Single-step Prediction Research Articles

A Novel Prediction Algorithm for the Cross Temperature Estimation of Blast Furnace

In order to predict the distribution of gas flow, we need to get the temperature of each point in blast furnace throat in advance. In this paper, firstly, two intelligent modeling methods are used to establish a multiple-input multiple-output prediction model, one is extreme learning machine (ELM) algorithm and the other is online sequential extreme learning machine (OS-ELM) algorithm. And the model is a single-step prediction model of temperature in blast furnace, single-step prediction means the prediction of temperature in the next moment. We use autocorrelation analysis to determine input vector and output vector of the model. The result of autocorrelation analysis indicates that the method of temperature sequence prediction has a higher prediction accuracy and better prediction stability than the method of single point prediction. Next, based on real industrial data, we make a comparison between the multiple - input multiple-output model and least squares support vector machines (LS-SVM) model used in common. The experiment results show that OS-ELM model has a better forecast effect than the ELM model and LS-SVM model.

Short communication: Calculating analytical reliabilities for single-step predictions

It has been shown that single-step genomic BLUP (ssGBLUP) can be reformulated, resulting in an equivalent SNP model that includes the explicit imputation of gene contents of all ungenotyped animals in the pedigree. This reformulation reveals the underlying mechanism enabling ungenotyped animals to contribute information to genotyped animals via estimates of marker effects and consequently to the reliability of genomic predictions, a key feature generally associated with the single-step approach. Irrespective of which BLUP formulation is used for genomic prediction, with increasing numbers of genotyped animals, the marker-oriented model is recommended when calculating the reliabilities of genomic predictions. This approach has the advantage of a manageable and stable size of the model matrix that needs to be inverted to calculate analytical prediction error variances of marker effects, an advantage that also holds for prediction with the single-step model. However, when including imputed genotypes in the design matrix of marker effects, an additional imputation residual term has to be considered to account for the prediction error of imputation. We summarize some of the theoretical aspects associated with the calculation of analytical reliabilities of single-step predictions. Derivations are based on the equivalent reformulation of ssGBLUP as a marker-oriented model and the calculation of prediction error variances of marker effects. We propose 2 approximations that allow for a substantial reduction of the complexity of the matrix operations involved, while retaining most of the relevant information required for reliability calculations. We additionally provide a general framework for an implementation of single-step reliability approximation using standard animal model reliabilities as a starting point. Finally, we demonstrate the effectiveness of the proposed approach using a small example extracted from data of the routine evaluation on dual-purpose Fleckvieh (Simmental) cattle.

Efficient genetic value prediction using incomplete omics data.

Covering a subset of individuals with a quantitative predictor, while imputing records for all others using pedigree or genomic data, could improve the precision of predictions while controlling for costs. Predicting genetic values with high accuracy is pivotal for effective candidate selection in animal and plant breeding. Novel 'omics'-based predictors have been shown to improve upon established genome-based predictions of important complex traits but require laborious and expensive assays. As a consequence, there are various datasets with full genetic marker coverage of all studied individuals but incomplete coverage with other 'omics' data. In animal breeding, single-step prediction was introduced to efficiently combine pedigree information, collected on a large number of animals, with genomic information, collected on a smaller subset of animals, for breeding value estimation without bias. Using two maize datasets of inbred lines and hybrids, we show that the single-step framework facilitates imputing transcriptomic data, boosting forecasts when their predictive ability exceeds that of pedigree or genomic data. Our results suggest that covering only a subset of inbred lines with 'omics' predictors and imputing all others using pedigree or genomic data could enable breeders to improve trait predictions while keeping costs under control. Employing 'omics' predictors could particularly improve candidate selection in hybrid breeding because the success of forecasts is a strongly convex function of predictive ability.

Improved Restricted Control Set Model Predictive Control (iRCS-MPC) Based Maximum Power Point Tracking of Photovoltaic Module

This paper presents a robust two stage maximum power point tracking (MPPT) system of the photovoltaic (PV) module using an improved restricted control set model predictive control (iRCS-MPC) technique. The suggested work is improved in two aspects; a revision in conventional P&O algorithm is made by employing three distinct step sizes for different conditions, and an improvement in conventional MPC algorithm. The improved MPC algorithm is based on the single step prediction horizon that provides less computational load and swift tracking of maximum power point (MPP) by applying the control pulses directly to the converter switch. The computer aided experimental results for various environmental scenarios revealed that compared with the conventional method (conventional P&O + MPC), for the PV power and inductor current, the undershoot and overshoot is decreased to 68% and 35% respectively under stiff environmental conditions. In addition, the settling time needed to reach a stable state is significantly reduced in the proposed system. The viability of the solution suggested is verified in MATLAB/Simulink and by hardware experimentation.

Kernel Estimation of Truncated Volterra Filter Model Based on DFP Technique and Its Application to Chaotic Time Series Prediction

In order to overcome some problems caused by improper parameters selection when applying Least mean square (LMS), Normalized LMS (NLMS) or Recursive least square (RLS) algorithms to estimate coefficients of second-order Volterra filter, a novel DavidonFletcher-Powell-based Second-order Volterra filter (DFPSOVF) is proposed. Analysis of computational complexity and stability are presented. Simulation results of system parameter identification show that the DFP algorithm has fast convergence and excellent robustness than LMS and RLS algorithm. Prediction results of applying DFPSOVF model to single step predictions for Lorenz chaotic time series illustrate stability and convergence and there have not divergence problems. For the measured multiframe speech signals, prediction accuracy using DFPSOVF model is better than that of Linear prediction (LP). The DFP-SOVF model can better predict chaotic time series and the real measured speech signal series.

A dual strategy to optimize hematopoietic progenitor cell collections: validation of a simple prediction algorithm and use of collect flow rates guided by mononuclear cell count.

Previous prediction algorithms to achieve target CD34+ goals have not been widely adopted, with many centers still using a set volume to process for hematopoietic progenitor cell collections. This may be because previous algorithms are challenging to implement. Additionally, no study has yet examined the utility of adjusting the collect flow rate (CFR) based on the donor's preprocedure total mononuclear cell (MNC) count, which correlates with CD34+ yield. In this retrospective analysis of mobilized allogeneic donors collected using MNC (COBE Spectra, Terumo BCT) or continuous mononuclear cell collection (CMNC) (Spectra Optia, Terumo BCT) procedures, we validated a one-step prediction algorithm to achieve the target CD34+ product dose (Appendix S1, available as supporting information in the online version of this paper). The COBE Spectra MNC Collect Flow Tool (Appendix S2, available as supporting information in the online version of this paper) was used to select the collect flow rate for both MNC and CMNC procedures. Procedural collection efficiency (CE) was compared to that of historical procedures utilizing fixed CFRs (1.0-1.5 mL/min). Ninety-three percent of collections achieved the target CD34+ goal using our algorithm-calculated process volumes. The remaining 7% of cases had CEs lower than the algorithm CE (0.40), and thus were below goal. Second, an MNC-based CFR improved MNC and CD34+ CEs in patients with higher MNC counts compared to our historical controls. We validated that this simple, single-step prediction algorithm achieves the target CD34+ goal in most HPC collections. Secondly, we showed that an MNC-based CFR for hematopoietic progenitor cell collections improves CE at higher MNCs; this may be preferable to a WBC-based CFR because of variability of MNC counts at a given WBC count.

Capability of the Bayesian Forecasting Method to Predict Field Time Series

This paper addresses the challenge of forecasting the future values of gas turbine measureable quantities. The final aim is the simulation of “virtual sensors” capable of producing statistically coherent measurements aimed at replacing anomalous observations discarded from the time series. Among the different available approaches, the Bayesian forecasting method (BFM) adopted in this paper uses the information held by a pool of observations as knowledge base to forecast the values at a future state. The BFM algorithm is applied in this paper to Siemens field data to assess its prediction capability, by considering two different approaches, i.e., single-step prediction (SSP) and multistep prediction (MSP). While SSP predicts the next observation by using true data as base of knowledge, MSP uses previously predicted data as base of knowledge to perform the prediction of future time steps. The results show that BFM single-step average prediction error can be very low, when filtered field data are analyzed. On the contrary, the average prediction error achieved in case of BFM multistep prediction is remarkably higher. To overcome this issue, the BFM single-step prediction scheme is also applied to clusters of time-wise averaged data. In this manner, an acceptable average prediction error can be achieved by considering clusters composed of 60 observations.

Model Predictive Control for DC–DC Boost Converters With Reduced-Prediction Horizon and Constant Switching Frequency

The implementation of multistep direct model predictive control (MPC) for dc–dc boost converters overcomes the well-known issue of nonminimum phase behavior. However, it can lead to a high computational burden depending on the prediction horizon length. In this paper, a simple and computationally efficient MPC method for dc–dc boost converters is proposed. The key novelty of the presented control strategy lies in the way dynamic references are handled. The control strategy is capable of providing suitable references for the inductor current and the output voltage, without requiring additional control loops. Moreover, this reference design allows the predictive controller to be implemented with a single-step prediction horizon. Thus, a significant reduction in the required real-time calculations executed in the control hardware is achieved. To obtain constant switching frequency, the power switch commutation instants within a sampling period are considered as control inputs. Therefore, the predictive controller is formulated as a continuous control set MPC. Additionally, the proposed formulation is able to deal with different operation modes of the converter without changing the controller structure. Finally, an observer is used to dynamically modify the reference to provide robustness to system parameter uncertainties. Simulation and experimental results show an accurate tracking of dynamic inductor current and output voltage references, while respecting the restrictions on maximum inductor current levels of the converter.

Short communication: Genomic prediction using different single-step methods in the Finnish red dairy cattle population

Single-step genomic prediction models utilizing both genotyped and nongenotyped animals are likely to become the prevailing tool in genetic evaluations of livestock. Various single-step prediction models have been proposed, based either on estimation of individual marker effects or on direct prediction via a genomic relationship matrix. In this study, a classical pedigree-based animal model, a regular single-step genomic BLUP (ssGBLUP) model, algorithm for proven and young (APY) with 2 strategies for choosing core animals, and a single-step Bayesian regression (ssBR) model were compared for 305-d production traits (milk, fat, protein) in the Finnish red dairy cattle population. A residual polygenic effect with 10% of total genetic variance was included in the single-step models to reduce inflation of genomic predictions. Validation reliability was calculated as the squared Pearson correlation coefficient between genomically enhanced breeding value (GEBV) and yield deviation for masked records for 2,056 validation cows from the last year in the data set investigated. The results showed that gains of 0.02 to 0.04 on validation reliability were achieved by using single-step methods compared with the classical animal model. The regular ssGBLUP model and ssBR model with an extra polygenic effect yielded the same results. The APY methods yielded similar reliabilities as the regular ssGBLUP and ssBR. Exact prediction error variance of GEBV could be obtained by ssBR to avoid any approximation methods used for ssGBLUP when inversion left-hand side of mixed model equations is computationally infeasible for large data sets.

