Linaro Daniele, Bizzarri Federico, Del Giudice Davide, Pisani Cosimo, Giannuzzi Giorgio M, Grillo Samuele, Brambilla Angelo M
DEIB, Politecnico di Milano, P.zza Leonardo da Vinci 32, Milano, 20133, Italy.
ARCES, University of Bologna, Bologna, 41026, Italy.
Nat Commun. 2023 Jul 24;14(1):4440. doi: 10.1038/s41467-023-40192-2.
Inertia is a measure of a power system's capability to counteract frequency disturbances: in conventional power networks, inertia is approximately constant over time, which contributes to network stability. However, as the share of renewable energy sources increases, the inertia associated to synchronous generators declines, which may pose a threat to the overall stability. Reliably estimating the inertia of power systems dominated by inverted-connected sources has therefore become of paramount importance. We develop a framework for the continuous estimation of the inertia in an electric power system, exploiting state-of-the-art artificial intelligence techniques. We perform an in-depth investigation based on power spectra analysis and input-output correlations to explain how the artificial neural network operates in this specific realm, thus shedding light on the input features necessary for proper neural-network training. We validate our approach on a heterogeneous power network comprising synchronous generators, static compensators and converter-interfaced generation: our results highlight how different devices are characterized by distinct spectral footprints - a feature that must be taken into account by transmission system operators when performing online network stability analyses.
在传统电网中，惯性随时间大致保持恒定，这有助于电网稳定。然而，随着可再生能源份额的增加，与同步发电机相关的惯性下降，这可能对整体稳定性构成威胁。因此，可靠估计以逆变器连接源为主导的电力系统的惯性变得至关重要。我们利用最先进的人工智能技术，开发了一个用于连续估计电力系统惯性的框架。我们基于功率谱分析和输入输出相关性进行了深入研究，以解释人工神经网络在这个特定领域的运行方式，从而阐明神经网络正确训练所需的输入特征。我们在一个包含同步发电机、静止补偿器和换流器接口发电的异构电网中验证了我们的方法：我们的结果突出了不同设备具有不同的频谱特征——输电系统运营商在进行在线电网稳定性分析时必须考虑这一特征。
