Short-term Prediction Method Research Articles

The short-term prediction of the mobile communication traffic based on the product seasonal model

The short-term forecast can be used to respond to the unexpected business shocks in advance, thus guaranteeing user experience. We present a practical communication traffic forecasting technology based on autoregressive moving average model. The proposed short-term prediction method is mainly based on the product seasonal model. The orders of product seasonal ARMA equation are recognized by the Akaike information criterion, and the parameters of equation are estimated by the maximum likelihood method. The unit root test is used to judge the stability and reversibility of the model. The performance of the proposed method is evaluated. The experimental result shows that the method has high prediction accuracy. The short-term forecast can provide a basis for mobile operators to accurately expand capacity.

Short-term Prediction of Output Power and Constrained Optimal Control for Point-Absorber Type Wave-Energy Converters with Linear Generators

This paper addresses the issue of a control subject to physical constraints, involving an energy maximization for wave energy converters with a linear generator. Previous approaches to this problem including model predictive control (MPC) have currently some challenges. The conventional control methods, on the other hand, to be able to estimate the performance of wave energy converters are required in practice. In this study, casual constrained optimal control based on the short-term prediction method is proposed. A novel short-term prediction method of both satisfying with maximum output-power and limited heave amplitudes using the energy spectrum method is shown in this paper. Maximizing estimated output power subject to making the estimated amplitude smaller than motion limitation realizes maximizing output power under the heave-motion limitation. To confirm the accuracy of the short-term prediction method and the performance of the proposed control method, the output power is compared with the output power obtained from other control methods through the frequency and time domain simulations in irregular waves. The results show that the short-term prediction method is useful, and the proposed method can maximize output power under the heave-motion limitation.

Short-Term Parking Demand Prediction Method Based on Variable Prediction Interval

With the rapid economic development, parking problems have become increasingly prominent due to the city's development model and the emergence of a large number of private cars. Parking management departments around the world focus on intelligent parking system in order to solve parking problems, but most of them are limited to upgrading the parking infrastructure. There is no effective solution from a perspective of the fundamental cause to solve the parking problem. At present, it is generally believed that parking guidance systems can effectively alleviate parking problems and provide drivers and traffic managers with real-time and accurate parking information. As one of the prerequisites of the parking guidance system, the accuracy of the short-term parking demand prediction method determines whether the implementation of the parking guidance scheme can effectively solve the parking problem in a certain area. Based on this, we have studied a short-term parking demand prediction in this paper. First, focusing on the distribution of typical parking arrivals and departures regular pattern, a parking demand prediction model was constructed utilizing the Markov birth and death process, and model parameters were calibrated utilizing curve fitting method and undetermined coefficients method. The simulation environment was set up utilizing the Markov process to verify the accuracy of the availability of parameter estimation method. Secondly, a method for determining the prediction interval based on the parking trend was given for different situations with the parking rush hours and ordinary hours which parking arrival and departure parameters were different. In order to verify the effectiveness of the model in practical applications, parking arrival and departure data from June 17 to June 23, 2019 in Jilin University of Nanling Campus was used to verify the short-term parking demand prediction method proposed in this paper. The results show that the parking demand prediction model proposed in this paper can accurately calibrate model parameters, predict parking demand quickly and effectively and provide theoretical reference and technical support for parking planning and management.

A novel fuzzy rough set based long short-term memory integration model for energy consumption prediction of public buildings

Building energy consumption (BEC) prediction is very important for energy management and conservation. This paper presents a short-term energy consumption prediction method that integrates the Fuzzy Rough Set (FRS) theory and the Long Short-Term Memory (LSTM) model, and is thus named FRS-LSTM. This method can find the most directly related factors from the complex and diverse factors influencing the energy consumption, which improves the prediction accuracy and efficiency. First, the FRS is used to reduce the redundancy of the input features by the attribute reduction of the factors affecting the energy consumption forecasting, and solves the data loss problem caused by the data discretization of a classical rough set. Then, the final attribute set after reduction is taken as the input of the LSTM networks to obtain the final prediction results. To validate the effectiveness of the proposed model, this study used the actual data of a public building to predict the building’s energy consumption, and compared the proposed model with the LSTM, Levenberg-Marquardt Back Propagation (LM-BP), and Support Vector Regression (SVR) models. The experimental results reveal that the presented FRS-LSTM model achieves higher prediction accuracy compared with other comparative models.