Model Predictive Control of Power Converters for Robust and Fast Operation of AC Microgrids

This paper proposes the application of a finite control set model predictive control (FCS-MPC) strategy in standalone ac microgrids (MGs). AC MGs are usually built from two or more voltage source converters (VSCs) which have the capability of regulating the voltage at the point of common coupling, while sharing the load power at the same time. Those functionalities are conventionally achieved by hierarchical linear control loops. However, they present severe limitations in terms of slow transient response and high sensitivity to parameter variations. This paper aims to mitigate these problems by first introducing an improvement of the FCS-MPC strategy for a single VSC that is based on explicit tracking of derivative of the voltage reference trajectory. Using only a single step prediction horizon, the proposed strategy exhibits very low computational expense, but provides steady-state performance comparable to carrier-based sinusoidal PWM, while its transient response and robustness to parameter variation is far superior to hierarchical linear control. These benefits are exploited in a general ac MG setting where a methodology for paralleling multiple FCS-MPC regulated VSCs is described. Such an MG is characterized by rapid transient response, inherent stability in all operating conditions, and fully decentralized operation of individual VSCs. These findings have been validated through comprehensive simulation and experimental verification.

Single-step prediction method of burning zone temperature based on real-time wavelet filtering and KELM

The single-step prediction of burning zone temperature plays an important role in the safety and stability control of cement rotary kiln. This is because, the abnormal temperature events can be found as early as possible and the operator can take effective emergency measures in time. In this paper, the burning zone temperature single-step prediction method based on real-time wavelet filtering and kernel extreme learning machine is studied. Firstly, the visual inspection device is used to detect the burning zone temperature. And then, the amplitude limited filtering method is used to weaken the effects of temperature anomalies. On this basis, the real-time filtering of the burning zone temperature is realized by combining the sliding time window and wavelet filtering method. After that, the single-step prediction of burning zone temperature is realized by combining the sliding time window and kernel extreme learning machine method. At last, the burning zone temperature prediction method is validated. The minimum root mean squared error of the 5 consecutive days is 0.4259°C. The single average running time of model training and prediction of kernel extreme learning machine is much less than support vector regression, which is very helpful for the online prediction of burning zone temperature. The result shows that the burning zone temperature single-step prediction method proposed in this paper is feasible and effective.

Condition Monitoring of Wind Turbine Based on Copula Function and Autoregressive Neural Network

The traditional wind turbine fault monitoring is often based on a single monitoring signal without considering the overall correlation between signals. A global condition monitoring method based on Copula function and autoregressive neural network is proposed for this problem. Firstly, the Copula function was used to construct the binary joint probability density function of the power and wind speed in the fault-free state of the wind turbine. The function was used as the data fusion model to output the fusion data, and a fault-free condition monitoring model based on the auto-regressive neural network in the faultless state was established. The monitoring model makes a single-step prediction of wind speed and power, and statistical analysis of the residual values of the prediction determines whether the value is abnormal, and then establishes a fault warning mechanism. The experimental results show that this method can provide early warning and effectively realize the monitoring of wind turbine condition.

An Adaptive Online Prediction Method With Variable Prediction Horizon for Future Driving Cycle of the Vehicle

Accurate prior knowledge of future driving cycle is quite essential in many research and applications related to optimal control of the vehicle and transportation, especially for model predictive control-based energy management for hybrid electric vehicles. Therefore, an adaptive online prediction method with variable prediction horizon is proposed for future driving cycle prediction in this paper. In particular, two aspects of efforts have been explored. First, combining Markov chain and Monte Carlo theory, a multi-scale single-step prediction method is proposed and compared with traditional fixed-scale multi-step method, improving by about 7% in prediction accuracy. Second, to further adapt to variable actual driving cycles, online reconstructions of driving cycle and state filling are introduced to guarantee continuous and robust online application; principal component analysis and cluster analysis are employed to adjust real-time prediction horizons for better overall prediction accuracy. In the end, the proposed method is verified by the experiment of hardware-in-loop simulation, showing more than 20% improvement in prediction accuracy than fixed-horizon prediction method, and relatively good robustness and universality in different driving conditions.

HMM-based predictive model for enhancing data quality in WSN

ABSTRACTWireless sensor network (WSN) has been widely used in the areas such as health care and industrial monitoring. However, WSN systems still suffer from inevitable problems of communication interference and data failure. In this paper, an improved Hidden Markov Model (HMM) is proposed to enhance the quality of WSN sensor data. This model can be used to recover the missing data and predict the upcoming data in order to improve the data integrity and reliability ultimately. K-means clustering is firstly used to group sensor data series on the basis of different patterns. Next, Particle Swarm Optimization is applied for optimizing HMM parameters, which is enhanced by a hybrid mutation strategy. Experiments on two real data-sets show that the proposed approach can outperform the baseline models (Naïve Bayes, Grey System, BP-Neural Network and Traditional HMM) on precision of both single-step prediction and multiple-step prediction. The results also demonstrate that the proposed approach can improve data quality of WSN significantly. The proposed model can be further extended for time series prediction in other fields.

Two-Tier Reactive Power and Voltage Control Strategy Based on ARMA Renewable Power Forecasting Models

To address the static voltage stability issue and suppress the voltage fluctuation caused by the increasing integration of wind farms and solar photovoltaic (PV) power plants, a two-tier reactive power and voltage control strategy based on ARMA power forecasting models for wind and solar plants is proposed in this paper. Firstly, ARMA models are established to forecast the output of wind farms and solar PV plants. Secondly, the discrete equipment is pre-regulated based on the single-step prediction information from ARMA forecasting models according to the optimization result. Thirdly, a multi-objective optimization model is presented and solved by particle swarm optimization (PSO) according to the measured data and the proposed static voltage stability index. Finally, the IEEE14 bus system including a wind farm and solar PV plant is utilized to test the effectiveness of the proposed strategy. The results show that the proposed strategy can suppress voltage fluctuation and improve the static voltage stability under the condition of high penetration of renewables including wind and solar power.

Bus arrival time prediction based on mixed model

How to predict the bus arrival time accurately is a crucial problem to be solved in Internet of Vehicle. Existed methods cannot solve the problem effectively for ignoring the traffic delay jitter. In this paper, a three-stage mixed model is proposed for bus arrival time prediction. The first stage is pattern training. In this stage, the traffic delay jitter patterns (TDJP) are mined by K nearest neighbor and K-means in the historical traffic time data. The second stage is the single-step prediction, which is based on real-time adjusted Kalman filter with a modification of historical TDJP. In the third stage, as the influence of historical law is increasing in long distance prediction, we combine the single-step prediction dynamically with Markov historical transfer model to conduct the multi-step prediction. The experimental results show that the proposed single-step prediction model performs better in accuracy and efficiency than short-term traffic flow prediction and dynamic Kalman filter. The multi-step prediction provides a higher level veracity and reliability in travel time forecasting than short-term traffic flow and historical traffic pattern prediction models.

Very-short-term wind power prediction by a hybrid model with single- and multi-step approaches

Very-short-term wind power prediction (VSTWPP) has played an essential role for the operation of electric power systems. This paper aims at improving and applying a hybrid method of VSTWPP based on historical data. The hybrid method is combined by multiple linear regressions and least square (MLR&LS), which is intended for reducing prediction errors. The predicted values are obtained through two sub-processes:1) transform the time-series data of actual wind power into the power ratio, and then predict the power ratio;2) use the predicted power ratio to predict the wind power. Besides, the proposed method can include two prediction approaches: single-step prediction (SSP) and multi-step prediction (MSP). WPP is tested comparatively by auto-regressive moving average (ARMA) model from the predicted values and errors. The validity of the proposed hybrid method is confirmed in terms of error analysis by using probability density function (PDF), mean absolute percent error (MAPE) and means square error (MSE). Meanwhile, comparison of the correlation coefficients between the actual values and the predicted values for different prediction times and window has confirmed that MSP approach by using the hybrid model is the most accurate while comparing to SSP approach and ARMA. The MLR&LS is accurate and promising for solving problems in WPP.

