Forecasting

21 pages, 2192 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 317

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)

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 521

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 571

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 311

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 529

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 615

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 643

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) – 7 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI