Wind energy represents one of the leading renewable energy sectors and is considered instrumental in the ongoing decarbonization process. Accurate forecasts are essential for a reliable large-scale wind power integration, allowing efficient operation and maintenance, planning of unit commitment, and scheduling by system operators. However, due to non-stationarity, randomness, and intermittency, forecasting wind power is challenging. This work investigates a multi-modal approach for wind power forecasting by considering turbine-level time series collected from SCADA systems and high-resolution Numerical Weather Prediction maps. A neural architecture based on stacked Recurrent Neural Networks is proposed to process and combine different data sources containing spatio-temporal patterns. This architecture allows combining the local information from the turbine’s internal operating conditions with future meteorological data from the surrounding area. Specifically, this work focuses on multi-horizon turbine-level hourly forecasts for an entire wind farm with a lead time of 90 h. This work explores the impact of meteorological variables on different spatial scales, from full grids to cardinal point features, on wind power forecasts. Results show that a subset of features associated with all wind directions, even when spatially distant, can produce more accurate forecasts with respect to full grids and reduce computation times. The proposed model outperforms the linear regression baseline and the XGBoost regressor achieving an average skill score of 25%. Finally, the integration of SCADA data in the training process improved the predictions allowing the multi-modal neural network to model not only the meteorological patterns but also the turbine’s internal behavior.

This paper investigates a use case of robust anomaly detection applied to the scenario of a photovoltaic production factory—namely, Enel Green Power’s 3SUN solar cell production plant in Catania, Italy—by considering a Monte Carlo based pre-processing technique as a valid alternative to other typically used methods. In particular, the proposed method exhibits the following advantages: (i) Outlier replacement, by contrast with traditional methods which are limited to outlier detection only, and (ii) the preservation of temporal locality with respect to the training dataset. After pre-processing, the authors trained an anomaly detection model based on principal component analysis and defined a suitable key performance indicator for each sensor in the production line based on the model errors. In this way, by running the algorithm on unseen data streams, it is possible to isolate anomalous conditions by monitoring the above-mentioned indicators and virtually trigger an alarm when exceeding a reference threshold. The proposed approach was tested on both standard operating conditions and an anomalous scenario. With respect to the considered use case, it successfully anticipated a fault in the equipment with an advance of almost two weeks, but also demonstrated its robustness to false alarms during normal conditions.

Distributed monitoring sensor networks are used in an ever increasing number of applications, particularly with the advent of IoT technologies. This has led to a growing demand for unconventional analytical tools to cope with a large amount of different signals. In this scenario, the modeling of time series in similar groups represents an interesting area especially for feature subset selection (FSS) purposes. Methods based on clustering algorithms are very promising for FSS, but in their original form they are unsuitable to manage the complexity of temporal dynamics in time series. In this paper we propose a clustering approach, based on complex network analysis, for the unsupervised FSS of time series in sensor networks. We used natural visibility graphs to map signal segments in the network domain, then extracted features in the form of node degree sequences of the graphs, and finally computed time series clustering through community detection algorithms. The approach was tested on multivariate signals monitored in a 1 MW cogeneration plant and the results show that it outperforms standard time series clustering in terms of both redundancy reduction and information gain. In addition, the proposed method demonstrated its merit in terms of retention of information content with respect to the original dataset in the analyzed condition monitoring system.