State Key Laboratory of Electrical Materials and Electrical Insulation, Shannxi Key Laboratory of Smart Grid School of Electrical Engineering Xi'an Jiaotong University Xi'an 710049 China
Wind speed is characterized by randomness and volatility, which makes the point forecast results cannot quantify the uncertainty of wind speed. Therefore, probabilistic wind speed forecasting is a hot topic in current wind speed forecasting research. In wind farms with large turbine intervals and irregular rows, the local wind speed of each turbine has significant differences. However, the traditional wind speed probabilistic forecasting models tend to treat the wind speeds in an area as the same value, which is not conducive to the detailed control of wind farms. To solve the above problems, this paper proposes a probabilistic wind speed forecasting model for multiple wind turbines based on Bayesian Graph Convolutional Neural Network (BGCNN).
Firstly, the original graph model of wind field was constructed based on the historical data of wind speed and wind direction of each turbine. After that, the wind field graph model was inputted into BGCNN, which can parameterize the graph model to change the graph information and extract the multi-turbine spatial correlation. In this process, the long and short-term memory network (LSTM) was plugged into the back of GCNN module in the BGCNN model, so that the feature matrix containing spatial information among turbines was inputted into the LSTM for temporal feature extraction, and the wind speed forecast results of multiple turbines considering the time-space two-dimensional correlation were obtained. Finally, the Monte Carlo method was used to sample multiple sets of model output values to achieve probabilistic wind speed forecasting for multiple turbines.
Simulation results on the wind farm data show that, multiple turbines in a wind farm present different graph structures under different epochs, indicating that the proposed model can fully consider various spatial relationships among different turbines. For point forecasting results, which are obtained by calculating the mean of the sampling results, the mean absolute error of the proposed model is 1.092m/s for all 100 wind turbines, and the root mean squared error among them is 1.530m/s. There are both smaller than the comparison model, BCNN-LSTM and Q-CNN-LSTM. For probabilistic forecasting, the reliability and sharpness of the proposed model are not all the best at different confidence level, such as in the case of 30%, 50% confidence level, etc. Nevertheless, the average forecast interval coverage bias index and average sharpness of the forecast results are 3.10% and 0.119, respectively, which are lower than the two comparison models. For turbine number 33, compared with the single turbine forecasting model, the probabilistic forecasting results of the proposed model are the best, with the smallest forecast interval coverage bias index, sharpness and Pinball score, which are 1.68%, 0.123 and 0.431m/s, respectively.
The following conclusions can be drawn from the simulation analysis: (1) In this paper, the clustering method is used to classify the output features of the GCNN-LSTM model, which enables the BGCNN to be used in regression problems and to extract the spatial features among wind turbine data well. (2) Compared to the comparison models, the model in this paper achieves higher forecast accuracy in both point forecasting and probabilistic forecasting, and the forecast intervals calculated from the forecast results have small deviations and concentrated distribution. (3) For a single wind turbine in a wind farm, the forecast accuracy of this paper's model is higher than that of the probabilistic forecasting model only for a single wind turbine, which reflects that the reasonable and effective extraction of spatial features is conducive to the reduction of forecast errors.
[1] 金梦, 朱鑫要, 周前. 新能源对电网调峰特性影响定量评估及应用[J]. 高压电器, 2023, 59(4): 70-76.
Jin Meng, Zhu Xinyao, Zhou Qian.Quantitative assessment of influence of renewable energy on peak regulation characteristics of power grid and its application[J]. High Voltage Apparatus, 2023, 59(4): 70-76.
[2] 刘雨佳, 樊艳芳, 白雪岩, 等. 基于特征交叉机制和误差补偿的风力发电功率短期预测[J]. 电工技术学报, 2023, 38(12): 3277-3288. Liu Yujia, Fan Yanfang, Bai Xueyan, et al. Short-term wind power prediction based on feature crossover mechanism and error compensation[J]. Transactions of China Electrotechnical Society, 2023, 38(12): 3277-3288.
[3] 李阳, 沈小军, 张扬帆, 等. 基于速度-关联约束的风电机组风速感知异常数据识别方法[J]. 电工技术学报, 2023, 38(7): 1793-1807. Li Yang, Shen Xiaojun, Zhang Yangfan, et al. Cleaning method of wind speed outliers for wind turbines based on velocity and correlation constraints[J]. Transactions of China Electrotechnical Society, 2023, 38(7): 1793-1807.
[4] 国家能源局. 国家能源局发布2023年全国电力工业统计数据[EB/OL].[2024-01-26]. https://www.nea.go v.cn/2024-01/26/c_1310762246.htm.
[5] 顾雪平,魏佳俊,白岩松,等.基于分层模型预测控制的含风电电力系统恢复在线决策方法[J/OL]. 电工技术学报, 2025: 1-16[2024-09-27]. https://doi.org/10.19595/j.cnki.1000-6753.tces.240331.
Gu Xueping, Wei Jiajun, Bai Yansong, et al. Online decision-making method for wind power integrated power system restoration based on hierarchical model predictive control[J/OL]. Transactions of China Electrotechnical Society, 2025: 1-16[2024-09-27]. https://doi.org/10.19595/j.cnki.1000-6753.tces.240331.
[6] 陈臣鹏, 赵鑫, 毕贵红, 等. 基于多模式分解和麻雀优化残差网络的短期风速预测模型[J]. 电网技术, 2022, 46(8): 2975-2985.
Chen Chenpeng, Zhao Xin, Bi Guihong, et al.SSA-res-GRU short-term wind speed prediction model based on multi-model decomposition[J]. Power System Technology, 2022, 46(8): 2975-2985.
[7] 徐询, 谢丽蓉, 梁武星, 等. 考虑风电预测误差时序性及风电可信度的双层优化模型[J]. 电工技术学报, 2023, 38(6): 1620-1632, 1661. Xu Xun, Xie Lirong, Liang Wuxing, et al. Bi-level optimization model considering time series characteristic of wind power forecast error and wind power reliability[J]. Transactions of China Electrotechnical Society, 2023, 38(6): 1620-1632, 1661.
[8] 黎静华, 骆怡辰, 杨舒惠, 等. 可再生能源电力不确定性预测方法综述[J]. 高电压技术, 2021, 47(4): 1144-1157. Li Jinghua, Luo Yichen, Yang Shuhui, et al. Review of uncertainty forecasting methods for renewable energy power[J]. High Voltage Engineering, 2021, 47(4): 1144-1157.
[9] 韩丽, 乔妍, 景惠甜. 基于误差分类的风电功率区间评估[J]. 电力系统自动化, 2021, 45(1): 97-104. Han Li, Qiao Yan, Jing Huitian. Interval estimation of wind power based on error classification[J]. Automation of Electric Power Systems, 2021, 45(1): 97-104.
[10] 杨茂, 杜刚. 基于t Location-Scale分布的风电功率概率预测研究[J]. 中国电力, 2017, 50(1): 140-145.
Yang Mao, Du Gang.Wind power probability prediction based on t location-scale distrabution[J]. Electric Power, 2017, 50(1): 140-145.
[10] 杨茂,杜刚.基于t Location-Scale分布的风电功率概率预测研究[J].中国电力,2017,50(1):140-145.
Yang Mao, Du Gang.Wind power probability prediction based on t Location-Scale distribution[J]. Electric Power, 2017, 50(1): 140-145.
[11] 岳国华, 杜志叶, 蔡泓威, 等. 基于风速概率分布与风切变指数的直流输电线路离子流场数值模拟方法[J]. 电工技术学报, 2024, 39(9): 2907-2915. Yue Guohua, Du Zhiye, Cai Hongwei, et al. Numerical simulation method of ion flow field in DC transmission line based on wind speed probability distribution and wind shear exponent[J]. Transactions of China Electrotechnical Society, 2024, 39(9): 2907-2915.
[12]Chen Niya, Qian Zheng, Nabney I T, et al. Wind power forecasts using Gaussian processes and numerical weather prediction[J]. IEEE Transactions on Power Systems, 2014, 29(2): 656-665.
[13] 余建明, 庞传军. 考虑数据和模型不确定性的短期风电功率概率预测[J]. 电网技术, 2022, 46(5): 1926-1933. Yu Jianming, Pang Chuanjun. Short-term wind power probabilistic prediction considering data and model uncertainties[J]. Power System Technology, 2022, 46(5): 1926-1933.
[14] 刘洪波, 刘珅诚, 盖雪扬, 等. 高比例新能源接入的主动配电网规划综述[J]. 发电技术, 2024, 45(1): 151-161. Liu Hongbo, Liu Shencheng, Gai Xueyang, et al. Overview of active distribution network planning with high proportion of new energy access[J]. Power Generation Technology, 2024, 45(1): 151-161.
[15] 李丹, 张远航, 杨保华, 等. 基于约束并行LSTM分位数回归的短期电力负荷概率预测方法[J]. 电网技术, 2021, 45(4): 1356-1364. Li Dan, Zhang Yuanhang, Yang Baohua, et al. Short time power load probabilistic forecasting based on constrained parallel-LSTM neural network quantile regression mode[J]. Power System Technology, 2021, 45(4): 1356-1364.
[16]Pinson P, Kariniotakis G. Conditional prediction intervals of wind power generation[J]. IEEE Transactions on Power Systems, 2010, 25(4): 1845-1856.
[17] 宋宇, 李涵. 基于核密度估计和Copula函数的风、光出力场景生成[J]. 电气技术, 2022, 23(1): 56-63. Song Yu, Li Han. Typical scene generation of wind and photovoltaic power output based on kernel density estimation and Copula function[J]. Electrical Engineering, 2022, 23(1): 56-63.
[18] 臧海祥, 赵勇凯, 张越, 等. 基于低风速功率修正和损失函数改进的超短期风电功率预测[J]. 电力系统自动化, 2024, 48(7): 248-257. Zang Haixiang, Zhao Yongkai, Zhang Yue, et al. Ultra-short-term wind power prediction based on power correction under low wind speed and improved loss function[J]. Automation of Electric Power Systems, 2024, 48(7): 248-257.
[19] 宋萌萌. 基于深度学习技术的风速预测方法研究[D]. 长沙: 中南大学, 2023. Song Mengmeng. Research on wind speed prediction method based on deep learning technology[D]. Changsha: Central South University, 2023.
[20] 甘迪, 柯德平, 孙元章, 等. 基于集合经验模式分解和遗传-高斯过程回归的短期风速概率预测[J]. 电工技术学报, 2015, 30(11): 138-147. Gan Di, Ke Deping, Sun Yuanzhang, et al. Short-term wind speed probabilistic forecasting based on EEMD and coupling GA-GPR[J]. Transactions of China Electrotechnical Society, 2015, 30(11): 138-147.
[21] 王晨, 寇鹏. 基于卷积神经网络和简单循环单元集成模型的风电场内多风机风速预测[J]. 电工技术学报, 2020, 35(13): 2723-2735. Wang Chen, Kou Peng. Wind speed forecasts of multiple wind turbines in a wind farm based on integration model built by convolutional neural network and simple recurrent unit[J]. Transactions of China Electrotechnical Society, 2020, 35(13): 2723-2735.
[22]Zou Mingzhe, Holjevac N, Đaković J, et al. Bayesian CNN-BiLSTM and vine-GMCM based probabilistic forecasting of hour-ahead wind farm power outputs[J]. IEEE Transactions on Sustainable Energy, 2022, 13(2): 1169-1187.
[23]Zhao Yanfang, Pu Haitao, Dai Yingjian, et al. Short-term wind power prediction method based on GCN-LSTM[C]//2023 8th Asia Conference on Power and Electrical Engineering (ACPEE), Tianjin, China, 2023: 1329-1333.
[24]Khodayar M, Wang Jianhui. Spatio-temporal graph deep neural network for short-term wind speed forecasting[J]. IEEE Transactions on Sustainable Energy, 2019, 10(2): 670-681.
[25]Zhang Yingxue, Pal S, Coates M, et al. Bayesian graph convolutional neural networks for semi-supervised classification[C]//Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, 2019: 5829-5836.
[26] Li W, Ahn S, Welling M.Scalable MCMC for mixed membership stochastic blockmodels[C]//Artificial Intelligence and Statistics. PMLR, 2016: 723-731.
[27]Yu Yunjun, Hu Guoping. Short-term solar irradiance prediction based on spatiotemporal graph convolutional recurrent neural network[J]. 2022, 14(5): 053702.