Unexpected large power surges will cause instantaneous grid shock, and thus emergency control plans must be implemented to prevent the system from collapsing. In this paper, by the aid of reinforcement learning (RL), novel model-free control (MFC)-based emergency control schemes are presented. Firstly, multi-Q-learning-based emergency plans are designed for limited emergency scenarios by using offline-training-online approximation methods. To solve the more general multi-scenario emergency control problem, a deep deterministic policy gradient (DDPG) algorithm is adopted to learn near-optimal solutions. With the aid of deep Q network, DDPG-based strategies have better generalization abilities for unknown and untrained emergency scenarios, and thus are suitable for multi-scenario learning. Through simulations using benchmark systems, the proposed schemes are proven to achieve satisfactory performances.

With the increase of cyberhacking activities, cyber attacks become urgent problems to system security. In this paper, cyber attacks on load frequency control (LFC) is studied. By unifying attack and detection, detection scheme considering specific attack strategies is presented. As for attack scheme design, four attack strategies are systematically analyzed with respect to their mechanism and influence on LFC performance, so that the most effective one is selected as the adopted attack scheme from the viewpoint of hackers. As for attack detection, a novel attack detection approach is proposed by analyzing differences between dynamic features of variables. Multilayer percepton classifier-based approach is used to extract the differences of area control error under attack and in normal situation, thus distinguishing compromised signals from normal ones. Simulation results show the effectiveness of the proposed detection approach.

With the advancement of communication technologies and the development of the smart grid, today's physical power systems present an ever-growing dependency on cyber resources. It increases cyber vulnerabilities, causing safety and system stability concerns. In this article, a data-driven resilient automatic generation control (AGC) scheme is proposed under a false data injection attack (FDIA). The key idea is to identify the relationship between AGC signals and system operational conditions. This is achieved by the proposed regression-based FDIA signal predictions, including sequence-to-point prediction and the long short-term memory network-based prediction. It allows us to reconstruct the AGC control signals without being affected by FDIAs and to attenuate attacks in the closed control loop, thus alleviating the impact of FDIA on system performance. Numerical results carried out on the benchmark systems validate the effectiveness of the proposed method.

Power system state estimation (PSSE) is the foundation of energy management system applications. Hence, operators impose stringent requirements on PSSE data integrity. False data injection attacks (FDIAs) can cause risks to PSSE data-driven operations and demand mitigation. In this article, we present a two-step FDIA detector design. In step one, we study a novel stealthy attack policy by simultaneously considering the attacker’s cost reduction and damage production. In step two, with the aid of a deep autoencoding Gaussian mixture model (DAGMM), we design an unsupervised detection scheme to detect the stealthy attack. The DAGMM-based detector can meet the requirement of rapidity, unsupervisedness, and data imbalance tolerance. Eventually, we simulate and validate the stealthy attack policy and the corresponding detector using the benchmark IEEE 39-bus and 118-bus systems.

In this paper, optimal attack schemes against load frequency control (LFC) are studied by considering coordinated attack. By attacking sensor measurement (load) simultaneously, the attacker disrupts the normal operation of LFC, thus causing excess system frequency/generation excursions. From the perspective of the attacker, LFC system information availability is essential to the attack scheme design. In this paper, two scenarios where LFC system information is and is not available to the attacker are considered, and optimal attack schemes are studied for these two scenarios respectively. The optimal attack scheme design is modelled by an optimization problem with different objectives (attack goals): 1) maximization of frequency/ generation disruption, and 2) least-effort attack (minimization of attack cost). In consideration of counterattack, a threshold based detection method is used to detect the optimal attack schemes. Two case studies, corresponding to these two scenarios, are simulated; and the results show that attack performances vary with different attack goals, and the detection approach can screen out the compromised signals.

Latency Attacks become emerging new types of cyber attacks with widely applied wireless wide-area network and internet of things (IoTs) technologies. The power system can suffer from several even tens of seconds of malicious time delay instead of normal latency of mere several milliseconds. Consequently, this exorbitant time delay or latency attack will significantly influence the system dynamics and stability. In this paper, from the perspective of parameter tuning, we study how to enhance the system redundancy of a secondary frequency control system with a high-order complex power system model under latency attacks. The tuning aims to achieve the maximal stability region under latency attacks and is performed with the aid of exhaustive and heuristic search methods. By testing the tuning method using a more practical and detailed power system model, it shows that the stability of the tuned system is greatly enhanced under latency attacks.