Generate Prediction Models Research Articles

Ultra-Short-Term Photovoltaic Power Prediction Based on BiLSTM with Wavelet Decomposition and Dual Attention Mechanism

Photovoltaic power generation relies on sunlight conditions, and traditional prediction models find it difficult to capture the deep features of power data, resulting in low prediction accuracy. In addition, there are problems such as outliers and missing values in the data collected on site. This article proposes an ultra-short-term photovoltaic power generation prediction model based on wavelet decomposition, a dual attention mechanism, and a bidirectional long short-term memory network (W-DA-BiLSTM), aiming to address the limitations of existing deep learning models in processing nonlinear data and automatic feature extraction and optimize for the common problems of outliers and missing values in on-site data collection. This model uses the quartile range method for outlier detection and multiple interpolation methods for missing value completion. In the prediction section, wavelet decomposition is used to effectively handle the volatility and nonlinear characteristics of photovoltaic power generation data, while the bidirectional long short-term memory network (LSTM) structure and dual attention mechanism enhance the model’s comprehensive learning ability for time series data. The experimental results show that compared with the SOTA method, the model proposed in this paper has higher accuracy and efficiency in predicting photovoltaic power generation and can effectively address common random fluctuations and nonlinear problems in photovoltaic power generation.

MinLinMo: a minimalist approach to variable selection and linear model prediction

Generating prediction models from high dimensional data often result in large models with many predictors. Causal inference for such models can therefore be difficult or even impossible in practice. The stand-alone software package MinLinMo emphasizes small linear prediction models over highest possible predictability with a particular focus on including variables correlated with the outcome, minimal memory usage and speed. MinLinMo is demonstrated on large epigenetic datasets with prediction models for chronological age, gestational age, and birth weight comprising, respectively, 15, 14 and 10 predictors. The parsimonious MinLinMo models perform comparably to established prediction models requiring hundreds of predictors.

Modelos de predicción para detectar pacientes con enfermedades cardiacas empleando redes neuronales y las bibliotecas Pytorch y TensorFlow

Neural Networks are used to generate prediction models aimed at determining whether an individual has heart conditions. The PyTorch and TensorFlow libraries are applied to a dataset of patients related to heart diseases, containing 17 predictor variables. The purpose of this work is to compare the results obtained using the aforementioned libraries with Neural Networks, analyzing the behavior of loss functions and the outcomes from the confusion matrix when creating the prediction model. DownSampling and UpSampling techniques are employed to address the imbalance in the dataset, which consists of a total of 319,795 patients, of whom only 27,373 have heart disease. It was found that for this dataset, the best results with PyTorch are achieved in models of 100 epochs and above, with execution times of only a few seconds, while TensorFlow shows good results starting from models with 10 epochs, though its execution time is considerably longer. An analysis is conducted on the difference in computation time between PyTorch and TensorFlow.

Application of Machine Learning Techniques to the Prediction of Onset and Persistence of Binge Eating: A Prospective Study.

Machine learning (ML) techniques have shown promise for enhancing prediction of clinical outcomes; however, its application to predicting binge eating has been scarcely explored. We applied ML techniques to predict binge eating onset (vs. continued absence) and persistence (vs. remission) over time. Data were used from a larger prospective study of 1106 participants who were assessed on a range of putative risk, maintaining, and protective factors at baseline and 8months follow-up. Nine ML models for classification were developed and compared against a generalised linear model (GLM) for predicting onset (n=334) and persistence (n=623) outcomes using 39 self-reported baseline variables as predictors. All models performed poorly at predicting onset (AUC=0.49-0.61) and persistence (AUC=0.50-0.59) outcomes, with ML models demonstrating comparable performance to the GLM. We suspect that poor ML performance may have been a result of the limited set of self-reported baseline predictors used to generate prediction models. Improved predictive accuracy and optimisation of ML models in future research may require consideration of a larger, more disparate set of predictors that also incorporate various data types, such as neuroimaging, physiological, or smartphone sensor data.