A New Short-Term Prediction Method for Estimation of the Evaporation Duct Height

Evaporation duct is a kind of chaotic phenomenon over the ocean. In this paper, a new nonlinear prediction algorithm, the Darwinian evolutionary algorithm (DEA), is introduced to obtain the specific nonlinear formula $P(\cdot)$ of the chaotic phenomenon. Based on Darwinian natural selection and survival theory, the method first selects a suitable training set of samples, and then produces an initial population before going through an evolutionary process of selection, reproduction and mutation until the optimal individual is found. Finally, a specific expression for a nonlinear chaotic time series is obtained, which can realize the short-term prediction of evaporation duct height (EDH) quickly and accurately. After that, the DEA, the support vector regression (SVR), and the back propagation (BP) neural network were applied to predict the EDH which were formed over the ocean by using sounding data. After interpolation and smoothing of the original data, we selected the first 250 data as training samples and the last 115 data as test samples to test the effect of the EDA algorithm. The results showed that the root mean squared error (RMSE) for the DEA was about 7% less than that of the SVR and 10% less than that of BP neural network; the mean absolute percent error (MAPE) for the DEA was about 9% less than that of the SVR and 15% less than that of BP neural network. In addition, the DEA obtained, for the first time, a nonlinear expression for EDH, which provides an important reference for future research on the evaporation ducts.

An Adaptive Short-Term Prediction Algorithm for Resource Demands in Cloud Computing

Cloud computing has been widely applied in various fields with the development of big data and artificial intelligence. The associated resource demands exhibit characteristics such as diversity, large scale, burst and uncertainty. This paper analyzes these characteristics of cloud resource demands based on Alibaba cluster data, and proposes an adaptive short-term prediction algorithm for those demands. The proposed algorithm uses a principal component analysis method to extract the primary types of container demands from a time series of resource demands, and executes outlier detection and replacement to obtain a more stationary sequence. An adaptive short-term prediction strategy is proposed to adaptively select a higher-accuracy short-term prediction method to implement the prediction. Further, an error adjustment factor is proposed to reduce the prediction error. Thus, the short-term prediction accuracy of cloud resource demands is improved via outlier detection and replacement, an adaptive selection strategy and an error adjustment. We evaluated the effectiveness of these improvements, and compared our algorithm with existing algorithms in terms of effectiveness and time cost. The experimental results demonstrate that the proposed algorithm improves short-term prediction accuracy effectively.

Comparison of TEC prediction methods in mid-latitudes with GIM maps

There are many long-term and short-term prediction methods of Total Electron Content (TEC) that need to be tested for each specific region. Recently, much attention has been paid to testing TEC models in high-, low-latitude and equatorial regions. This paper compares the TEC prediction methods in the mid-latitude zone according to the data of the Juliusruh, Rostov, Manzhouli stations in 2008 and 2015. For a long-term prediction, the IRI-Plas and NeQuick models are compared with the Global Ionospheric Maps (GIM) presented by the Jet Propulsion Laboratory (JPL) and the Technical University of Catalonia (UPC). For a short-term prediction, the Standard Persistence Model (SPM) method, a 27 day median model, and the proposed short-term prediction method are compared for one day ahead. It is shown that for all stations the IRI-Plas model provides better compliance with GIM maps than the NeQuick model irrespective of a solar activity level. An average absolute error lays in the range of 3–3.5 TECU, relative root square mean (RMS) error in the range of 22–27% in 2015 and 1.7–2 TECU, 20–25% in 2008. For the NeQuick model, these estimates were 6.7–8.2 TECU and 42–45% in 2015 and 2.2–3.6 TECU, 30–37% in 2008. For the short-term forecast, the best results were obtained by the SPM method with an average absolute error in the range of 1.95–2.15 TECU in 2015 and 0.59–0.98 TECU in 2008, a relative RMS error in the range of 17–21% in 2015, 11.5–15% in 2008. For the proposed short-term prediction method, these errors were 2.04–2.2 TECU and 12–14% in 2015 and 0.7–1.0 TECU, 7–11% in 2008. Using medians, the errors were 3.1–3.4 TECU and 17–21% in 2015 and 1.0–1.3 TECU, 10–15% in 2008. The dependence of results on the Dst-index was obtained.

On Methods of Short-Term Earthquake Prediction Based on Monitoring the Hydrogeodeformation Field

The permanent analysis of the hydrogeodeformation (HGD) field is one promising direction in the field of predicting strong earthquakes. As a result of long-term monitoring of the HGD field, it has been found that the underground hydrosphere contains extensive information about changes in geodynamic stresses and the evolution of deformation processes in the Earth’s crust. The development of short-term earthquake prediction methods has been preceded by long-term studies aimed at improving the HGD field monitoring. This paper presents examples of successful predictions of the place, time, and magnitude for a number of strong earthquakes. The examples are obtained based on a complex analysis of the variations in the HGD field. Proposals on the use of these methods for short-term prediction of strong seismic events in the near-real-time mode are formulated.

