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, semitargeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of a wind farm 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 0.81 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.06 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.

翻译：近年来，研究人员提出了多种用于风电功率预测的深度学习模型。这些模型能比传统机器学习算法或物理模型更准确地预测风电场或整个区域的风电功率输出。然而，最新研究表明，深度学习模型常会受到对抗攻击的操纵。由于风电功率预测对现代电力系统的稳定性至关重要，因此保护其免受此类威胁具有重要意义。本研究探究了两种不同预测模型在面对目标性、半目标性和非目标性对抗攻击时的脆弱性。我们考虑了用于预测风电场发电功率的长短期记忆网络（LSTM）以及用于预测德国全境风电功率的卷积神经网络（CNN）。此外，我们提出了总对抗鲁棒性评分（TARS），这是一种用于量化回归模型对目标性和半目标性对抗攻击鲁棒性的评估指标。该指标通过分配0（极易受攻击）到1（强鲁棒性）之间的评分，评估攻击对模型性能的影响以及攻击者目标实现的程度。在我们的实验中，LSTM预测模型具有较强的鲁棒性，在所有研究的对抗攻击中均获得了超过0.81的TARS值。而CNN预测模型在常规训练下仅获得低于0.06的TARS值，因此非常脆弱。然而，通过对抗训练，其鲁棒性得到显著提升，TARS值始终高于0.46。