国家自然科学基金青年基金项目 (61903333); 浙江省“钱江人才”特殊急需类项目 (QJD1902010)
College of Information Engineering,Zhejiang University of Technology
成功地检测隐匿虚假数据入侵（False Data Injection, FDI）攻击是确保电力系统安全运行的关键. 然而,大多数工作通过建立FDI攻击模型来模拟真实的入侵行为,所得到的模拟数据往往与真实数据存在一定的差异,导致基于机器学习的检测方法出现较差的学习效果. 为此,针对源域中模拟样本数据量大而目标域中真实样本标记少的特点,提出了基于深度信念网络(DBN)和迁移学习的检测算法, DBN中的受限玻尔兹曼机(Restrict Boltzmann Machine, RBM)能对目标域大量无标签样本进行特征自学习,而基于模型的迁移学习方法克服了数据之间的差异性,同时解决了有标签真实样本稀缺的问题. 最后,在IEEE 14-bus电力系统模型上验证了所提方法的优点和有效性.
Successful detection of False Data Injection (FDI) attacks is essential for ensuring secure power grids operation. However, most work simulates real intrusion behaviors by establishing FDI attack models, and the simulated data obtained is often different from the real data, resulting in poor learning effects based on machine learning detection methods. Motivated by this fact, considering the large amount of simulated sample data in the source domain and a small number of labeled real samples in the target domain, a detection algorithm based on Deep Belief Network (DBN) and transfer learning is proposed. The Restrict Boltzmann Machine (RBM) in DBN can automatically extract features from a large number of unlabeled samples in the target domain, and the model-based transfer learning method overcomes the differences between data and solves the problem of the scarcity of labeled real samples. Finally,the IEEE 14-Bus power system is employed to show the advantages and effectiveness of the proposed method.