Prediction short-term photovoltaic power using improved chicken swarm optimizer - Extreme learning machine model

Photovoltaic power generation is greatly affected by weather conditions while the photovoltaic power has a certain negative impact on the power grid. The power sector takes certain measures to abandon photovoltaic power generation, thus limiting the development of clean energy power generation. This study is to propose an accurate short-term photovoltaic power prediction method. A new short-term photovoltaic power output prediction model is proposed Based on extreme learning machine and intelligent optimizer. Firstly, the input of the model is determined by correlation coefficient method. Then the chicken swarm optimizer is improved to strengthen the convergence. Secondly, the improved chicken swarm optimizer is used to optimize the weights and the extreme learning machine thresholds to improve the prediction effect. Finally, the improved chicken swarm optimizer extreme learning machine model is used to predict the photovoltaic power under different weather conditions. The testing results show that the average mean absolute percentage error and root mean square error of improved chicken swarm optimizer - extreme learning machine model are 5.54% and 3.08%. The proposed method is of great significance for the economic dispatch of power systems and the development of clean energy.

A Two-Layer Nonlinear Combination Method for Short-Term Wind Speed Prediction Based on ELM, ENN, and LSTM

As a typical kind of the Internet of Things, smart grid has attracted a lot of attentions. The power energy management of smart grid is of great importance for energy distribution, system security, and market economics. One of the most important issues is the accurate and stable prediction of wind speed for the optimal operation and management of wind power generations connected to smart grid. In this paper, a novel two-layer nonlinear combination method termed as EEL-ELM is developed for short-term wind speed prediction problems, such as 10-min ahead and 1-h ahead. The first layer is based on extreme learning machine (ELM), Elman neural network (ENN), and long short term memory neural network (LSTM) to separately forecast wind speed by making use of their merits of calculation speed or strong ability in forecasting, and obtain three forecasting results. Then, we propose the second layer by making use of ELM-based nonlinear aggregated mechanism to alleviate the inherent weakness of single method and linear combination. Two real-world case studies, gathered from Inner Mongolia's wind farm in China, are implemented to demonstrate the effectiveness of the proposed EEL-ELM method. By comparing with other eight wind speed prediction methods, the simulation results reveal that EEL-ELM can achieve better forecasting performance according to three evaluation metrics and three statistical tests.

Short-Term Prediction of Passenger Demand in Multi-Zone Level: Temporal Convolutional Neural Network With Multi-Task Learning

Accurate short-term passenger demand prediction contributes to the coordination of traffic supply and demand. This paper proposes an end-to-end multi-task learning temporal convolutional neural network (MTL-TCNN) to predict the short-term passenger demand in a multi-zone level. Along with a feature selector named spatiotemporal dynamic time warping (ST-DTW) algorithm, this proposed MTL-TCNN is quite qualified for the multi-task prediction problem with the consideration of spatiotemporal correlations. Then, based on the car-calling demand data from Didi Chuxing, Chengdu, China, and taxi demand data from the New York City, the numerical results show that the MTL-TCNN outperforms both classic methods (i.e., historical average (HA), v -support vector machine ( v -SVM), and XGBoost) and the state-of-the-art deep learning approaches [e.g., long short-term memory (LSTM) and convolutional LSTM (ConvLSTM)] in both the single task learning (STL) and multi-task learning (MTL) scenarios. In summary, the proposed MTL-TCNN with the ST-DTW algorithm is a promising method for short-term passenger demand prediction in a multi-zone level.

Multi-task and multi-view learning based on particle swarm optimization for short-term traffic forecasting

