;其次,构建了条件生成对抗网络修复不均衡问题;最后,采用迁移学习结合时间卷积网络构建了风电集群功率超短期预测模型。测试结果表明,所提方法能够显著提高风电集群功率超短期预测精度。

基于自适应优化AP聚类与BP加权网络的多区域复合短期风电功率预测

精准的风电集群区域功率预测对电源侧的竞价上网具有重要意义。由于同一地区多个风电场受气候影响波动程度相近,可看作具有时空相关性的风电场群,并以此进行集群的合理划分。为此,提出一种基于自适应优化近邻传播(AP)聚类与反向传播(BP)加权神经网络的多区域复合短期风电功率预测模型。首先,通过粒子群优化算法(PSO)优化AP聚类方法对风电场群的历史数据进行集群的聚类与划分;然后,根据得到的最优聚类结果构建风电场群子区域样本训练集;最后,利用基于相关系数权重的BP神经网络对各子区域进行功率预测。算例结果表明:所提方法在24 h日前预测相较传统叠加法与单一BP神经网络可提高1.35%和2.62%的精度,可表明该模型具有优越的预测性能。

基于密度聚类模态分解的卷积神经网络和长短期记忆网络短期风电功率预测

近年来,随着碳达峰和碳中和“双碳”战略目标的提出,风力发电已成为可再生能源发电的关键部分。为提高风电功率短期预测的准确度,提出基于密度聚类与自适应噪声完备集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和卷积神经网络与长短期记忆网络结合的短期风电功率预测方法。首先,利用密度聚类将风电功率与天气特征分成不同类别的数据集,通过自适应噪声完备集成经验模态分解算法将不同类别的数据进行频域分解得到子序列分量。以此为基础,将不同的子序列分量与天气特征进行特征选择,输入到卷积神经网络与长短期记忆网络的预测模型。最后,将不同的预测结果进行叠加得到最终的预测结果。整个预测过程通过聚类、分解和特征选择,有效提高了短期风电功率预测的准确度。

考虑灵活性供需平衡的新型电力系统长短期 储能联合规划

随着可再生能源渗透率的不断提高,以电化学储能为代表的短期储能技术将难以满足新型电力系统消纳可再生能源的需求,与此同时,灵活性也将成为系统运行特性的核心和关键。因此,提出了一种考虑灵活性供需平衡的长短期储能联合规划方法。首先,针对不同时间尺度储能技术的特点,统筹短时功率和长期能量的双重调节,考虑灵活性供需平衡并结合价格型需求响应机制,建立了以系统年化综合成本最低为优化目标的长短期储能联合规划模型。其次,为简化问题规模,利用深度卷积嵌入聚类算法在各月份提取典型场景重新刻画全年时序,并通过风光储容量规划和灵活性校验2个阶段的迭代优化求解模型。最后,以中国东部某地区为算例,验证了所提规划方法在兼顾未来可再生能源高渗透的新型电力系统规划经济性和运行灵活性方面的有效性。

风电机组数据采集与监控系统异常数据识别方法

为了解决原始的风电机组数据采集与监控系统(SCADA)中包含大量异常记录的数据、难以准确反映机组运行状态的问题,提出了一种带噪声基于密度的空间聚类(DBSCAN)模型的风电机组SCADA异常数据识别方法。该方法从分析风速-功率曲线的特点出发,采用预测误差和分类准确度来选取关键聚类参数邻域半径和邻域最小样本点数,避免了人工确定聚类参数的主观性,且参数选择过程可以完全自动化,实现了风电机组SCADA异常数据的有效识别。通过某风场中风电机组的监测数据进行实例验证,结果表明:所提方法能够在保证异常数据被剔除的前提下,保留尽可能多的正常数据,异常识别效果好于现有的k-dist图法和基于k-平均最近邻算法的改进算法(KANN-DBSCAN)。该研究可为开展风电机组状态分析提供参考。

基于多尺度分解的风火储协同调频控制策略

为提升风火两大主力电源对电网频率的主动支撑能力,提出一种基于多尺度分解的风火储协同调频控制策略。首先,考虑风火及储能参与电网调频时的不同响应时间尺度,提出基于小波包分解的频差指令多尺度分解方法及风火储分别响应中低高频差分量的互补匹配方案;提出适应火电调频响应特性的频差指令低频分量获取方法,发展考虑风电有功裕度和储能容量约束的风储出力自趋优调配方法,实现风火储与中低高频分量的精准对应;针对不同运行工况,提出基于调频裕度的风电场聚类分区方法及风力机有功功率智能调控方法,提升风电场对电网频率的主动支撑能力。仿真结果表明,所提策略能有效实现风火储联合参与一次调频,在满足约束的前提下,充分利用风储调频容量,有效改善系统频率特性。

考虑功率预测偏差和出力调节不确定性的风电集群功率分配策略

当因输电通道限制需对风电集群进行限电时,应考虑各风电场功率预测和调节能力的差异。考虑功率预测偏差和调节能力不确定性,构建机会约束规划和机会约束目标规划相结合的风电集群日前功率调度模型,并采用采样排序的方法将不确定变量转化为确定性变量对模型进行求解。对华北某地区风电集群进行案例分析,结果表明,在满足风电场间期望调度电量比例要求的基础上,相较于传统模型,所提模型能有效降低弃风率和系统负荷不平衡时的缺额电量。

基于风电场景概率的电热混合储能优化配置

为有效提高风电入网的经济性和可行性,文中提出一种考虑风电典型场景概率的电热混合储能优化配置方案。首先通过场景分析,利用K-means聚类法将大量风机历史出力数据简化为6个典型出力场景,确定各场景发生的概率,其中聚类数目由肘部曲线法和Dunn指数法综合确定;其次提出电热混合储能系统控制策略,建立适用于多场景的风储联合系统模型;最后,以经济性成本最低与弃风量最小为目标,建立包含电、热负荷综合响应的容量配置优化模型,并将场景概率以权值的形式加入到目标函数中,采用粒子群算法求解模型。通过仿真分析和与其他储能配置场景对比,发现所提配置策略能够提高风电利用率约16.12%,同时减少系统综合成本约43.76%,验证了所提策略的合理性和有效性。