Estimating Solar and Wind Power Production Using Computer Vision Deep Learning Techniques on Weather Maps

Bosma, Sebastian B. M.; Nazari, Negar

doi:10.1002/ente.202200289

Cited by 5 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the dimensionality of the input data we used is still comparatively low. In real applications, such as in Bosma and Nazari (2022), various other weather predictions are used besides wind speed forecasts, e.g., predictions for air pressure, air temperature, and air humidity. Such input data gives attackers even more attack possibilities.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Targeted adversarial attacks on wind power forecasts

Heinrich,

Scholz,

Vogt

et al. 2023

Mach Learn

View full text Add to dashboard Cite

In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a long short-term memory (LSTM) network for predicting the power generation of individual wind farms and a convolutional neural network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model’s performance, as well as the extent to which the attacker’s goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.

show abstract

Section: Discussionmentioning

confidence: 99%

“…A new approach for forecasting the generated wind power in large-scale regions was proposed by Bosma and Nazari (2022). In this approach, the problem of wind power forecasting is divided into two distinct subproblems, each of which is solved separately.…”

Section: Appendix a Adversarial Robustness Scoresmentioning

confidence: 99%

Targeted adversarial attacks on wind power forecasts

Heinrich,

Scholz,

Vogt

et al. 2023

Mach Learn

View full text Add to dashboard Cite

show abstract

“…In parallel, the field of computer vision, an integral part of deep learning, has made significant inroads in the energy sector. As elucidated in the studies by Bosma and Nazari, computer vision techniques are being employed to refine the forecasting of regional energy outputs, particularly in the context of renewable energy sources [17]. This approach underscores the multifaceted nature of deep learning applications, extending beyond numerical data analysis to include visual data interpretation, thereby broadening the horizon for more accurate and comprehensive energy forecasting models.…”

Section: State Of the Artmentioning

confidence: 99%

Deep Learning for Wind and Solar Energy Forecasting in Hydrogen Production

Nikulins,

Sudars,

Edelmers

et al. 2024

Energies

View full text Add to dashboard Cite

This research delineates a pivotal advancement in the domain of sustainable energy systems, with a focused emphasis on the integration of renewable energy sources—predominantly wind and solar power—into the hydrogen production paradigm. At the core of this scientific endeavor is the formulation and implementation of a deep-learning-based framework for short-term localized weather forecasting, specifically designed to enhance the efficiency of hydrogen production derived from renewable energy sources. The study presents a comprehensive evaluation of the efficacy of fully connected neural networks (FCNs) and convolutional neural networks (CNNs) within the realm of deep learning, aimed at refining the accuracy of renewable energy forecasts. These methodologies have demonstrated remarkable proficiency in navigating the inherent complexities and variabilities associated with renewable energy systems, thereby significantly improving the reliability and precision of predictions pertaining to energy output. The cornerstone of this investigation is the deployment of an artificial intelligence (AI)-driven weather forecasting system, which meticulously analyzes data procured from 25 distinct weather monitoring stations across Latvia. This system is specifically tailored to deliver short-term (1 h ahead) forecasts, employing a comprehensive sensor fusion approach to accurately predicting wind and solar power outputs. A major finding of this research is the achievement of a mean squared error (MSE) of 1.36 in the forecasting model, underscoring the potential of this approach in optimizing renewable energy utilization for hydrogen production. Furthermore, the paper elucidates the construction of the forecasting model, revealing that the integration of sensor fusion significantly enhances the model’s predictive capabilities by leveraging data from multiple sources to generate a more accurate and robust forecast. The entire codebase developed during this research endeavor has been made available on an open access GIT server.

show abstract

“…[ 21 ] Finally, Bosma and Nazari proposed using computer vision on weather maps to predict power production. [ 22 ]…”

Section: Introductionmentioning

confidence: 99%

“…[21] Finally, Bosma and Nazari proposed using computer vision on weather maps to predict power production. [22] The solar power generation domain produces time series data, characterized by the collection of data points at fixed time intervals. Providing additional information, the time dimension allows analyses to reveal dependencies between variables or, in other words, model historical cause and consequence relations.…”

mentioning

confidence: 99%

Time Series Prediction of Solar Power Generation Using Trend Decomposition

Kavakci,

Cicekdag,

Ertekin

2023

Energy Tech

View full text Add to dashboard Cite

High‐accuracy predictions of future solar power generations are important for monitoring, maintenance, dispatching, and scheduling. The goal of this study is to create a forecasting workflow that increases prediction accuracy independent of the machine learning method and has minimal computational requirements. The proposed trend decomposition method incorporates irradiance and seasonal features as exogenous inputs. In order to extract the linear part of the data, a moving average filter is used. The nonlinear (stable) component of the time series is then calculated by subtracting this linear part from the original data. The stable portion is modeled using several machine learning methods, while the ordinary least squares method is applied to the linear series. By aggregating both results, the final forecast is obtained. The forecasting performances of the machine learning algorithms on unprocessed data are used as baselines for evaluations. Improvements up to 39% in the mean absolute error and up to 31% in the root mean square error metrics are observed compared to the baselines. Experimental results show that the proposed trend decomposition with extrapolation method increases the forecasting performance and generalization capacity of machine learning algorithms.

show abstract

Estimating Solar and Wind Power Production Using Computer Vision Deep Learning Techniques on Weather Maps

Cited by 5 publications

References 24 publications

Targeted adversarial attacks on wind power forecasts

Targeted adversarial attacks on wind power forecasts

Deep Learning for Wind and Solar Energy Forecasting in Hydrogen Production

Time Series Prediction of Solar Power Generation Using Trend Decomposition

Contact Info

Product

Resources

About