Spatiotemporal prediction modeling of traffic is an important issue in the field of spatiotemporal data mining. However, it is encountering multiple challenges such as the global spatiotemporal correlation between predictive tasks, balanced between spatiotemporal heterogeneity and the global predictive power of the model, and parameter optimization of prediction models. Most existing short-term traffic prediction methods only emphasize spatiotemporal dependence and heterogeneity, so it is difficult to get satisfactory prediction accuracy. In this paper, spatiotemporal multi-task and multi-view feature learning models based on particle swarm optimization are combined to concurrently address these challenges. First, cross-correlation is used to construct the spatiotemporal proximity view, periodic view and trend view of each road segment to characterize spatiotemporal dependence and heterogeneity. Second, the prediction results of three spatiotemporal views are obtained using a set of kernels, which is further regarded as a high-level heterogeneous semantic feature as the input of the multi-task multi-view feature learning model. Third, additional regularization terms (e.g., group Lasso penalty, graph Laplacian regularization) are utilized to constrain all tasks to select a set of shared features and ensure the relatedness between tasks and consistency between views, so that the predictive model has a good global predictive ability and can capture global spatiotemporal correlation in the road network. Finally, particle swarm optimization is introduced to obtain the optimal parameter set and enhance the training speed of the proposed model. Experimental studies on real vehicular-speed datasets collected on city roads demonstrate that the proposed model significantly outperform the existing nine baseline methods in terms of prediction accuracy. The results suggest that the proposed model merits further attention for other spatiotemporal prediction tasks, such as water quality, crowd flow, owing to the versatility of the modeling process for spatiotemporal data.

Research on short-term prediction method of coal flow on conveyor belt

Research on short-term prediction method of coal flow on conveyor belt

Short-Term Photovoltaic Power Output Prediction Based on k-Fold Cross-Validation and an Ensemble Model

Short-term photovoltaic power forecasting is of great significance for improving the operation of power systems and increasing the penetration of photovoltaic power. To improve the accuracy of short-term photovoltaic power forecasting, an ensemble-model-based short-term photovoltaic power prediction method is proposed. Firstly, the quartile method is used to process raw data, and the Pearson coefficient method is utilized to assess multiple features affecting the short-term photovoltaic power output. Secondly, the structure of the ensemble model is constructed, and a k-fold cross-validation method is used to train the submodels. The prediction results of each submodel are merged. Finally, the validity of the proposed approach is verified using an actual data set from State Power Investment Corporation Limited. The simulation results show that the quartile method can find outliers which contributes to processing the raw data and improving the accuracy of the model. The k-fold cross-validation method can effectively improve the generalization ability of the model, and the ensemble model can achieve higher prediction accuracy than a single model.

A Hybrid Method for Short-Term Host Utilization Prediction in Cloud Computing

Dynamic resource scheduling is a critical activity to guarantee quality of service (QoS) in cloud computing. One challenging problem is how to predict future host utilization in real time. By predicting future host utilization, a cloud data center can place virtual machines to suitable hosts or migrate virtual machines in advance from overloaded or underloaded hosts to guarantee QoS or save energy. However, it is very difficult to accurately predict host utilization in a timely manner because host utilization varies very quickly and exhibits strong instability with many bursts. Although machine learning methods can accurately predict host utilization, it usually takes too much time to ensure rapid resource allocation and scheduling. In this paper, we propose a hybrid method, EEMD-RT-ARIMA, for short-term host utilization prediction based on ensemble empirical mode decomposition (EEMD), runs test (RT), and autoregressive integrated moving average (ARIMA). First, the EEMD method is used to decompose the nonstationary host utilization sequence into relatively stable intrinsic mode function (IMF) components and a residual component to improve prediction accuracy. Then, efficient IMF components are selected and then reconstructed into three new components to reduce the prediction time and error accumulation due to too many IMF components. Finally, the overall prediction results are obtained by superposing the prediction results of three new components, each of which is predicted by the ARIMA method. An experiment is conducted on real host utilization traces from a cloud platform. We compare our method with the ARIMA model and the EEMD-ARIMA method in terms of error, effectiveness, and time-cost analysis. The results show that our method is a cost-effective method and is more suitable for short-term host utilization prediction in cloud computing.

Dynamical Short-Term Prediction of Rain Attenuation in W Band: A Time-Series Model With Simpler Structure and Higher Accuracy

Most existing rain attenuation prediction models are tested only at 55 GHz. Few W-band models have been tested, and these models present problems associated with high complexity and cannot predict with high accuracy in the short term. A dynamical short-term prediction method is proposed here, and it has a simpler structure and higher accuracy than previous rain attenuation models and can theoretically be implemented at any station and frequency. The method uses the relationship among time series to establish an autoregression integrated moving average (ARIMA) model, conducts a stationary test, transforms the nonstationary series into a stationary series, and estimates the parameters.

