Speed Prediction Model Research Articles

Predicting Traffic Performance During a Wildfire Using Machine Learning

Many places around the world periodically suffer from wildfires that threaten lives and disrupt normal traffic operations. Poor traffic performance during wildfires can inhibit the effectiveness of evacuations. Understanding traffic performance during a wildfire would therefore help transportation operators develop emergency traffic control plans. In this study, we developed a traffic speed and flow prediction model that uses support vector regression (SVR), for use during wildfire incidents. This was constructed using historical data for wildfires in California from 2010 to 2019, which were paired with records of the traffic speed and flow on adjacent highways and the prevailing weather conditions during the wildfire events. The results showed that traffic performance during a wildfire could be predicted using the SVR model. Based on our prediction results, we recommend that policies be implemented to encourage or mandate more detailed data collection of wildfire events, such as the fire’s boundary over time, to facilitate better prediction results in models like the one proposed in this paper. This paper should inspire further work on the topic to improve the model and provide a reliable prediction tool for transportation operators in the future.

Research on neural network wind speed prediction model based on improved sparrow algorithm optimization

The wind speed signal measured by the mechanical anemometer lags behind the wind speed at the wind wheel surface of the wind turbine in time. The wind speed reconstruction algorithm adopted by the ordinary lidar anemometer is insufficient. For the sake of enhancing the accuracy of wind speed forecast on the surface of wind turbines in wind farms for wind turbine pitch control strategies, an modified sparrow search algorithm (SSA) based on sinusoidal chaotic mapping is proposed to improve the BP neural network wind speed prediction model. According to the characteristics that lidar measure wind speed at multiple points, a multiple regression forecast model is build, and then the wind speed is predicted. Simulation tests were conducted using lidar wind measurement data from a wind farm in Xinjiang and analyzed and in contrast to a BP neural network wind speed prediction model. The experimental results indicated that the four error evaluation indicators of the Sine-SSA-BP algorithm are all smaller than the BP neural network. In contrast to the single BP neural network wind speed forecast model, sine chaotic mapping modified sparrow search algorithm optimized BP neural network has significantly improved prediction accuracy.

A Hybrid Model for GRU Ultra-Short-Term Wind Speed Prediction Based on Tsfresh and Sparse PCA

Wind power is a popular renewable energy source, and the accurate prediction of wind speed plays an important role in improving the power generation efficiency of wind turbines and ensuring the normal operation of wind power equipment. Due to the instability and randomness of wind speed, it is difficult to achieve accurate prediction by traditional prediction methods. To improve the power generation efficiency of wind turbines and realize the predictability of wind speed, a hybrid wind speed prediction model based on GRUs (gated recurrent units) was constructed in this paper based on a deep neural network and feature extraction method. The hybrid model feature extraction module was implemented based on a combination of Tsfresh (a python package for time series feature extraction) and sparse PCA (sparse principal component analysis), and the network structure and other hyperparameters of the GRU module were determined through experiments. The model was validated using actual wind measurement data from a wind farm on the west coast of the United States. The results showed that the proposed model had less computational time and higher computational accuracy than the SARIMAX (seasonal auto-regressive integrated moving average with exogenous factors) and LSTM (long short-term memory) models.

Integrated energy management of hybrid power supply based on short-term speed prediction

The energy management strategy and output limitation of energy storage system affect the actual regenerative braking recovery. In order to optimize the performance and energy efficiency of vehicle energy storage system in the process of braking energy recovery, an integrated energy management strategy based on short-term speed prediction is proposed in this paper. Firstly, support vector machine classification method is used for off-line training and on-line recognition of driving patterns, and then input-output hidden Markov model and Gaussian mixture model are fused to establish speed prediction models under urban, suburban, and high-speed conditions for real-time prediction of speed sequences. Then, the power is distributed by the dynamic programming algorithm according to the short-term speed prediction results, and the distribution coefficient is corrected through the integrated strategy of braking force distribution and power distribution. Finally, the simulation results under continuously changing driving conditions show that the pattern recognition with changeable span is conducive to improving its accuracy during the transition period, and the proposed integrated energy management strategy is helpful to optimizing the performance of the hybrid energy storage system. The renewable energy utilization efficiency index indicates the efficiency of the integrated energy management strategy.

