Hybrid Prediction Research Articles

Data-driven learning-based Model Predictive Control for energy-intensive systems

Efficient control of energy-intensive systems is essential for reducing energy consumption and realizing sustainable development. However, considering the complex inter-dependent energy-consumption devices, numerous control parameters, and dynamic environments, the energy-efficient control of energy-intensive system is always challenging. To address such problems, this paper proposes a data-driven learning-based Model Predictive Control (MPC) method for the integrated control of various devices in energy-intensive systems. Specifically, a hybrid prediction model based on two variants of RNN is integrated with the MPC scheme to learn and predict the system dynamics based on massive time-series sensing data. Then an efficient tree-based prioritized group control model for heterogeneous devices is developed with a rolling optimization and feedback correction mode. A real-life case study is provided to evaluate the performance of the proposed method, which demonstrates its superiority over existing methods on saving the energy consumption.

Cryptocurrency Price Prediction Using Frequency Decomposition and Deep Learning

Given the substantial volatility and non-stationarity of cryptocurrency prices, forecasting them has become a complex task within the realm of financial time series analysis. This study introduces an innovative hybrid prediction model, VMD-AGRU-RESVMD-LSTM, which amalgamates the disintegration–integration framework with deep learning techniques for accurate cryptocurrency price prediction. The process begins by decomposing the cryptocurrency price series into a finite number of subseries, each characterized by relatively simple volatility patterns, using the variational mode decomposition (VMD) method. Next, the gated recurrent unit (GRU) neural network, in combination with an attention mechanism, predicts each modal component’s sequence separately. Additionally, the residual sequence, obtained after decomposition, undergoes further decomposition. The resultant residual sequence components serve as input to an attentive GRU (AGRU) network, which predicts the residual sequence’s future values. Ultimately, the long short-term memory (LSTM) neural network integrates the predictions of modal components and residuals to yield the final forecasted price. Empirical results obtained for daily Bitcoin and Ethereum data exhibit promising performance metrics. The root mean square error (RMSE) is reported as 50.651 and 2.873, the mean absolute error (MAE) stands at 42.298 and 2.410, and the mean absolute percentage error (MAPE) is recorded at 0.394% and 0.757%, respectively. Notably, the predictive outcomes of the VMD-AGRU-RESVMD-LSTM model surpass those of standalone LSTM and GRU models, as well as other hybrid models, confirming its superior performance in cryptocurrency price forecasting.

Short-term wind power forecasting model based on temporal convolutional network and Informer

Wind power forecast remains challenging owing to the unpredictable peculiarity of wind. The accuracy of wind power predictions is critical to the stability of the whole system. This research proposes a hybrid prediction model based on a temporal convolutional network and an Informer to increase the accuracy of wind power forecasting. The hidden temporal features in the dataset are first extracted using TCN, and the Informer is then employed to predict wind power. Additionally, a cutting-edge AdaBelief optimizer is used to boost prediction accuracy even more. The validity of the model is verified by comparing with other wind speed prediction methods. The findings reveal that the proposed model has the highest prediction accuracy and the best forecast effect.

Modelling of compression ignition engine by soft computing techniques (ANFIS-NSGA-II and RSM) to enhance the performance characteristics for leachate blends with nano-additives

Integrating nanoparticles in waste oil-derived biodiesel can revolutionize its performance in internal combustion engines, making it a promising fuel for the future. Nanoparticles act as combustion catalysts, enhancing combustion efficiency, reducing emissions, and improving fuel economy. This study employed a comprehensive approach, incorporating both quantitative and qualitative analyses, to investigate the influence of selected input parameters on the performance and exhaust characteristics of biodiesel engines. The focus of this study is on the potential of using oils extracted from food waste that ended up in landfills. The study's results are analysed and compared with models created using intelligent hybrid prediction approaches including adaptive neuro-fuzzy inference system, Response surface methodology-Genetic algorithm, and Non sorting genetic algorithm. The analysis takes into account engine load, blend percentage, nano-additive concentration, and injection pressure, and the desired responses are the thermal efficiency and specific energy consumption of the brakes, as well as the concentrations of carbon monoxide, unburned hydrocarbon, and oxides of nitrogen. Root-mean-square error and the coefficient of determination were used to assess the predictive power of the model. Comparatively to Artificial Intelligence and the Response Surface Methodology-Genetic Algorithm model, the results provided by NSGA-II are superior. This is because it achieved a pareto optimum front of 24.45 kW, 2.76, 159.54 ppm, 4.68 ppm, and 0.020243% for Brake Thermal Efficiency, Brake Specific Energy Consumption, Oxides of nitrogen, Unburnt Hydro Carbon, and Carbon monoxide. Combining the precision of ANFIS's prediction with the efficiency of NSGA-optimization II's gives a reliable and thorough evaluation of the engine's settings. The qualitative assessment considered practical aspects and engineering constraints, ensuring the feasibility of applying the parameters in real-world engine applications.

A Hybrid Prediction Model for CatBoost Tomato Transpiration Rate Based on Feature Extraction

The growth and yield of crops are highly dependent on irrigation. Implementing irrigation plans that are tailored to the specific water requirements of crops can enhance crop yield and improve the quality of tomatoes. The mastery and prediction of transpiration rate (Tr) is of great significance for greenhouse crop water management. However, due to the influence of multiple environmental factors and the mutual coupling between environmental factors, it is challenging to construct accurate prediction models. This study focuses on greenhouse tomatoes and proposes a data-driven model configuration based on the Competitive adaptive reweighted sampling (CARS) algorithm, using greenhouse environmental sensors that collect six parameters, such as air temperature, relative humidity, solar radiation, substrate temperature, light intensity, and CO2 concentration. In response to the differences in crop transpiration changes at different growth stages and time stages, the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm was used to identify three characteristic intervals: florescence stage, fruiting stage daytime, and fruiting stage night-time. Based on this, a greenhouse tomato Tr prediction model (CARS-CatBoost model) based on the CatBoost machine learning algorithm was constructed. The experimental verification shows that the coefficient of determination (R2) of the constructed CARS-CatBoost single model for the whole growth stage is 0.92, which is higher than the prediction accuracy of the traditional single crop coefficient model (R2 = 0.54). Among them, the prediction accuracy at night during the fruiting stage is the highest, and the Root Mean Square Error (RMSE) drops to 0.427 g·m−2·h−1. This study provides an intelligent prediction method based on the zonal modeling of crop growth characteristics, which can be used to support precise irrigation regulation of greenhouse tomatoes.

A novel hybrid approach to mooring tension prediction for semi-submersible offshore platforms

The accuracy of mooring tension prediction significantly affects the safety of semi-submersible offshore platform operations and the efficiency of production planning. Nevertheless, traditional single prediction models have difficulty accurately forecasting for complex measured mooring tension data. This work provides a hybrid method for predicting mooring tension on semi-submersible maritime platforms based on VMD, error correction, and the convolutional neural network–long short-term memory (CNN-LSTM) and convolutional neural network–bidirectional long short-term memory (CNN-BiLSTM) models. The proposed hybrid prediction model was trained, validated, and tested using monitored mooring tension data acquired from the “Deepsea One” semi-submersible ocean platform in the South China Sea under different orientations and sea conditions. The results showed that the proposed hybrid prediction model for mooring tension on semi-submersible offshore platforms had lower values of the root mean square error, mean absolute error, and mean absolute percentage error and higher values of the coefficient of determination (R2) than almost all of the other comparison models when predicting complex time series data of the actual monitored mooring tension. This indicated that the proposed hybrid prediction model had better precision and stability than other models. Furthermore, this method can be used to anticipate nonlinear, nonstationary time series data in different fields of maritime engineering.

