Dynamic Thermal Rating (DTR) enhances grid flexibility by adapting line capabilities to weather conditions. For this purpose, DTR-based technologies require reliable and continuous measurement of the conductor temperature along the line route, which could hinder their wide-scale deployment due to the prohibitively high number of required sensors. Existing machine learning-based DTR methods infer conductor temperature from weather variables avoiding using complex and expensive measurement techniques, but their estimation accuracy greatly relies on the availability of a comprehensive set of measured data. To face these issues, this paper proposes the usage of transfer learning, a data-driven technique allowing the reduction of the number of sensors by transferring knowledge from a single calibrated source sensor to many target sensors. To the best of the author's knowledge, at the time of writing, the proposed approach is the first application of Transfer Learning in the domain of DTR which is validated on real transmission lines data. Experimental results from several real transmission lines equipped with self-organizing sensors-based DTR architecture show that transfer learning enhances the conductor temperature estimation reliability and accuracy of machine learning-based DTR techniques, suggesting the potential for practical applications, and reducing costs without losing accuracy for practitioners and system operators.@en

The limitation of transmission lines thermal capacity plays a crucial role in the safety and reliability of power systems. Dynamic thermal line rating approaches aim to estimate the transmission line’s temperature and assess its compliance with the limitations above. Existing physics-based standards estimate the temperature based on environment and line conditions measured by several sensors. This manuscript shows that estimation accuracy can be improved by adopting a data-driven Digital Twin approach. The proposed method exploits machine learning by learning the input–output relation between the physical sensors data and the actual conductor temperature, serving as a digital equivalent to physics-based standards. An experimental assessment on real data, comparing the proposed approach with the IEEE 738 standard, shows a reduction of 60% of the Root Mean Squared Error and a decrease in the maximum estimation error from above 10 °C to below 7 °C. These preliminary results suggest that the Digital Twin provides more accurate and robust estimations, serving as a complement, or a potential alternative, to traditional methods.@en

Most multivariate forecasting methods in the literature are restricted to vector time series of low dimension, linear methods and short horizons. Big data revolution is instead shifting the focus to problems (e.g., issued from the IoT technology) characterized by very large dimension, nonlinearity and long forecasting horizons. This paper discusses and compares a set of state-of-the-art methods which could be promising in tackling such challenges. Also, it proposes DFML, a machine-learning version of the dynamic factor model, a successful forecasting methodology well-known in econometrics. The DFML strategy is based on a out-of-sample selection of the nonlinear forecaster, the number of latent components and the multi-step-ahead strategy. We will discuss both a batch and an incremental version of DFML, and we will show that it can consistently outperform state-of-the-art methods in a number of Synthetic and real forecasting tasks.@en

State-of-the-art multivariate forecasting methods are restricted to low dimensional tasks, linear dependencies and short horizons. The technological advances (notably the Big data revolution) are instead shifting the focus to problems characterized by a large number of variables, non-linear dependencies and long forecasting horizons. In the last few years, the majority of the best performing techniques for multivariate forecasting have been based on deep-learning models. However, such models are characterized by high requirements in terms of data availability and computational resources and suffer from a lack of interpretability. To cope with the limitations of these methods, we propose an extension to the DFML framework, a hybrid forecasting technique inspired by the Dynamic Factor Model (DFM) approach, a successful forecasting methodology in econometrics. This extension improves the capabilities of the DFM approach, by implementing and assessing both linear and non-linear factor estimation techniques as well as model-driven and data-driven factor forecasting techniques. We assess several method integrations within the DFML, and we show that the proposed technique provides competitive results both in terms of forecasting accuracy and computational efficiency on multiple very large-scale (>102 variables and > 103 samples) real forecasting tasks.@en

State-of-the-art multivariate forecasting methods are restricted to low dimensional tasks, linear dependencies and short horizons. The technological advances (notably the Big data revolution) are instead shifting the focus to problems characterized by a large number of variables, non-linear dependencies and long forecasting horizons. In the last few years, the majority of the best performing techniques for multivariate forecasting have been based on deep-learning models. However, such models are characterized by high requirements in terms of data availability and computational resources and suffer from a lack of interpretability. To cope with the limitations of these methods, we propose an extension to the DFML framework, a hybrid forecasting technique inspired by the Dynamic Factor Model (DFM) approach, a successful forecasting methodology in econometrics. This extension improves the capabilities of the DFM approach, by implementing and assessing both linear and non-linear factor estimation techniques as well as model-driven and data-driven factor forecasting techniques. We assess several method integrations within the DFML, and we show that the proposed technique provides competitive results both in terms of forecasting accuracy and computational efficiency on multiple very large-scale (>102 variables and > 103 samples) real forecasting tasks.@en