The intermittent and uncertain nature of wind places a premium on accurate wind power forecasting for the reliable and efficient operation of power grids with large-scale wind power penetration. Herein, six-month-ahead wind power forecasting models were developed using tree-based learning algorithms. Three models were developed to investigate the impact of input data on forecasting accuracy. The first model was trained with the average and standard deviation of wind speed values measured at a height of 40 m with a 10-min sampling time. To evaluate the impact of sampling time on model performance, a second model was trained with wind speed values measured at a height of 40 m with 1-h, 12-h, and 24-h sampling times. To assess the effect of measuring height on model accuracy, the third model was trained with wind speed values measured at 40 m extrapolated from values measured at heights of 30 m and 10 m. Experiments revealed that using longer time intervals and height extrapolation leads to considerable accuracy degradation in forecasted models. Finally, to study the generalization ability of the forecasted models, they were tested against wind data measured at heights and locations different from what the models had been trained with. Simulation results substantiated that tree-based learning algorithms can be successfully adopted not only for long-term wind power forecasting, but for potential wind power forecasting at different heights and geographical locations.

As power systems are gradually evolving into more efficient and intelligent cyber–physical energy systems with the large-scale penetration of renewable energies and information technology, they become increasingly reliant upon more accurate and complex forecasting. The accuracy and generalizability of the forecasting rest, to a great extent, upon the data quality, which is very susceptible to cyberattacks. False data injection (FDI) attacks constitute a class of cyberattacks that could maliciously alter a large portion of supposedly protected data, which may not be easily detected by existing operational practices, thereby deteriorating the forecasting performance causing catastrophic consequences in the power system. This article proposes a novel data-driven FDI attack detection mechanism to automatically detect the intrusions and thus enrich the reliability and resiliency of energy forecasting systems. The proposed mechanism is based on cross-validation, least-squares, and z -score metric providing accurate detections with low computational cost and high scalability without utilizing either system’s models or parameters. The effectiveness of the proposed detector is corroborated through six representative tree-based wind power forecasting models. Experiments indicate that corrupted data injected into input, output, and input–output data is properly located and removed, whereby the accuracy and generalizability of the final forecasts are recovered.

Given the growing installed capacity, wind energy will exert a profound impact on the flexibility of modern energy systems. Wind power forecasting is a practical solution for dealing with the attributed variations and uncertainties, balancing supply and demand, and improving the reliability of the system. To achieve more accurate and generalizable forecast models, comprehensive data sets, supplied by multiple wind farms owing to their spatio-temporal dependencies, are required. In addition, data aggregation/collaboration across many wind farms scattered around a country is difficult, if not impossible, due to complex administrative processes, industry competition, and data privacy and security concerns. This article offers federated learning-based wind energy forecasting as a novel decentralized collaborative modeling method capable of training a single model on data from many wind farms without jeopardizing the privacy or security of data. To this end, rather than sending private data across sites, local model parameters are securely transmitted. A comparison between the proposed private distributed model and non-private centralized and fully private localized models indicates the high performance of the proposed federated learning-based wind power forecasting with 87.96% accuracy. Enjoying the smoothing effect, the higher generalizability of the proposed model with 83.63% accuracy is also substantiated in comparison to localized and centralized approaches while the privacy of the underlying data is preserved.

The transmission congestion issue from the high penetration of renewable energies places a premium on accurate dynamic line rating (DLR) as a short-term solution for the more efficient exploitation of the existing transmission infrastructure and the efficient and reliable operation of the power grids. Even though the DLR methods produce a worthy estimation of ampacity, they need the placement of measurement devices and communication networks along with the precise calibration of the estimators and the installation of sensors on the conductor surface. Herein, as a viable alternative, the DLR forecasting models with respect to historical meteorological data were developed using ensemble learning algorithms. Several cases were designed to explore the resiliency and accuracy of the presented approach for various forecasting horizons. The result of simulations proved that ensemble learning algorithms can be fruitfully used for DLR forecasting, even in the presence of severe cyberattacks. The proposed method yielded an approximate capacity increase of 30% for 400 kV lines between Ghadamgah and Binalood wind farms, which is enough to relieve the congestion issue. Ultimately, the developed models were tested against data that is measured at points different from what the algorithms had been trained with to investigate the generalizability of the predictors. Experiments revealed the generalizability and reliability of the forecasting models for the DLR at various points of the line without the deployment of measurement devices and communication infrastructures.

Uncertainty in renewable energy generation, energy consumption, and electricity prices, as well as transmission congestion, pose a number of problems in modern power grids, necessitating stability on the supply, grid, and demand sides. Grid‐side stability can be achieved by dynamic line rating (DLR) forecasting, which reliably predicts the overall current carrying potential of overhead transmission lines. Long short‐term memory proved beneficiary in this field, owing to its ability to learn highly variable and uncertain data. To empower this network to tackle the non‐stationary nature of meteorological parameters, a novel machine learning (ML) architecture based on Dagging technique is proposed and tested on the data collected from a 400 kV overhead transmission line. Simulation results corroborate that the proposed Dagging‐based stacked LSTM can successfully handle the non‐stationary issue and outperform the decomposition‐based technique, as the state‐of‐the‐art algorithm, for various forecasting horizons. The results confirm the generalizability of models with an application in forecasting DLR over the line without utilizing additional sensors and communication networks. Moreover, the proposed model is compared to several ML architectures, including support vector machines (SVM), random forest (RF), and multi‐layer perceptron (MLP) in a comprehensive benchmark study. The introduced algorithm outperforms MLP by 3.4%, RF by 9.4%, and SVM by 6.7% in terms of average prediction accuracy.

Effective exploitation of overhead transmission lines needs reliable and precise dynamic line rating forecasting. High-accuracy dynamic line rating forecasting, in particular, is an important short-term method for coping with grid congestion, enhancing grid stability, and accommodating high renewable energy penetration. Due to the non-stationarity and stochasticity of the meteorological variables, a single model is often not sufficient to accurately predict the dynamic line rating. Herein, a new stacked bagging boosting ensemble is developed based on multivariate empirical mode decomposition to overcome single models' restrictions and increase the dynamic line rating forecasting performance. The developed ensemble is utilized on the data gathered from a 400 kV aluminum conductor steel-reinforced overhead power line with a length of 32.85 Km between Ghadamgah and Binalood wind farms, located in the northeast of Iran. The simulation results substantiate that the proposed ensemble can capture meteorological variables' non-linear characteristics, yielding more accurate yet to noisy data forecasts than single forecasting models.