Short-term Forecasting Model Research Articles

Hybrid CNN-Multivariate LSTM Model for Accurate Short-Term Electricity Price Forecasting and Energy System Optimization

Hybrid CNN-Multivariate LSTM Model for Accurate Short-Term Electricity Price Forecasting and Energy System Optimization

MIESTC: A Multivariable Spatio-Temporal Model for Accurate Short-Term Wind Speed Forecasting

Wind speed forecasting is an essential part of weather prediction, with significant value in economics, business, and management. Utilizing multiple meteorological variables can improve prediction accuracy, but existing methods face challenges such as mixing and noise due to variable differences, as well as difficulty in capturing complex spatio-temporal dependencies. To address these issues, this study introduces a novel short-term wind speed forecasting model named as MIESTC. The proposed model employs an independent encoder to extract features from each meteorological variable, mitigating the issues of noise that are caused by variable mixing. Then, a multivariate spatio-temporal correlation module is used to capture the global spatio-temporal dependencies between variables and model their interactions. Experimental results on the ERA5-LAND dataset show that, compared to the ConvLSTM, UNET, and SimVP models, the MIESTC model reduces RMSE by 14.60%, 8.64%, and 10.41%, respectively, for a 1 h prediction duration. For a 6 h prediction duration, the corresponding reductions are 13.91%, 8.20%, and 6.95%, validating its superior performance in short-term wind speed forecasting. Furthermore, an analysis of variable impacts reveals that U10, V10, and T2M play dominant roles in wind speed prediction, while TP exhibits a relatively lower impact, aligning with the results of the correlation analysis. These findings underscore the potential of MIESTC as an effective and reliable tool for short-term wind speed prediction.

MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting

MPM: Multi Patterns Memory Model for Short-Term Time Series Forecasting

Short-term solar irradiance forecasting using deep learning models

Population growth and evolving consumer technology have resulted in an ever-increasing demand for energy and power. Traditional energy sources such as coal, oil, and gas are not only quickly depleting but have also contributed to global pollution. As a result, the demand for renewable energy for power generation has increased tremendously. Short-term solar irradiance is a critical area in renewable energy for the optimal operation and power prediction of grid-connected photovoltaic (PV) plants and other solar energy applications. However, solar irradiance is complex to handle due to the nonuniform characteristics of inconsistent weather conditions. Deep Learning techniques have shown outstanding performance in modeling these complexities. In this paper, short-term solar forecasting models are proposed using deep learning to reliably predict the amount of solar irradiance for optimal power generation. Furthermore, it is also evaluated whether the model can forecast the amount of Global Horizontal Irradiance (GHI) within one hour given the current recorded features including air temperature, azimuth, cloud opacity, and zenith. The data for Penang, Malaysia is used in this research. A Dense Neural Network (DNN) with 32 units achieved a validation MAE of 21.33 and MSE of 1343.68 in the 6th fold. Long-Short Term Memory (LSTM) with 256 units achieved a validation MAE of 8.23 and MSE of 246.98 in the 7th fold. On test data, the DNN achieved MAE and MSE of 31.71 and 2560.80 respectively whereas the LSTM model achieved MAE and MSE of 5.78 and 106.65 respectively.

ЭКОНОМЕТРИЧЕСКИЙ АНАЛИЗ ОБЪЕМОВ ВЗАИМНОЙ ТОРГОВЛИ ГОСУДАРСТВ-ЧЛЕНОВ БРИКС

The article provides an econometric analysis of the volumes of mutual trade of the BRICS member states: Brazil, Russia, China, India and the Republic of South Africa before the joining of the new countries. Also the presented diagrams depict the share of BRICS member countries in the mutual trade in 2017 and 2023. Based on annual data for 2004-2023 of mutual trade volumes of BRICS member countries, an adaptive first-order polynomial model for short-term forecasting has been constructed

Photovoltaic Short-Term Output Power Forecast Model Based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Kernel Principal Component Analysis–Long Short-Term Memory

To solve the problem of photovoltaic power prediction in areas with large climate changes, this article proposes a hybrid Long Short-Term Memory method to improve the prediction accuracy and noise resistance. It combines the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and kernel principal component analysis (KPCA) algorithm. The ICEEMDAN algorithm reduces the instability of the environmental factor sequence. The KPCA algorithm reduces the input dimensions of the model. LSTM performs dynamic time modeling of the multivariate feature sequences to predict the output PV power. The adaptability of the ICEEMDAN-KPCA-LSTM model is assessed with datasets from a PV plant in west China and evaluated by root mean squared error (RMSE), mean absolute percentage error (MAPE), and R-squared metrics. Using 70% of the datasets for output PV power estimation, the results show a good performance, with an RMSE of 4.3715, MAPE of 8.9264%, and R-squared value of 89.973%. By comparing with other prediction models, the ICEEMDAN-KPCA-LSTM photovoltaic output power model outperforms other models.

Enhancing the Statistical Evaluation of Earthquake Forecasts—An Application to Italy

Abstract Testing earthquake forecasts is essential to obtain scientific information on forecasting models and sufficient credibility for societal usage. We aim to enhance the testing phase proposed by the Collaboratory for the Study of Earthquake Predictability (CSEP, Schorlemmer et al., 2018) with new statistical methods supported by mathematical theory. To demonstrate their applicability, we evaluate three short-term forecasting models that were submitted to the CSEP-Italy experiment, and two ensemble models thereof. The models produce weekly overlapping forecasts for the expected number of M4+ earthquakes in a collection of grid cells. We compare the models’ forecasts using consistent scoring functions for means or expectations, which are widely used and theoretically principled tools for forecast evaluation. We further discuss and demonstrate their connection to CSEP-style earthquake likelihood model testing, and specifically suggest an improvement of the T-test. Then, using tools from isotonic regression, we investigate forecast reliability and apply score decompositions in terms of calibration and discrimination. Our results show where and how models outperform their competitors and reveal a substantial lack of calibration for various models. The proposed methods also apply to full-distribution (e.g., catalog-based) forecasts, without requiring Poisson distributions or making any other type of parametric assumption.

Multi 2D-CNN-based model for short-term PV power forecast embedded with Laplacian Attention

Amid the bloom of Renewable energy (RE) integrated into the grid, an accurate Photovoltaic(PV) power forecast is considered to be a crucial task in maintaining the reliability and stability of the power systems since this technology strongly depends on various external factors, causing the fluctuation in the output power. However, the poor quality of input data, which is very common in practical circumstances owing to the low-cost measurement and data acquisition devices, poses an enormous challenge for the predictive model to deeply extract the spatial and temporal correlation of the input data. This study proposes a Multi Two-Dimensional Convolutional Neural Network (2D-CNN) for short-term PV power forecast embedded with Laplacian Attention mechanism. By viewing the input sequences in a 2D form, the input map is constructed, and the interconnected feature among variables can be captured by convolution operation. Moreover, with the multiple CNN layers working in parallel architecture, different representations hidden inside the input map can be detected, enabling the proposed model to bring out promising performance across forecast time-step without modifying its initial parameters. In order to reduce the decay impact of irrelevant variables existing inside the input data, the Laplacian Attention mechanism is employed. The Attention matrix is dynamically modified during the training process to produce an accurate attention matrix, which represents the correlation between variables. Therefore, the model is able to focus on informative features and ignore negative ones. The experiments conducted on two different datasets with opposite characteristics provide deep insights into the strength of the proposed model over the baseline model, which strongly demonstrates the efficiency of the proposed model, especially when dealing with datasets bearing tough characteristics.