Based on Deep Learning Model and Flink Streaming Computing Short Term Photovoltaic Power Generation Prediction for Suburban Distribution Network

With the advancement of global energy internet construction, accurate prediction of new energy generation power such as photovoltaic is an important foundation for ensuring the safety and economic working of new power systems. A short-term photovoltaic power generation prediction method for suburban distribution networks based on deep learning model fusion and Flink flow calculation is proposed to address the challenges of complex power grids, diversified disturbance factors, and isolated monitoring points. This method uses Bi directional Long Short Term Memory(BiLSTM) to extract cross sequential nonlinear characteristic of photovoltaic power generation time series data. Compared with standard LSTM, BiLSTM can consider both historical and future information simultaneously, thus extracting richer extracted features from power generation time series data. This method also integrates attention mechanism to capture the importance distribution of historical temporal features for power generation prediction, effectively solving the problem of long-term temporal dependence in standard LSTM models. The Flink streaming computing framework embeds a trained BiLSTM-Attention photovoltaic power generation prediction model, enabling real-time prediction and monitoring analysis of photovoltaic power generation at various monitoring points in the suburban distribution network. This article uses a dataset of a suburban photovoltaic power station for validation, and trains the model with historical power generation data, meteorological factors, weather types, seasons, and other information as inputs. The BiLSTM-Attention fusion model studys the temporal characteristics of power generation, and has high accuracy in predicting short-term photovoltaic power generation in different scenarios. The Flink streaming computing platform can not only process high throughput predicted power data, but also has low time delay.

Application of FFBP neural network to the prediction of swirling flow

Since ancient times, man has been seeking to improve in the field of transportation and energy consumption, as the combination of optimal energy consumption and not polluting the environment in exchange for obtaining a better return made him constantly searching for optimal methods in the field of anxiety and industry based on combustion. The swirl or vortex flow is one of the most important discoveries of the last century seeking to develop combustion, as research is still focused on it in many aspects, whether in terms of the shape of the rotational areas it forms. This study aims to determine the extent to which artificial intelligence can predict the characteristics of the Swirl flow. The model adopted experimental data of the Swirl flow, both descriptive and positional data as inputs and horizontal, vertical, and kinetic energy as outputs for several positions within the combustion chamber. The results indicate that the model can capture the spatial characteristics of the vortex flow field and the combined Learning of the relationship between the input and output parameters. The results of the velocity density distribution and the position of the vortex center of the vortex flow field agree well with the experimental results. The generated prediction model has good prediction accuracy based on previously observed datasets and can reconstruct the vortex flow field. In addition, it can perform inductive prediction on a previously unseen dataset and has some generalization ability. Finally, this study suggests that many potential architectures have applications based on the induction prediction model created here.

Analysis of Inverter Efficiency Using Photovoltaic Power Generation Element Parameters

Photovoltaic power generation is influenced not only by variable environmental factors, such as solar radiation, temperature, and humidity, but also by the condition of equipment, including solar modules and inverters. In order to preserve energy production, it is essential to maintain and operate the equipment in optimal condition, which makes it crucial to determine the condition of the equipment in advance. This paper proposes a method of determining a degradation of efficiency by focusing on photovoltaic equipment, especially inverters, using LSTM (Long Short-Term Memory) for maintenance. The deterioration in the efficiency of the inverter is set based on the power generation predicted through the LSTM model. To this end, a correlation analysis and a linear analysis were performed between the power generation data collected at the power plant to learn the power generation prediction model and the data collected by the environmental sensor. With this analysis, a model was trained using solar radiation data and power data that are highly correlated with power generation. The results of the evaluation of the model’s performance show that it achieves a MAPE of 7.36, an RMSE of 27.91, a MAE of 18.43, and an R2 of 0.97. The verified model is applied to the power generation data of the selected inverters for the years 2020, 2021, and 2022. Through statistical analysis, it was determined that the error rate in 2022, the third year of its operation, increased by 159.55W on average from the error rate of the power generation forecast in 2020, the first year of operation. This indicates a 0.75% decrease in the inverter’s efficiency compared to the inverter’s power generation capacity. Therefore, it is judged that it can be applied effectively to analyses of inverter efficiency in the operation of photovoltaic plants.

A Short-Term Power Prediction Method for Photovoltaics Based on Similar Day Clustering and Spatio-Temporal Feature Extraction

Accurate PV power prediction is crucial for enhancing grid planning, optimizing dispatch operations, and advancing management strategies. In pursuit of this objective, this study proposes a short-term distributed PV power prediction method that incorporates temporal and spatial feature extraction as well as similar day analysis. Firstly, to address the poor adaptability of traditional clustering methods to time-series data, the K-shape clustering algorithm is employed to categorize the time series into different weather types. Secondly, to overcome the challenges posed by varying time resolutions in similar day analysis, a novel method based on Dynamic Time Warping (DTW) is proposed. This method calculates the similarity between the target days and the days to be collected, considering both the time of day and the day of the week. Subsequently, a PV power generation prediction model based on a convolutional long short-term memory (CNN-LSTM) network is developed to enhance prediction accuracy. To tackle the difficulty of manual hyperparameter tuning, the chaos reverse sparrow search algorithm (CRSSA) is introduced. Finally, a case study is conducted on the measured data of a distributed photovoltaic power station in a certain region of China. By comparing RMSE and MAPE, compared with other prediction models, the proposed prediction model and solving algorithm effectively reduced the relative error by more than 1%, verifying the effectiveness of the proposed method.

Assessment of green hydrogen production by volatile renewable energy under different SSPs scenarios in China

In the context of increasing global concerns about climate change and sustainable energy, the production of green hydrogen (GH) from volatile renewable energy (VRE) sources, such as solar and wind, is a natural choice for China to meet its climate change mitigation goals. However, there are a number of challenges in current research on the assessment of green hydrogen potential. This study evaluates the potential of GH production through VRE at the regional level in China, under the various scenarios of Shared Socioeconomic Pathways (SSPs). For this purpose, a power generation prediction model suitable for VRE is proposed to predict the energy supply capacity for GH production in six regions of China, which combined Multilevel Discrete Wavelet Decomposition and Bi-directional Long Short-Term Memory with attention mechanism (MDWD - AMBiLSTM). The total amount of GH could potentially reach up to 428.01 Mt under the SSP1, with the northern region leading at the regional level at 104.21 Mt. Furthermore, the study evaluated the potential for GH promotion in six regions of China between 2023 and 2035 b y combining the three dimensions of GH production potential, economic evaluation, and environmental contribution. This study tentative identify priority areas and development scenarios for promoting GH production in China, and made policy recommendations for the promotion of green hydrogen in disparate areas.

Prediction of long-term photovoltaic power generation in the context of climate change

Accurate long-term prediction of power generation in photovoltaic (PV) power stations is crucial for preparing generation plans and future planning. Quantitative prediction of future power generation from PV stations not only contributes to the stable operation of the local power system but also assists managers in formulating regional energy policies to promote renewable energy consumption. We utilized the NEX-GDDP-CMIP6 high-resolution climate dataset and employed the Vine Copula method for post-downscaling. This approach enabled high-resolution forecasts of key meteorological factors under different shared socioeconomic pathways (SSPs) scenarios (SSP245 and SSP585) for a PV power station in Yunnan, China. Additionally, we developed the KM-PSO-SVR power generation prediction model, which enables future accurate long-term PV power generation prediction. The results show that the Vine Copula multi-model ensemble downscaling model can effectively simulate the changes in key meteorological factors in the PV power station area. The KM-PSO-SVR model exhibited good simulation performance, with a mean absolute error of 0.843, root mean square error of 1.136, and correlation coefficient of 0.874 during the validation period. The results indicate that during the decade spanning from January 1, 2025, to December 31, 2034, radiation and wind speed will be decrease, while the temperature is expected to increase. In the SSP245 scenario, there is a 1.585 % increase in the average annual power generation during the future carbon peaking period (2025–2034). However, the SSP585 scenario, representing higher future emissions, shows a lower increase of 1.479 %.

Prediction of photovoltaic power generation based on a hybrid model

In order to fully exploit the relationship between temporal features in photovoltaic power generation data and improve the prediction accuracy of photovoltaic power generation, a photovoltaic power generation forecasting method is proposed based on a hybrid model of the convolutional neural network (CNN) and extreme gradient boost (XGBoost). Taking the historical data of China’s photovoltaic power plants as a sample, the high-dimensional mapping relationship of photovoltaic power generation variables is extracted based on the convolutional layer and pooling layer of the CNN network to construct a high-dimensional time-series feature vector, which is an input for the XGBoost. A photovoltaic power generation prediction model is established based on CNN-XGBoost by training CNN and XGBoost parameters. Since it is difficult for a single model to achieve optimal prediction accuracy under different weather conditions, the k-means clustering algorithm is used to group the power datasets and train independent models to improve prediction accuracy. Through the actual data verification of photovoltaic power plants, the proposed photovoltaic power generation prediction model can accurately predict the power, which shows high prediction accuracy and generalization ability compared with other methods.

Ensemble prediction of RRC session duration in real-world NR/LTE networks

In the rapidly evolving realm of telecommunications, Machine Learning (ML) stands as a key driver for intelligent 6 G networks, leveraging diverse datasets to optimize real-time network parameters. This transition seamlessly extends from 4 G LTE and 5 G NR to 6 G, with ML insights from existing networks, specifically in predicting RRC session durations. This work introduces a novel use of weighted ensemble approach using AutoGluon library, employing multiple base models for accurate prediction of user session durations in real-world LTE and NR networks. Comparative analysis reveals superior accuracy in LTE, with 'Data Volume' as a crucial feature due to its direct impact on network load and user experience. Notably, NR sessions, marked by extended durations, reflect unique patterns attributed to Fixed Wireless Access (FWA) devices. An ablation study underscores the weighted ensemble's superior performance. This study highlights the need for techniques like data categorization to enhance prediction accuracies for evolving technologies, providing insights for enhanced adaptability in ML-based prediction models for the next network generation.

A novel decision optimization for thermal power unit based on condition-based predictive maintenance and equilibrium optimizer

A novel maintenance decision method for thermal power unit is proposed in paper. The proposed method tackles the issues of inflexibility and high cost in current thermal power unit maintenance strategies. It takes into account both intelligent fault prediction results and the current unit condition to make predictive maintenance decisions. It constructs a unit state model and a power generation prediction model based on DCS data from the thermal power unit. Constraints such as unit constraints, unit failure constraints, and unit power generation constraints are utilized in the construction of the objective function. The objective function incorporates start-stop cost, maintenance cost and downtime loss, and the Equilibrium Optimizer is used to determine the optimal maintenance strategy. Operational data from a power plant is used to verify the superiority of the method in enhancing unit power generation efficiency and the economic benefits of the power plant. The results show that the proposed method can reduce the cost by 34.9 % in case of minor failures.

Sustainable data-driven insights: Statistical analysis and artificial intelligence-driven modelling of aerosol concentrations in Hyderabad district, India

Air pollution stands as a pressing issue in contemporary times, leading to the loss of millions of lives and exerting detrimental effects on the economy. The aerosols especially particulate matter, which are dispersions of matter in air medium play an important role in manipulating the climatological variables in an area. The current study was developed in response to the need to study aerosols and particulates on annual levels using 20-year (2002–2021) daily mean Aerosol Optical Depth (AOD) product released by Moderate Resolution Imaging Spectrometer (MODIS) sensors, and to generate prediction models for AOD using artificial intelligence (AI) techniques for Hyderabad district in India. The results of daily mean analysis revealed a rising trend in the number of days with severe AOD (> 1). Yearly mean AOD distribution showed a percentage increase of 45.31 % from 2002 to 2021. Furthermore, factor analysis was carried out to check for correlations of AOD and PM2.5 with various meteorological and pollutant variables. It was observed that both PM2.5 and AOD had significant weak to moderate (p < 0.05; r < 0.5) correlations with both pollutants and meteorological variables. The hybrid deep learning-based CNN-LSTM was identified as the best-fit model to predict AOD, outperforming MLP – ARIMA and MLP models. CNN – LSTM showed an R2 of 0.70, MAE of 0.08, MSE of 0.02 and RMSE of 0.14.

Neural network fusion optimization for photovoltaic power forecasting

This paper aims to establish a comprehensive photovoltaic power generation prediction model. By collecting photovoltaic power generation data and weather data for a year, we analyzed the photovoltaic output characteristics in different seasons and found that the output characteristics in different seasons are also different. This article uses three neural network models, Long Short Term Memory Network, Recurrent Neural Network, and Dense Neural Network, to analyze the output characteristics of different seasons. Training, prediction, and prediction error analysis found that different models have different prediction accuracy in different seasons. Therefore, this paper proposes a weighted ensemble model add weights model based on the Nelder-Mead method to train and predict different seasons respectively. By analyzing the prediction error, the prediction accuracy needs to be better than a single model. We add noise to the data set to simulate unstable lighting conditions such as rainy days, and train and predict the data set after adding noise. The prediction results show that the comprehensive model has higher prediction accuracy than a single model in extreme weather. In order to verify the reliability of the model, this article uses a sliding window to extract the confidence interval of the prediction results, and uses the Bootstrap method to calculate the confidence interval. By analyzing and comparing each model’s Average Coverage, Root Mean Squared Length, and Mean Width, the prediction accuracy and reliability of add weights model are better than those of a single model.

Application of artificial intelligence technology in photovoltaic power generation prediction

As a new type of clean energy, photovoltaic power generation has been widely used in production and life. Compared with traditional energy, because the energy of photovoltaic power generation comes from the sun, photovoltaic power generation is mainly affected by the weather, which leads to the intermittency and volatility of this energy and makes the supply and demand relationship of this kind of energy more complex and changeable. With the continuous development of artificial intelligence technology, the field of photovoltaic power generation forecasting is also gradually realizing intelligence. At present, the photovoltaic power generation prediction model based on machine learning and deep learning has gradually become mainstream, which can effectively improve prediction accuracy and efficiency. In addition, the use of artificial intelligence technology can also achieve real-time monitoring and diagnosis of the operating status of photovoltaic power generation systems, further improving the stability and reliability of the system. In the future, with the continuous development and application of artificial intelligence technology, the field of photovoltaic power generation prediction will usher in broader development prospects.

Solid waste generation prediction model framework using socioeconomic and demographic factors with real-time MSW collection data.

This article proposes a framework for developing predictive models of end-of-life product flows, highlighting the importance of conducting thorough analyses before developing waste management and end-of-life product flow strategies. The framework emphasizes the importance of recognizing the nature and quality of the available data and finding a balance between model development time and detail requirements. It is designed to adapt to source material heterogeneity and address varying data availability scenarios, such as the presence or absence of radio frequency identification chips. A case study for the city of Gatineau is presented, showcasing the framework's application through agent-based simulation models in a geographic information systems environment. The study focuses on creating models of municipal solid waste generation based on socioeconomic and demographic factors and collection data to accurately predict the quantity and quality of waste streams, enabling municipalities to assess the environmental impact of their waste management strategies.

Photovoltaic power generation prediction and optimization configuration model based on GPR and improved PSO algorithm

As the growing demand for energy as well as the strengthening of environmental awareness, photovoltaic power generation, as a clean and renewable energy source, has gradually attracted people's attention and attention. To facilitate the dispatching and planning of power system, this study uses historical data and meteorological data to build a photovoltaic power generation prediction and configuration optimization model on the ground of Gaussian process regression and improved particle swarm optimization algorithm. The simulation results show that the regression prediction curve of the Gaussian process regression prediction model is the closest to the real curve, and the prediction curve is stable and not easily disturbed by noise data. The Root-mean-square deviation and the average absolute proportional error of the model are small, and the disparity in the predicted value and the true value of the model is small; The integration of multi factor data has improved the accuracy of prediction data, and the regression prediction effect is good. The improved Particle swarm optimization algorithm could continuously enhance in the search for the optimal solution, and the Rate of convergence is fast. The Pareto solution can provide different solutions suitable for photovoltaic power generation optimization. Reasonable optimization configuration can effectively reduce active power line loss and voltage deviation, with the maximum reduction values reaching 132kW and 0.028, respectively. The research and design of predictive models and optimized configuration models can promote the formation of smart grids.

Imputation of plasma lipid species to facilitate integration of lipidomic datasets

Recent advancements in plasma lipidomic profiling methodology have significantly increased specificity and accuracy of lipid measurements. This evolution, driven by improved chromatographic and mass spectrometric resolution of newer platforms, has made it challenging to align datasets created at different times, or on different platforms. Here we present a framework for harmonising such plasma lipidomic datasets with different levels of granularity in their lipid measurements. Our method utilises elastic-net prediction models, constructed from high-resolution lipidomics reference datasets, to predict unmeasured lipid species in lower-resolution studies. The approach involves (1) constructing composite lipid measures in the reference dataset that map to less resolved lipids in the target dataset, (2) addressing discrepancies between aligned lipid species, (3) generating prediction models, (4) assessing their transferability into the targe dataset, and (5) evaluating their prediction accuracy. To demonstrate our approach, we used the AusDiab population-based cohort (747 lipid species) as the reference to impute unmeasured lipid species into the LIPID study (342 lipid species). Furthermore, we compared measured and imputed lipids in terms of parameter estimation and predictive performance, and validated imputations in an independent study. Our method for harmonising plasma lipidomic datasets will facilitate model validation and data integration efforts.

Enhancing predictive performance for spectroscopic studies in wildlife science through a multi-model approach: A case study for species classification of live amphibians.

Near infrared spectroscopy coupled with predictive modeling is a growing field of study for addressing questions in wildlife science aimed at improving management strategies and conservation outcomes for managed and threatened fauna. To date, the majority of spectroscopic studies in wildlife and fisheries applied chemometrics and predictive modeling with a single-algorithm approach. By contrast, multi-model approaches are used routinely for analyzing spectroscopic datasets across many major industries (e.g., medicine, agriculture) to maximize predictive outcomes for real-world applications. In this study, we conducted a benchmark modeling exercise to compare the performance of several machine learning algorithms in a multi-class problem utilizing a multivariate spectroscopic dataset obtained from live animals. Spectra obtained from live individuals representing eleven amphibian species were classified according to taxonomic designation. Seven modeling techniques were applied to generate prediction models, which varied significantly (p < 0.05) with regard to mean classification accuracy (e.g., support vector machine: 95.8 ± 0.8% vs. K-nearest neighbors: 89.3 ± 1.0%). Through the use of a multi-algorithm approach, candidate algorithms can be identified and applied to more effectively model complex spectroscopic data collected for wildlife sciences. Other key considerations in the predictive modeling workflow that serve to optimize spectroscopic model performance (e.g., variable selection and cross-validation procedures) are also discussed.