Speed Time Series Data Research Articles

Wind Speed Forecasting Based on Phase Space Reconstruction and a Novel Optimization Algorithm

The wind power generation capacity is increasing rapidly every year. There needs to be a corresponding development in the management of wind power. Accurate wind speed forecasting is essential for a wind power management system. However, it is not easy to forecast wind speed precisely since wind speed time series data are usually nonlinear and fluctuant. This paper proposes a novel combined wind speed forecasting model that based on PSR (phase space reconstruction), NNCT (no negative constraint theory) and a novel GPSOGA (a hybrid optimization algorithm that combines global elite opposition-based learning strategy, particle swarm optimization and the genetic algorithm) optimization algorithm. SSA (singular spectrum analysis) is firstly applied to decompose the original wind speed time series into IMFs (intrinsic mode functions). Then, PSR is employed to reconstruct the intrinsic mode functions into input and output vectors of the forecasting model. A combined forecasting model is proposed that contains a CBP (cascade back propagation network), RNN (recurrent neural network), GRU (gated recurrent unit), and CNNRNN (convolutional neural network combined with recurrent neural network). The NNCT strategy is used to combine the output of the four predictors, and a new optimization algorithm is proposed to find the optimal combination parameters. In order to validate the performance of the proposed algorithm, we compare the forecasting results of the proposed algorithm with different models on four datasets. The experimental results demonstrate that the forecasting performance of the proposed algorithm is better than other comparison models in terms of different indicators. The DM (Diebold–Mariano) test, Akaike’s information criterion and the Nash–Sutcliffe efficiency coefficient confirm that the proposed algorithm outperforms the comparison models.

Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method

Against global warming, wind energy has increasingly become a stable form of power supply. Accurate prediction of wind speed is crucial for turbine control and wind farm dispatch, contributing to stable and continued wind energy utilization. However, it is very difficult to accomplish satisfactory wind speed forecasting, especially multi-step forecasting, due to the stochastic, random and volatile characteristic of wind speed series with complex fluctuations. This study is elaborated to propose a novel method based on “data graph” reconstruction and long short term memory (LSTM) network, to achieve accurate and robust multi-step wind speed forecasting. To obtain implicit correlations between wind speed series, the time series data are reconstructed into matrices like “data graphs”. To achieve better computing efficiency and forecasting accuracy, the convolutional neural network (CNN) is adopted to extract the features in the “data graphs”. Then the extracted data graph features are imported into the bidirectional-LSTM (bi-LSTM) network module, which takes the input in forward and backward directions, respectively, to extract more temporal information. For adequate performance assessment, experiments are carried out on data sets of an actual wind farm located in a mountainous region in China. The results show that the proposed method outperforms classic meta-model based and hybrid-model based methods in accuracy, stability and computing efficiency. The results reveal that the data graph reconstruction combined with the CNN is able to extract the hidden features of the wind speed time series data. The proposed CNN-bi-LSTM method effectively improve the multi-step wind speed prediction accuracy.

Decomposition-based wind speed forecasting model using causal convolutional network and attention mechanism

With the growth of global energy demand, the proportion of the total installed wind capacity continues to increase. Wind speed forecasting is essential to enhance the utilization of wind energy. However, it is not easy to make accurate wind speed forecasting since wind speed time series data has nonlinearity, fluctuation, and intermittence. These features of wind speed time series data make classical models unable to obtain expected forecasting results. Many researchers proposed wind speed forecasting models to overcome the shortage. Nevertheless, some wind speed prediction methods are limited because they cannot mine all implicit features of wind speed data. This paper proposes a novel wind speed forecasting model that can capture all implicit information of wind speed data and obtain accuracy prediction results. To be specific, ensemble empirical mode decomposition (EEMD) is firstly applied to remove the noise in the original wind speed data. Secondly, we build a novel deep learning model based on the attention mechanism and convolutional neural network (CNN). The proposed forecasting model can focus the important part of wind speed data and reduce the high computational complexity of CNN. Finally, a full connect neural network layer is employed to obtain wind speed forecasting results. In order to validate the performance of the proposed model, we take the wind speed data of the M2 tower at 20-meter height of the National Wind Power Technology Center of the United States as an example. The experimental results demonstrate that the forecasting errors of the proposed model are smaller than other comparative models. And the Diebold-Mariano test confirms that the proposed model exhibits a significant difference in performance compared with the comparison models.

Unsupervised Fault Detection Driven by Multivariate Time Series for Aeroengines

Aeroengine fault detection is extremely significant to ensure flight safety. However, it still poses a vast challenge due to the complexity of aeroengine systems. In this paper, an unsupervised deep autoencoder (DAE) with dimension fusion function (DFF) method (DFF-DAE) was proposed to effectively detect aeroengine faults based on multivariate time-series data. The proposed method does not rely on mathematical models and expert experience to automatically extract the hierarchical representation features of raw data. The DFF-DAE has a three-layer autoencoder with its first encoding layer incorporating a DFF, which is developed for multivariate time-series fusion before encoding. A case study of aeroengine rolling bearing locking fault was conducted on the turbofan engine ground test data composed of vibration and rotational speed time-series data in variable working states. The results indicated that DFF-DAE succeeds in efficiently employing multivariate time-series data to perform accurate fault detection. Compared with other state-of-the-art methods, DFF-DAE yields superior predictive ability and detection accuracy. Furthermore, DFF-DAE provides application potential for online fault detection because it is effective in variable working states of the aeroengine.

Efficiency of Using One-Dimensional Convolutional Layers in a Neural Network on the Example of Classification a Meteorological Station According to Wind Speeds Time Series Data

Data analytics using neural networks is a modern trend in scientific research. One of these scientific tasks is the use of artificial intelligence in the time series research and forecasting. The paper considers the results of experiments on the use of one-dimensional convolutional layers in a neural network within the framework of the meteorological (wind speed) time series data classifying task. The improving of the forecast accuracy by adding convolutional layers is shown, which in the considered real problem reaches 9 %. Several variants of architectures for building a model with convolutional layers with an estimate of the accuracy of their prediction are given.

Statistical modelling of the joint probability density function of air density and wind speed for wind resource assessment: A case study from China

This paper proposes a joint probability density function of air density and wind speed, aiming to integrate the air density distribution into statistical wind resource models, thereby helping better understand the correlation between air density and wind speed at different spatiotemporal scales. Hourly air pressure, temperature, and wind speed time series data from 1745 meteorological stations distributed over China for the period 2008–2019 were used to calculate the empirical distributions of air density and wind speed. Four one-component probability density functions and ten two-component mixture probability density functions were fitted to the empirical distributions. It is indicated that the five-parameter Weibull–Gamma distribution is able to achieves more accurate and stable effects in both unimodal and bimodal air density empirical distribution, and the six-parameter Weibull–Burr distribution is the most appropriate distribution for describing wind speed regimes. The parameterised air density and wind speed marginal distributions were linked using five joint copulas. The goodness-of-fit evaluation of the copula models demonstrates that the Gumbel copula most accurately reproduces the bivariate empirical distribution of air density and wind speed. The application of joint distribution has the capability to simplify the evaluation procedures for wind resource assessment while significantly increasing the accuracy of the evaluation results, and also achieve a systematic assessment of available wind resources, considering the temporal patterns of air density. The results of this study will contribute to offering critical information for making better decisions on wind energy projects to realise full development and effective utilisation of wind resources.

Wind Resource Assessment: Optimizing the Weibull Distribution Curve

Abstract: In this paper, it was analyze the wind speed characteristics and provide projections of optimal wind resources by comparing data at different hub heights using wind power law. We have acquired data from an operational project site in the western part of India using data points acquired from the site from August 2017 to February 2018.Weibull distribution probability distribution function and cumulative distribution function for wind speed and other parameters involved in an accurate wind resource assessment methodology. To predict wind regimes, the Weibull probability function is commonly used. A comparison of alternative methods for estimating Weibull parameters of a wind regime is presented in this research. For the estimation, five alternative methods are discussed and employed. The study examined wind speed time series data at two sites over the course of a year. Although all five methods produce similar results when plotting error versus wind speed, the standard deviation method produces the best results.

Change point detection-based simulation of nonstationary sub-hourly wind time series

In this paper, we present a wind speed simulation method by detecting change points in multivariate nonstationary wind speed time series data. The change point detection method identifies changes in the covariance structure and decomposes the nonstationary multivariate time series into stationary segments. Parametric and nonparametric techniques are also provided to model and simulate new time series within each stationary segment. The proposed simulation approach retains the statistical properties of the original time series (as obtained from a Numerical Weather Prediction system) and therefore, can be employed for simulation-based analysis of power systems planning and operations problems. We demonstrate the capabilities of the change point detection method through computational experiments conducted on wind speed time series at five-minute resolution. We also conduct experiments on the economic dispatch problem to illustrate the impact of nonstationarity in wind generation on conventional generation and location marginal prices.

Wind speed forecasting based on model selection, fuzzy cluster, and multi-objective algorithm and wind energy simulation by Betz's theory

Wind energy is of increasing interest to wind farm administrators as a clean and renewable energy source. Accurate wind speed forecasting and effective wind energy simulation can increase the capability of wind power combined with a grid and decrease the operating cost of wind farms. However, many previous studies have been restricted to wind speed forecasting, ignoring wind energy simulations. Thus, grid management cannot effectively estimate the power production of wind farms and leads to an increase in the abandonment wind rate in wind farms. In this study, a wind farm auxiliary management system is developed, which includes two modules: wind speed forecasting and wind energy simulation. In the wind speed forecasting module, first, a data mining algorithm is used to analyze different features of wind speed time series data in a wind farm. Subsequently, a feature selection algorithm is used to determine the representative wind speed time series of the wind farm, and it is combined with a data preprocessing method to effectively eliminate the noise of the original wind speed time series. Second, six hybrid neural network forecasting models based on a modified multi-objective algorithm are established to forecast wind speed. Finally, they are combined with a model selection strategy to yield the best forecasting value for each time point. In the wind energy simulation module, using Betz's theory, the physical transformation process of a wind turbine is estimated to determine the range of wind power generation.

Data-Driven Continuous-Time Modeling of Power System Uncertainty Using a Multi-Dimensional Stochastic Differential Equation

This paper proposes a generalized continuous random process modeling framework for imposing any desired probability distribution, autocorrelation and power spectral density of measured data of power system uncertainty by developing a multi-dimension stochastic differential equation (SDE) together with a quadratic output equation. An algorithm for determining appropriate parameters of the proposed SDE model is presented. The effectiveness of derived random modeling scheme is verified by carrying out comparative simulations using actual time series data of wind speed, solar radiation, PJM dynamic regulation, and wind power. The proposed SDE model can be readily integrated in various electrical component models for reliable operation, stability assessment and control of renewable power systems.

Effect of Sparse Representation of Time Series Data on Learning Rate of Time-Delay Neural Networks

In this paper, we examine how sparsifying input to a time-delay neural network (TDNN) can significantly improve the learning time and accuracy of the TDNN for time series data. The sparsifying of input is done through a sparse transform input layer. Many applications that involve prediction or forecasting of the state of a dynamic system can be formulated as a time series forecasting problem. Here, the task is to forecast some state variable, which is represented as a time series in applications such as weather forecasting, energy consumption prediction or predicting future state of a moving object. While there are many tools for time-delay forecasting, TDNNs have recently received more attention. We show that through applying a sparsifying input transform layer to the TDNN, we can considerably improve the learning time and accuracy. Through analyzing the learning process, we demonstrate the mathematical reasons for this improvement. Experiments with several datasets are used to show the improvement and the reason behind it. We use data from national weather forecast datasets, vehicle speed time series and synthetic data. Several different sparse representations are evaluated including principal component analysis (PCA), discrete cosine transform (DCT) and a mixture of DCT and Haar transforms. It is observed that the higher sparsity leads to better performance. The relative simplicity of TDNNs, compared with deep networks, and the use of sparse transforms for quicker learning open up possibilities for online learning in small embedded devices that do not have powerful computing capabilities.

Wind Speed Prediction Using Hybrid 1D CNN and BLSTM Network

As the world witnesses population increase, the global power demand is increasing and the need for exploring other alternative clean and self-renewable sources of energy such as wind has become necessary. For optimal operation of the wind farms and stability of the grid, wind prediction ahead of time is of key importance. An accurate forecast of wind speed is often difficult due to the unpredictable nature of the wind. In this work, we utilized different machine learning models and proposed a hybrid machine learning approach. This approach combines 1D convolutional neural network (CNN) and bidirectional long short term memory (BLSTM) network for accurate prediction of short term wind prediction at different heights above ground level (AGL). The 1D CNN model extracts high-level features of the input wind speed data. The extracted features are then fed as input to the BLSTM network for wind speed prediction. The wind speed time series data used in this study are measured at 18, and 98 meters AGL. The study further presents a relationship between the utilized models and prediction accuracy at different heights. The forecasting performance of the models tends to increase as the height AGL increases. A real-world case study is implemented to demonstrate the effectiveness of the proposed CNN-BLSTM method in Saudi Arabia. The mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and mean absolute percentage error (MAPE) are used as performance indices to evaluate the performance of the proposed CNN-BLTSM model. The corresponding results show that the proposed method outperforms other benchmark models.

Online Parameter Estimation Methods for Adaptive Cruise Control Systems

Two new methods are presented for estimating car-following model parameters using data collected from the Adaptive Cruise Control (ACC) enabled vehicles. The vehicle is assumed to follow a constant time headway relative velocity model in which the parameters are unknown and to be determined. The first technique is a batch method that uses a least-squares approach to estimate the parameters from time series data of the vehicle speed, space gap, and relative velocity of a lead vehicle. The second method is an online approach that uses a particle filter to simultaneously estimate both the state of the system and the model parameters. Numerical experiments demonstrate the accuracy and computational performance of the methods relative to a commonly used simulation-based optimization approach. The methods are also assessed on empirical data collected from a 2019 model year ACC vehicle driven in a highway environment. Speed, space gap, and relative velocity data are recorded directly from the factory-installed radar unit via the vehicle's CAN bus. All three methods return similar mean absolute error values in speed and spacing compared to the recorded data. The least-squares method has the fastest run-time performance, and is up to 3 orders of magnitude faster than other methods. The particle filter is faster than real-time, and therefore is suitable in streaming applications in which the datasets can grow arbitrarily large.

GA-based design of optimal discrete wavelet filters for efficient wind speed forecasting

Wind energy is getting more and more integrated into power grids, giving rise to some challenges because of its inherent intermittent and irregular nature. Wind speed forecasting plays a fundamental role in overcoming such challenging issues and, thus, assisting the power utility manager in optimizing the supply–demand balancing through wind energy generation. This paper suggests a new hybrid scheme WNN, based on discrete wavelet transform (DWT) combined with artificial neural network (ANN), for wind speed forecasting. More specifically, this work aims at designing the most appropriate discrete wavelet filters, best adapted to a one day ahead wind speed forecasting. The optimized DWT filters are intended to effectively preprocess the wind speed time series data in order to enhance the prediction accuracy. Using wind speed data collected from three different locations in the Magherbian region, the obtained simulation results indicate that the proposed approach outperforms other conventional wavelet-based forecasting structures regarding the wind speed prediction precision. Moreover, compared to the standard wavelet ‘db4’ based approach, the optimized wavelet filter-based structure leads to a forecasting accuracy improvement, in terms of RMSE and MAPE index errors, that amounts to nearly 13% and 19%, respectively.

Network‐wide traffic speed forecasting: 3D convolutional neural network with ensemble empirical mode decomposition

AbstractAccurate traffic speed forecasting is one of the most critical tasks in proactive traffic management and the deployment of advanced traveler information systems. This paper proposes a hybrid forecasting approach named DeepEnsemble by integrating the three‐dimensional convolutional neural network (3D CNN) with ensemble empirical mode decomposition (EEMD). There are four steps in this hybrid approach. First, EEMD is adopted to decompose the complex traffic speed time series data with noise into several intrinsic mode functions (IMFs) and a residue. Second, a three‐dimensional tensor is established and fed into 3D CNN for prediction. Third, the output of 3D CNN prediction is obtained by a linear combination of the results of all components. Finally, the 3D CNN prediction output, external features, and historical features are fused to predict the network‐wide traffic speed simultaneously. The proposed DeepEnsemble approach is tested on the three‐month traffic speed series data of a real‐world large‐scale urban expressway network with 308 traffic flow detectors in Beijing, China. The experimental results indicate that DeepEnsemble outperforms the state‐of‐the‐art network‐wide traffic speed forecasting models. 3D CNN learns temporal, spatial, and depth information better than 2D CNN. Moreover, forecasting accuracy can be improved by employing EEMD. DeepEnsemble is a promising model with scalability and portability for network‐wide traffic speed prediction and can be further extended to conduct traffic status monitoring and congestion mitigation strategies.

Fractal characteristics of tall tower wind speeds in Missouri

The Hurst exponent H is used to determine the measure of predictability of a time series. The value between 0 and 1 with 0.5 representative of a random or uncorrelated series, H>0.5 and H<0.5 reflect a data set which is persistent and anti-persistent respectively. The fractal dimension can be given from the Hurst exponent. The fractal dimension is a factor of the complexity of which the system is being repeated at various scales. If the fractal dimension does not change with scale it is deemed monofractal if not, multifractal. The Hurst exponents were determined in this study using the Rescale Range Analysis (R/S Analysis) and Multifractal Detrended Fluctuation Analysis (MF-DFA) for monofractal and multifractal investigations respectively. These methods were applied to daily 10 min wind speed time series data for the year 2009 from three locations within Missouri: Columbia, Neosho and Blanchard for three tall tower stations. The results obtained from the monofractal analysis showed minor variations in the Hurst exponents for the three stations and heights for all the months in 2009. These values ranged from 0.7 to 0.9 and its corresponding fractal dimension was ranged between 1.3 and 1.1. The results for the MF-DFA showed that the wind speed time series were multifractal in nature as the Hurst exponents were functions of the scaling parameters. Also, the plots of the Renyi Exponent were non-linear for the stations and the various channels; this is representative of multifractal signals. The fractal dimensions of the time series using multifractal analysis were determined to be greater than these values determined using monofractal analysis. However, there were no indications of consistent increases in the complexity of the systems’ multifractality with increasing heights for the various stations’ tall towers.

Study on Fractal Multistep Forecast for the Prediction of Driving Behavior

The application and development of new technology make it possible to acquire real-time data of vehicles. Based on these real-time data, the behavior of vehicles can be analyzed. The prediction of vehicle behavior provides data support for the fine management of traffic. This paper proposes speed and acceleration have fractal features by R/S analysis of the time series data of speed and acceleration. Based on the characteristic analysis of microscopic parameters, the characteristic indexes of parameters are quantified, the fractal multistep prediction model of microparameters is established, and the BP (back propagation neural networks) model is established to estimate predictable step of fractal prediction model. The fractal multistep prediction model is used to predict speed acceleration in the predictable step. NGSIM trajectory data are used to test the multistep prediction model. The results show that the proposed fractal multistep prediction model can effectively realize the multistep prediction of vehicle speed.

Learning Traffic as Images for Incident Detection Using Convolutional Neural Networks

The timely and accurate detection of traffic incidents is beneficial to reduce associated economic losses and avoid secondary crashes. Inspired by the impressive success of the image classification algorithms, especially convolutional neural networks (CNNs), this study proposes a novel framework to detect highway traffic incidents by learning the traffic state as images. In such a framework, the probe vehicles equipped with the global positioning system equipment are used to obtain data. The Gramian Angular Difference Fields and Piecewise Aggregation Approximation algorithms are used to convert the link speed time series data into images. CNNs can extract the traffic features based on these images and consider an incident detection problem as a binary classification task. Further, the effectiveness of the proposed framework is evaluated by applying it to detect the traffic in a real-world environment, i.e., the Guangzhou Airport Expressway. The results illustrate that the proposed model outperforms several other algorithms with respect to almost all the performance indexes, including the detection rate with different false alarm rates and the area under the receiver operating characteristic curve.

A New Hybrid ARAR and Neural Network Model for Multi-Step Ahead Wind Speed Forecasting in Three Regions of Pakistan

Wind is one of the most essential sources of clean, environmental friendly, socially constructive, economically beneficial, and renewable energy. To intuit the potential of this energy in a region the accurate wind speed modeling and forecasting are crucially important, even for planning, conversion of wind energy to electricity, energy trading, and reducing instability. However, accurate prediction is difficult due to intermittency and intrinsic complexity in wind speed data. This study aims to suggest a more appropriate model for accurate wind speed forecasting in the Jhimpir, Gharo, and Talhar, regions of Sindh, Pakistan. Therefore, the present study combined the Autoregressive-Autoregressive (ARAR) and Artificial Neural Network (ANN) models to propose a new hybrid ARAR-ANN model for better prediction by precisely capturing different patterns of the wind speed time-series data sets. The proposed hybrid model is efficient in modeling, reducing statistical errors, and forecasting the wind speed effectively. The performance of the proposed hybrid ARAR-ANN model is compared using three error-statistics and Nash-Sutcliffe efficiency-coefficient. The empirical results of the four performance indices fully demonstrated the superiority of the hybrid ARAR-ANN model than persistence model, ARAR, ANN and SVM. Indeed, the proposed model is an effective and feasible approach for wind speed forecasting.

Interval Deep Generative Neural Network for Wind Speed Forecasting

In recent years, wind speed forecasting is a challenging task required for the prediction of wind energy resources. As a highly varying data source, wind speed time series requires highly nonlinear temporal features for the prediction tasks. However, most forecasting approaches apply shallow supervised features extracted using architectures with few nonlinear hidden layers. Moreover, the exact features captured in such methodologies cannot decrease the wind data uncertainties. In this paper, an interval probability distribution learning (IPDL) model is proposed based on restricted Boltzmann machines and rough set theory to capture unsupervised temporal features from wind speed data. The proposed model contains a set of interval latent variables tuned to capture the probability distribution of wind speed time series data using contrastive divergence with Gibbs sampling. A real-valued interval deep belief network (IDBN) is further designed employing a stack of IPDLs with a fuzzy type II inference system (FT2IS) for the supervised regression of future wind speed values. In order to automatically learn meaningful unsupervised features from the underlying wind speed data, real-valued input units are designed inside IDBN to better approximate the wind speed probability distribution function compared to classic deep belief networks. The high generalization capability of our unsupervised feature learning model incorporated with the robustness of IPDLs and FT2IS leads to accurate predictions. Simulation results on the Western Wind Dataset reveal significant performance improvement in 1-h up to 24-h ahead predictions compared to single-model approaches including both shallow and deep architectures, as well as recently proposed hybrid methodologies.