Wind power time series prediction using optimized kernel extreme learning machine method

Since wind has an intrinsically complex and stochastic nature, accurate wind power prediction is necessary for the safety and economics of wind energy utilization. Aiming at the prediction of very short-term wind power time series, a new optimized kernel extreme learning machine (O-KELM) method with evolutionary computation strategy is proposed on the basis of single-hidden layer feedforward neural networks. In comparison to the extreme learning machine (ELM) method, the number of the hidden layer nodes need not be given, and the unknown nonlinear feature mapping of the hidden layer is represented with a kernel function. In addition, the output weights of the networks can also be analytically determined by using regularization least square algorithm, hence the kernel extreme learning machine (KELM) method provides better generalization performance at a much faster learning speed. In the O-KELM, the structure and the parameters of the KELM are optimized by using three different optimization algorithms, i.e., genetic algorithm (GA), differential evolution (DE), and simulated annerling (SA), meanwhile, the output weights are obtained by a least squares algorithm just the same as by the ELM, but using Tikhonovs regularization in order to further improve the performance of the O-KELM. The utilized optimization algorithms of the O-KELM are respectively used to select the set of input variables, regularization coefficient as well as hyperparameter of kernel function. The proposed method is first applied to the direct six-step prediction for Mackey-Glass chaotic time series, under the same condition as the existing optimized ELM method. From the analysis of the simulation results it can be verified that the prediction accuracy of the proposed O-KELM method is increased by about one order of magnitude over that of the optimized ELM method. Furthermore, the DE-KELM algorithm can achieve the lowest root mean square error (RMSE). The O-KELM method is then applied to real-world wind power prediction instance, i.e., the Western Dataset from NERL. The 10-minute ahead single-step prediction as well as 20-minute ahead, 30-minute ahead, 40-minute ahead multi-step prediction for wind power time series are respectively implemented to evaluate the O-KELM method. Experimental results of each of the short-term wind power time series predictions at different time horizons confirm that the proposed O-KELM method tends to have better prediction accuracy than the optimized ELM method. Moreover, the GA-KELM algorithm outperforms other two O-KELM algorithms at future 10-minute, 20-minute, 40-minute ahead prediction in terms of the RMSE value. The DE-KELM algorithm outperforms other algorithms at future 30-minute ahead prediction in terms of the normalized mean square error (NMSE) and the RMSE value. The results from these applications demonstrate the effectiveness and feasibility of the proposed O-KLEM method. Therefore, the O-KELM method has a potential future in the field of wind power prediction.

Using string invariants for prediction searching for optimal parameters

We have developed a novel prediction method based on string invariants. The method does not require learning but a small set of parameters must be set to achieve optimal performance. We have implemented an evolutionary algorithm for the parametric optimization. We have tested the performance of the method on artificial and real world data and compared the performance to statistical methods and to a number of artificial intelligence methods. We have used data and the results of a prediction competition as a benchmark. The results show that the method performs well in single step prediction but the method’s performance for multiple step prediction needs to be improved. The method works well for a wide range of parameters.

Time series prediction of lung cancer patients' breathing pattern based on nonlinear dynamics

This study focuses on predicting breathing pattern, which is crucial to deal with system latency in the treatments of moving lung tumors. Predicting respiratory motion in real-time is challenging, due to the inherent chaotic nature of breathing patterns, i.e. sensitive dependence on initial conditions. In this work, nonlinear prediction methods are used to predict the short-term evolution of the respiratory system for 62 patients, whose breathing time series was acquired using respiratory position management (RPM) system. Single step and N-point multi step prediction are performed for sampling rates of 5 Hz and 10 Hz. We compare the employed non-linear prediction methods with respect to prediction accuracy to Adaptive Infinite Impulse Response (IIR) prediction filters. A Local Average Model (LAM) and local linear models (LLMs) combined with a set of linear regularization techniques to solve ill-posed regression problems are implemented. For all sampling frequencies both single step and N-point multi step prediction results obtained using LAM and LLM with regularization methods perform better than IIR prediction filters for the selected sample patients. Moreover, since the simple LAM model performs as well as the more complicated LLM models in our patient sample, its use for non-linear prediction is recommended.