Search Results (224)

This article presents a comprehensive review of methods used for forecasting electricity consumption. The studies analyzed by the authors encompass both classical statistical models and modern approaches based on artificial intelligence, including machine-learning and deep-learning techniques. Electricity load forecasting is categorized into four time horizons: very short term, short term, medium term, and long term. The authors conducted a comparative analysis of various models, such as autoregressive models, neural networks, fuzzy logic systems, hybrid models, and evolutionary algorithms. Particular attention was paid to the effectiveness of these methods in the context of variable input data, such as weather conditions, seasonal fluctuations, and changes in energy consumption patterns. The article emphasizes the growing importance of accurate forecasts in the context of the energy transition, integration of renewable energy sources, and the management of the evolving electricity system, shaped by decentralization, renewable integration, and data-intensive forecasting demands. In conclusion, the authors highlight the lack of a universal forecasting approach and the need for further research on hybrid models that combine interpretability with high predictive accuracy. This review can serve as a valuable resource for decision-makers, grid operators, and researchers involved in energy system planning. Full article

With the availability of more ground-based remote-sensing meteorological equipment at Hong Kong International Airport, many more interesting features of terrain-disrupted airflow have been observed, such as the applications of short-range Doppler LIDAR. This paper documents a number of new features observed at the airport area, such as the hydraulic jump-like feature, vortex, and extensive mountain wake/reverse flow. The technical feasibility of using a numerical resolution weather prediction model to simulate such features is also explored. It is found that the presently available input data and numerical model may not be able to capture the fine features of the atmospheric boundary layer, and thus they are not very successful in reproducing many small-scale terrain-disrupted airflow features downstream of an isolated hill. On the other hand, more larger-scale terrain-disrupted flow features may be better captured, but there are still limitations with the available turbulence parameterization schemes. This paper aims at documenting the newly observed flow features at the Hong Kong International Airport, enhancing the understanding of low-level windshear, and evaluating the outputs of numerical resolution simulations for reproducing such observed features and its technical feasibility on short-term forecasting. Full article

The exploitation of renewable energy is essential for mitigating climate change and reducing fossil fuel emissions. Wind energy, the most mature technology, is highly dependent on wind speed, and the accurate prediction of the latter substantially supports wind power generation. In this work, various artificial neural networks (ANNs) were developed and evaluated for their wind speed prediction ability using the ERA5 historical reanalysis data for four potential Offshore Wind Farm Organized Development Areas in Greece, selected as suitable for floating wind installations. The training period for all the ANNs was 80% of the time series length and the remaining 20% of the dataset was the testing period. Of all the ANNs examined, the hybrid model combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks demonstrated superior forecasting performance compared to the individual models, as evaluated by standard statistical metrics, while it also exhibited a very good performance at high wind speeds, i.e., greater than 15 m/s. The hybrid model achieved the lowest root mean square errors across all the sites—0.52 m/s (Crete), 0.59 m/s (Gyaros), 0.49 m/s (Patras), 0.58 m/s (Pilot 1A), and 0.55 m/s (Pilot 1B)—and an average coefficient of determination (R²) of 97%. Its enhanced accuracy is attributed to the integration of the LSTM and GRU components strengths, enabling it to better capture the temporal patterns in the wind speed data. These findings underscore the potential of hybrid neural networks for improving wind speed forecasting accuracy and reliability, contributing to the more effective integration of wind energy into the power grid and the better planning of offshore wind farm energy generation. Full article

This paper presents a very short-term load forecasting (VSTLF) model tailored for large-scale power systems, employing a gated recurrent unit (GRU) network enhanced with an attention mechanism. To improve forecasting accuracy, a systematic input feature selection method based on Normalized Mutual Information (NMI) is introduced. Additionally, a novel input feature termed the load variationis proposed to explicitly capture real-time dynamic load patterns. Tailored data preprocessing techniques are applied, including load reconstitution to account for the impact of Behind-The-Meter (BTM) solar generation, and a weighted averaging method for constructing representative weather inputs. Extensive case studies using South Korea’s national power system data from 2021 to 2023 demonstrate that the proposed GRU-attention model significantly outperforms existing approaches and benchmark models. In particular, when expressing the accuracy of the proposed method in terms of the error rate, the Mean Absolute Percentage Error (MAPE) is 0.77%, which shows an improvement of 0.50 percentage points over the benchmark model using the Kalman filter algorithm and an improvement of 0.27 percentage points over the hybrid deep learning benchmark (CNN-BiLSTM). The simulation results clearly demonstrate the effectiveness of the NMI-based feature selection and the combination of load characteristics for very short-term load forecasting. Full article

