Forecasting

20 pages, 1758 KiB

Open AccessArticle

Synthetic Demand Flow Generation Using the Proximity Factor

by Ekin Yalvac and Michael G. Kay

Forecasting 2025, 7(1), 14; https://doi.org/10.3390/forecast7010014 - 19 Mar 2025

Viewed by 283

One of the biggest challenges in designing a logistics network is predicting the demand flows between all pairs of points in the network. Currently, the gravity model is mainly used for estimating the demand flow between points. However, the gravity model uses historical [...] Read more.

One of the biggest challenges in designing a logistics network is predicting the demand flows between all pairs of points in the network. Currently, the gravity model is mainly used for estimating the demand flow between points. However, the gravity model uses historical data to estimate values for its multiple parameters and distance between pairs to forecast the demand flow. Distance values close to zero and unprecedented changes in demand flow data create numerical instability for the gravity model’s output. Hence, the proximity factor, a single parameter model that uses the relative ordering of pairs instead of distance, was developed. In this paper, we systematically compare the proximity factor and the gravity model. It is shown that the proximity factor is a robust in terms of reliability and competitive alternative to the gravity model. According to our analysis, the proximity factor model can replace the gravity model in some applications when no historical data are available to adjust the parameters of the latter. Full article

(This article belongs to the Section Forecasting in Economics and Management)

► Show Figures

Figure 1

23 pages, 7135 KiB

Open AccessArticle

Forecasting Wind Speed Using Climate Variables

by Rafael Araujo Couto, Paula Medina Maçaira Louro and Fernando Luiz Cyrino Oliveira

Forecasting 2025, 7(1), 13; https://doi.org/10.3390/forecast7010013 - 11 Mar 2025

Viewed by 418

Abstract

Wind energy in Brazil has been steadily growing, influenced significantly by climate change. To enhance wind energy generation, it is essential to incorporate external climatic variables into wind speed modeling to reduce uncertainties. Periodic Autoregressive Models with Exogenous Variables (PARX), which include the [...] Read more.

Wind energy in Brazil has been steadily growing, influenced significantly by climate change. To enhance wind energy generation, it is essential to incorporate external climatic variables into wind speed modeling to reduce uncertainties. Periodic Autoregressive Models with Exogenous Variables (PARX), which include the exogenous variable ENSO, are effective for this purpose. This study modeled wind speed series in Rio Grande do Norte, Paraíba, Pernambuco, Alagoas, Sergipe, Rio Grande do Sul, and Santa Catarina, considering the spatial correlation between these states through PARX-Cov modeling. Additionally, the correlation with ENSO indicators was used for out-of-sample prediction of climatic variables, aiding in wind speed scenario simulation. The proposed PARX and PARX-Cov models outperformed the current model used in the Brazilian electric sector for simulating future wind speed series. Specifically, the PARX-Cov model with the Cumulative ONI index is most suitable for Pernambuco, Rio Grande do Sul, and Santa Catarina, while the PARX-Cov with the SOI index is more appropriate for Rio Grande do Norte. For Alagoas and Sergipe, the PARX with the Cumulative ONI index is the best fit, and the PARX with the Cumulative Niño 4 index is most suitable for Paraíba. Full article

(This article belongs to the Special Issue Advance Techniques for Solar Radiation, Wind Speed and Photovoltaic Forecasting)

► Show Figures

Figure 1

24 pages, 5390 KiB

Open AccessArticle

Multifeature-Driven Multistep Wind Speed Forecasting Using NARXR and Modified VMD Approaches

by Rose Ellen Macabiog and Jennifer Dela Cruz

Forecasting 2025, 7(1), 12; https://doi.org/10.3390/forecast7010012 - 5 Mar 2025

Cited by 1 | Viewed by 700

Abstract

The global demand for clean and sustainable energy has driven the rapid growth of wind power. However, wind farm managers face the challenge of forecasting wind power for efficient power generation and management. Accurate wind speed forecasting (WSF) is vital for predicting wind [...] Read more.

The global demand for clean and sustainable energy has driven the rapid growth of wind power. However, wind farm managers face the challenge of forecasting wind power for efficient power generation and management. Accurate wind speed forecasting (WSF) is vital for predicting wind power; yet, the variability and intermittency of the wind make forecasting wind speeds difficult. Consequently, WSF remains a challenging area of wind research, driving continuous improvement in the field. This study aimed to enhance the optimization of multifeature-driven short multistep WSF. The primary contributions of this research include the integration of ReliefF feature selection (RFFS), a novel approach to variational mode decomposition for multifeature decomposition (NAMD), and a recursive non-linear autoregressive with exogenous inputs (NARXR) neural network. In particular, RFFS aids in identifying meteorological features that significantly influence wind speed variations, thus ensuring the selection of the most impactful features; NAMD improves the accuracy of neural network training on historical data; and NARXR enhances the overall robustness and stability of the wind speed forecasting results. The experimental results demonstrate that the predictive accuracy of the proposed NAMD–NARXR hybrid model surpasses that of the models used for comparison, as evidenced by the forecasting error and statistical metrics. Integrating the strengths of RFFS, NAMD, and NARXR enhanced the forecasting performance of the proposed NAMD–NARXR model, highlighting its potential suitability for applications requiring multifeature-driven short-term multistep WSF. Full article

(This article belongs to the Special Issue Advance Techniques for Solar Radiation, Wind Speed and Photovoltaic Forecasting)

► Show Figures

Figure 1

27 pages, 6528 KiB

Open AccessArticle

Dynamic Bayesian Network Model for Overhead Power Lines Affected by Hurricanes

by Kehkashan Fatima and Hussain Shareef

Forecasting 2025, 7(1), 11; https://doi.org/10.3390/forecast7010011 - 5 Mar 2025

Viewed by 920

Abstract

This paper investigates the dynamics of Hurricane-Induced Failure (HIF) by developing a probabilistic framework using a Dynamic Bayesian Network (DBN) model. The model captures the complex interplay of factors influencing Hurricane Wind Speed Intensity (HWSI) and its impact on asset failures. In the [...] Read more.

This paper investigates the dynamics of Hurricane-Induced Failure (HIF) by developing a probabilistic framework using a Dynamic Bayesian Network (DBN) model. The model captures the complex interplay of factors influencing Hurricane Wind Speed Intensity (HWSI) and its impact on asset failures. In the proposed DBN model, the pole failure mechanism is represented using Bayesian probabilistic principles, encompassing bending elasticity endurance and the foundational strength of the system poles. To characterize the stochastic properties of HIF, Monte Carlo simulation (MCS) is employed in conjunction with fragility curves (FC) and the scenario reduction (SCENRED) algorithm. The proposed DBN model evaluates the probability of asset failure and compares the results using stochastic Monte Carlo simulation based on the fragility curve scenario reduction algorithm (FC-MCS-SCENRED) model. The results are validated on a standard IEEE 15 bus and IEEE 33 bus radial distribution system as a case study. The DBN results show that they are consistent with the data obtained using the FC-MCS-SCENRED model. The results also reveal that the HWSI plays a critical role in determining HIF rates and the likelihood of asset failures. These findings hold significant implications for the inspection and maintenance scheduling of distribution overhead power lines susceptible to hurricane-induced impacts. Full article

(This article belongs to the Section Power and Energy Forecasting)

► Show Figures

Figure 1

14 pages, 1684 KiB

Open AccessArticle

Exchange Rates, Supply Chain Activity/Disruption Effects, and Exports

by Simiso Msomi and Paul-Francios Muzindutsi

Forecasting 2025, 7(1), 10; https://doi.org/10.3390/forecast7010010 - 28 Feb 2025

Viewed by 760

Abstract

In the past, South African monetary policy aimed to protect the external value of the domestic currency (Rand); however, these efforts failed. Later, its monetary policy approach changed to allow the foreign exchange rate market to determine the exchange rates. In such a [...] Read more.

In the past, South African monetary policy aimed to protect the external value of the domestic currency (Rand); however, these efforts failed. Later, its monetary policy approach changed to allow the foreign exchange rate market to determine the exchange rates. In such a change, the South African Reserve Bank (SARB) aimed to stabilize the demand for the Rand in the foreign exchange market by providing information to stabilize market expectations and create favorable market conditions. However, South African policymakers have struggled with currency depreciation since the early 60s, increasing the uncertainty of South African exports. This study aims to examine the effect of currency depreciation on exports using the Threshold Autoregressive (TAR) model. Additionally, this study created and validated the supply chain activity/disruption index to capture the sea trade activity. The sample period for the analysis is 2009 to 2023. The study finds that currency depreciation does not improve trade between South Africa and its trading partners over time. Furthermore, the currency depreciation was found to be asymmetric to the effect of international trade across the different regimes. The supply chain activity index shows that the effect of supply chain activity/disruption on exports is regime-dependent. This implies that the effect on exports is dependent on the economic environment. Full article

(This article belongs to the Special Issue Forecasting and Foresight in Business and Economics in the Turbulent and Uncertain New Normal)

► Show Figures

Figure 1

21 pages, 4128 KiB

Open AccessArticle

Comparative Analysis of Physics-Guided Bayesian Neural Networks for Uncertainty Quantification in Dynamic Systems

by Xinyue Xu and Julian Wang

Forecasting 2025, 7(1), 9; https://doi.org/10.3390/forecast7010009 - 21 Feb 2025

Viewed by 640

Abstract

Uncertainty quantification (UQ) is critical for modeling complex dynamic systems, ensuring robustness and interpretability. This study extends Physics-Guided Bayesian Neural Networks (PG-BNNs) to enhance model robustness by integrating physical laws into Bayesian frameworks. Unlike Artificial Neural Networks (ANNs), which provide deterministic predictions, and [...] Read more.

Uncertainty quantification (UQ) is critical for modeling complex dynamic systems, ensuring robustness and interpretability. This study extends Physics-Guided Bayesian Neural Networks (PG-BNNs) to enhance model robustness by integrating physical laws into Bayesian frameworks. Unlike Artificial Neural Networks (ANNs), which provide deterministic predictions, and Bayesian Neural Networks (BNNs), which handle uncertainty probabilistically but struggle with generalization under sparse and noisy data, PG-BNNs incorporate the laws of physics, such as governing equations and boundary conditions, to enforce physical consistency. This physics-guided approach improves generalization across different noise levels while reducing data dependency. The effectiveness of PG-BNNs is validated through a one-degree-of-freedom vibration system with multiple noise levels, serving as a representative case study to compare the performance of Monte Carlo (MC) dropout ANNs, BNNs, and PG-BNNs across interpolation and extrapolation domains. Model accuracy is assessed using Mean Squared Error (MSE), Mean Absolute Percentage Error (MAE), and Coefficient of Variation of Root Mean Square Error (CVRMSE), while UQ is evaluated through 95% Credible Intervals (CIs), Mean Prediction Interval Width (MPIW), the Quality of Confidence Intervals (QCI), and Coverage Width-based Criterion (CWC). Results demonstrate that PG-BNNs can achieve high accuracy and good adherence to physical laws simultaneously, compared to MC dropout ANNs and BNNs, which confirms the potential of PG-BNNs in engineering applications related to dynamic systems. Full article

(This article belongs to the Special Issue Feature Papers of Forecasting 2024)

► Show Figures

Figure 1

14 pages, 3050 KiB

Open AccessArticle

White Noise and Its Misapplications: Impacts on Time Series Model Adequacy and Forecasting

by Hossein Hassani, Leila Marvian Mashhad, Manuela Royer-Carenzi, Mohammad Reza Yeganegi and Nadejda Komendantova

Forecasting 2025, 7(1), 8; https://doi.org/10.3390/forecast7010008 - 5 Feb 2025

Cited by 1 | Viewed by 1247

Abstract

This paper contributes significantly to time series analysis by discussing the empirical properties of white noise and their implications for model selection. This paper illustrates the ways in which the standard assumptions about white noise typically fail in practice, with a special emphasis [...] Read more.