Short-term load forecasting method based on multiple meteorological factors and improved TCN-LSTM

Abstract Effective scheduling plans, optimized energy deployment, and grid stability assurance hinge on precisely forecasting short-term power loads. Therefore, this paper introduces an innovative approach to short-term load forecasting that integrates meteorological factors with an enhanced TCN-LSTM methodology. Firstly, the impact of meteorological factors on loads is quantified using Pearson’s phase relationship, facilitating the identification of meteorological input variables for the short-term load forecasting model. Secondly, a novel time-series convolutional neural network (TCN) tailored to power load characteristics is developed. The introduction of a network structure adapted to the characteristics of power loads improves the TCN model, enabling the effective capture of the long-term dependence and short-term fluctuation in load data. Finally, the paper details the construction of the improved TCN-LSTM model for short-term load forecasting. The new vectors, formed based on the load data features extracted by the improved TCN, are used as inputs for LSTM for load forecasting. The proposed short-term load forecasting method is validated using load-meteorological data from a typical period in a specific area, and the results demonstrate a notable enhancement in forecasting.

A Novel Multi-Objective Hybrid Evolutionary-Based Approach for Tuning Machine Learning Models in Short-Term Power Consumption Forecasting

Accurately forecasting power consumption is crucial important for efficient energy management. Machine learning (ML) models are often employed for this purpose. However, tuning their hyperparameters is a complex and time-consuming task. The article presents a novel multi-objective (MO) hybrid evolutionary-based approach, GA-SHADE-MO, for tuning ML models aimed at solving the complex problem of forecasting power consumption. The proposed algorithm simultaneously optimizes both hyperparameters and feature sets across six different ML models, ensuring enhanced accuracy and efficiency. The study focuses on predicting household power consumption at hourly and daily levels. The hybrid MO evolutionary algorithm integrates elements of genetic algorithms and self-adapted differential evolution. By incorporating MO optimization, GA-SHADE-MO balances the trade-offs between model complexity (the number of used features) and prediction accuracy, ensuring robust performance across various forecasting scenarios. Experimental numerical results show the superiority of the proposed method compared to traditional tuning techniques, and random search, showcasing significant improvements in predictive accuracy and computational efficiency. The findings suggest that the proposed GA-SHADE-MO approach offers a powerful tool for optimizing ML models in the context of energy consumption forecasting, with potential applications in other domains requiring precise predictive modeling. The study contributes to the advancement of ML optimization techniques, providing a framework that can be adapted and extended for various predictive analytics tasks.

Two-Stage Combined Model for Short-Term Electricity Forecasting in Ports

Two-Stage Combined Model for Short-Term Electricity Forecasting in Ports

A CNN-LSTM Model for Short-Term Passenger Flow Forecast Considering the Built Environment in Urban Rail Transit Stations

A CNN-LSTM Model for Short-Term Passenger Flow Forecast Considering the Built Environment in Urban Rail Transit Stations

Models for Short-Term Forecast of Maximum X-ray Class of Solar Flares Based on Magnetic Energy of Active Regions

Models for Short-Term Forecast of Maximum X-ray Class of Solar Flares Based on Magnetic Energy of Active Regions

A hybrid deep learning-based short-term forecast model for ionospheric foF2 in East Asia region

The short-term forecast of the critical frequency of the ionospheric F2 layer (foF2) is particularly challenging due to its nonlinear and non-stationary characteristics. To improve the short-term forecast accuracy of foF2, we propose a short-term hybrid deep learning model that integrates the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and long short-term memory (LSTM) algorithms. The proposed model leverages the ICEEMDAN decomposition algorithm to expand foF2 time series data into multi-dimensional space and utilizes the LSTM algorithm to preserve long-term data information, capturing detailed changes in foF2 parameters and obtaining internal information about foF2. The 2014 and 2017 foF2 data from four observation stations located in Mohe, Beijing, Jeju, and Kokubunji in the mid-latitudes of East Asia were utilized for modeling and 1-hour forecast analysis. The forecast values of the proposed model align closely with the measured data, exhibiting minimal fluctuation in forecast error and effectively tracking the changing trend of foF2. The average root mean square error (RMSE) across the four stations in 2014 is 0.40 MHz, with a relative RMSE (RRMSE) of 7.11 % and a coefficient of determination (R2) of 0.98. The average RMSE in 2017 is 0.43 MHz, RRMSE is 7.68 %, and R2 is 0.92. The proposed model reveals significant improvements in the forecast accuracy of the comparison model compared with the CCIR, URSI, NN, and LSTM models. Especially compared with the CCIR and URSI models in the International Reference Ionosphere (IRI), demonstrating superior real-time tracking capability for foF2 and effectively addressing the challenge of poor short-term forecast accuracy observed in the IRI model.

Short-term forecasting of consumption of the oil and gas enterprises using technological factors and Shapley additive explanations

RELEVANCE of the study lies in the development of system for the short-term forecasting of power consumption by the enterprise of the oil and gas industry with consideration of technological factors and interpretation of their influence on the result of the forecast.THE PURPOSE. To consider the problems of short-term forecasting. To test the applicability of the multi-agent approach to determine the features used to build a machine learning model of short-term forecasting of power consumption. To build machine learning models. To study the influence of technological factors on the accuracy of forecasting of power consumption. To apply the SHapley Additive exPlanations and analyze its interpretation of the forecasting results.METHODS. Pre-processing of the dataset, construction and testing of machine learning models were made in the programming language Python 3 using opensource libraries Scikit-Learn, XGBoost, LightGBM, Shap.RESULTS. The article describes the relevance of the topic of short-term forecasting of power consumption by the enterprise of the oil and gas industry within the ESG-approach. The method of selecting the features used using a multi-agent approach to build a machine learning model was developed. Machine learning models were built. Experimentations with the consideration of different features were made. Interpretation of results using SHapley Additive exPlanations was made.CONCLUSION. The use of technological factors of power consumption of compressor yards and natural gas air coolers allowed to increase the accuracy of forecast of power consumption from 8.82 % to 3.65 %. The application of the SHapley Additive exPlanations allows to interpret the results of machine learning models and confirms the need to consider technological factors in the task of short-term forecasting of power consumption of oil and gas industry.

Short-term photovoltaic forecasting model with parallel multi-channel optimization based on improved dung beetle algorithm

Accurate prediction of photovoltaic(PV) generation plays a vital role in power dispatching and is one of the effective ways to ensure the safe operation of power grid. In response to this issue, this paper improves the Rhino beetle optimization algorithm (LSDBO) using Logistic chaos mapping and sine function strategies an optimizes the PCL-MHA model (running CNN-MHA and LSTM-MHA models in parallel, PCL; Multi-Head-Attention, MHA) to enhance predictive accuracy. Various experiments were conducted using historical data from the Alice Springs PV system in Australia. PV component technologies comprise monocrystalline silicon and polycrystalline silicon, with array fixed on the ground. Through experiments, the proposed model in this paper achieved the best results in 16 metrics under different weather conditions, with average values of 98.43 % for R2, 2.69 % for MSE, 7.8 % for MAE, and 15.09 % for RMSE. Compared to other models, an average improvement of 2.41 %, 6.6 %, 7.77 %, and 11.21 % in these metrics.

Polynomial fuzzy information granule based [formula omitted]-triple I fuzzy reasoning algorithm and its short-term forecasting of time series

Short-term forecasting of time series is an important research topic, which involves data characteristic capture and intelligent reasoning. For this topic, the Gaussian polynomial fuzzy information granule with interpretability is granulated on data, enabling the extraction of data trend characteristic, besides, the associate characteristic within the data is captured through building fuzzy association rule. Building upon the data characteristics captured in fuzzy information granule and fuzzy association rule, an intelligent reasoning algorithm called the fuzzy information granule based α-Triple I algorithm is proposed, where the membership degree of data to granule is considered in reasoning, and next the accurate level of deviation from data to granule can be inferenced. Based on the excavated data characteristics and a rational inference, a short-term forecasting model is established. Its superiority in terms of accuracy and reliability when compared to 7 other models in real time series has been tested. Notably, the prediction of the novel model is accurate because the function of FAR is identified from FAR’s truth degree, which means the validity degree of prediction. The application of the proposed model for short-term forecasting holds a potential impact across various fields.

Artificial neural network-based models for short term forecasting of solar PV power output and battery state of charge of solar electric vehicle charging station

The main objective of this study is to develop ANN-based predictive models for short-term forecasting of solar PV power output and battery state of charge. The 3Ds energy model that integrates Decarbonization, Digitalization, and Decentralization of the energy system to facilitate the shift towards sustainable energy sources is used for this electric vehicle project. The experimental set up includes solar PV panels, a solar inverter, a battery inverter, and a battery bank. Additionally, smart meters were installed to collect real-time performance data from the solar PV-powered electric vehicle (EV) charging station. The weather and real-time system performance data were used to develop short term forecasting models based on Artificial Neural Networks (ANN) and the Levenberg-Marquardt method, to predict the performance of the system (power output and state of the charge) ahead. The R values for the prediction models of solar photovoltaic (PV) specific power and battery state of charge fall within the range of 0.9957–0.9969 and 0.9990 to 0.9996, respectively. Furthermore, the mean squared errors (MSEs) for the artificial neural network (ANN) models pertaining to solar photovoltaic (PV) power output and battery state of charge exhibit a variety of values. Specifically, the MSEs for solar PV power output range from 1.242 x 10^-4 to 1.579 x 10^-4, while the MSEs for battery status of charge range from 0.1889 to 0.3402. Artificial neural network (ANN) models possess considerable promise for practical implementations as they simplify intricate connections among inputs, parameters, and outputs in real-world scenarios. The level of accuracy and short-term predictive models of the solar PV powered EV charging station are very important for achieving a balance between the supply of solar photovoltaic (PV) system and the demand for electric vehicles (EVs). Predictive models will help build complex control mechanisms for controlling and optimizing solar PV-powered charging stations, supervising their operation and maintenance, and simplifying renewable energy pre-purchase. Future works will include the development of an energy management system to improve the efficiency of the solar stations charging the EVs, the establishment of blockchain networks for both the solar PV system and battery bank, and the integration of cybersecurity protocols for the charging station.

Multi-step electric vehicles charging loads forecasting: An autoformer variant with feature extraction, frequency enhancement, and error correction blocks

The extensive integration of electric vehicles (EVs) into power grids has raised safety concerns. Meanwhile current EVs charging loads forecasting models mainly focus on single-step predictions, neglect load sparsity and underutilize residuals, limiting their accuracy. To tackle these issues, a multi-step short-term forecasting model, specifically designed to predict charging loads at public EVs charging stations using historical data, is proposed. The model begins with a preprocessing phase to handle missing data and outliers. Subsequently, an Autoformer variant is intruduced, which initially integrates feature extraction block leveraging the Temporal Convolutional Network (TCN) to adeptly capture temporal dynamics. This is further enhanced with a Discrete Cosine Transform (DCT)-based frequency enhancement block to learn sparsity and periodicity features of EVs charging loads by frequency mapping. In addition, an advanced error correction block, comprising Bayesian optimization algorithm, Convolutional Neural Networks, Multi-Head Self-Attention, and Gated Recurrent Units (BCMG), is incorporated to refine initial prediction results. Above all, the TCN-DCT enhanced Autoformer-BCMG (TDformerBCMG) model is proposed. Finally, a comprehensive experimental analysis is conducted on ACN-data for EVs charging load forecasting in 1–3 h steps. It is demonstrated that TDformerBCMG not only is effective and superior in each component, but also achieves a reduction in Mean Absolute Error by 20.94 % to 74.05 % compared to existing models. Moreover, stability is evidenced across 50 repeated trials, with the standard deviation for the Coefficient of Determination varying between 8.5844e-3 and 3.1580e-2. Further discussion on application analysis is provided. Consequently, TDformerBCMG offers a viable methodology and establishes a new benchmark for power system implementation.

A dynamic ensemble model for short-term forecasting in pandemic situations.

During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata-Google searches-to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations.