Multi-step Prediction Research Articles

An improved gain-scheduling robust MPC for path following of autonomous independent-drive electric vehicles with time-varying and uncertainties

This paper proposes a gain-scheduling robust model predictive control (GS-RMPC) algorithm for the path-following problem of autonomous independent-drive electric vehicles (AIDEVs) with consideration of time-varying and uncertainties. Firstly, the polytopic uncertainty method and norm-bounded uncertainty method are introduced to characterise the vehicle dynamics model. Secondly, the infinite predict horizon optimisation process of online GS-RMPC is transformed into a series of linear matrix inequalities (LMIs) by minimising the worst-case objective function while considering all scheduling states in the polytope. Thirdly, an offline solution is also proposed to reduce the computational burden based on asymptotically stable invariant ellipse sets. Then, a hierarchical control structure is proposed to distribute the additional yaw moment, and a multi-step predictor is designed to compensate for the actuator time delay. Finally, the hardware-in-the-loop (HIL) testing is conducted to verify the efficacy of the proposed strategy.

A robust real-time energy scheduling strategy of integrated energy system based on multi-step interval prediction of uncertainties

The uncertainties of renewable energies and loads in integrated energy system (IES) result in unstable operation and performance degradation. To consider the impact of the uncertainties, the scheduling strategies of IES with the prediction of uncertainties are required. This paper designs a hybrid solar and gas turbine IES, in which the thermal and electrical storage units are integrated to address the uncertainties. A robust real-time energy scheduling strategy is proposed according to the real-time load and the predicted loads in the future time, in which the errors of multi-step interval prediction of renewable sources and loads are combined. The multi-step prediction method based on gated recurrent unit and time classification is constructed for the interval prediction of uncertain sources and loads by analyzing the probability statistics of prediction errors. In the robust optimization, the penalty factors of time sequences are proposed and considered to decrease the influences of future predicted information on current real-time scheduling, in which the future uncertainties in larger interval with current time has less influence. The optimal results in the hybrid IES demonstrate that the daily operation cost is 13.67 % lower than the method that does not consider the prediction parameters. Compared to the traditional scheduling strategies, the proposed strategy declines the operation cost by 2.93 %. The analysis of the confidence level of predictions ranging from 60 % to 98 % illustrates that the operation cost under the penalty factor of 0.94 is the lowest when the confidence level is from 94 % to 96 %.

Multistep short‐term wind speed prediction with rank pooling and fast Fourier transformation

AbstractShort‐term wind speed prediction is essential for economical wind power utilization. The real‐world wind speed data are typically intermittent and fluctuating, presenting great challenges to existing shallow models. In this paper, we present a novel deep hybrid model for multistep wind speed prediction, namely, LR‐FFT‐RP‐MLP/LSTM (linear fast Fourier transform rank pooling multiple‐layer perceptron/long short‐term memory). Our hybrid model processes the local and global input features simultaneously. We leverage RP for the local feature extraction to capture the temporal structure while maintaining the temporal order. Besides, to understand the wind periodic patterns, we exploit FFT to extract global features and relevant frequency components in the wind speed data. The resulting local and global features are, respectively, integrated with the original data and are fed into an MLP/LSTM layer for the initial wind speed predictions. Finally, we leverage a linear regression layer to collaborate these initial predictions to produce the final wind speed prediction. The proposed hybrid model is evaluated using real wind speed data collected from 2010 to 2020, demonstrating superior forecasting capabilities when compared with state‐of‐the‐art single and hybrid models. Overall, this study presents a promising approach for improving the accuracy of wind speed forecasting.

