Search

We propose a generative adversarial network (GAN) based deep learning method that serves the dual role of both identification and mitigation of cyber-attacks in wide-area damping control loops of power systems. Two specific types of attacks considered are false data injection and denial-of-service (DoS). Unlike existing methods, which are either model-based or model-free and yet require two separate learning modules for detection and mitigation leading to longer response times before clearing an attack, our deep learner incorporate both goals within the same integrated framework. A Long Short-Term Memory (LSTM) encoder-decoder based GAN is proposed that captures the temporal dynamics of the power system significantly more accurately than fully-connected GANs, thereby providing better accuracy and faster response for both goals. The method is validated using the IEEE 68-bus power system model., Comment: AAAI 2023 workshop

We study how high charging rate demands from electric vehicles (EVs) in a power distribution grid may collectively cause its dynamic instability, and, accordingly, how a price incentivization strategy can be used to steer customers to settle for lesser charging rate demands so that these instabilities can be avoided. We pose the problem as a joint optimization and optimal control formulation. The optimization determines the optimal charging setpoints for EVs to minimize the $\mathcal{H}_2$-norm of the transfer function of the grid model, while the optimal control simultaneously develops a linear quadratic regulator (LQR) based state-feedback control signal for the battery-currents of those EVs to jointly minimize the risk of grid instability. A subsequent algorithm is developed to determine how much customers may be willing to sacrifice their intended charging rate demands in return for financial incentives. Results are derived for both unidirectional and bidirectional charging, and validated using numerical simulations of multiple EV charging stations in the IEEE 33-bus power distribution model.

We study the equilibrium-independent (EI) passivity of a nonlinear power system composed of two-axis generator models. The model of our interest consists of a feedback inter-connection of linear and nonlinear subsystems, called mechanical and electromagnetic subsystems. We mathematically prove the following three facts by analyzing the nonlinear electromagnetic subsystem. First, a lossless transmission network is necessary for the EI passivity of the electromagnetic subsystem. Second, the convexity of a strain energy function characterizes the largest set of equilibria over which the electromagnetic subsystem is EI passive. Finally, we prove that the strain energy function for the network of the two-axis generator models is convex if and only if its flux linkage dynamics is stable, and the strain energy function for the network of the classical generator models derived by singular perturbation approximation of the flux linkage dynamics is convex. Numerical simulation of the IEEE 9-bus power system model demonstrates the practical implications of the various mathematical results. In particular, we validate that the convex domain of the strain energy function over which the electromagnetic subsystem is EI passive is almost identical to the set of all stable equilibria. This result is also generalized to lossy power systems based on our finding that the convexity of the strain energy function is equivalent to the positive semidefiniteness of a synchronizing torque coefficient matrix.

We develop data-driven reinforcement learning (RL) control designs for input-affine nonlinear systems. We use Carleman linearization to express the state-space representation of the nonlinear dynamical model in the Carleman space, and develop a real-time algorithm that can learn nonlinear state-feedback controllers using state and input measurements in the infinite-dimensional Carleman space. Thereafter, we study the practicality of having a finite-order truncation of the control signal, followed by its closed-loop stability analysis. Finally, we develop two additional designs that can learn structured as well as sparse representations of the RL-based nonlinear controller, and provide theoretical conditions for ensuring their closed-loop stability. We present numerical examples to show how our proposed method generates closed-loop responses that are close to the optimal performance of the nonlinear plant. We also compare our designs to other data-driven nonlinear RL control methods such as those based on neural networks, and illustrate their relative advantages and drawbacks., Comment: 18 pages, extended version, preprint version

We develop investment approaches to secure electric power systems against load attacks where a malicious intruder (the attacker) covertly changes reactive power setpoints of loads to push the grid towards voltage instability while the system operator (the defender) employs reactive power compensation (RPC) to prevent instability. Extending our previously reported Stackelberg game formulation for this problem, we develop a robust-defense sequential algorithm and a novel genetic algorithm that provides scalability to large-scale power system models. The proposed methods are validated using IEEE prototype power system models with time-varying load uncertainties, demonstrating that reliable and robust defense is feasible unless the operator's RPC investment resources are severely limited relative to the attacker's resources., Comment: 6 pages, 6 figures, accepted by IEEE CDC 2023

Achieving distributed reinforcement learning (RL) for large-scale cooperative multi-agent systems (MASs) is challenging because: (i) each agent has access to only limited information; (ii) issues on convergence or computational complexity emerge due to the curse of dimensionality. In this paper, we propose a general computationally efficient distributed framework for cooperative multi-agent reinforcement learning (MARL) by utilizing the structures of graphs involved in this problem. We introduce three coupling graphs describing three types of inter-agent couplings in MARL, namely, the state graph, the observation graph and the reward graph. By further considering a communication graph, we propose two distributed RL approaches based on local value-functions derived from the coupling graphs. The first approach is able to reduce sample complexity significantly under specific conditions on the aforementioned four graphs. The second approach provides an approximate solution and can be efficient even for problems with dense coupling graphs. Here there is a trade-off between minimizing the approximation error and reducing the computational complexity. Simulations show that our RL algorithms have a significantly improved scalability to large-scale MASs compared with centralized and consensus-based distributed RL algorithms., Comment: This paper has been accepted by IEEE Transactions on Automatic Control as a full paper and published online. Different from the published paper, the arxiv version contains more results. Moreover, we will continuously update the arxiv version if we find any typos in the published paper. So we suggest you to read this arxiv paper instead of the published one. Thank you for your interest in our work

Existing distributed cooperative multi-agent reinforcement learning (MARL) frameworks usually assume undirected coordination graphs and communication graphs while estimating a global reward via consensus algorithms for policy evaluation. Such a framework may induce expensive communication costs and exhibit poor scalability due to requirement of global consensus. In this work, we study MARLs with directed coordination graphs, and propose a distributed RL algorithm where the local policy evaluations are based on local value functions. The local value function of each agent is obtained by local communication with its neighbors through a directed learning-induced communication graph, without using any consensus algorithm. A zeroth-order optimization (ZOO) approach based on parameter perturbation is employed to achieve gradient estimation. By comparing with existing ZOO-based RL algorithms, we show that our proposed distributed RL algorithm guarantees high scalability. A distributed resource allocation example is shown to illustrate the effectiveness of our algorithm.

We propose a novel hierarchical frequency and voltage control design for multi-area power system integrated with inverter-based resources (IBRs). The design is based on the idea of prioritizing the use of IBRs over conventional generator-based control in compensating for sudden and unpredicted changes in loads and generations, and thereby mitigate any undesired dynamics in the frequency or the voltage by exploiting their fast actuation time constants. A new sequential optimization problem, referred to as Area Prioritized Power Flow (APPF), is formulated to model this prioritization. It is shown that compared to conventional power flow APPF not only leads to a fairer balance between the dispatch of active and reactive power from the IBRs and the synchronous generators, but also limits the impact of any contingency from spreading out beyond its respective control area, thereby guaranteeing a better collective dynamic performance of the grid. This improvement, however, comes at the cost of adding an extra layer of communication needed for executing APPF in a hierarchical way. Results are validated using simulations of a 9-machine, 6-IBR, 33-bus, 3-area power system model, illustrating how APPF can mitigate a disturbance faster and more efficiently by prioritizing the use of local area-resources.