Speed Prediction Research Articles

Hierarchical control of plug-in hybrid electric vehicle platoon with DQL optimized SOC reference trajectories incorporating traffic information prediction working condition

To address the problem of the traditional linear state-of-charge (SOC) reference trajectory cannot adapt to the driving conditions, a hierarchical control of plug-in hybrid electric vehicle (PHEV) platoon with deep Q-learning (DQL) optimized SOC reference trajectories incorporating traffic information prediction working conditions is proposed. Based on the traffic information, the upper-level controller uses a long short-term memory (LSTM) neural network to achieve global speed prediction for the lead vehicle, and a nonlinear model predictive control (NMPC) algorithm to achieve longitudinal control of the platoon and obtain the optimal demand torque for the vehicle. The lower-level uses principal component analysis (PCA) and a K-means clustering algorithm to construct four typical working conditions. The radial basis function (RBF) neural network is used to predict the vehicle speed in a short time, and then the SOC reference trajectory in the prediction time domain is generated by the coupled DQL network. Under the framework of MPC, real-time energy management of the platoon is achieved through rolling optimization using the dynamic programing (DP) algorithm. The results show that the strategy can significantly improve the fuel economy of the platoon. Compared with the time-based and distance-based SOC reference trajectories, the platoon’s fuel consumption is reduced by 7.94% and 3.72%, respectively. Compared with the SOC reference trajectory based on DP, the platoon’s fuel consumption is roughly the same. However, the strategy can not only adapt to the change of driving conditions but also be applied online.

Highway Travel-Time Forecasting with Greenshields Model-Based Cascaded Fuzzy Logic Systems

Intelligent Transportation Systems (ITSs) play a vital role in improving urban and regional mobility by reducing traffic congestion and enhancing trip planning. A key element of ITS is travel-time prediction, which supports informed decisions for both travelers and traffic management. While non-parametric models offer flexibility, they often require large datasets and significant computation. Parametric models, though easier to fit and interpret, are less adaptable. Fuzzy logic models, by contrast, provide robustness and scalability, adjusting to new data and changing conditions. This paper proposes a cascaded fuzzy logic system for highway travel-time prediction, using the Greenshields model as its reasoning foundation. The system consists of multiple fuzzy subsystems, each representing a highway segment. These subsystems transform traffic flow and density inputs into speed predictions through fuzzification, Greenshields-based rules, and defuzzification. The approach enables localized and segment-specific predictions, enhancing route planning and congestion avoidance. The system’s accuracy is evaluated by comparing its predictions with those of a regression model using real traffic data from the Sun Yat-Sen Highway in Taiwan. Simulation results confirm that the proposed model achieves reliable, adaptable travel-time forecasts, including for long-distance trips.

Comparison of Empirical and Deep Learning Models for Solar Wind Speed Prediction

Abstract In this study, we compare representative empirical models with a deep learning model for predicting solar wind speed at 1 au. The empirical models are the Wang–Sheeley–Arge–ENLIL model, which combines empirical methods with a magnetohydrodynamic model, and the empirical solar wind forecast model, which uses the relationship between the fractional coronal hole area and solar wind speed. Our deep learning model predicts solar wind speed over 3 days ahead using extreme-ultraviolet images and up to 5 days of solar wind speed before the prediction date. We evaluate the models over the test period (October–December in each year from 2012 to 2020) in view of solar activity phases and the entire period. To validate the model’s performance, we use two evaluation methods: a statistical approach and an event-based approach. For statistical verification during the entire period, our model outperforms the other empirical models, with a much lower mean absolute error of 51.4 km s−1 and rms error of 68.6 km s−1, along with a much higher correlation coefficient of 0.69. For the event-based verification for high-speed solar wind streams, our model has superior performance in most of the six metrics evaluated within a ±1 day time window. In particular, it achieves a high success ratio of 0.82, emphasizing the model’s stable performance and ability to minimize false alarms. These results show that our deep learning model has strong potential for practical application as a reliable tool for fast solar wind forecasting with its high accuracy and stability.