This paper contributes significantly to time series analysis by discussing the empirical properties of white noise and their implications for model selection. This paper illustrates the ways in which the standard assumptions about white noise typically fail in practice, with a special emphasis on striking differences in sample ACF and PACF. Such findings prove particularly important when assessing model adequacy and discerning between residuals of different models, especially ARMA processes. This study addresses issues involving testing procedures, for instance, the Ljung–Box test, to select the correct time series model determined in the review. With the improvement in understanding the features of white noise, this work enhances the accuracy of modeling diagnostics toward real forecasting practice, which gives it applied value in time series analysis and signal processing. Full article

(This article belongs to the Special Issue Forecasting and Foresight in Business and Economics in the Turbulent and Uncertain New Normal)

► Show Figures

Figure 1

21 pages, 2196 KiB

Open AccessArticle

Evaluating the Potential of Copulas for Modeling Correlated Scenarios for Hydro, Wind, and Solar Energy

by Anderson M. Iung, Fernando L. Cyrino Oliveira, Andre L. M. Marcato and Guilherme A. A. Pereira

Forecasting 2025, 7(1), 7; https://doi.org/10.3390/forecast7010007 - 30 Jan 2025

Viewed by 826

Abstract

The increasing global adoption of variable renewable energy (VRE) sources has transformed the use of forecasting, scenario planning, and other techniques for managing their inherent generation uncertainty and interdependencies. What were once desirable enhancements are now fundamental requirements. This is more prominent in [...] Read more.

The increasing global adoption of variable renewable energy (VRE) sources has transformed the use of forecasting, scenario planning, and other techniques for managing their inherent generation uncertainty and interdependencies. What were once desirable enhancements are now fundamental requirements. This is more prominent in Brazil, given the large hydro capacity that has been installed. Given the need to understand the interdependencies within variable renewable energy systems, copula-based techniques are receiving increasing consideration. The objective is to explore and model the correlation and complementarity, based on the copula approach, evaluating the potential of this methodology considering a case test composed of hydro, wind, and solar assets. The proposed framework simulated joint scenarios for monthly natural energy (streamflows transformed into energy), wind speed and solar radiation, applied to a small case test, considering historical data from the Brazilian energy system. The results demonstrate that simulated scenarios are validated by their ability to replicate key statistical attributes of the historical record, as well as the interplay and complementarity among hydrology, wind speed, and solar radiation. Full article

(This article belongs to the Special Issue Feature Papers of Forecasting 2024)

► Show Figures

Figure 1

21 pages, 3256 KiB

Open AccessArticle

Assessment of Deep Neural Network Models for Direct and Recursive Multi-Step Prediction of PM10 in Southern Spain

by Javier Gómez-Gómez, Eduardo Gutiérrez de Ravé and Francisco J. Jiménez-Hornero

Forecasting 2025, 7(1), 6; https://doi.org/10.3390/forecast7010006 - 26 Jan 2025

Viewed by 1033

Abstract

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 [...] Read more.

