Spatio-temporal wind speed prediction of multiple wind farms using capsule network

Abstract Spatio-temporal wind speed prediction is of great significance to the grid-connected operation of multiple wind farms in smart grid. This paper proposes a spatio-temporal wind speed prediction method based on capsule network (CapsNet) for geographically dispersed wind farms over a region. In the proposed method, the historical wind speed data from the wind farms are originally converted into chronological images in a 3D space, and the spatial features implicit in the images are extracted by the convolutional operation. Then, the temporal information of wind speed spatial properties is encapsulated in multi-dimensional time-capsules and learned by the dynamic routing mechanism, thus capturing the nonlinear temporal dependencies based on the extracted spatial features. A regression layer activated by the leaky rectified linear unit (Leaky ReLU) function integrates the spatio-temporal features and generates the final prediction results. Furthermore, a two-layer iterative training approach is employed to well-tune the model parameters and accelerate the convergence speed. Finally, the real data of multiple wind farms from Ohio are collected in the case studies to demonstrate the superior performance of the proposed method compared with other forecasting methods.

[1]  Miao He,et al.  A Spatio-Temporal Analysis Approach for Short-Term Forecast of Wind Farm Generation , 2014, IEEE Transactions on Power Systems.

[2]  Yong Chen,et al.  Multifactor spatio-temporal correlation model based on a combination of convolutional neural network and long short-term memory neural network for wind speed forecasting , 2019, Energy Conversion and Management.

[3]  Juan José Pantrigo,et al.  Bayesian capsule networks for 3D human pose estimation from single 2D images , 2020, Neurocomputing.

[4]  Ahmet Murat Ozbayoglu,et al.  Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 , 2019, Appl. Soft Comput..

[5]  Zhenwei Liu,et al.  A Dimensionless Parameter Analysis of a Cylindrical Tube Electromagnetic Vibration Energy Harvester and Its Oscillator Nonlinearity Effect , 2018 .

[6]  Fernando Luiz Cyrino Oliveira,et al.  Componentnet: Processing U- and V-components for spatio-Temporal wind speed forecasting , 2020 .

[7]  Jonathan Li,et al.  A Hybrid Capsule Network for Land Cover Classification Using Multispectral LiDAR Data , 2020, IEEE Geoscience and Remote Sensing Letters.

[8]  Jay Lee,et al.  A combined filtering strategy for short term and long term wind speed prediction with improved accuracy , 2019, Renewable Energy.

[9]  B. Zhang,et al.  Numerical simulation and prediction of spatial wind field under complex terrain , 2018, Journal of Wind Engineering and Industrial Aerodynamics.

[10]  Jie Zhang,et al.  Conditional aggregated probabilistic wind power forecasting based on spatio-temporal correlation , 2019, Applied Energy.

[11]  Hai Wang,et al.  3D-CNN-based feature extraction of ground-based cloud images for direct normal irradiance prediction , 2019, Solar Energy.

[12]  Cheng Zeng,et al.  Short-term wind power prediction based on spatial model , 2017 .

[13]  Yu Ding,et al.  Spatio-Temporal Asymmetry of Local Wind Fields and Its Impact on Short-Term Wind Forecasting , 2018, IEEE Transactions on Sustainable Energy.

[14]  David Infield,et al.  Short-term spatio-temporal prediction of wind speed and direction , 2014 .

[15]  Peng Lu,et al.  Correlation-Constrained and Sparsity-Controlled Vector Autoregressive Model for Spatio-Temporal Wind Power Forecasting , 2018, IEEE Transactions on Power Systems.

[16]  Jianhui Wang,et al.  Spatio-Temporal Graph Deep Neural Network for Short-Term Wind Speed Forecasting , 2019, IEEE Transactions on Sustainable Energy.

[17]  Ahmed Al-Durra,et al.  Smoothing of Wind Farm Output by Prediction and Supervisory-Control-Unit-Based FESS , 2013, IEEE Transactions on Sustainable Energy.

[18]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[19]  Zhu Han,et al.  Capsule Network Assisted IoT Traffic Classification Mechanism for Smart Cities , 2019, IEEE Internet of Things Journal.

[20]  Qingshan Xu,et al.  Wind farm layout optimization with a three-dimensional Gaussian wake model , 2020 .

[21]  Xiaolei Ma,et al.  Forecasting Transportation Network Speed Using Deep Capsule Networks With Nested LSTM Models , 2018, IEEE Transactions on Intelligent Transportation Systems.

[22]  Xiaoxia Qi,et al.  Deep belief network based k-means cluster approach for short-term wind power forecasting , 2018, Energy.

[23]  Jay Lee,et al.  Gaussian Process Regression for numerical wind speed prediction enhancement , 2020 .

[24]  Okyay Kaynak,et al.  Rough Deep Neural Architecture for Short-Term Wind Speed Forecasting , 2017, IEEE Transactions on Industrial Informatics.

[25]  Caiming Zhang,et al.  Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network , 2019, Optics and Lasers in Engineering.

[26]  Peng Lu,et al.  A novel spatio-temporal wind power forecasting framework based on multi-output support vector machine and optimization strategy , 2020 .

[27]  Jing Lu,et al.  BG-SAC: Entity relationship classification model based on Self-Attention supported Capsule Networks , 2020, Appl. Soft Comput..

[28]  Jianzhong Zhou,et al.  Probabilistic spatiotemporal wind speed forecasting based on a variational Bayesian deep learning model , 2020 .

[29]  Haojun Tang,et al.  A novel framework for wind speed prediction based on recurrent neural networks and support vector machine , 2018, Energy Conversion and Management.

[30]  Sung-Bae Cho,et al.  Predicting residential energy consumption using CNN-LSTM neural networks , 2019, Energy.

[31]  Jinfu Chen,et al.  Learning Temporal and Spatial Correlations Jointly: A Unified Framework for Wind Speed Prediction , 2020, IEEE Transactions on Sustainable Energy.

[32]  Mingjian Cui,et al.  Flexible Machine Learning-Based Cyberattack Detection Using Spatiotemporal Patterns for Distribution Systems , 2020, IEEE Transactions on Smart Grid.

[33]  Stefano Squartini,et al.  Polyphonic Sound Event Detection by Using Capsule Neural Networks , 2018, IEEE Journal of Selected Topics in Signal Processing.

[34]  Yanbin Yuan,et al.  Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine , 2017 .

[35]  Volker Coors,et al.  One dimensional convolutional neural network architectures for wind prediction , 2019, Energy Conversion and Management.

[36]  Xueshan Han,et al.  Multi-dimensional scenario forecast for generation of multiple wind farms , 2015, Journal of Modern Power Systems and Clean Energy.

[37]  Filiberto Pla,et al.  Capsule Networks for Hyperspectral Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Jie Li,et al.  Wind speed prediction method using Shared Weight Long Short-Term Memory Network and Gaussian Process Regression , 2019, Applied Energy.

[39]  Zhi Li,et al.  Short-term wind power prediction based on extreme learning machine with error correction , 2016, Protection and Control of Modern Power Systems.

[40]  Jinfu Chen,et al.  Wind Speed Prediction with Spatio–Temporal Correlation: A Deep Learning Approach , 2018 .

[41]  Jianchun Peng,et al.  A review of deep learning for renewable energy forecasting , 2019, Energy Conversion and Management.

[42]  Wei Zhao,et al.  Investigating the transferring capability of capsule networks for text classification , 2019, Neural Networks.

[43]  Yitao Liu,et al.  Deep learning based ensemble approach for probabilistic wind power forecasting , 2017 .

[44]  Bijaya Ketan Panigrahi,et al.  A multiobjective framework for wind speed prediction interval forecasts , 2016 .