This study explores advanced multivariate models that incorporate non-climatic exogenous variables for very short-term photovoltaic energy forecasting. By integrating historical energy data from multiple photovoltaic plants, the research aims to improve the prediction accuracy of a target plant while addressing critical challenges in electric power systems (EPS), such as frequency stability. Frequency stability becomes increasingly complex as renewable energy sources penetrate the grid because of their intermittent nature. To mitigate this challenge, precise forecasting of photovoltaic energy generation is essential for balancing supply and demand in real time. The performance of long short-term memory (LSTM) networks and bidirectional LSTM (BiLSTM) networks was compared over a 5 min horizon. Including energy generation data from neighboring plants significantly improved prediction accuracy compared to univariate models. Among the models, multivariate BiLSTM showed superior performance, achieving a lower root-mean-square error (RMSE) and higher correlation coefficients. Quantile regression applied to manage prediction uncertainty, providing robust confidence intervals. The results suggest that incorporating an exogenous power series effectively captures spatial correlations and enhances prediction accuracy. This approach offers practical benefits for optimizing grid management, reducing operational costs, improving the integration of renewable energy sources, and supporting frequency stability in power generation systems. Full article

To maximize photovoltaic (PV) production, it is necessary to estimate the amount of solar radiation that is available on Earth’s surface, as it can occasionally vary. This study aimed to systematize the parametric forecast (PF) of solar energy over time, adopting the validation of estimates by machine learning models (MLMs), with highly complex analyses as inclusion criteria and studies not validated in the short or long term as exclusion criteria. A total of 145 scholarly sources were examined, with a value of 0.17 for bias risk. Four components were analyzed: atmospheric, temporal, geographic, and spatial components. These quantify dispersed, absorbed, and reflected solar energy, causing energy to fluctuate when it arrives at the surface of a PV plant. The results revealed strong trends towards the adoption of artificial neural network (ANN), random forest (RF), and simple linear regression (SLR) models for a sample taken from the Nipepe station in Niassa, validated by a PF model with errors of 0.10, 0.11, and 0.15. The included studies’ statistically measured parameters showed high trends of dependence on the variability in transmittances. The synthesis of the results, hence, improved the accuracy of the estimations produced by MLMs, making the model applicable to any reality, with a very low margin of error for the calculated energy. Most studies adopted large time intervals of atmospheric parameters. Applying interpolation models can help extrapolate short scales, as their inference and treatment still require a high investment cost. Due to the need to access the forecasted energy over land, this study was funded by CS–OGET. Full article

Facing the decarbonization trend in power systems, there appears to be a growing requirement on agile response and delicate supply from electricity suppliers. To accommodate this request, it is of key significance to precisely extrapolate the upcoming power load, which is well acknowledged as VSTLF, i.e., Very Short-Term Power Load Forecasting. As a time series forecasting problem, the primary challenge of VSTLF is how to identify potential factors and their very long-term affecting mechanisms in load demands. With the help of a public dataset, this paper first locates several intensely related attributes based on Pearson’s correlation coefficient and then proposes an adaptive Informer network with the probability sparse attention to model the long-sequence power loads. Additionally, it uses the Shapley Additive Explanations (SHAP) for ablation and interpretation analysis. The experiment results show that the proposed model outperforms several state-of-the-art solutions on several metrics, e.g., 18.39% on RMSE, 21.70% on MAE, 21.24% on MAPE, and 2.11% on R². Full article

As the forefront of inland extension on the Indian plate, the northeastern Tibetan Plateau, marked by low strain rates and high stress levels, is one of the regions with the highest seismic risk. Analyzing seismicity through statistical methods holds significant scientific value for understanding tectonic conditions and assessing earthquake risk. However, seismic monitoring capacity in this region remains limited, and earthquake frequency is low, complicating efforts to improve earthquake catalogs through enhanced identification and localization techniques. Bi-scale empirical probability integral transformation (BEPIT), a statistical method, can address these data gaps by supplementing missing events shortly after moderate to large earthquakes, resulting in a more reliable statistical data set. In this study, we analyzed six earthquake sequences with magnitudes of M_S ≥ 6.0 that occurred in northeastern Tibet since 2009, following the upgrade of the regional seismic network. Using BEPIT, we supplemented short-term missing aftershocks in these sequences, creating a more complete earthquake catalog. ETAS model parameters and b values for these sequences were then estimated using maximum likelihood methods to analyze parameter variability across sequences. The findings indicate that the b value is low, reflecting relatively high regional stress. The background seismicity rate is very low, with most mainshocks in these sequences being background events rather than foreshock-driven events. The p-parameter of the ETAS model is high, indicating that aftershocks decay relatively quickly, while the α-parameter is also elevated, suggesting that aftershocks are predominantly induced by the mainshock. These conditions suggest that earthquake prediction in this region is challenging through seismicity analysis alone, and alternative approaches integrating non-seismic data, such as electromagnetic and fluid monitoring, may offer more viable solutions. This study provides valuable insights into earthquake forecasting in the northeastern Tibetan Plateau. Full article

Western Europe has been strongly affected in the last decades by Saharan dust incursions, causing a high PM10 concentration and red rain. In this study, dust events and the performance of seven neural network prediction models, including convolutional neural networks (CNN) and recurrent neural networks (RNN), have been analyzed in a PM10 concentration series from a monitoring station in Córdoba, southern Spain. The models were also assessed here for recursive multi-step prediction over different forecast periods in three different situations: background concentration, a strong dust event, and an extreme dust event. A very important increase in the number of dust events has been identified in the last few years. Results show that CNN models outperform the other models in terms of accuracy for direct 24 h prediction (RMSE values between 10.00 and 10.20 μg/m³), whereas the recursive prediction is only suitable for background concentration in the short term (for 2–5-day forecasts). The assessment and improvement of prediction models might help the development of early-warning systems for these events. From the authors’ perspective, the evaluation of trained models beyond the direct multi-step predictions allowed to fill a gap in this research field, which few articles have explored in depth. Full article

With the proliferation of smart home devices and the ever-increasing demand for household energy management, very-short-term load forecasting (VSTLF) has become imperative for energy usage optimization, cost saving and for sustaining grid stability. Despite recent advancements, VSTLF in the household scenario still poses challenges. For instance, some characteristics (e.g., high-frequency, noisy and non-stationary) exacerbate the data processing and model training procedures, and the heterogeneity in household consumption patterns causes difficulties for models with the generalization capability. Further, the real-time data processing requirement calls for both the high forecasting accuracy and improved computational efficiency. Thus, we propose a diffusion–attention-enhanced temporal (DATE-TM) model with multi-feature fusion to address the above issues. First, the DATE-TM model could integrate residents’ electricity consumption patterns with climatic factors. Then, it extracts the temporal feature using an encoder and meanwhile models the data uncertainty through a diffusion model. Finally, the decoder, enhanced with the attention mechanism, creates the precise prediction for the household load forecasting. Experimental results reveal that DATE-TM significantly surpasses classical neural networks such as BiLSTM and DeepAR, especially in handling the data uncertainty and long-term dependency. Full article

This article devises the Artificial Intelligence (AI) methods of designing models of short-term forecasting (in 12 h and 24 h horizons) of electricity production in a selected Small Hydropower Plant (SHP). Renewable Energy Sources (RESs) are difficult to predict due to weather variability. Electricity production by a run-of-river SHP is marked by the variability related to the access to instantaneous flow in the river and weather conditions. In order to develop predictive models of an SHP facility (installed capacity 760 kW), which is located in Southern Poland on the Skawa River, hourly data from nearby meteorological stations and a water gauge station were collected as explanatory variables. Data on the water management of the retention reservoir above the SHP were also included. The variable to be explained was the hourly electricity production, which was obtained from the tested SHP over a period of 3 years and 10 months. Obtaining these data to build models required contact with state institutions and private entrepreneurs of the SHP. Four AI methods were chosen to create predictive models: two types of Artificial Neural Networks (ANNs), Multilayer Perceptron (MLP) and Radial Base Functions (RBFs), and two types of decision trees methods, Random Forest (RF) and Gradient-Boosted Decision Trees (GBDTs). Finally, after applying forecast quality measures of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²), the most effective model was indicated. The decision trees method proved to be more accurate than ANN models. The best GBDT models’ errors were MAPE 3.17% and MAE 9.97 kWh (for 12 h horizon), and MAPE 3.41% and MAE 10.96 kWh (for 24 h horizon). MLPs had worse results: MAPE from 5.41% to 5.55% and MAE from 18.02 kWh to 18.40 kWh (for 12 h horizon), and MAPE from 7.30% to 7.50% and MAE from 24.12 kWh to 24.83 kWh (for 24 h horizon). Forecasts using RBF were not made due to the very low quality of training and testing (the correlation coefficient was approximately 0.3). Full article

Accurate prediction of PM_2.5 concentrations is essential for public health management, especially in areas affected by long-range pollutant transport. This study presents a hybrid model combining convolutional long short-term memory (ConvLSTM) and deep neural networks (DNNs) to enhance PM_2.5 forecasting in Seoul, South Korea. The hybrid model leverages ConvLSTM’s ability to capture spatiotemporal dependencies and DNN’s strength in feature extraction, enabling it to outperform standalone CMAQ and DNN models. For the T1 forecast (6 h averages), the ConvLSTM-DNN model exhibited superior performance, with an RMSE of 7.2 µg/m³ compared to DNN’s 8.5 µg/m³ and CMAQ’s 10.1 µg/m³. The model also maintained high categorical accuracy (ACC) and probability of detection (POD) for critical PM_2.5 levels while reducing false alarms (FARs), particularly in bad and very bad events. Although its performance decreases over extended forecast periods, the ConvLSTM-DNN model demonstrates its utility as a robust forecasting tool. Future work will focus on optimizing the network structure to improve long-term forecast accuracy. Full article