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

(This article belongs to the Section Environmental Forecasting)

► Show Figures

Figure 1

21 pages, 7620 KiB

Open AccessArticle

Methodology Based on BERT (Bidirectional Encoder Representations from Transformers) to Improve Solar Irradiance Prediction of Deep Learning Models Trained with Time Series of Spatiotemporal Meteorological Information

by Llinet Benavides-Cesar, Miguel-Ángel Manso-Callejo and Calimanut-Ionut Cira

Forecasting 2025, 7(1), 5; https://doi.org/10.3390/forecast7010005 - 17 Jan 2025

Viewed by 1143

Abstract

Accurate solar resource forecasting is important because of the inherent variability associated with solar energy and its significant impact on the cost for energy producers. The traditional method applied in solar irradiance forecasting involves two main phases, related to (1) data selection and [...] Read more.

Accurate solar resource forecasting is important because of the inherent variability associated with solar energy and its significant impact on the cost for energy producers. The traditional method applied in solar irradiance forecasting involves two main phases, related to (1) data selection and (2) model selection, training, and evaluation. In this study, we propose a novel end-to-end methodology for solar irradiance forecasting that starts with the search for the data and all of the preprocessing operations involved in obtaining a quality dataset, continuing by imputing missing data with the BERT (Bidirectional Encoder Representations from Transformers) model, and ending with obtaining and evaluating the predicted values. This novel methodology is based on three phases; namely, Phase_1, related to the acquisition and preparation of the data, Phase_2, related to the proposed imputation with a BERT model, and Phase_3, related to the training and prediction with new models based on deep learning. These phases of the proposed methodology can be applied in a disjointed manner, and were used on two public datasets accessible to the scientific community. Each of the proposed phases proved to be valuable for the workflow, and the application of the novel method delivered increases in performance of up to 3 percentage points (3%) when compared to the traditional approach. Full article

► Show Figures

Figure 1

8 pages, 2115 KiB

Open AccessArticle

Testing for Bias in Forecasts for Independent Multinomial Outcomes

by Philip Hans Franses and Richard Paap

Forecasting 2025, 7(1), 4; https://doi.org/10.3390/forecast7010004 - 13 Jan 2025

Viewed by 562

Abstract

This paper deals with a test on forecast bias in predicting independent multinomial outcomes where the predictions are probabilities. The new Likelihood Ratio (and Wald) test extends the familiar Mincer Zarnowitz regression to a multinomial logit model instead of a linear regression. The [...] Read more.

This paper deals with a test on forecast bias in predicting independent multinomial outcomes where the predictions are probabilities. The new Likelihood Ratio (and Wald) test extends the familiar Mincer Zarnowitz regression to a multinomial logit model instead of a linear regression. The test is evaluated using various simulation experiments, which indicate that the size and power properties are good, even for small sample sizes, in the sense that the size is close to the used 5% level, and the power quickly reaches 1. We implement the test in an empirical setting on brand choice by individual households. Full article

(This article belongs to the Special Issue Feature Papers of Forecasting 2024)

► Show Figures

Figure 1

27 pages, 2690 KiB

Open AccessArticle

The MECOVMA Framework: Implementing Machine Learning Under Macroeconomic Volatility for Marketing Predictions

by Manuel Muth

Forecasting 2025, 7(1), 3; https://doi.org/10.3390/forecast7010003 - 7 Jan 2025

Viewed by 1186

Abstract

The methodological framework introduced in this paper, MECOVMA, is a novel framework that guides the application of Machine Learning specifically for marketing predictions within volatile macroeconomic environments. MECOVMA has been developed in response to the identified gaps displayed by existing frameworks—when it comes [...] Read more.

The methodological framework introduced in this paper, MECOVMA, is a novel framework that guides the application of Machine Learning specifically for marketing predictions within volatile macroeconomic environments. MECOVMA has been developed in response to the identified gaps displayed by existing frameworks—when it comes to consolidation, relevance, interdisciplinarity, and individuality—and in light of the polycrises occurring in the current decade. The methodology to develop MECOVMA comprises three phases: firstly, synthesizing existing frameworks based on their thematic relevance to select MECOVMA’s process steps; secondly, integrating the evidence provided by a systematic literature review to design the content of these process steps; and thirdly, using an expert evaluation, structured through a qualitative content analysis, to validate MECOVMA’s applicability. This leads to the final framework with four overarching P_MECOVMA process steps, guiding the Machine Learning application process in this context with specific tasks. These include, for example, the processing of multidimensional data inputs, complexity reduction in a dynamic environment, and training methods adapted to particular macro-conditions. In addition, features are provided on how Machine Learning can be put into marketing practice, incorporating both narrower statistical- and broader business-oriented evaluations, and iterative feedback loops to mitigate limitations. Full article

(This article belongs to the Special Issue Forecasting and Foresight in Business and Economics in the Turbulent and Uncertain New Normal)

► Show Figures

Figure 1

28 pages, 1589 KiB

Open AccessArticle

Temporal Attention-Enhanced Stacking Networks: Revolutionizing Multi-Step Bitcoin Forecasting

by Phumudzo Lloyd Seabe, Edson Pindza, Claude Rodrigue Bambe Moutsinga and Maggie Aphane

Forecasting 2025, 7(1), 2; https://doi.org/10.3390/forecast7010002 - 30 Dec 2024

Viewed by 1291

Abstract

This study presents a novel methodology for multi-step Bitcoin (BTC) price prediction by combining advanced stacking-based architectures with temporal attention mechanisms. The proposed Temporal Attention-Enhanced Stacking Network (TAESN) integrates the complementary strengths of diverse machine learning algorithms while emphasizing critical temporal features, leading [...] Read more.

This study presents a novel methodology for multi-step Bitcoin (BTC) price prediction by combining advanced stacking-based architectures with temporal attention mechanisms. The proposed Temporal Attention-Enhanced Stacking Network (TAESN) integrates the complementary strengths of diverse machine learning algorithms while emphasizing critical temporal features, leading to substantial improvements in forecasting accuracy over traditional methods. Comprehensive experimentation and robust evaluation validate the superior performance of TAESN across various BTC prediction horizons. Additionally, the model not only demonstrates enhanced predictive accuracy but also offers interpretable insights into the temporal dynamics underlying cryptocurrency markets, contributing to both practical forecasting applications and theoretical understanding of market behavior. Full article

► Show Figures

Figure 1

20 pages, 6292 KiB

Open AccessArticle

Comparative Analysis of Supervised Learning Techniques for Forecasting PV Current in South Africa

by Ely Ondo Ekogha and Pius A. Owolawi

Forecasting 2025, 7(1), 1; https://doi.org/10.3390/forecast7010001 - 26 Dec 2024

Viewed by 1079

Abstract

The fluctuations in solar irradiance and temperature throughout the year require an accurate methodology for forecasting the generated current of a PV system based on its specifications. The optimal technique must effectively manage rapid weather fluctuations while maintaining high accuracy in forecasting the [...] Read more.

The fluctuations in solar irradiance and temperature throughout the year require an accurate methodology for forecasting the generated current of a PV system based on its specifications. The optimal technique must effectively manage rapid weather fluctuations while maintaining high accuracy in forecasting the performance of a PV panel. This work presents a comparative examination of supervised learning algorithms optimized with particle swarm optimization for estimating photovoltaic output current. The empirical formula’s measured currents are compared with outputs from various neural networks techniques, including feedforward neural networks (FFNNs), the general regression network known as GRNN, cascade forward neural networks also known as CFNNs, and adaptive fuzzy inference systems known as ANFISs, all optimized for enhanced accuracy using the particle swarm optimization (PSO) method. The ground data utilized for these models comprises hourly irradiations and temperatures from 2023, sourced from several places in South Africa. The accuracy levels indicated by statistical error margins from the root mean square error (RMSE), mean bias error (MBE), and mean absolute percentage error (MAPE) imply a universal enhancement in the algorithms’ precision upon optimization. Full article

(This article belongs to the Section Power and Energy Forecasting)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Forecasting, Volume 7, Issue 1 (March 2025) – 14 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI