Speed Forecasting Research Articles

High-resolution spatiotemporal forecasting of the European crane migration

In this paper we present three different models to forecast bird migration. They are species-specific individual-based models that operate on a high spatiotemporal resolution (kilometres, 15 min-hours), as an addition to radar-based migration forecast models that currently exist. The models vary in complexity, and use GPS-tracked location, flying direction and speed, and/or wind data to forecast migration speed and direction. Our aim is to quantitatively evaluate the forecasting performance and assess which metrics improve forecasts at different ranges. We test the models through cross-validation using GPS tracks of common cranes during spring and autumn migration. Our results show that recordings of flight speed and direction improve the accuracy of forecasts on the short range (<2 h). Adding wind data at flight altitude results in consistent improvements of the forecasts across the entire range, particularly in the predicted speed. Direction forecasts are less affected by adding wind data because cranes mostly compensate for wind drift during migration. Migration in spring is more difficult to forecast than in autumn, resulting in larger errors in flight speed and direction during spring. We further find that a combination of flight behaviours – thermal soaring, gliding, and flapping – complicates the forecasts by inducing variance in flight speed and direction. Fitting those behaviours into flight optimisation models proves to be challenging, and even results in significant biases in speed forecasts in spring. We conclude that flight speed is the most difficult parameter to forecast, whereas flight direction is the most critical for practical applications of these models. Such applications could e.g., be prevention of bird strikes in aviation or with wind turbines, and public engagement with bird migration.

A Proposed Hybrid Machine Learning Model Based on Feature Selection Technique for Tidal Power Forecasting and Its Integration

Renewable energy resources are playing a crucial role in minimizing fossil fuel emissions. Integrating machine learning techniques with tidal power forecasting could greatly enhance the accuracy and reliability of predictions, which is crucial for efficient energy production and management. A hybrid approach combining different methods often yields better results than relying on individual techniques. The accuracy of tidal current power is very important, especially for smart grid applications. This work proposes hybrid adaptive neuro-fuzzy inference system (ANFIS) with the Kalman filter (KF) and a neuro-wavelet (WNN) for tidal current speed, direction, and power forecasting. The turbine used in this study is driven by a direct drive permanent magnet synchronous generator (DDPMSG). The predictions of individual and hybrid models including the ANFIS, the Kalman filter, and the WNN for tidal current speed and the power it generates are compared with another dataset as a way of validation which is the tidal currents direction. Also, other published work results in the literature are compared to the proposed work. Different hybrid models are proposed for smart grid integration. The results of this work indicate that the hybrid model of the WNN and the ANFIS for tidal current power or speed forecasting has the highest performance compared to all other models.

Traffic flow and speed forecasting through a Bayesian deep multi-linear relationship network

Both traffic flow and speed forecasting are of great importance to intelligent transportation systems, which have been studied intensely in the past decades. In recent years, forecasting approaches based on deep learning have attracted the most extensive attention. However, most studies only predict traffic flow and speed separately, without taking advantage of the correlation between the two tasks. Unlike single-task learning, multi-task learning (MTL) approaches can learn related tasks simultaneously. MTL enhances the learning of each task by exploiting useful information from other related tasks. Nevertheless, traditional MTL methods only share transferable features at the feature layers and simply make an assumption that given the shared representation, the multiple tasks can be well correlated with each other, which leads to under-transfer and negative-transfer. In this paper, we propose a new MTL approach to forecast both traffic flow and speed, which shares transferable features at feature layers but learns the correlation between tasks at task-specific layers. By learning the multi-linear relationships between tasks and features as well as the transferable features, the proposed approach can mitigate the above-mentioned issues. Comprehensive experiments from a case study based on real data show that the proposed method steadily achieves the best forecasting results and good robustness.

Retraction Note: Forecasting of the wind speed under uncertainty

Retraction Note: Forecasting of the wind speed under uncertainty

Predictive Battery State of Charge Reference Generation Using Basic Route Information for Optimal Energy Management of Heavy-Duty Fuel Cell Vehicles

One of the main challenges for the energy management of heavy-duty fuel cell/battery hybrid vehicles is to control the battery charge within safe operating levels without hindering fuel efficiency. This article proposes a novel method that uses basic route information from navigation systems to implement an optimal and predictive energy management scheme to improve battery charge control, fuel economy, and fuel cell system lifetime. Indeed, it is possible to obtain a rough estimate of the electric load profile using elevation and speed forecasts and optimize the power split before starting the trip. The result of this offline optimization is saved as a location-based battery state of charge (SoC) reference for the online power-split strategy. The novelty of this work is related to the formulation of a quadratic program to generate the predictive SoC reference by optimizing the hydrogen economy while respecting the battery charge constraints. Afterward, a simple but effective online energy management strategy is used to track the predictive references during the simulations. The use of real-world driving cycles is essential to demonstrate the benefits of the proposed method. In particular, it is critical to consider the road elevation because it highly influences the power demand of heavy-duty vehicles. The simulation results prove that using the predictive SoC reference significantly improves the hydrogen economy and battery charge control compared to a non-predictive energy management scheme. In addition, the high-power operation time of the fuel cell system is reduced, resulting in slower system degradation compared to the non-predictive strategy. The effectiveness and robustness of the proposed method are tested against 1750 hours of real-world driving scenarios, considering uncertain speed and vehicle mass information for the reference generation. Statistical and global analyses of the results prove that the implementation of the predictive SoC reference generation method is highly beneficial for the performance of heavy-duty fuel cell vehicles.

Examination of turbulence impacts on ultra-short-term wind power and speed forecasts with machine learning

Wind turbines’ economic and secure operation can be optimized through accurate ultra-short-term wind power and speed forecasts. Turbulence, considered as a local short-term physical wind phenomenon, affects wind power generation. This paper investigates the use of turbulence intensity for ultra-short-term predictions of wind power and speed with a wind farm in the Arctic, including and excluding wind turbulence, within three hours by employing several different machine learning algorithms. A rigorous and detailed statistical comparison of the predictions is conducted. The results show that the algorithms achieve reasonably accurate predictions, but turbulence intensity does not statistically contribute to wind power or speed forecasts. This observation illustrates the uncertainty of turbulence in wind power generation. Besides, differences between the types of algorithms for ultra-short-term wind forecasts are also statistically insignificant, demonstrating the unique stochasticity and complexity of wind speed and power.

An application of a feed-forward neural network model for wind speed predictions

ABSTRACT Since wind energy covers an important part of the increasing electricity demands, accurate wind speed and direction forecasts are essential for the optimal operation of both the wind farms and the grid. Here we present the set-up and optimisation of a selected feed-forward neural network model in order to forecast, 24-hour ahead, the wind speed at specific points of three wind farms, using past data measured at the same locations. The model combines the k-fold cross-validation method for selecting the appropriate input data consisted either of hourly or 10-min average input values, while the impact of the length of the input time series is also investigated. Our method is tested against persistence method forecasts using the RMSE and MAPE statistics.

Validation of Ensemble-Based Probabilistic Tropical Cyclone Intensity Change

Although there has been substantial improvement to numerical weather prediction models, accurate predictions of tropical cyclone rapid intensification (RI) remain elusive. The processes that govern RI, such as convection, may be inherently less predictable; therefore a probabilistic approach should be adopted. Although there have been numerous studies that have evaluated probabilistic intensity (i.e., maximum wind speed) forecasts from high resolution models, or statistical RI predictions, there has not been a comprehensive analysis of high-resolution ensemble predictions of various intensity change thresholds. Here, ensemble-based probabilities of various intensity changes are computed from experimental Hurricane Weather Research and Forecasting (HWRF) and Hurricanes in a Multi-scale Ocean-coupled Non-hydrostatic (HMON) models that were run for select cases during the 2017–2019 seasons and verified against best track data. Both the HWRF and HMON ensemble systems simulate intensity changes consistent with RI (30 knots 24 h−1; 15.4 m s−1 24 h−1) less frequent than observed, do not provide reliable probabilistic predictions, and are less skillful probabilistic forecasts relative to the Statistical Hurricane Intensity Prediction System Rapid Intensification Index (SHIPS-RII) and Deterministic to Probabilistic Statistical (DTOPS) statistical-dynamical systems. This issue is partly alleviated by applying a quantile-based bias correction scheme that preferentially adjusts the model-based intensity change at the upper-end of intensity changes. While such an approach works well for high-resolution models, this bias correction strategy does not substantially improve ECMWF ensemble-based probabilistic predictions. By contrast, both the HWRF and HMON systems provide generally reliable predictions of intensity changes for cases where RI does not take place. Combining the members from the HWRF and HMON ensemble systems into a large multi-model ensemble does not improve upon HMON probablistic forecasts.

Wind speed and power prediction using MK-PINN

A multi-kernel pseudo inverse neural network (MKPINN) is proposed in this paper for efficient wind speed and power forecasting. The proposed model has been compared with Gaussian, wavelet, polynomial and sigmoid kernel. To get best output and learning methodology and stability pseudo inverse neural network is added, which substitutes the hidden layer with kernel function. This helps to achieve more accurate and faster response. Various case studies have been carried out from ten minutes to five hours interval in order to prove it accuracy.

Efficient deep learning based method for multi‐lane speed forecasting: a case study in Beijing

Real-time and accurate multi-lane traffic condition forecasting is of great importance to the connected and automated vehicle highway system. However, the majority of existing deep learning based traffic prediction methods focus on pursuing the precision of the methods while neglect to improve the efficiency of the methods. To achieve the high accuracy and high efficiency of multi-lane traffic flow prediction simultaneously, this study proposes a novel combination method via the integration of the clockwork recurrent neural network (CWRNN) and random forest (RF) method, which is RF-CWRNN. To the best of the authors’ knowledge, this is the first time that the CWRNN is introduced to capture the temporal feature of lane-level traffic flow and make traffic speed prediction. Meanwhile, the RF method is employed to measure the temporal relevance of the traffic flow and determine the optimal input time window. To verify the performance of the RF-CWRNN method, the ground-truth data of the expressways in Beijing were utilised to carry out experiments. The results indicate that the RF-CWRNN method is superior to the baseline models in terms of accuracy and robustness. Besides, the proposed method can save plenty of training time compared with the classical long short-term memory neural network.

Forecasting of the wind speed under uncertainty

In this paper, the semi-average method under neutrosophic statistics is introduced. The trend regression line for the semi-average method is given in the presence of Neutrosophy in the data. The application of the semi-average method under indeterminacy is given with the help of wind speed data. The efficiency of the semi-average method under the neutrosophic statistics is discussed over the semi-average method under classical statistics. From the analysis, it is concluded that the proposed method is effective, informative, and flexible for the forecasting of wind speed.

PortWeather: A Lightweight Onboard Solution for Real-Time Weather Prediction.

Maritime journeys significantly depend on weather conditions, and so meteorology has always had a key role in maritime businesses. Nowadays, the new era of innovative machine learning approaches along with the availability of a wide range of sensors and microcontrollers creates increasing perspectives for providing on-board reliable short-range forecasting of main meteorological variables. The main goal of this study is to propose a lightweight on-board solution for real-time weather prediction. The system is composed of a commercial weather station integrated with an industrial IOT-edge data processing module that computes the wind direction and speed forecasts without the need of an Internet connection. A regression machine learning algorithm was chosen so as to require the smallest amount of resources (memory, CPU) and be able to run in a microcontroller. The algorithm has been designed and coded following specific conditions and specifications. The system has been tested on real weather data gathered from static weather stations and onboard during a test trip. The efficiency of the system has been proven through various error metrics.

Soft computing based techniques for comparative analysis of wind speed and power prediction

Currently industrial, agricultural, residential and economical development of any country mostly depends on energy availability and per capita energy consumption by its peoples. Today power demand in various sectors are increasing with increasing population, so it is very challenging task for power generating company to maintain proper balance of demand & supply . Currently most of the countries of the world uses fossil fuel as a main source for power generation, so pollution / Carbon dioxide emissions into the atmosphere from burning of fossil fuels has become a very serious concern all around the world, to counter this problem there is strongly need of such types of energy sources that are capable to generate adequate amount of power with lowest possible pollution, cost and highly reliable to insure the balance between supply and demand. Additional power requirement and integration of renewable energy sources into smart grid, forced the power generating companies to divert their attention towards power generation from renewable sources along with conventional sources, as power generation from the conventional sources faces many challenges such as pollution, adequate availability, storage and security, to mitigate the above problems renewable energy sources may be better alternative. So, many countries are expensing major portion of their energy fund into the development of renewable setup for power generation. In India currently major sources of renewable power are wind and solar out of which wind power contribution is slightly more as compare to solar power, but power generation from wind puts many barriers in term of intermittent nature, frequency instability and availability with certain speed range that is capable for power generation from wind mills. Although above challenge cannot eliminate completely, but it can be minimize with the help of forecasting technique / method that have accuracy / error up to certain level which will be acceptable / reliable for power generation. In this regard I have used the different soft computing based techniques such as NARX, SVM tuned NARX, GA-NFIS, PSO-NFIS, for comparative analysis of wind speed and power forecasting and their results are compare with benchmark method like Persistence method.

A Multitask Learning Model for Traffic Flow and Speed Forecasting

Intelligent Transportation Systems (ITS) research and applications benefit from accurate short-term traffic state forecasting. To improve the forecasting accuracy, this paper proposes a deep learning based multitask learning Gated Recurrent Units (MTL-GRU) with residual mappings. To enhance the performance of the MTL-GRU, feature engineering is introduced to select the most informative features for the forecasting. Then, based on real-world datasets, numerical results show that the MTL-GRU can well estimate traffic flow and speed simultaneously, and performs better than other counterparts. Experiments also show that the deep learning based MTL-GRU model can overpower the bottleneck caused by enlarging training datasets and continue to gain benefits. The results suggest the proposed MTL-GRU model with residual mappings is promising to forecast short-term traffic state.

Day ahead powerful probabilistic wind power forecast using combined intelligent structure and fuzzy clustering algorithm

Nowadays, Operational power forecasts are associated with the one-value deterministic Numerical Weather Forecasting (NWF) simulation in the anticipated wind speed. This article introduced a novel predicting methodology called SSOFC-Apriori-WRP, which presents one-day-ahead wind power and speed forecasting. This methodology relies highly on a Weather Research and Prediction (WRP) simulation, a shark smell optimization (SSO), enhanced fuzzy clustering (EFC), and an Apriori association procedure. The wind speed prediction with the help of shaped WRP model was produced. Then by dividing wind speed predictions series into different parts, definite conditions were met and were introduced. Next the suggested methodology by the combination of SSO-optimized fuzzy clustering and Apriori algorithm withdraws the association rules, which are dominated among the anticipating errors in the divided waves and the shape features. The suggested methodology could be implemented to the other compared models and decrease the unreliability of the WRP simulation, if the association rules are used in the ultimate optimization process.

Long-Term Traffic Speed Prediction Based on Multiscale Spatio-Temporal Feature Learning Network

Speed plays a significant role in evaluating the evolution of traffic status, and predicting speed is one of the fundamental tasks for the intelligent transportation system. There exists a large number of works on speed forecast; however, the problem of long-term prediction for the next day is still not well addressed. In this paper, we propose a multiscale spatio-temporal feature learning network (MSTFLN) as the model to handle the challenging task of long-term traffic speed prediction for elevated highways. Raw traffic speed data collected from loop detectors every 5 min are transformed into spatial–temporal matrices; each matrix represents the one-day speed information, rows of the matrix indicate the numbers of loop detectors, and time intervals are denoted by columns. To predict the traffic speed of a certain day, nine speed matrices of three historical days with three different time scales are served as the input of MSTFLN. The proposed MSTFLN model consists of convolutional long short-term memories and convolutional neural networks. Experiments are evaluated using the data of three main elevated highways in Shanghai, China. The presented results demonstrate that our approach outperforms the state-of-the-art work and it can effectively predict the long-term speed information.

Irregular distribution of wind power prediction

Wind power is volatile and uncertain, which makes it difficult to establish an accurate prediction model. How to quantitatively describe the distribution of wind power output is the focus of this paper. First, it is assumed that wind speed is a random variable that satisfies the normal distribution. Secondly, based on the nonlinear relationship between wind speed and wind power, the distribution model of wind power prediction is established from the viewpoint of the physical mechanism. The proposed model successfully shows the complex characteristics of the wind power prediction distribution. The results show that the distribution of wind power prediction varies significantly with the point forecast of the wind speed.

Bayesian Model Averaging을 이용한 풍속의 확률론적 예측

Bayesian Model Averaging을 이용한 풍속의 확률론적 예측

Short-Term Traffic States Forecasting Considering Spatial–Temporal Impact on an Urban Expressway

Forecasting of short-term traffic states on expressways by adopting spatial–temporal models has gained increasing attention. Traffic data from neighboring sites were demonstrated to provide valuable information for predicting traffic states at sites of interest. However, when one considers the need to analyze the multivariate nature of traffic states over spatial dimensions, as well as of different models for various times of day, the interaction effects between spatial–temporal patterns require further investigation. This study addressed this issue on a segment of Shanghai North–South Expressway. Temporal characteristics of traffic volumes and speeds were analyzed by dividing the time of day into ordinal periods with relatively stable states. Then, spatial vector autoregressive (VAR) models were constructed at typical analysis periods for volume and speed forecasting by considering different combinations of upstream and downstream impacts. The results showed that the impact of downstream traffic conditions on upstream traffic cannot be neglected, especially in peak periods. For off-peak periods, traffic states at a location largely depended on upstream states, while downstream states appeared to have fewer effects. In such cases, models incorporating only upstream states were proved able to achieve sufficient accuracy. In addition, encouraging forecasting results were found when VAR models were compared with traditional methods (e.g., autoregressive integrated moving average and historical average), which failed to consider the spatial component of spatial–temporal patterns. All analyses helped to demonstrate the applicability of VAR models and to provide practical guidance for incorporating spatial–temporal dynamics into forecasting of expressway traffic states.

USING ARTIFICIAL NEURAL NETWORKS FOR FORCASTING WIND SPEED CHANGES IN THE CITY OF KERMAN

Abstract. Nowadays, taking advantage of renewable energies has increased in order to produce electric energy. Wind energy is one of renewable energies which has been the center of attention in industrial communities. Correct wind –speed forecast has a considerable number of applications in military and civilian affairs for air traffic control, missile , and ship navigation .Furthermore, forecasting wind-speed changes has also become important due to controlling appropriate reactions in wind turbines in order to prevent sudden shocks and take advantage of maximum capacity of wind turbines .According to inevitable role of wind energy in the future, the capability to predict this energy can play a noticeable role on related predictions of production or electricity energy buying and selling as a result of substantial effect on energy final price .In this study , considering one-year collected data of wind speed and temperature in one meteorology station in Kerman, one applied model has been recommended for forecasting wind speed using artificial neural network.