Forecasting Models for Wind Power Using Extreme-Point Symmetric Mode Decomposition and Artificial Neural Networks

The randomness and volatility of wind power poses a serious threat to the stability, continuity, and adjustability of the power system when it is connected to the grid. Accurate short-term wind power prediction methods have important practical value for achieving high-precision prediction of wind farm power generation and safety and economic dispatch. Therefore, this paper proposes a novel combined model to improve the accuracy of short-term wind power prediction, which involves grey correlation degree analysis, ESMD (extreme-point symmetric mode decomposition), sample entropy (SampEn) theory, and a hybrid prediction model based on three prediction algorithms. The meteorological data at different times and altitudes is firstly selected as the influencing factors of wind power. Then, the wind power sub-series obtained by the ESMD method is reconstructed into three wind power characteristic components, namely PHC (high frequency component of wind power), PMC (medium frequency component of wind power), and PLC (low frequency component of wind power). Similarly, the wind speed sub-series obtained by the ESMD method is reconstructed into three wind speed characteristic components, called SHC (high frequency component of wind speed), SMC (medium frequency component of wind speed), and SLC (low frequency component of wind speed). Subsequently, the Bat-BP model, Adaboost-ENN model, and ENN (Elman neural network), which have high forecasting accuracy, are selected to predict PHC, PMC, and PLC, respectively. Finally, the prediction results of three characteristic components are aggregated into the final prediction values of the original wind power series. To evaluate the prediction performance of the proposed combined model, 15-min wind power and meteorological data from the wind farm in China are adopted as case studies. The prediction results show that the combined model shows better performance in short-term wind power prediction compared with other models.

Short-Term Demand Prediction Method for Online Car-Hailing Services Based on a Least Squares Support Vector Machine

The purpose of this paper is to study the short-term demand prediction for online car-hailing services problem. Prediction of short-term network car demand can provide many benefits such as an increase in the income of network car drivers. In addition, demand prediction is an important resource for recommendation systems, carpooling systems, and network car scheduling; and therefore, predicting the demand for network cars has great significance. In the last few decades, scholars have studied various problems related to short-term demand prediction for online car-hailing services based on clustering algorithms and regression algorithms. However, these studies are still problematic because the accuracy of demand prediction is not high enough. Therefore, this paper studies a method of improving the accuracy and the efficiency of demand prediction. Due to the high prediction accuracy and the fast training efficiency of least squares support vector machine (LS-SVM), a short-term demand prediction method for online car-hailing services based on LS-SVM is proposed. The modeling process involves selecting the dependent and independent variables, the basic principles of the LS-SVM, the kernel function and superparameter, model training, and prediction. In a numerical experiment, we use network car order data as the network car demand data to test the model. We show that the experimental results with the LS-SVM method implemented in this paper and then compare the model with lasso linear regression, nearest neighbor regression, decision tree regression, and neural network. The experimental results show that the short-term demand prediction model for online car-hailing services based on LS-SVM performs better than the other methods.

Short-Term Vehicle Traffic Prediction for Terahertz Line-of-Sight Estimation and Optimization in Small Cells

Significant efforts have been made and are still being made on short-term traffic prediction methods, especially for highway traffic based on punctual measurements. The literature on predicting the spatial distribution of the traffic in urban intersections is, however, very limited. This paper presents a novel data-driven prediction algorithm based on random forests regression over spatiotemporal aggregated data of vehicle counts inside a grid. The proposed approach aims to estimate the future distribution of vehicle to everything (V2X) traffic demand, providing valuable input for dynamic management of radio resources in small cells. Radio access networks (RANs) working in the terahertz band and deployed in small cells are expected to meet the high-demanding data rate requirements of connected vehicles. However, terahertz frequency propagation has important limitations in outdoor scenarios, including distance propagation, high-absorption coefficients values, and low-reflection properties. More concretely, in settings such as complex road intersections, dynamic signal blockage, and shadowing effects may cause significant power losses and compromise the quality of service for some vehicles. The forthcoming network demand estimated from the regression algorithm is used to compute the losses expected due to other vehicles potentially located between the transmitter and the receiver. We conclude that our approach, which is designed from a grid-like perspective, outperforms other traffic prediction methods and the combined result of these predictions with a dynamic reflector orientation algorithm, as a use case application, allows reducing the ratio of vehicles that do not receive minimum signal power.

Bayesian regularized NAR neural network based short-term prediction method of water consumption

With the continuous construction of urban water supply infrastructure, it is extremely urgent to change the management mode of water supply from traditional manual experience to modern and efficient means. The water consumption forecast is the premise of water supply scheduling, and its accuracy also directly affects the effectiveness of water supply scheduling. This paper analyzes the regularity of water consumption time series, establishes a short-term water consumption prediction model based on Bayesian regularized NAR neural network, and compares and evaluates the prediction effect of the model. The verification results show that the Bayesian based NAR neural network prediction model has higher adaptability to the water consumption prediction than the standard BP neural network and the Bayesian regularized BP neural network. The prediction accuracy can more accurately reflect the short-term variation of water consumption.