考虑分布式光伏特性的配电网虚假数据注入攻击

With the advancement of carbon-neutral and new power system construction, numerous information devices are continuously connected to power distribution systems, gradually breaking the original unobservable state of power distribution systems and making them more vulnerable to false data injection attacks (FDIAs). Contrary to most existing research focusing on the unbalanced network, less attention has been paid to the influence of randomness and fluctuation of distributed photovoltaic (PV) to perform FDIAs in the power distribution system. In this article, the failure mechanism of FDIAs and the improved FDIAs method are proposed simultaneously for the distribution system with a high penetration of distributed PV scenarios. Specifically, based on the reactive power optimization process, the randomness and fluctuation of distributed PV are applied to decrease significantly the stealthiness of the FDIAs. Subsequently, an improved FDIA method, based on time-dependent loss conditional generative adversarial networks, is proposed to enhance the stealth and effectiveness of the attack. Finally, numerical results based on the modified IEEE 33 bus test systems demonstrate the effectiveness of the failure mechanism and the improved FDIAs. Research results can facilitate the execution of countermeasures for distribution systems with a high penetration of distributed PV, posing serious and pressing security concerns in power distribution systems with a high penetration of distributed PV scenarios.