In this research, we investigate the power quality of the grid where an Electric Arc Furnace (EAF) with a very high load operates. An Electric Arc Furnace (EAF) is a highly nonlinear load that uses very high and variable currents, causing major power quality issues such as voltage sags, flickers, and harmonic distortions. These disturbances produce electrical grid instability, affect the operation of other equipment, and require strong mitigation measures to reduce their impact. To investigate these issues, data are collected from the Point of Common Coupling where the Electric Arc Furnace is fed. The following three main factors are identified for evaluating power quality: apparent power, active and reactive power, and distorted power. Along with these powers, Total Harmonic Distortion, an important indicator of power quality, is calculated. These data are collected during the full process of producing a complete steel batch. To create a Deep Neural Network that can model and forecast power quality parameters, a network is developed using LSTM layers, Convolutional Layers, and GRU Layers, all of which demonstrate good prediction performance. The results of the prediction models are examined, as well as the primary metrics characterizing the prediction, using the following: MAE, RMSE, R-squared, and sMAPE. Predicting active and reactive power and Total Harmonic Distortion (THD) proves useful for anticipating power quality problems in an Electric Arc Furnace (EAF). By reducing the EAF’s impact on the power system, accurate predictions will anticipate and minimize disturbances, optimize energy consumption, and improve grid stability. This research’s principal scientific contribution is the development of a hybrid deep neural network that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) layers. This deep neural network was designed to predict power quality metrics, including active power, reactive power, distortion power, and Total Harmonic Distortion (THD). The proposed methodology indicates an important step in improving the accuracy of power quality forecasting for Electric Arc Furnaces (EAFs). The hybrid model’s ability for analyzing both time-series data and complex nonlinear patterns improves its predictive accuracy compared to traditional methods. Full article

Hydrodynamic models are often used to obtain insights into potential dike breaches, because dike breaches can have severe consequences. However, their high computational cost makes them unsuitable for real-time flood forecasting. Machine learning models are a promising alternative, as they offer reasonable accuracy at a significant reduction in computation time. In this study, we explore the effectiveness of a Long Short-Term Memory (LSTM) neural network in fast flood modelling for a dike breach in the Netherlands, using training data from a 1D–2D hydrodynamic model. The LSTM uses the outflow hydrograph of the dike breach as input and produces water depths on all grid cells in the hinterland for all time steps as output. The results show that the LSTM accurately reflects the behaviour of overland flow: from fast rising and high water depths near the breach to slowly rising and lower water depths further away. The water depth prediction is very accurate (MAE = 0.045 m, RMSE = 0.13 m), and the inundation extent closely matches that of the hydrodynamic model throughout the flood event (Critical Success Index = 94%). We conclude that machine learning techniques are suitable for fast modelling of the complex dynamics of dike breach floods. Full article

Accurate precipitation intensity forecasting is crucial for effective flood management and early warning systems. This study evaluates the performances of convolutional neural network (CNN) and long short-term memory (LSTM) models in predicting hourly precipitation intensity using data from Sainte Catherine de la Jacques Cartier station near Québec City. The models predict precipitation levels from one to six hours ahead, which are categorized into slight, moderate, heavy, and very heavy precipitation intensities. Our methodology involved gathering hourly precipitation data, defining input combinations for multistep ahead forecasting, and employing CNN and LSTM models. The performances of these models were assessed through qualitative and quantitative evaluations. The key findings reveal that the LSTM model excelled in the short-term (1HA to 2HA) and long-term (3HA to 6HA) forecasting, with higher R² (up to 0.999) and NSE values (up to 0.999), while the CNN model was more computationally efficient, with lower AICc values (e.g., −16,041.1 for 1HA). The error analysis shows that the CNN demonstrated higher precision in the heavy and very heavy categories, with a lower relative error, whereas the LSTM performed better for the slight and moderate categories. The LSTM outperformed the CNN in minor- and high-intensity events, but the CNN exhibited a better performance for significant precipitation events with shorter lead times. Overall, both models were adequate, with the LSTM providing better accuracy for extended forecasts and the CNN offering efficiency for immediate predictions, highlighting their complementary roles in enhancing early warning systems and flood management strategies. Full article