A Hybrid Random Forest and Least Squares Support Vector Machine Model Based on Particle Swarm Optimization Algorithm for Slope Stability Prediction: A Case Study in Sichuan–Tibet Highway, China

Slope stability estimation is an engineering problem that involves several parameters. The problems of low accuracy of the model and blind data preprocessing are commonly existent in slope stability prediction research. To address these problems, 10 quantitative indicators are selected from 135 field cases to improve the accuracy of the model. These indicators were analyzed and visualized to examine their reliabilities after preprocessing. Combined with random forest (RF), particle swarm optimization (PSO), and least squares support vector machine (LSSVM) algorithms, a hybrid prediction model that the RF–PSO–LSSVM model is proposed for identifying slope stability, and its reliability is verified by other prediction models that SVM, logistic regression, decision trees, k-nearest neighbor, naive Bayes, and linear discriminant analysis. Besides, the importance score of each indicator in the prediction of slope stability is discussed by employing the RF algorithm. The research results show that the proposed hybrid model exhibits the best accuracy and superiority in slope stability prediction than other models in this paper, which its values of the best fitness, area under the curve, T-measure, and accuracy are 98.15%, 96.4%, 96.55%, and 95.82%, respectively. The most influential factors affecting slope stability are precipitation and gravity, and the slope type and pore water ratio are identified as the least significant factors in this paper. The results provide a novel approach toward slope stability prediction in the field of geotechnical engineering.

Precise Short-Term Small-Area Sunshine Forecasting for Optimal Seedbed Scheduling in Plant Factories

Photosynthesis is one of the key issues for vertical cultivation in plant factories, and efficient natural sunlight utilization requires predicting the light falling on each seedbed in a real-time manner. However, public weather services neither provide sunshine data nor meet spatial resolution requirement. Facing these short-term and small-area weather forecasting challenges, we propose a cross-scale approach to infer seedbed-sized areas of sunshine from the city-level public weather services, and then design a seedbed rotation scheduling system for optimal natural sunlight utilization. First, an end-edge-cloud coordinated computing architecture was employed to concurrently aggregate the multi-scale data from weather satellites to sunshine sensors in the plant factory. Second, the small area of sunshine deterministically depends on the meteorological data given a fixed environment, and this correlation was described by a hybrid mapping model, which combined the long short-term memory (LSTM) and gradient boosting decision tree (GBDT) algorithms to form the LSTM-GBDT hybrid prediction algorithm (LGHPA). By training the LGHPA with historical local sensory sunshine and the city-scale meteorological data, the hourly sunshine on a seedbed can be predicted from the public weather forecasting service. Finally, a dynamic seedbed scheduling scheme was constructed to provide uniform solar energy absorption according to the one-hour-ahead radiation estimation. Experiment results show that the hourly sunshine prediction error was less than 18.44% over a seasonal period and the deviation for different solar absorption by seedbeds with rotation capability is less than 7.1%. Consequently, it was demonstrated that the application of short-term, small-area sunshine forecasting improved the performance of seedbed rotation for uniformly absorbed solar radiation. The proposed method verifies the feasibility of precisely predicting small-area sunshine down to the seedbed scale by leveraging a model-based approach and a cloud-edge-end merged cybernetic computing paradigm.

Multivariate Genomic Hybrid Prediction with Kernels and Parental Information.

Genomic selection (GS) plays a pivotal role in hybrid prediction. It can enhance the selection of parental lines, accurately predict hybrid performance, and harness hybrid vigor. Likewise, it can optimize breeding strategies by reducing field trial requirements, expediting hybrid development, facilitating targeted trait improvement, and enhancing adaptability to diverse environments. Leveraging genomic information empowers breeders to make informed decisions and significantly improve the efficiency and success rate of hybrid breeding programs. In order to improve the genomic ability performance, we explored the incorporation of parental phenotypic information as covariates under a multi-trait framework. Approach 1, referred to as Pmean, directly utilized parental phenotypic information without any preprocessing. While approach 2, denoted as BV, replaced the direct use of phenotypic values of both parents with their respective breeding values. While an improvement in prediction performance was observed in both approaches, with a minimum 4.24% reduction in the normalized root mean square error (NRMSE), the direct incorporation of parental phenotypic information in the Pmean approach slightly outperformed the BV approach. We also compared these two approaches using linear and nonlinear kernels, but no relevant gain was observed. Finally, our results increase empirical evidence confirming that the integration of parental phenotypic information helps increase the prediction performance of hybrids.

Block Chain and Machine Learning Models to Evaluate Faults in the Smart Manufacturing System

Smart Manufacturing Systems (SMS) have revolutionized industrial processes by incorporating automation, data analytics, and real-time monitoring to improve efficiency and quality. However, ensuring the reliability and fault tolerance of SMS remains a challenge. This paper proposes an innovative approach that combines Blockchain technology with Machine Learning (ML) models to evaluate faults in SMS. By leveraging the immutability and transparency of the blockchain and the predictive capabilities of ML, this approach enhances fault detection, facilitates traceability, and ultimately contributes to the resilience of smart manufacturing. The industrial sector's increase in data creation has made monitoring systems a crucial idea for management and decision-making. The Internet of Things (IoT), which is sensor-based and one of the most advanced and potent technologies today, can process appropriate ways to monitor the manufacturing process. The research's suggested method combines IoT, machine learning (ML), and monitoring of the industrial system. Temperature, humidity, gyroscope, and accelerometer IoT sensors are used to gather environmental data. Sensor data is produced in unstructured, enormous, and real-time data forms. Many big data approaches are used to process the data further. This system's hybrid prediction model employs the Random Forest classification approach to weed out outliers in the sensor data and aid in defect identification throughout the production process. The suggested approach was examined for South Korean vehicle production. This system uses a strategy to protect and strengthen data trust in order to prevent genuine data changes with fictitious data and system interactions. The efficacy of the suggested methodology in comparison to other methods is provided in the results section. Furthermore, compared to other inputs, the hybrid prediction model offers a respectable fault prediction. The suggested technique is anticipated to improve decision-making and decrease errors during the production process.

Earthquake prediction technique: a comparative study

Earthquakes are one of the most dangerous natural disasters facing humans because of their occurrence without warning and their impact on their lives and property. In addition, predicting seismic movement is one of the main research topics in seismic disaster prevention. In geological studies, scientists can predict and know the locations of earthquakes in the long term. Therefore, about 80% of the major global earthquakes lie along the Pacific Ring belt, known as the Ring of Fire. Machine learning methods have also been used for short-term earthquake prediction, and studies have applied the random forest method to determine the factors that precede earthquakes. The machine learning method was based on various decision trees, each of which predicted the time to the nearest oscillation. The third group of scientists used the hybrid prediction method, which combines machine learning and geological studies. This research deals with a review of most of the geological studies and machine learning techniques applied to earthquake data sets, which showed a total lack of prediction of potential earthquakes through one approach, so studies designed by geologists were combined with machine learning.

Hybrid Prediction-Driven High-Throughput Sustainability Screening for Advancing Waste-to-Dimethyl Ether Valorization.

Assessing the prospective climate preservation potential of novel, innovative, but immature chemical production techniques is limited by the high number of process synthesis options and the lack of reliable, high-throughput quantitative sustainability pre-screening methods. This study presents the sequential use of data-driven hybrid prediction (ANN-RSM-DOM) to streamline waste-to-dimethyl ether (DME) upcycling using a set of sustainability criteria. Artificial neural networks (ANNs) are developed to generate in silico waste valorization experimental results and ex-ante model the operating space of biorefineries applying the organic fraction of municipal solid waste (OFMSW) and sewage sludge (SS). Aspen Plus process flowsheeting and ANN simulations are postprocessed using the response surface methodology (RSM) and desirability optimization method (DOM) to improve the in-depth mechanistic understanding of environmental systems and identify the most benign configurations. The hybrid prediction highlights the importance of targeted waste selection based on elemental composition and the need to design waste-specific DME synthesis to improve techno-economic and environmental performances. The developed framework reveals plant configurations with concurrent climate benefits (-1.241 and -2.128 kg CO2-eq (kg DME)-1) and low DME production costs (0.382 and 0.492 € (kg DME)-1) using OFMSW and SS feedstocks. Overall, the multi-scale explorative hybrid prediction facilitates early stage process synthesis, assists in the design of block units with nonlinear characteristics, resolves the simultaneous analysis of qualitative and quantitative variables, and enables the high-throughput sustainability screening of low technological readiness level processes.

MRI-based Radiomics Model for Preoperative Prediction of Lateral Pelvic Lymph Node Metastasis in Locally Advanced Rectal Cancer

To develop a magnetic resonance imaging (MRI)-based radiomics model for preoperative prediction of lateral pelvic lymph node (LPLN) metastasis (LPLNM) in patients with locally advanced rectal cancer MATERIALS AND METHODS: We retrospectively enrolled 263 patients with rectal cancer who underwent total mesorectal excision and LPLN dissection. Radiomics features from the primary lesion and LPLNs on baseline MRI images were utilized to construct a radiomics model, and their radiomics scores were combined to develop a radiomics scoring system. A clinical prediction model was developed using logistic regression. A hybrid predicting model was created through multivariable logistic regression analysis, integrating the radiomics score with significant clinical risk factors (baseline Carcinoembryonic Antigen (CEA), clinical circumferential resection margin status, and the short axis diameter of LPLN). This hybrid model was presented with a hybrid clinical-radiomics nomogram, and its calibration, discrimination, and clinical usefulness were assessed. A total of 148 patients were included in the analysis and randomly divided into a training cohort (n=104) and an independent internal testing cohort (n=44). The hybrid clinical-radiomics model exhibited the highest discrimination, with an area under the receiver operating characteristic (AUC) of 0.843 [95% confidence interval (CI), 0.706-0.968]in the testing cohort compared to the clinical model [AUC (95% CI)=0.772 (0.589-0.856)]and radiomics model [AUC (95% CI)=0.731 (0.613-0.849)]. The hybrid prediction model also demonstrated good calibration, and decision curve analysis confirmed its clinical usefulness. This study developed a hybrid MRI-based radiomics model that incorporates a combination of radiomics score and significant clinical risk factors. The proposed model holds promise for individualized preoperative prediction of LPLNM in patients with locally advanced rectal cancer. The data presented in this study are available on request from the corresponding author.

Continuous blood pressure monitoring using photoplethysmography and electrocardiogram signals by random forest feature selection and GWO-GBRT prediction model

Blood pressure (BP) is an important indicator of a person's cardiovascular status, but accurate, continuous BP monitoring remains a challenge. To improve the monitoring performance of continuous BP using electrocardiogram (ECG) and photoplethysmography (PPG) signals, a continuous BP monitoring method based on random forest feature selection (RFFS) and a gray wolf optimization-gradient boosting regression tree (GWO-GBRT) prediction model is developed in this study. First, features in time, frequency, and time–frequency domains are extracted from PPG and ECG signals to supply comprehensive characteristics for BP monitoring. Then, the RFFS method is employed to select sensitive features highly correlated with BP from the candidate feature sets, which reduced redundant information and improved monitoring efficiency. Next, a hybrid prediction model of the gray wolf optimization (GWO) technique and gradient boosting regression tree (GBRT) algorithm is established to learn the dependency relationship between BP and sensitive features. And a new fitness function of GWO is designed to balance the monitoring accuracy and consistency. Finally, ablation and comparative experiments demonstrate the effectiveness and advancement of the proposed method, using the ECG and PPG signals of 150 people downloaded from the MIMIC-III database. The mean absolute error (MAE) and standard deviation (STD) of the proposed method in predicting systolic blood pressure were 2.91 mmHg and 3.97 mmHg, and those of diastolic blood pressure were 1.71 mmHg and 2.35 mmHg. Its monitoring accuracy has surpassed the Association for Advancement of Medical Instrumentation (AAMI) standard and reached the “A” level standard of the British Hypertension Society (BHS) protocol.

A hybrid coal prediction model based on grey Markov optimized by GWO – A case study of Hebei province in China

Accurate prediction of coal consumption is crucial to the structural adjustment and high-quality development of the coal industry, and provides an effective basis for the government to formulate energy strategies. To enhance the prediction accuracy, a hybrid prediction model combining grey wolf optimization algorithm and grey Markov model (GWO_Markov_DNGM) is proposed in this study, which introduces the idea of Markov interval division in order to make up the defect of obtaining interval by experience in the past. In this research, coal consumption in Hebei Province from 2001 to 2020 is used as an example to verify the accuracy of the model and the results show that the proposed model has higher accuracy than the comparison models, including ARIMA, GM (1, 1), DGM (1, 1), DNGM (1, 1) and the grey Markov model with equidistant division of state interval. In addition, this study also discusses the influence of numbers of state intervals on the prediction accuracy of the proposed model, which further illustrates the high prediction accuracy of the proposed hybrid model. Finally, the proposed model is employed to predict the coal consumption of Hebei Province under three scenarios from 2021 to 2025, and several suggestions are put forward.

Next activity prediction of ongoing business processes based on deep learning

AbstractNext activity prediction of business processes (BPs) provides valid execution information of ongoing (i.e., unfinished) process instances, which enables process executors to rationally allocate resources and detect process deviations in advance. Current researches on next activity prediction, however, concentrate mostly on model construction without in‐depth analysis of historical event logs. In this article, we are dedicated to proposing an approach to forecast the next activity effectively in BPs. After in‐depth analysis of historical event logs, three types of candidate activity attributes are defined and calculated as additional input for the prediction based on three essential elements, that is, frequent activity patterns, trace similarity and position information. Furthermore, we construct an effective hybrid prediction model combining the popular convolutional neural network (CNN) and bidirectional long short‐term memory (Bi‐LSTM) with self‐attention mechanism. Specifically, CNN is used to extract the temporal features before importing into Bi‐LSTM for accurate prediction, and self‐attention mechanism is applied to strengthen features that have decisive effects on the prediction results. Comparison experiments on four real‐life datasets demonstrate that our hybrid model with selected attributes achieves better performance on next activity prediction than single models, and improves the prediction accuracy by 2.98%, 6.05%, 2.70% and 5.26% on Helpdesk, Sepsis, BPIC2013 Incidents and BPIC2012O datasets than the state‐of‐the‐art methods, respectively.

A Parametric Study of MPSO-ANN Techniques in Gas-Bearing Distribution Prediction Using Multicomponent Seismic Data

Predicting the oil–gas-bearing distribution of unconventional reservoirs is challenging because of the complex seismic response relationship of these reservoirs. Artificial neural network (ANN) technology has been popular in seismic reservoir prediction because of its self-learning and nonlinear expression abilities. However, problems in the training process of ANNs, such as slow convergence speed and local minima, affect the prediction accuracy. Therefore, this study proposes a hybrid prediction method that combines mutation particle swarm optimization (MPSO) and ANN (MPSO-ANN). It uses the powerful search ability of MPSO to address local optimization problems during training and improve the performance of ANN models in gas-bearing distribution prediction. Furthermore, because the predictions of ANN models require good data sources, multicomponent seismic data that can provide rich gas reservoir information are used as input for MPSO-ANN learning. First, the hyperparameters of the ANN model were analyzed, and ANNs with different structures were constructed. The initial ANN model before optimization exhibited good predictive performance. Then, the parameter settings of MPSO were analyzed, and the MPSO-ANN model was obtained by using MPSO to optimize the weights and biases of the developed ANN model. Finally, the gas-bearing distribution was predicted using multicomponent seismic data. The results indicate that the developed MPSO-ANN model (MSE = 0.0058, RMSE = 0.0762, R2 = 0.9761) has better predictive performance than the PSO-ANN (MSE = 0.0062, RMSE = 0.0786, R2 = 0.9713) and unoptimized ANN models (MSE = 0.0069, RMSE = 0.0833, R2 = 0.9625) on the test dataset. Additionally, the gas-bearing distribution prediction results were consistent overall with the actual drilling results, further verifying the feasibility of this method. The research results may contribute to the application of PSO and ANN in reservoir prediction and other fields.

A Hybrid Prediction Model for Local Resistance Coefficient of Water Transmission Tunnel Maintenance Ventilation Based on Machine Learning

Multiple ducts in the working shaft and main body of tunnels form a combined tee structure. An efficient and accurate prediction method for the local resistance coefficient is the key to the design and optimization of the maintenance ventilation scheme. However, most existing studies use numerical simulations and model experiments to analyze the local resistance characteristics of specific structures and calculate the local resistance coefficient under specific ventilation conditions. Therefore, there are shortcomings of low efficiency and high cost in the ventilation scheme optimization when considering the influence of the local resistance. This paper proposes a hybrid prediction model for the local resistance coefficient of water transmission tunnel maintenance ventilation based on machine learning. The hybrid prediction model introduces the hybrid kernel into a relevance vector machine to build the hybrid kernel relevance vector machine model (HKRVM). The improved artificial jellyfish search algorithm (IAJS), which utilizes Fuch chaotic mapping, lens-imaging reverse learning, and adaptive hybrid mutation strategies to improve the algorithm performance, is applied to the kernel parameter optimization of the HKRVM model. The results of a case study show that the method proposed in this paper can achieve the efficient and accurate prediction of the local resistance coefficient of maintenance ventilation and improve the prediction accuracy and prediction efficiency to a certain extent. The method proposed in this paper provides a new concept for the prediction of the ventilation local resistance coefficient and can further provide an efficient prediction method for the design and optimization of maintenance ventilation schemes.

A novel wind power prediction model improved with feature enhancement and autoregressive error compensation

Wind energy is a widely utilized form of clean energy with significant implications for maximizing its utilization and ensuring the stability of power systems. However, existing methods for short-term wind power prediction face challenges in effectively capturing hidden features in historical data characterized by local random fluctuations. Furthermore, these methods lack appropriate compensation mechanisms to account for deviations between predicted and actual wind farm results. This paper proposes a novel wind power prediction model that addresses these limitations through feature enhancement and autoregressive error compensation. The model emphasizes the relationship between six wind power variables collected in the field and utilizes bidirectional long short-term memory to capture bidirectional time series characteristics. The attention mechanism is employed to assign different weights to these features, enhancing their representation and reducing computational complexity. To overcome frequent local fluctuations in wind power, an autoregressive error compensation model is integrated to further improve prediction accuracy. The proposed method is validated through practical application in a wind power plant, and experimental results demonstrate significant reduction in root mean square error compared to other models. This approach effectively extracts change trends in non-stationary wind power data, enhancing short-term power prediction performance. The proposed method has potential for application in other large-scale wind farms within the hybrid prediction framework.

River-dust induced airborne particulate matter forecasting using a hybrid model of improved complete ensemble empirical mode decomposition with adaptive noise and radial basis function neural network

In the western plains of Taiwan, several rivers originate from the central Taiwanese mountains. Turbulent flow transports large quantities of river sediment that accumulates in the riverbed downstream. River-dust events are extreme dust events that are occasionally caused by drought along riverbeds. The Choushui and Kaoping Rivers demonstrate the highest potential for river-dust events in central and southern Taiwan, respectively. During monsoons, the accumulated river sediment in the estuary can easily become airborne. Consequently, vulnerable populations living along riverbanks are exposed to high PM10 concentrations, which may exert adverse health effects. To reduce the significant health risks associated with river-dust events, a hybrid pmodel composed of improved complete ensemble empirical mode decomposition with adaptive noise and radial basis function neural network (ICEEMDAN-RBFNN) is proposed. The hybrid model is compared with the RBFNN and Multilayer Perceptron (MLP) models for forecasting 3-h PM10 concentrations. In the hybrid prediction model, temperatures, relative humidity, wind speeds, wind direction indices, and previous hourly PM10 concentrations are accounted for. The results indicate that the hybrid model is more accurate than the RBFNN and MLP models in forecasting high and low PM10 concentrations in 3 h advance. The hybrid model achieves a reduction of up to 50% in both the MAPE (Mean Absolute Percentage Error) and RMSE (Root Mean Squared Error) compared to the RBFNN and MLP prediction models. Therefore, the hybrid ICEEMDAN-RBFNN model can forecast PM10 efficiently and can serve as an early-warning system for river-dust events. Finally, risk assessments are conducted to exemplify the application of the proposed hybrid model.