A novel multi-step-ahead approach for cloud server aging prediction based on hybrid deep learning model

Predicting software aging in cloud servers is essential for preventing cloud system breakdown and unexpected failures. However, the aging time series data in cloud servers often exhibits non-linearity and stochastic fluctuations, posing challenges for accurate prediction. To address this issue, this study proposes a novel multi-step ahead approach for cloud server aging prediction. Firstly, the original aging time series data is denoised using discrete wavelet transformation (DWT) and then reconstructed into multi-dimensional data by phase state reconstruction (PSR) to capture potential aging patterns. Subsequently, a deep long short-term memory network (DLSTM) is developed to predict the aging trend. Additionally, a stacked auto-encoder LSTM (SAE-LSTM) is designed to optimize the initial weight matrix of DLSTM to enhance prediction abilities. Finally, multi-step prediction experiments are conducted on our time series datasets from OpenStack cloud servers and a public dataset from Alibaba Cluster Trace Program. The comparative analysis of the proposed method with five baseline methods confirms its superiority in terms of prediction accuracy. For response time and free memory test sets, the range of root mean square error (RMSE) values are produced by the proposed method distributed in [0.1688–0.1931] and [139.05–146.05] respectively, with respect to the multi-step ahead prediction horizon from 1 up to 10. These results demonstrate that the proposed method can tackle the limitations of one-step ahead prediction, effectively extracting relevant aging features, and achieving low prediction accuracy. The study provides valuable insights into revealing future aging trends in cloud servers and offers a reference for implementing preventive maintenance and prognostics in cloud servers.

Utilizing sequential modeling in collaborative method for flood forecasting

Flood forecasting has been a major challenge in hydrology for decades. A variety of approaches have been developed, including numerical models and data-driven models, such as Deep Learning (DL), for disaster early-warning and monitoring systems. This study proposed two combination models, exploring different feature separation techniques to improve the 12-hour multi-step discharge prediction. Specifically, two different approaches were implemented, namely the separation of wet and dry periods (Combination Model No. 1; CM-1) and the separation of flood and non-flood events (Combination Model No. 2; CM-2) for comparison with the baseline model trained on an entire dataset. Multivariate time series discharge data were used, measured at upstream and downstream stations within the same river basins. Experiments were conducted in three case study areas in Thailand: the Lower Loei River Basin, the Upper Nan River Basin, and the Upper Chi River Basin.In the proposed model combination approach, three deep-learning models were investigated: vanilla recurrent neural networks (RNNs) and their variants, long short-term memory networks (LSTMs), and gated recurrent units (GRUs). In general, CM-2 exhibited superior performance compared to the other models in most of the experimented neural networks, while the CM-1 approach outperformed the baseline model. This emphasized the advantages of our proposed feature separation framework, particularly in improving model performance, with respect to flood events. However, some variations were observed in the Upper Chi River Basin because the more complex models, such as LSTMs and GRUs, possibly overfitted the training set with less fluctuating data. Our study highlighted the significant contribution of combining two models through feature separation, tailored to specific periods, thereby enhancing the accuracy of flood predictions.

Research of proton exchange membrane fuel cell degradation index and prediction method for automotive vehicles

Comprehensively describing proton exchange membrane fuel cell (PEMFC) degradation behavior and accurately predicting degradation under dynamic operating conditions have become a prerequisite for automotive PEMFC health maintenance and life extension control. In this paper, a PEMFC comprehensive degradation index that incorporates time-varying physical parameters with multi-scale degradation information is proposed. The nonlinear degradation tendency of exchange current density at dynamic operating conditions is considered in this index. Then a Holt-Winters convolutional neural network (H-W CNN) prediction framework is proposed. The PEMFC reversible degradation features are enhanced by the Holt-Winters smoothing algorithm and a multivariate CNN model is constructed to conduct PEMFC multi-step degradation prediction under insufficient degradation data. Experimental result shows that the degradation index can characterize the comprehensive degradation of PEMFC under dynamic operating conditions. For mean absolute percentage error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) under 3 h prediction horizon, the H-W CNN prediction framework improves the performance by 38.8%, 38.4%, 37.9% compared to echo state network (ESN). Under 15 to 45 h prediction horizon, the H-W CNN demonstrates better learning potential for PEMFC reversible degradation and degradation trend prediction ability compared with long short-term memory networks (LSTM), ESN d univariate CNN models.

A dynamic graph deep learning model with multivariate empirical mode decomposition for network‐wide metro passenger flow prediction

AbstractNetwork‐wide short‐term passenger flow prediction is critical for the operation and management of metro systems. However, it is challenging due to the inherent non‐stationarity, nonlinearity, and spatial–temporal dependencies within passenger flow. To tackle these challenges, this paper introduces a hybrid model called multi‐scale dynamic propagation spatial–temporal network (MSDPSTN). Specifically, the model employs multivariate empirical mode decomposition to jointly decompose the multivariate passenger flow into multi‐scale intrinsic mode functions. Then, a set of dynamic graphs is developed to reveal the passenger propagation law in metro networks. Based on the representation, a deep learning model is proposed to achieve multistep passenger flow prediction, which employs the dynamic propagation graph attention network with long short‐term memory to extract the spatial–temporal dependencies. Extensive experiments conducted on a real‐world dataset from Chengdu, China, validate the superiority of the proposed model. Compared to state‐of‐the‐art baselines, MSDPSTN reduces the mean absolute error, root mean squared error, and mean absolute percentage error by at least 3.243%, 4.451%, and 4.139%, respectively. Further quantitative analyses confirm the effectiveness of the components in MSDPSTN. This paper contributes to addressing inherent features of passenger flow to enhance prediction performance, offering critical insights for decision‐makers in implementing real‐time operational strategies.

Transfer learning integrating similarity analysis for short-term and long-term building energy consumption prediction

Currently, building energy consumption prediction models are usually based on a large amount of historical operational data in high demands of building operating hours and monitoring systems. However, many buildings may lack operational data due to relatively limited monitoring systems, causing the failure to use data-driven methods to characterize the energy profile. In this context, transfer learning is a promising method to establish the knowledge transfer between many high-quality building operation datasets and a small amount of target building data, and to help predict energy consumption in the target building. This paper studies the possibility of employing transfer learning to achieve both short and long-term building energy consumption prediction. Firstly, a similarity analysis method, based on variable modal decomposition and dynamic time warping, is proposed for identifying the source buildings with the most similar energy features to the target building. Then, transfer learning for long-term prediction air-conditioning energy consumption is developed with weather parameters generated by the Morphing method as inputs. For the short-term single-step prediction, the proposed model CV-RMSE improves 81.3% (AEC) and 77.4% (EEC), respectively, compared to the prediction model that does not implement the transfer learning strategy and directly uses the target BEC data. As for the short-term multi-step prediction, the proposed model CV-RMSE improves 62.0% (AEC) and 65.5% (EEC), respectively. For the long-term prediction, the average CV-RMSE for the whole year is 6.62% and 11.15% for the proposed and directly target domain-based model, respectively. The proposed method explores the practicality of transfer learning in building energy forecasting, contributing to the use of existing building operation data for energy management at different timespan.

QoS prediction using EMD-BiLSTM for II-IoT-secure communication systems

Abstract To address the challenges of secure and reliable communication and system quality of service (QoS) prediction in intelligent production lines (IPL) in the Industrial Intelligent Internet of Things (II-IOT) environment, a redundant collaborative security model-based communication architecture is designed. First, the redundant collaborative security communication model is introduced to construct the network communication architecture of IPL, including the industrial-site mechanical floor, data awareness layer, and gateway and application layer. Then, to leverage the advantages of the empirical-mode decomposition (EMD) method and the bidirectional long short-term memory (BiLSTM) model in time-series data analysis and processing, an EMD-BiLSTM-based QoS prediction model is proposed that can synchronously achieve one-step and multi-step prediction of QoS attributes. The proposed model exhibits a prediction accuracy of up to 94.01% on the SourceForge dataset, with prediction, recall, and F1 values as high as 91.37, 90.60, and 90.99%, respectively. The proposed EMD-BiLSTM model can achieve better performance than the state-of-the-art QoS prediction models, indicating that the proposed model can be more effectively used to improve the reliable communication level of II-IoT.

