Bearing in mind European Green Deal assumptions regarding a significant reduction of green house emissions, electricity generation from Renewable Energy Sources (RES) is more and more important nowadays. Besides this, accurate and reliable electricity generation forecasts from RES are needed for capacity planning, scheduling, managing inertia and frequency response during contingency events. The recent three years have proved that Machine Learning (ML) models are a promising solution for forecasting electricity generation from RES. In this review, the 8-step methodology was used to find and analyze 262 relevant research articles from the Scopus database. Statistic analysis based on eight criteria (ML method used, renewable energy source involved, affiliation location, hybrid model proposed, short term prediction, author name, number of citations, and journal title) was shown. The results indicate that (1) Extreme Learning Machine and ensemble methods were the most popular methods used for electricity generation forecasting from RES in the last three years (2020–2022), (2) most of the research was carried out for wind systems, (3) the hybrid models accounted for about a third of the analyzed works, (4) most of the articles concerned short-term models, (5) the most researchers came from China, (6) and the journal which published the most papers in the analyzed field was Energies. Moreover, strengths, weaknesses, opportunities, and threats for the analyzed ML forecasting models were identified and presented in this paper.

Representing and analyzing the complexity of models constructed by data is a difficult and challenging task, hence the need for new, more effective techniques emerges, despite the numerous methodologies recently proposed in this field. In the present paper, the main idea is to systematically create a nested structure, based on a fuzzy cognitive map (FCM), in which each element/concept at a higher map level is decomposed into another FCM that provides a more detailed and precise representation of complex time series data. This nested structure is then optimized by applying evolutionary learning algorithms. Through the application of a dynamic optimization process, the whole nested structure based on FCMs is restructured in order to derive important relationships between map concepts at every nesting level as well as to determine the weights of these relationships on the basis of the available time series. This process allows discovering and describing hidden relationships among important map concepts. The paper proposes the application of the suggested nested approach for time series forecasting as well as for decision-making tasks regarding appliances’ energy consumption prediction.

This article is focused on the issue of learning of Fuzzy Cognitive Maps designed to model and predict time series. The multi-step supervised-learning based-on-gradient methods as well as population-based learning, with the use of real coded genetic algorithms, are described. In this study, a new structure optimization genetic algorithm for fuzzy cognitive maps learning is proposed for automatic construction of FCM applied to time series prediction. The proposed learning methodologies are based on an FCM reconstruction procedure using historical time series. The main contribution of this study is the analysis of the use of FCMs with their learning algorithms based on the multi-step gradient method (MGM) and other population-based methods to predict water demand. The performance of learning algorithms is presented through the analysis of real data of daily water demand and the corresponding prediction. The multivariate analysis of historical water demand data is held for five variables, mean and high temperature, precipitation, wind speed and touristic activity. Simulation results were obtained with the ISEMK (Intelligent Expert System based on Cognitive Maps) software tool. Through the experimental analysis, we demonstrate the usefulness of the new proposed FCM learning algorithm in water demand prediction, by calculating the known prediction errors. The advantage of the optimization genetic algorithm structure is its ability to select the most significant relations between concepts for prediction.

This paper introduced a new ensemble learning approach, based on evolutionary fuzzy cognitive maps (FCMs), artificial neural networks (ANNs), and their hybrid structure (FCM-ANN), for time series prediction. The main aim of time series forecasting is to obtain reasonably accurate forecasts of future data from analyzing records of data. In the paper, we proposed an ensemble-based forecast combination methodology as an alternative approach to forecasting methods for time series prediction. The ensemble learning technique combines various learning algorithms, including SOGA (structure optimization genetic algorithm)-based FCMs, RCGA (real coded genetic algorithm)-based FCMs, efficient and adaptive ANNs architectures, and a hybrid structure of FCM-ANN, recently proposed for time series forecasting. All ensemble algorithms execute according to the one-step prediction regime. The particular forecast combination approach was specifically selected due to the advanced features of each ensemble component, where the findings of this work evinced the effectiveness of this approach, in terms of prediction accuracy, when compared against other well-known, independent forecasting approaches, such as ANNs or FCMs, and the long short-term memory (LSTM) algorithm as well. The suggested ensemble learning approach was applied to three distribution points that compose the natural gas grid of a Greek region. For the evaluation of the proposed approach, a real-time series dataset for natural gas prediction was used. We also provided a detailed discussion on the performance of the individual predictors, the ensemble predictors, and their combination through two well-known ensemble methods (the average and the error-based) that are characterized in the literature as particularly accurate and effective. The prediction results showed the efficacy of the proposed ensemble learning approach, and the comparative analysis demonstrated enough evidence that the approach could be used effectively to conduct forecasting based on multivariate time series.