Determining Factors Influencing Operating Speeds on Road Tangents

Road traffic accidents remain a critical global issue with approximately 1.19 million fatalities each year, on which excessive and inappropriate speeds contribute significantly. Managing vehicle speeds is essential for improving road safety, yet predicting and understanding operating speeds remains a challenge. Among different road elements, tangents play a crucial role, as they serve as transition segments between curves and allow for free acceleration, making them particularly relevant for speed management and road design. This study investigates the operating speeds on both single- and dual-carriageway road tangents to identify the key influencing factors. Data were collected from 24 single-carriageway and 20 dual-carriageway road tangents in Croatia, comprising a total of 14,854 speed observations (filtered sample size). The analysis focuses on the impact of geometric, traffic, and roadside environment characteristics on operating vehicle speeds. The results reveal that for single-carriageway road tangents, the most influential factors were traffic volume and terrain type, while for dual-carriageway road tangents, the factors traffic flow density, average summer daily traffic, and heavy goods vehicle share. These findings provide essential insights for the future development of operating speed prediction models, enhancing road design guidelines, and improving speed management strategies.

Association between socio-demographic and injury factors, and physical activity behaviour in people with spinal cord injury: a theory-informed systematic review and meta-analysis

BackgroundIdentifying the determinants of physical (in)activity behaviour among people with spinal cord injury (PWSCI) will aid the prediction of speed and extent of recovery and inform strategies to optimise physical activity participation during physical rehabilitation. This review examined the association between socio-demographics, injury factors, and physical activity in PWSCI.MethodsThe Preferred Items for Reporting Systematic Reviews and Meta-analysis Protocols (PRISMA-P) provided the structure for this review. The epidemiological triangle and Bradford criteria further informed the review, as well as Rothman's causality model and Nweke's viewpoints. The review outcomes included injury factors and socio-demographic (intrinsic and extrinsic) factors associated with physical (in)activity in PWSCI. We searched four databases: PubMed, Medline, the Cumulative Index for Nursing and Allied Health Literature (CINHAL) and Academic Search Complete. The review used predefined eligibility criteria and a data screening and extraction template. The first author verified the extracted data. We employed narrative and quantitative syntheses and used a comprehensive Meta-analysis 4 to answer the review question.ResultsWe retrieved 4,129 articles, of which 16 (nine cross-sectional studies, six cohorts and one non-randomised clinical trial) with 2,716 participants were eligible. The mean age of participants in the included studies was 45 years, and about 14% were female. Physical (in) activity was statistically significantly associated with income (OR = 1.58, CI 1.23–2.04), completeness of lesion (OR = 0.86 CI 0.82–0.90), and mobility aid (3.12, CI 1.57–6.19). No statistically significant association existed between physical (in) activity and age (OR = 1.09, CI 0.46–2.58), sex (OR = 0.66, CI 0.43–1.03), education (OR = 0.66, CI 0.42–1.06), time since injury (OR = 0,971, CI 0,749–1,26), vertebral level of the lesion (OR = 0.92, CI 0.71–1.11), or mechanism of injury (OR = 1.48, CI 0.74–2.97) among PWSCI.ConclusionsEfforts to optimise physical activity participation among PWSCI should consider the completeness of injury, income and type of mobility aid during rehabilitation programs. Factors such as employment status, residence, and type of house were less underscoring, and most studies needed more robust conceptual and theoretical underpinnings.Trial registrationThe review was registered with PROSPERO (ID: CRD42024544295).

An Informer-BiGRU-temporal attention multi-step wind speed prediction model based on spatial-temporal dimension denoising and combined VMD decomposition

An Informer-BiGRU-temporal attention multi-step wind speed prediction model based on spatial-temporal dimension denoising and combined VMD decomposition

The environmental challenge of HPC: finding green power and cooling solutions for supercomputers

In today's world, High-Performance Computing (HPC) is driving scientific research forward at an astonishing rate, but behind every top HPC device lies a high-load power grid, which has sparked deep concern among environmentalists. This study develops a mathematical model to evaluate the power consumption of global HPC equipment and quantify its environmental impact, providing a basis for energy optimization and sustainable development. By systematically analyzing the global environmental impact of HPC through a series of models focused on energy consumption and related emissions, we first created a GPU survival function to estimate the global number of HPC devices in 2023. Using Monte Carlo simulation and Markov chain models, we estimated the power consumption of individual HPC centers under both full load and average utilization conditions, subsequently calculating the total annual power consumption of global HPC centers. Next, we developed models to estimate the total carbon emissions from global HPC energy consumption, considering various energy production methods and energy mix scenarios. Additionally, we created a gray prediction model to forecast the GPU market value in 2030, combining it with the GPU survival function to predict the number of global HPC centers in 2030. We also developed an electricity price fluctuation model to account for increased energy demand from other sectors and analyzed the environmental impact of global HPC centers in 2030 under different energy mix structures. Furthermore, we extended the model to assess the impact of increasing renewable energy (specifically wind energy) to 100% in the energy mix, evaluating its potential to reduce carbon emissions. Finally, we conducted a sensitivity analysis, incorporating seawater cooling for HPC centers and artificial intelligence to dynamically adjust GPU power based on wind speed predictions.

A physics-informed temporal convolutional network-temporal fusion transformer hybrid model for probabilistic wind speed predictions with quantile regression

A physics-informed temporal convolutional network-temporal fusion transformer hybrid model for probabilistic wind speed predictions with quantile regression

Energy management strategy for plug-in hybrid electric vehicles based on vehicle speed prediction and limited traffic information

Energy management strategy for plug-in hybrid electric vehicles based on vehicle speed prediction and limited traffic information

Retraction notice to "Improving extreme offshore wind speed prediction by using deconvolution" [Heliyon 9 (2023) e13533

Retraction notice to "Improving extreme offshore wind speed prediction by using deconvolution" [Heliyon 9 (2023) e13533

Correction to “Short‐Term Wind Speed Prediction Model Based on Hybrid Decomposition Method and Deep Learning”

Correction to “Short‐Term Wind Speed Prediction Model Based on Hybrid Decomposition Method and Deep Learning”

Real-Time Energy-Efficient Control Strategy for Distributed Drive Electric Tractor Based on Operational Speed Prediction

This study develops a real-time energy-efficient control strategy for distributed-drive electric tractors (DDETs) to minimize electrical energy consumption during traction operations. Taking a four-wheel independently driven DDET as the research object, we conduct dynamic analysis of draft operations and establish dynamic models of individual components in the tractor’s drive and transmission system. A backpropagation (BP) neural network-based operational speed prediction model is constructed to forecast operational speed within a finite prediction horizon. Within the model predictive control (MPC) framework, a real-time energy-efficient control strategy is formulated, employing a dynamic programming algorithm for receding horizon optimization of energy consumption minimization. Through plowing operation simulation with comparative analysis against a conventional equal torque distribution strategy, the results indicate that the proposed real-time energy-efficient control strategy exhibits superior performance across all evaluation metrics, providing valuable technical guidance for future research on energy-efficient control strategies in agricultural electric vehicles.

Wind energy resource assessment based on joint wolf pack intelligent optimization algorithm

Wind energy is a clean and renewable energy source with great potential for development, but the intermittent and stochastic characteristics of wind speed have brought great challenges to the effective development and utilisation of wind energy resources, resulting in high development costs. Therefore, how to accurately assess the wind energy resources and effectively predict the wind speed has become a key issue to be solved in the current wind energy field. In view of this, the study proposes the Weibull model to model the wind speed data, and then introduces the wolf pack intelligent optimisation algorithm and improves it through the pollination mechanism to improve the accuracy of wind energy resource assessment. Secondly, considering the complexity and diversity of wind speed data characteristics, data decomposition technique, autoregressive moving average (ARIMA) model and cuckoo search algorithm are used to achieve data preprocessing, serial data modelling and hybrid prediction. The experimental results show that the Weibull model has good fitting accuracy for wind speed data, with residual sum of squares, RMSE, and average coefficient of determination of 0.05, 0.014, and 0.96, respectively, accurately reflecting the statistical characteristics of wind speed data. The wind speed prediction performance of the hybrid prediction model is good, with a maximum deviation of no more than 3% from the true value, which is significantly better than the compared VMD-ISOA-KELM model and CNN-BLSTM model, and its prediction error is relatively small. The hybrid prediction model has a smaller relative error value compared to a single algorithm, with a maximum value of less than 0.2. It has better prediction performance than the combination model, with a coefficient of determination approaching 1.0, a fitting accuracy of 0.994, a mean square error of 0.1947, a root mean square error of 0.3847, and an average absolute percentage error of 15.23%. And the research method can effectively evaluate the status of wind energy resources, with low time complexity at different data scales, taking no more than 5 seconds, and improving operational efficiency. This research method can provide strong technical support and reference basis for the development and utilisation of wind energy resources, and help to promote the sustainable development of wind energy industry.

Wind Speed Forecasting in the Greek Seas Using Hybrid Artificial Neural Networks

The exploitation of renewable energy is essential for mitigating climate change and reducing fossil fuel emissions. Wind energy, the most mature technology, is highly dependent on wind speed, and the accurate prediction of the latter substantially supports wind power generation. In this work, various artificial neural networks (ANNs) were developed and evaluated for their wind speed prediction ability using the ERA5 historical reanalysis data for four potential Offshore Wind Farm Organized Development Areas in Greece, selected as suitable for floating wind installations. The training period for all the ANNs was 80% of the time series length and the remaining 20% of the dataset was the testing period. Of all the ANNs examined, the hybrid model combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks demonstrated superior forecasting performance compared to the individual models, as evaluated by standard statistical metrics, while it also exhibited a very good performance at high wind speeds, i.e., greater than 15 m/s. The hybrid model achieved the lowest root mean square errors across all the sites—0.52 m/s (Crete), 0.59 m/s (Gyaros), 0.49 m/s (Patras), 0.58 m/s (Pilot 1A), and 0.55 m/s (Pilot 1B)—and an average coefficient of determination (R2) of 97%. Its enhanced accuracy is attributed to the integration of the LSTM and GRU components strengths, enabling it to better capture the temporal patterns in the wind speed data. These findings underscore the potential of hybrid neural networks for improving wind speed forecasting accuracy and reliability, contributing to the more effective integration of wind energy into the power grid and the better planning of offshore wind farm energy generation.

Leveraging Machine Learning for Optimal Pilgrim Crowd Management

The Hajj pilgrimage involves high crowd density within limited time and space, making traditional crowd control methods insufficient for real-time alerts or predictive safety measures. This research proposes a machine learning-based system to enhance crowd management by detecting abnormal behavior and forecasting future conditions. The study utilizes the Hajjv2 dataset, which consists of annotated video frames capturing various crowd behaviors across multiple Hajj locations. After data preprocessing and feature extraction, including crowd density, speed, direction, and object area, two models are employed: the Isolation Forest algorithm for anomaly detection and a Long Short-Term Memory (LSTM) neural network for forecasting crowd behavior. The system integrates the results of both models to issue real-time alerts based on predefined thresholds. Evaluation results indicate that the Isolation Forest model achieved an average accuracy of 91% across all test sets, effectively identifying abnormal movement patterns. The LSTM model produced reliable predictions of average crowd speed with a low Mean Squared Error (MSE) of 0.000439. Together, these models form a robust alert mechanism that enables early identification of risks. In summary, this study presents an intelligent, scalable solution for enhancing crowd safety during the Hajj. It illustrates the practical value of machine learning in enabling proactive and informed crowd management strategies.

Leveraging multi-head attention transformer deep neural network architecture for improved wind speed forecasting

Wind energy has great potential for electricity generation, but its variability makes accurate wind speed forecasting essential for efficient integration. This study explores the application of a transformer-based deep learning model for wind speed forecasting. The model features an encoder-decoder architecture with multi-head attention, feed-forward layers, and normalization functions. By leveraging a self-attention mechanism, the transformer model effectively captures temporal dependencies in time series data through weighted relationships among input sequences, leading to improved forecasting accuracy. To evaluate its effectiveness, we collected and pre-processed wind speed data from the Hong Phong 1 wind power plant, cleaned the data by removing outliers and addressed missing values. The processed data was then embedded and added positional encoding to prepare for model input. The model was trained, and its performance was benchmarked against other models, including Long Short-Term Memory, Convolutional Neural Networks, and Artificial Neural Networks. The obtained RMSE is quite low, with 0,26 m/s for single-step forecast, 0,73 m/s for 4-step forecast and 1,70 m/s for 16-step forecast. These results demonstrated that the transformer model achieved superior predictive performance, suggesting it as a powerful alternative to traditional forecasting methods, with significant potential for enhancing the accuracy of wind speed predictions.

Wind speed prediction for trains on bridges using enhanced variational mode decomposition assisted feature extraction and physical auxiliary mechanism

The operation safety and stability of trains is closely related with the wind speed. However, given the intricate nature of its characteristics, which encompass linearity, nonlinearity, nonstationarity etc., accurately predicting the short-term wind speed presents a notable obstacle. To this end, this paper presents a novel forecasting approach using the hybrid of enhanced variational mode decomposition (EVMD), auto-regressive integrated moving average (ARIMA), fully convolutional neural network (FCN), and physical auxiliary mechanism (PAM). This method not only can provide the accurately deterministic prediction, but also can produce the desired probabilistic prediction. Specifically, EVMD is developed based the mode aliasing problem for performing the data decomposition and reconstruction. Then, the combination of ARIMA and FCN is used to perform linear and nonlinear predictions. Finally, PAM is introduced into the above established model for realizing the desired deterministic and probabilistic predictions where the relationship among the wind speed data recorded at various time intervals and the data variability are considered. Numerical examples, utilizing two sets of measured wind speed data, underscore the efficacy and advantage of the developed method. For example, the proposed method can realize the reduction of the average of mean absolute error from 1.08 to 0.73 in comparison with ARIMA-FCN-PAM. Hence, the proposed method stands as a viable and efficient alternative for forecasting the short-term wind speed.

Improvement of speed prediction for an urban network under GA-LSTM-CNN method

Improvement of speed prediction for an urban network under GA-LSTM-CNN method

A Hybrid Deep Learning Framework for Wind Speed Prediction with Snake Optimizer and Feature Explainability

Renewable energy, especially wind power, is required to reduce greenhouse gas emissions and fossil fuel use. Variable wind patterns and weather make wind energy integration into modern grids difficult. Energy trading, resource planning, and grid stability demand accurate forecasting. This study proposes a hybrid deep learning framework that improves forecasting accuracy and interpretability by combining advanced deep learning (DL) architectures, explainable artificial intelligence (XAI), and metaheuristic optimization. The intricate temporal relationships in wind speed data were captured by training Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), LSTM-GRU hybrid, and Bidirectional LSTM-GRU following data preprocessing and normalization. To enhance transparency, Local Interpretable Model-Agnostic Explanations (LIMEs) were applied, revealing key time-step contributions across three urban datasets (Los Angeles, San Francisco, and San Diego). The framework further incorporates the Snake Optimizer Algorithm (SOA) to optimize hyperparameters such as LSTM units, dropout rate, learning rate, and batch size, ensuring improved training efficiency and reduced forecast error. The model predicted 2020–2040 wind speeds using rolling forecasting; the SOA-optimized LSTM model outperformed baseline and hybrid models, achieving low MSE, RMSE, and MAE and high R2 scores. This proves its accuracy, stability, and adaptability across climates, supporting wind energy prediction and sustainable energy planning.

Research on Intelligent Hierarchical Energy Management for Connected Automated Range-Extended Electric Vehicles Based on Speed Prediction

To address energy management challenges for intelligent connected automated range-extended electric vehicles under vehicle-road cooperative environments, a hierarchical energy management strategy (EMS) based on speed prediction is proposed from the perspective of multi-objective optimization (MOO), with comprehensive system performance being significantly enhanced. Focusing on connected car-following scenarios, acceleration sequence prediction is performed based on Kalman filtering and preceding vehicle acceleration. A dual-layer optimization strategy is subsequently developed: in the upper layer, optimal speed curves are planned based on road network topology and preceding vehicle trajectories, while in the lower layer, coordinated multi-power source allocation is achieved through EMSMPC-P, a Bayesian-optimized model predictive EMS based on Pontryagin’ s minimum principle (PMP). A MOO model is ultimately formulated to enhance comprehensive system performance. Simulation and bench test results demonstrate that with SoC0 = 0.4, 7.69% and 5.13% improvement in fuel economy is achieved by EMSMPC-P compared to the charge depleting-charge sustaining (CD-CS) method and the charge depleting-blend (CD-Blend) method. Travel time reductions of 62.2% and 58.7% are observed versus CD-CS and CD-Blend. Battery lifespan degradation is mitigated by 16.18% and 5.89% relative to CD-CS and CD-Blend, demonstrating the method’s marked advantages in improving traffic efficiency, safety, battery life maintenance, and fuel economy. This study not only establishes a technical paradigm with theoretical depth and engineering applicability for EMS, but also quantitatively reveals intrinsic mechanisms underlying long-term prediction accuracy enhancement through data analysis, providing critical guidance for future vehicle–road–cloud collaborative system development.