A truncated Gaussian distribution based multi-scale segment-wise fusion transformer model for multi-step commodity price forecasting

Accurately forecasting commodity price trends is crucial for producers, market participants, and related enterprises to make informed decisions regarding production planning and scheduling. However, achieving high accuracy in multi-step forecasting poses significant challenges due to the unique financial characteristics inherent in commodities. Thus, this paper proposes a novel truncated Gaussian distribution based multi-scale segment-wise fusion Transformer for multi-step commodity price forecasting. First, a multi-scale segment-wise fusion module, which capture the time dependencies from different time granularity, is designed to describe the time-varying trend characteristics of commodity prices. Second, considering the characteristics of price range fluctuation and truncation, a truncated Gaussian distribution is introduced to describe price uncertainty. Last, to evaluate the proposed method’s effectiveness, extensive experiments are conducted using real data on energy chemical product prices. The experimental results demonstrate that the proposed method accurately captures price change trends and effectively estimates price uncertainty. Compared to the widely adopted Autoformer, our approach achieves approximately 30% reductions in both root mean square error (RMSE) and mean absolute error (MAE) metrics. Additionally, it exhibits certain advantages over the current state-of-the-art (SOTA). In the 20-step and 60-step multi-step prediction tasks, the proposed method achieves RMSE values of 91.18 and 142.94, respectively, surpassing the current SOTA. The introduced research framework provides valuable insights for decision-makers engaged in analyzing and forecasting commodity markets. The code is available on https://github.com/dean-ob/TGD-MSSF.

Wind-Speed Multi-Step Forecasting Based on Variational Mode Decomposition, Temporal Convolutional Network, and Transformer Model

Reliable and accurate wind-speed forecasts significantly impact the efficiency of wind power utilization and the safety of power systems. In addressing the performance enhancement of transformer models in short-term wind-speed forecasting, a multi-step prediction model based on variational mode decomposition (VMD), temporal convolutional network (TCN), and a transformer is proposed. Initially, the Dung Beetle Optimizer (DBO) is utilized to optimize VMD for decomposing non-stationary wind-speed series data. Subsequently, the TCN is used to extract features from the input sequences. Finally, the processed data are fed into the transformer model for prediction. The effectiveness of this model is validated by comparison with six other prediction models across three datasets, demonstrating its superior accuracy in short-term wind-speed forecasting. Experimental findings from three distinct datasets reveal that the developed model achieves an average improvement of 52.1% for R2. To the best of our knowledge, this places our model at the leading edge of wind-speed prediction for 8 h and 12 h forecasts, demonstrating MSEs of 1.003 and 0.895, MAEs of 0.754 and 0.665, and RMSEs of 1.001 and 0.946, respectively. Therefore, this research offers significant contributions through a new framework and demonstrates the utility of the transformer in effectively predicting short-term wind speed.

Liquid-Liquid Dispersion Performance Prediction and Uncertainty Quantification Using Recurrent Neural Networks.

We demonstrate the application of a recurrent neural network (RNN) to perform multistep and multivariate time-series performance predictions for stirred and static mixers as exemplars of complex multiphase systems. We employ two network architectures in this study, fitted with either long short-term memory and gated recurrent unit cells, which are trained on high-fidelity, three-dimensional, computational fluid dynamics simulations of the mixer performance, in the presence and absence of surfactants, in terms of drop size distributions and interfacial areas as a function of system parameters; these include physicochemical properties, mixer geometry, and operating conditions. Our results demonstrate that while it is possible to train RNNs with a single fully connected layer more efficiently than with an encoder-decoder structure, the latter is shown to be more capable of learning long-term dynamics underlying dispersion metrics. Details of the methodology are presented, which include data preprocessing, RNN model exploration, and methods for model performance visualization; an ensemble-based procedure is also introduced to provide a measure of the model uncertainty. The workflow is designed to be generic and can be deployed to make predictions in other industrial applications with similar time-series data.

A combined framework for carbon emissions prediction integrating online search attention

As CO2 emissions continue to rise, the problem of global warming is becoming increasingly serious. It is important to provide a robust management decision-making basis for the reductions of carbon emissions worldwide by predicting carbon emissions accurately. However, affected by various factors, the prediction of carbon emissions is challenging due to its nonlinear and nonstationary characteristics. Thus, we propose a combination forecast model, named CEEMDAN-GWO-SVR, which incorporates multiple features to predict trends in China’s carbon emissions. First, the impact of online search attention and public health emergencies are considered in carbon emissions prediction. Since the impact of different variables on carbon emissions is lagged, the grey relational degree is used to identify the appropriate lag series. Second, irrelevant features are eliminated through RFECV. To address the issue of feature redundancy of online search attention, we propose a dimensionality reduction method based on keyword classification. Finally, to evaluate the features of the proposed framework, four evaluation indicators are tested in multiple machine learning models. The best-performed model (SVR) is optimized by CEEMDAN and GWO to enhance prediction accuracy. The empirical results indicate that the proposed framework maintains good performance in both multi-scenario and multi-step prediction.

The Carbon Emission Accounting and Prediction of the Power Generation Side based on LSTM in Jilin Province

In the context of global warming and the dramatic increase in greenhouse gas emissions, the power industry is the largest source of carbon emissions. Adjusting and optimizing the carbon dioxide emissions from the power industry will help China achieve its “dual carbon” goals and is of great significance for mitigating global carbon dioxide emissions. This paper takes six power plants in Jilin Province as the research objects, and firstly accounts for the carbon emission production data between January 2020 and December 2023 according to the "Accounting Methods and Reporting Guidelines for Greenhouse Gas Emissions from Enterprises - Power Generation Facilities". Then, LSTM was used to establish carbon emission prediction models for six different power plants in Jilin Province, and the analysis of each model showed that that the single-step prediction RMSEs are all less than one, with higher prediction accuracy, but only can used in short-term prediction, the multi-step prediction RMSEs are bigger than one, with lower prediction accuracy, but can used in long-term carbon emission trend prediction can be achieved. The carbon emission trend prediction of six power plants in Jilin province between January 2024 and August 2031 confirms that the carbon emissions of power plants will be affected by seasons and shown cyclical changes. Finally, reasonable policy recommendations are provided for the successful realisation of the "double carbon" target for electricity in Jilin Province.

Predicting energy prices based on a novel hybrid machine learning: Comprehensive study of multi-step price forecasting

Accurate prediction of energy prices is crucial to the development of energy security and environmental policies in various countries. This paper proposes a novel multi-step prediction hybrid model with genetic algorithm for variational mode decomposition, improved complete ensemble empirical modal decomposition with adaptive noise, bidirectional gated recurrent unit, temporal convolutional network, and multi-layer perceptron (GVMD-ICEEMDAN-BIGRU-TCN-MLP) for predicting carbon and natural gas futures prices. First genetic algorithm (GA) is used to fix the parameters of VMD model, the carbon and natural gas prices are decomposed into subsequences. Then the difference between the original series and the VMD after decomposition is further decomposed into subseries using ICEEMDAN. Next, the highest frequency series is predicted using the MLP model, and other subsequences are predicted using the BIGRU-TCN model. Finally, each predicted value is added linearly to determine the final result of steps 1, 3, and 5 of the entire forecasting process. According to the experimental results, it is shown that the model has lower prediction errors than the comparison model under mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R2), and modified Diebold-Mariano test (MDM). The good prediction results of the novel hybrid model are demonstrated in multi-step ahead integrated prediction experiments, especially in the experiments with 1-step ahead prediction, as well as in the experiments with varying training ratios.

A novel machine learning-based framework for the water quality parameters prediction using hybrid long short-term memory and locally weighted scatterplot smoothing methods

ABSTRACT Water quality prediction is crucial for effective river stream management. Dissolved oxygen, conductivity and chemical oxygen demand are vital chemical parameters for water quality. Development of machine learning (ML) and deep learning (DL) methods made them widely used in this domain. Sophisticated DL techniques, especially long short-term memory (LSTM) networks, are required for accurate, real-time multistep prediction. LSTM networks are effective in predicting water quality due to their ability to handle long-term dependencies in sequential data. We propose a novel hybrid approach for water quality parameters prediction combining DL with data smoothing method. The Sava river at the Jamena hydrological station serves as a case study. Our workflow uses LSTM networks alongside LOcally WEighted Scatterplot Smoothing (LOWESS) technique for data filtering. For comparison, Support Vector Regressor (SVR) is used as the baseline method. Performance is evaluated using Root Mean Squared Error (RMSE) and Coefficient of Determination R2 metrics. Results demonstrate that LSTM outperforms the baseline method, with an R2 up to 0.9998 and RMSE of 0.0230 on the test set for dissolved oxygen. Over a 5-day prediction period, our approach achieves R2 of 0.9912 and RMSE of 0.1610 confirming it as a reliable method for water quality multistep parameters prediction.

A novel paradigm: Addressing real-time decomposition challenges in carbon price prediction

Carbon price prediction serves as a market indicator and economic driver, facilitating the adoption of more environmentally friendly production methods to achieve the emission reduction targets outlined in the Paris Agreement. In recent years, time series analysis and decomposition techniques have been widely applied to carbon price forecasting. However, few researchers have considered the issue of data feature drift caused by real-time decomposition. Specifically, as the sample size increases, data features undergo changes, rendering the trained models unable to fit the new data. This paper explains the underlying reasons for this phenomenon from new perspectives and proposes a novel paradigm that replaces the intrinsic mode function with a single-step fuzzy particle. This new paradigm corrects the issue of data feature drift and concentrates noise into a completely new sequence during the preprocessing stage. In the subsequent processing steps, the loss of correlation between the sequence and time lag, as well as the sequence and carbon prices, is addressed through multi-information association. This paradigm hybrid model can be applied to deterministic and interval multi-step predictions. Experimental results on the datasets from Guangdong and Hubei demonstrate that the proposed model outperforms other comparative models, achieving better predictive results than existing decomposition-based forecasting models. In the case of Guangdong, the normalized root mean square error (NRMSE%) for one-step, three-step, and five-step deterministic predictions are 2.18%, 2.51%, and 2.89%, respectively. The average interval score (AIS) for interval predictions are −0.357 and − 0.2375, respectively.

Channel prediction method based on the data-driving for distribution automation main station

A data-driven channel prediction method for distribution automation master is proposed to address the poor quality of communication network and communication system transmission problems in distribution network communication. In this paper, an adaptive broad learning network (ABLN) consisting of a standard broad learning network and a hybrid learning network is introduced to predict the channel state information of the communication system. Among them, the hybrid learning network is used to solve the ill-conditioned solution problem when estimating the output weight matrix of the standard broad learning network. Therefore, the ABLN produces sparse output weight matrices and provides excellent prediction performance. In the simulation analysis, the outdoor and indoor scenes are considered based on OFDM system. The prediction performance of ABLN is subsequently evaluated in one step prediction and multistep prediction. The results show that for the prediction performance is concerned, the maximum improvement of ABLN is about 96.49% as compared to other evaluation models, indicating that the CSI is effectively predicted by the ABLN to support the adaptive transmission of the main station of the distribution automation and to satisfy the quality of the communication network of the distribution network.

A 3-D Convolution-Based Burn-Through Point Multistep Prediction Model for Sintering Process

Predicting burn-through point (BTP) in advance is a quite critical task for the sintering process. However, sintering is a complex physicochemical reaction process, and the strong spatial-temporal correlations of data make the multi-step prediction task very challenging. The previous BTP multi-step prediction model only extracts spatial features in the high-level layers, leaving the spatial features in the low-level layers not learned. Specifically, the previous model only considers the relationships between the process variables and BTP, ignoring the spatial coupling relations among process variables. Further, the existing loss function is mainly based on Euclidean distance, which cannot learn dynamic information of multi-step prediction sequence. To tackle these problems, in this study, we propose a 3D convolution-based BTP multi-step prediction model (CBMP) to simultaneously capture spatial-temporal features. First, the 3D convolution is employed to capture the spatial-temporal features from low-level to high-level layers at the same time. Secondly, a spatial-temporal recalibration block is proposed to further refine the extracted features to increase the contributions of informative features and suppress the less useful ones. Finally, we design a time-aware multi-step prediction loss function to dynamically weigh the similarity between the actual sequence and the predicted sequence. The experimental results on two real-world BTP datasets demonstrate the effectiveness and feasibility of the proposed model on the BTP multi-step prediction task.

Improving multi-step prediction performance of multi-channel QoT over optical backbone networks: deep echo state attention network

Improving multi-step prediction performance of multi-channel QoT over optical backbone networks: deep echo state attention network