The dependence on advanced information and communication technology increases the vulnerability in smart grids under cyber-attacks. Recent research on unobservable false data injection attacks (FDIAs) reveals the high risk of secure system operation, since these attacks can bypass current bad data detection mechanisms. To mitigate this risk, this paper proposes a data-driven learning-based algorithm for detecting unobservable FDIAs in distribution systems. We use autoencoders for efficient dimension reduction and feature extraction of measurement datasets. Further, we integrate the autoencoders into an advanced generative adversarial network (GAN) framework, which successfully detects anomalies under FDIAs by capturing the unconformity between abnormal and secure measurements. Also, considering that the datasets collected from practical power systems are partially labeled due to expensive labeling costs and missing labels, the proposed method only requires a few labeled measurement data in addition to unlabeled data for training. Numerical simulations in three-phase unbalanced IEEE 13-bus and 123-bus distribution systems validate the detection accuracy and efficiency of this method.
This paper develops a model-free volt-VAR optimization (VVO) algorithm via multi-agent deep reinforcement learning (DRL) in unbalanced distribution systems. This method is novel since we cast the VVO problem in distribution networks to an intelligent deep Q-network (DQN) framework, which avoids solving a specific optimization model directly when facing time-varying operating conditions in the systems. We consider statuses/ratios of switchable capacitors, voltage regulators, and smart inverters installed at distributed generators as the action variables of the agents. A delicately designed reward function guides these agents to interact with the distribution system, in the direction of reinforcing voltage regulation and power loss reduction simultaneously. The forward-backward sweep method for radial three-phase distribution systems provides accurate power flow results within a few iterations to the DRL environment. The proposed method realizes the dual goals for VVO. We test this algorithm on the unbalanced IEEE 13-bus and 123-bus systems. Numerical simulations validate the excellent performance of this method in voltage regulation and power loss reduction.
Distribution system state estimation (DSSE), which provides critical information for system monitoring and control, is being challenged by multiple sources of uncertainties such as random meter errors, stochastic power output of distributed generation (DG), and imprecise network parameters. This paper originally proposes a general interval state estimation (ISE) model to simultaneously formulate these uncertainties in unbalanced distribution systems by interval arithmetic. Moreover, this model can accommodate partially available measurements of DG outputs and inaccurate line parameters. Further, a modified Krawczyk-operator (MKO) algorithm is proposed to solve the general ISE model efficiently, and effectively provides the upper and lower bounds of state variables under coordinated impacts of these uncertainties. The proposed algorithm is tested on unbalanced IEEE 13-bus and 123-bus systems. Comparison with various methods including Monte Carlo simulation indicates that the proposed algorithm is many orders of magnitude faster and encloses tighter boundaries of state variables.
Motivated by increasing penetration of distributed generators (DGs) and fast development of micro-phasor measurement units (μPMUs), this paper proposes a novel graph-based faulted line identification algorithm using a limited number of μPMUs in distribution networks. The core of the proposed method is to apply advanced distribution system state estimation (DSSE) techniques integrating μPMU data to the fault location. We propose a distributed DSSE algorithm to efficiently restrict the searching region for the fault source in the feeder between two adjacent μPMUs. Based on the graph model of the feeder in the reduced searching region, we further perform the DSSE in a hierarchical structure and identify the location of the fault source. Also, the proposed approach captures the impact of DGs on distribution system operation and remains robust against high-level noises in measurements. Numerical simulations verify the accuracy and efficiency of the proposed method under various fault scenarios covering multiple fault types and fault impedances.
25 January 2024 in IEEE Transactions on Neural Networks and Learning Systems
Grid emergency voltage control (GEVC) is paramount in electric power systems to improve voltage stability and prevent cascading outages and blackouts in case of contingencies. While most deep reinforcement learning (DRL)-based paradigms perform single agents in a static environment, real-world agents for GEVC are expected to cooperate in a dynamically shifting grid. Moreover, due to high uncertainties from combinatory natures of various contingencies and load consumption, along with the complexity of dynamic grid operation, the data efficiency and control performance of the existing DRL-based methods are challenged. To address these limitations, we propose a multi-agent graph-attention (GATT)-based DRL algorithm for GEVC in multi-area power systems. We develop graph convolutional network (GCN)-based agents for feature representation of the graph-structured voltages to improve the decision accuracy in a data-efficient manner. Furthermore, a cutting-edge attention mechanism concentrates on effective information sharing among multiple agents, synergizing different-sized subnetworks in the grid for cooperative learning. We address several key challenges in the existing DRL-based GEVC approaches, including low scalability and poor stability against high uncertainties. Test results in the IEEE benchmark system verify the advantages of the proposed method over several recent multi-agent DRL-based algorithms.
Due to the vulnerability of civilian global positioning system (GPS) signals, the accuracy of phasor measurement units (PMUs) can be greatly compromised by GPS spoofing attacks (GSAs), which introduce phase shifts into true phase angle measurements. Focusing on simultaneous GSAs for multiple PMU locations, this paper proposes a novel identification and correction algorithm in distribution systems. A sensitivity analysis of state estimation residuals on a single GSA phase angle is firstly implemented. An identification algorithm using a probing technique is proposed to determine the locations of spoofed PMUs and the ranges of GSA phase shifts. Based on the identification results, these GSA phase shifts are determined via an estimation algorithm that minimizes the mismatch between measurements and system states. Further, with the attacked PMU data corrected, the system states are recovered. Simulations in unbalanced IEEE 34-bus and 123-bus distribution systems demonstrates the efficiency and accuracy of the proposed method.