Hybrid systems, which combine statistical and machine learning (ML) techniques using residual (error forecasting) modeling, have been highlighted in the literature due to their accuracy and ability to forecast time series with different characteristics. In these architectures, a crucial task is the proper modeling of the residuals since they may present random fluctuations, complex nonlinear patterns, and heteroscedastic behavior. Hence, the selection, specification, and training of one ML model to forecast the residuals are costly and challenging tasks since issues, such as underfitting, overfitting, and misspecification, can lead to a system with low accuracy or even deteriorate the linear forecast of the time series. This article proposes a hybrid system, named dynamic residual forecasting (DReF), that employs a modified dynamic selection (DS) algorithm to decide: the most suitable ML model to forecast a pattern of the residual series and if it is a promising candidate to increase the accuracy of the time series forecast from the linear combination. Thus, the DReF aims to reduce the uncertainty of the ML model selection and avoid the deterioration of the time series forecast. Furthermore, the proposed system searches for the most suitable parameters of the DS algorithm for each data set. In this article, the proposed method uses a pool of five ML models widely adopted in the literature: multilayer perceptron, support vector regression, radial basis function, long short-term memory, and convolutional neural network. An experimental evaluation was conducted using ten well-known time series. The results show that the DReF obtains superior results for the majority of the data sets compared with single and hybrid models of the literature.

This work presents a novel Automated Machine Learning (AutoML) approach for Real-Time Fault Detection and Diagnosis (RT-FDD). The approach’s particular characteristics are: it uses only data that are commonly available in industrial automation systems; it automates all ML processes without human intervention; a non-ML expert can deploy it; and it considers the behavior of cyclic sequential machines, combining discrete timed events and continuous variables as features. The capacity for fault detection is analyzed in two case studies, using data from a 3D machine simulation system with faulty and non-faulty conditions. The enhancement of the RT-FDD performance when the proposed approach is applied is proved with the Feature Importance, Confusion Matrix, and F1 Score analysis, reaching mean values of 85% and 100% in each case study. Finally, considering that faults are rare events, the sensitivity of the models to the number of faulty samples is analyzed.

Solar irradiance forecasting has been an essential topic in renewable energy generation. Forecasting is an important task because it can improve the planning and operation of photovoltaic systems, resulting in economic advantages. Traditionally, single models are employed in this task. However, issues regarding the selection of an inappropriate model, misspecification, or the presence of random fluctuations in the solar irradiance series can result in this approach underperforming. This paper proposes a heterogeneous ensemble dynamic selection model, named HetDS, to forecast solar irradiance. For each unseen test pattern, HetDS chooses the most suitable forecasting model based on a pool of seven well-known literature methods: ARIMA, support vector regression (SVR), multilayer perceptron neural network (MLP), extreme learning machine (ELM), deep belief network (DBN), random forest (RF), and gradient boosting (GB). The experimental evaluation was performed with four data sets of hourly solar irradiance measurements in Brazil. The proposed model attained an overall accuracy that is superior to the single models in terms of five well-known error metrics.

The usage of smart grids is growing steadily around the world. This technology has been proposed as a promising solution to enhance energy efficiency and improve consumption management in buildings. Such benefits are usually associated with the ability of accurately forecasting energy demand. However, the energy consumption series forecasting is a challenge for statistical linear and Machine Learning (ML) techniques due to temporal fluctuations and the presence of linear and non-linear patterns. Traditional statistical techniques are able to model linear patterns, while obtaining poor results in forecasting the non-linear component of the time series. ML techniques are data-driven and can model non-linear patterns, but their feature selection process and parameter specification are a complex task. This paper proposes an Evolutionary Hybrid System (EvoHyS) which combines statistical and ML techniques through error series modeling. EvoHyS is composed of three phases: (i) forecast of the linear and seasonal component of the time series using a Seasonal Autoregressive Integrated Moving Average (SARIMA) model, (ii) forecast of the error series using an ML technique, and (iii) combination of both linear and non-linear forecasts from (i) and (ii) using a a secondary ML model. EvoHyS employs a Genetic Algorithm (GA) for feature selection and hyperparameter optimization in phases (ii) and (iii) aiming to improve its accuracy. An experimental evaluation was conducted using consumption energy data of a smart grid in a one-step-ahead scenario. The proposed hybrid system reaches statistically significant improvements when compared to other statistical, hybrid, and ML approaches from the literature utilizing well known metrics, such as Mean Squared Error (MSE).