A ML-Based Wind Speed Prediction Model with Truncated Real-Time Decomposition and Multi-Resolution Data

Accurate wind speed prediction is of importance for long-span cross-sea bridges. To this end, data decomposition techniques are usually employed to promote accuracy of the prediction model. Since wind speed data come sequentially, real-time decomposition should be adopted. However, real-time decomposition may degrade the accuracy due to the end effect. In this paper, a novel scheme of real-time decomposition that is a combination of truncated real-time decomposition and multi-resolution data is developed. Specifically, truncated real-time decomposition firstly denoises the data and eliminates the end effect; high-resolution data are then introduced to compensate for the information loss. Further, a novel wind speed prediction model that consists of the proposed scheme and neural networks is proposed. Specifically, two gated recurrent unit neural networks are employed to extract features from the obtained original-resolution and high-resolution data, respectively, and a multi-layer perceptron is adopted to utilize extracted features and make predictions. The proposed model is validated on the monitoring wind speed data of two long-span cross-sea bridges. Specifically, the mean absolute error and the root of mean square error of the proposed model on the two datasets are 0.334, 0.445 and 0.233 and 0.316 m/s, which are smaller than benchmark models and demonstrate superiority of the proposed model.

Natural phase space reconstruction-based broad learning system for short-term wind speed prediction: Case studies of an offshore wind farm

Accurate prediction of wind speed can not only help to develop strategies for wind turbine operation, but also reduce impact on power systems when wind energy is integrated into the grid. However, it is difficult to predict speed accurately due to the stochastic nature of wind. To address this issue, this paper presents a novel wind speed prediction model based on phase space reconstruction and broad learning system (BLS). First, phase spaces under various delay dimensions and phase scales are reconstructed. Afterwards, natural neighbor spectrum is constructed without parameter setting based on phase vectors for selecting the optimal phase space. Then, the optimal inputting number of BLS is decided, elastic-net regularization is introduced to alleviate overfitting and BLS is trained in an incremental way. Finally, predicting values are given by output layer. Two cases about an offshore wind farm are used to demonstrate the effectiveness of the proposed model and five traditional models are used for comparison. Results show that compared with the other models, proposed model not only achieves higher predicting accuracy, but also has faster learning speed, meeting the requirement of online prediction for scale-growing wind speed and leaving more time for making strategies about grid planning.

Research on adaptive combined wind speed prediction for each season based on improved gray relational analysis.

The stability of the power grid and the operational security of the power system depend on the precise prediction of wind speed. In consideration of the nonlinear and non-stationary characteristics of wind speed in different seasons, this paper employs the weight of wind resource index calculated by triangular fuzzy analytic hierarchy process (TF-AHP), criteria importance through inter-criteria correlation (CRITIC), and entropy weight method (EWM) to improve gray correlation analysis (GRA) and obtain the gray correlation degree of each season. In addition, a wind speed prediction model is provided that includes single-layer and two-layer weighting and is based on both deep and shallow machine learning models. At first, we establish each quarter's wind resource characteristics at typical monthly intervals of 10min, 30min, 60min, and 120min. The GRA's TF-AHP-CRITIC-EWM, enhanced with subjective and objective weights, is used to assess the available wind resources in each season and to compute the forecasted combination of wind speed for each season. As the final prediction results, the prediction values of each layer model are evaluated independently. For the intervals with considerable errors, we apply wavelet denoising and replacement combination. The simulation findings show that the proposed combined model surpasses earlier benchmark models in terms of goodness of fit, prediction accuracy, and generalizability.

A Novel Hybrid Method for Short-Term Wind Speed Prediction Based on Wind Probability Distribution Function and Machine Learning Models

The need to deliver accurate predictions of renewable energy generation has long been recognized by stakeholders in the field and has propelled recent improvements in more precise wind speed prediction (WSP) methods. Models such as Weibull-probability-density-based WSP (WEB), Rayleigh-probability-density-based WSP (RYM), autoregressive integrated moving average (ARIMA), Kalman filter and support vector machines (SVR), artificial neural network (ANN), and hybrid models have been used for accurate prediction of wind speed with various forecast horizons. This study intends to incorporate all these methods to achieve a higher WSP accuracy as, thus far, hybrid wind speed predictions are mainly made by using multivariate time series data. To do so, an error correction algorithm for the probability-density-based wind speed prediction model is introduced. Moreover, a comparative analysis of the performance of each method for accurately predicting wind speed for each time step of short-term forecast horizons is performed. All the models studied are used to form the prediction model by optimizing the weight function for each time step of a forecast horizon for each model that contributed to forming the proposed hybrid prediction model. The National Oceanic and Atmospheric Administration (NOAA) and System Advisory Module (SAM) databases were used to demonstrate the accuracy of the proposed models and conduct a comparative analysis. The results of the study show the significant improvement on the performance of wind speed prediction models through the development of a proposed hybrid prediction model.

Multistep short-term wind speed forecasting using transformer

Wind power can effectively alleviate the energy crisis. However, its integration into the grid affects power quality and power grid stability. Accurate wind speed prediction is a key factor in the efficient use of wind power. Because of its intermittent and nonstationary nature, wind speed forecasting is difficult, and is the topic of much research, especially long-time multistep forecasts. In this paper, the multistep wind speed prediction problem is regarded as a sequence-to-sequence mapping problem, and a multistep wind speed prediction model based on a transformer is proposed. This model is based on an encoder–decoder architecture, where the encoder generates representations of historical wind speed sequences of any length, the decoder generates arbitrarily long future wind speed sequences, and the encoder and decoder are associated by an attention mechanism. At the same time, the encoder and decoder of Transformer are completely based on a multi-head attention mechanism. For easy modeling, a 1-dimensional original wind speed sequence is transformed to a 16-dimensional sequence by ensemble empirical mode decomposition (EEMD), and the multidimensional wind speed data are directly modeled with Transformer. We trained the model with very large-scale (19 years of data) wind speed data averaged at 10-minute intervals, and performed the evaluation over one-year wind speed data. Results show that our one-step forecast model achieved an average mean absolute error (MAE) and root mean square error (RMSE) of 0.167 and 0.221, respectively. To the best of our knowledge, our 3-, 6-, 12-, and 24-hour multistep forecast model achieves a new state of the art in wind speed forecasting, with respective MAEs of 0.243, 0.290, 0.362, and 0.453, and RMSEs of 0.326, 0.401, 0.513, and 0.651. It is believed that performance can be further improved with better model parameter optimization.

Time-variant post-processing method for long-term numerical wind speed forecasts based on multi-region recurrent graph network

Weather Research and Forecasting (WRF) is widely used for long-term wind speed prediction. To reduce the inherent systematic error of the WRF, a graph-based wind speed prediction model is proposed by post-processing the WRF. The proposed model contains four stages. In stage 1, the WRF model is applied to generate raw wind speed prediction results. In stage 2, Planar Maximally Filtered Graph (PMFG) is used to construct an informative graph of the wind field. In stage 3, Deep Autoencoder-like Nonnegative Matrix Factorization (DANMF) and Subgraph Alignment and Region Organization (SARO) are utilized to divide the graph into several regions. In stage 4, Multi-region Recurrent Graph Network (MRGN) model is proposed to build multiple regional models, aggregate them via time-variant ensemble weights, and generate improved long-term wind speed prediction results. The wind speed prediction results on 25 real meteorological monitoring nodes show that: (1) the proposed model outperforms WRF and 3 state-of-the-art models with a 95% confidence level; (2) the proposed model tends to produce better performance in strongly dynamic wind speed; (3) the proposed model has enough computational efficiency for practice. In conclusion, the proposed model is effective to improve WRF performance and has application potential.

Modelling the Free Flow Speed and 85th Percentile Speed Using Artificial Neural Network (ANN) and Genetic Algorithm

One of the main and crucial purposes of highway system is to provide a safe, comfortable, and efficient mode of transportation. Vehicular speed is considered as one of the high-priority issue to transportation engineers, planners and researchers, where it is a significant measure of effectiveness of traffic performance particularly under mixed traffic condition, which affects the traffic movement and level of service at different transportation facilities. In order to propose a new analytical method for vehicular speed, speed prediction models based on Artificial Neural Network (ANN) models and Genetic Algorithm (GA) have been developed for major urban arterial roads in Jordan. Prediction models have been developed with several input parameters and included within the ANN and GA. Traffic and geometric variables such as left lateral clearance, right lateral clearance, speed limit, Present Condition Index (PCI), shoulder width, lane width, access point density, International Roughness Index (IRI) and Present Serviceability Rating (PSR) have been included in both models. Meanwhile, the outputs of prediction models have been 85th percentile speed and Mean Free Flow Speed (MFFS) km/hr. The computational results show that the speeds predicted by the developed models are highly correlated with the measured ones. ANN modeling has a better performance than GA in estimation of 85th percentile speed. This study provides useful information to predict the FFS and 85th percentile speed on roads depending on variables, which are available on any constructed or to be constructed roads.

Wind Speed Prediction Model Based on Improved VMD and Sudden Change of Wind Speed

An accurate wind speed prediction system is of great importance prerequisite for realizing wind power grid integration and ensuring the safety of the power system. Quantifying wind speed fluctuations can better provide valuable information for power dispatching. Therefore, this paper proposes a deterministic wind speed prediction system and an interval prediction method based on the Lorentzian disturbance sequence. For deterministic forecasting, a variational modal decomposition algorithm is first used to reduce noise. The preprocessed data are then predicted by a long and short-term neural network, but there is a significant one-step lag in the results. In response to such limitation, a wind speed slope is introduced to revise the preliminary prediction results, and the final deterministic wind speed prediction model is obtained. For interval prediction, on the basis of deterministic prediction, the Lorenz disturbance theory is introduced to describe the dynamic atmospheric system. B-spline interpolation is used to fit the distribution of Lorenz disturbance theory series to obtain interval prediction results. The experimental results show that the model proposed in this paper can achieve higher forecasting accuracy than the benchmark model, and the interval prediction based on the Lorentzian disturbance sequence can achieve a higher ground truth coverage rate when the average diameter is small through B-spline interpolation fitting.

Wind Speed Forecasting using Machine Learning Approach based on Meteorological Data-A case study

This paper presents a forecasting method to anticipate wind speed accurately. This method is applied to an energy production site using an artificial intelligence method based on machine learning. The accuracy of this method is higher compared to other existing methods in the literature for time series analysis such as artificial neural networks and the complexity of wind speed prediction models without loss of information content. We tested several thousand data between 1985 and 2018 in the city of Basel, a city in northwestern Switzerland. We have used the MATLAB Software for this modeling. The study demonstrates that the use of statistical models based on machine learning is relevant to predict of speed and direction of the wind in power generation systems from meteorological data. The results obtained are presented and discussed.

Wind speed prediction using a hybrid model of EEMD and LSTM considering seasonal features

As a clean and renewable energy source, wind power is of great significance for addressing global energy shortages and environmental pollution. However, the uncertainty of wind speed hinders the direct use of wind power, resulting in a high proportion of abandoned wind. Therefore, the accurate prediction of wind speed is of great significance in improving the utilization rate of wind energy. In this study, a hybrid wind speed prediction model is proposed based on seasonal autoregressive integrated moving average (SARIMA), ensemble empirical mode decomposition (EEMD), and long short-term memory (LSTM) methods. First, the original wind speed data were resampled to obtain wind speed data within time scales of 15, 30, and 60 min. The SARIMA model was used to extract the linear features and nonlinear residual sequences of wind speed time series at different time scales, and EEMD was used to decompose the nonlinear residual sequence to obtain intrinsic mode functions (IMFs) and sub-residual sequences. For the IMFs and sub-residual sequence obtained after decomposition, the LSTM method was used for training, and the predicted IMFs, sub-residual sequence, seasonal time series, and linear time series were integrated to obtain the final prediction wind speed. To verify the superiority of the wind speed hybrid prediction model proposed in this study, the original wind speed data of a large wind farm were used as a case study. Finally, the proposed wind speed hybrid prediction model was compared with other prediction models, verifying that this experimental model has a higher prediction accuracy.

A novel and hybrid framework based on generative adversarial network and temporal convolutional approach for wind speed prediction

Accurate wind speed forecasting is a precondition for improving grid integration of wind energy. High-dimensional input is required for wind speed prediction models to deliver reliable results. However, owing to the failure of data measuring instruments, the process of obtaining wind speed data encounters various problems. Missing data must be imputed, and dynamic properties must be interpreted accurately in order to forecast successfully. Addressing these, in this study, hybrid forecasting approach using generative adversarial network (GAN) and temporal convolutional network based gated recurrent unit (TCN-GRU) for 5-min, 10-min and 30-min ahead missing value imputation and wind speed forecasting is proposed. TCN is utilized for the feature extraction and GRU forecasts the wind speed. To prove the novelty and performance of the proposed approach, experiments are conducted using data acquired from wind farms located in Bend, and Idalia. The results of the two experiments are compared with robust approaches for imputation as well as forecasting. The proposed hybrid approach is assessed using different performance metrics, and experimental results reveal that the proposed approach's performance for the imputation is improved by 30% and 37% and WSF is improved by 45%, 37% respectively in the two experiments.

An efficient short-term wind speed prediction model based on cross-channel data integration and attention mechanisms

With the growing focus on renewable energy, wind power is increasingly valued and advocated. In order to guarantee the stability of wind power system dispatch and management, reliable prediction of future wind speeds is essential. In this study, a short-term wind speed prediction model based on cross-channel data convolution, intelligent signal extension and attention mechanisms is proposed to enhance the prediction efficiency. The model first classifies the wind speed signal into IMFs (intrinsic mode functions) and residual data with the EMD (empirical mode decomposition) method, and then divides IMFs into rough prediction part and accurate prediction part according to the signal characteristics. CNN (convolutional neural network) modules are adopted for the rough prediction part to ensure a speedy process, whereas a CNN-AM (attentional mechanism)-LSTM (long short-term memory)-ECA (efficient channel attention) hybrid network is developed to for the accurate prediction part. Through the time-history prediction on measured 10 min average wind speed data, the results show that: (a) The channel-crossing one-dimensional (1D) convolution, intelligent signal extension, and attention mechanisms applied in the proposed model can effectively improve the accuracy of predictions; (b) The proposed prediction model is superior to the compared baseline models in precision and efficiency; and (c) The proposed model features strong migration learning ability for fast application on new datasets.

Development of Mode-Wise Speed Prediction Models for Urban Roads with Side Friction Characteristics

The present study has developed regression models to study the impact of side friction factors on speeds of vehicles in urban roads. The factors that were considered are on-street parking, pedestrian movement, water stagnation, encroachment, poor road condition and wrong side driving. Three locations from Vellore and Chikmagalur cities in India were selected and vehicle speeds, side friction parameters and flow were collected through videographic survey for 6 hours duration. It was found that the speeds of vehicles were in the range of only 11-23 km/h due to side friction. The study has proposed a "simple arithmetic operand" method to overcome the multicollinearity problem and it predicts well, the speeds with mean absolute percentage error (MAPE) between 8-29 %. The arithmetic operand method proposed in the present study can be applied in other fields as well to overcome the multicollinearity problem.

Multi-Step Short-Term Wind Speed Prediction Models Based on Adaptive Robust Decomposition Coupled with Deep Gated Recurrent Unit

Accurate wind speed prediction is a premise that guarantees the reliable operation of the power grid. This study presents a combined prediction model that integrates data preprocessing, cascade optimization, and deep learning prediction to improve prediction performance. In data preprocessing, the wavelet soft threshold denoising (WSTD) is employed to filter the blurring noise of the original data. Then, the robust empirical mode decomposition (REMD) and adaptive variational mode decomposition (AVMD) are adopted to carry out a two-stage adaptive decomposition. Spearman correlation is used to quantify the mode that need to be decomposed for the second time. In the cascade optimization, the hybrid grey wolf algorithm (HGWO) is employed to optimize the parameters of the VMD and the gated recurrent unit (GRU), which overcomes the problem of empirical parameter adjustment. The HGWO is also adopted in the prediction strategy to optimize the GRU model to predict the grouped intrinsic mode functions (IMFs). Lastly, the final wind speed prediction result is obtained by superimposing the values of all the predicted models. The proposed model was validated with the measured wind speed data of the four quarters in the Bay area of China and was compared with 20 models of the classic method to further evaluate the effectiveness of the model. The results show that the whole process of the proposed model is adaptive, the final multi-step prediction performance is good, and high prediction accuracy can be attained.

Analysis and prediction models for operating speed of vehicles in expressway superlong tunnels based on geometric and traffic related parameters

Objectives Operating speeds on roads are critical indicators for evaluating traffic safety. Currently available research on the operating speed’s prediction focuses on open roads and highways. Insufficient attention has been paid, so far, to tunnels, which form bottlenecks on expressways. The present research aims to establish an operating speed prediction model for tunnels and analyze the influence of their geometric parameters on the operating speeds of vehicles. Methods We consider the speed of vehicles collected through field measurements in the portals and lay-bys of six superlong tunnels (length greater than 3000 ). Using linear regression, a prediction model for the speed in an expressway superlong tunnel is obtained considering tunnel’s geometric parameters. The influence of various parameters on the operating speed are analyzed through comparisons with existing research findings. Results We establish the first operating speed prediction model for tunnels considering geometric parameters and find that the vehicle type is the most important parameter affecting the operating speed. Other important parameters include the preceding curve length up to speed observation point (), preceding tangent length () and preceding tangent length up to speed observation point (). Conclusions The influence of geometric parameters on vehicle operating speed in super long tunnels differs from that observed in non-tunnel roadways. The effects of the preceding or subsequent curve radius ( or ) of the tangent section, curvature (), and curve degree () are not important in this case. Furthermore, we find that the influence of the posted speed limit () is closely related to the driving scene and safety awareness of drivers. These findings can improve the design and joint evaluation of tunnel geometric parameters and traffic safety.

XGBoost-DNN Mixed Model for Predicting Driver’s Estimation on the Relative Motion States during Lane-Changing Decisions: A Real Driving Study on the Highway

This study is conducted on a real live highway to investigate the driver’s performance in estimating the speed and distance of vehicles behind the target lane during lane changes. Data on the participants’ estimated and actual data on the rear car were collected in the experiment. Ridge regression is used to analyze the effects of both the driver’s features, as well as the relative and absolute motion characteristics between the target vehicle and the subject vehicle, on the driver’s estimation outcomes. Finally, a mixed algorithm of extreme gradient boosting (XGBoost) and deep neural network (DNN) was proposed in this paper for establishing driver’s speed estimation and distance prediction models. Compared with other machine learning models, the XGBoost-DNN prediction model performs more accurate prediction performance in both classification scenarios. It is worth mentioning that the XGBoost-DNN mixed model exhibits a prediction accuracy approximately two percentage points higher than that of the XGBoost model. In the two-classification scenarios, the accuracy estimations of XGBoost-DNN speed and distance prediction models are 91.03% and 92.46%, respectively. In the three-classification scenarios, the accuracy estimations of XGBoost-DNN speed and distance prediction models are 87.18% and 87.59%, respectively. This study can provide a theoretical basis for the development of warning rules for lane-change warning systems as well as insights for understanding lane-change decision failures.