Search for: All records

In a power system, when the participation factors of generators are computed to rank their participations into an oscillatory mode, a model-based approach is conventionally used on the linearized system model by means of the corresponding right and left eigenvectors. This paper proposes a new approach for estimating participation factors directly from measurement data on generator responses under selected disturbances. The approach computes extended participation factors that coincide with accurate model-based participation factors when the measured responses satisfy an ideally symmetric condition. This paper relaxes this symmetric condition with the original measurement space by identifying and utilizing a coordinate transformation to a new space optimally recovering the symmetry. Thus, the optimal estimates of participation factors solely from measurements are achieved, and the accuracy and influencing factors are discussed. The proposed approach is first demonstrated in detail on a two-area system and then tested on an NPCC 48-machine power system. The penetration of inverter-based resources is also considered. 

Deep reinforcement learning (DRL) holds significant promise for managing voltage control challenges in simulated power grid environments. However, its real-world application in power system operations remains underexplored. This study rigorously evaluates DRL’s performance and limitations within actual operational contexts by utilizing detailed experiments across the IEEE 14-bus system, Illinois 200-bus system, and the ISO New England node-breaker model. Our analysis critically assesses DRL’s effectiveness for grid control from a system operator's perspective, identifying specific performance bottlenecks. The findings provide actionable insights that highlight the necessity of advancing AI technologies to effectively address the growing complexities of modern power systems. This research underscores the vital role of DRL in enhancing grid management and reliability. 

Abstract Deep Reinforcement Learning (DRL) has shown promise for voltage control in power systems due to its speed and model‐free nature. However, learning optimal control policies through trial and error on a real grid is infeasible due to the mission‐critical nature of power systems. Instead, DRL agents are typically trained on a simulator, which may not accurately represent the real grid. This discrepancy can lead to suboptimal control policies and raises concerns for power system operators. In this paper, we revisit the problem of RL‐based voltage control and investigate how model inaccuracies affect the performance of the DRL agent. Extensive numerical experiments are conducted to quantify the impact of model inaccuracies on learning outcomes. Specifically, techniques that enable the DRL agent are focused on learning robust policies that can still perform well in the presence of model errors. Furthermore, the impact of the agent's decisions on the overall system loss are analyzed to provide additional insight into the control problem. This work aims to address the concerns of power system operators and make DRL‐based voltage control more practical and reliable. 

Ensuring the stability of power systems is gaining more attention today than ever before due to the rapid growth of uncertainties in load and increased renewable energy penetration. Lately, wide-area measurement system (WAMS)-based centralized controlling techniques are offering flexibility and more robust control to keep the system stable. WAMS-based controlling techniques, however, face pressing challenges of irregular delays in long-distance communication channels and subsequent responses of equipment to control actions. This paper presents an innovative control strategy for damping down low-frequency oscillations in transmission systems. The method uses a reinforcement learning technique to overcome the challenges of communication delays and other non-linearity in wide-area damping control. It models the traditional problem of oscillation damping control as a novel faster exploration-based deep deterministic policy gradient (DDPG-S). An effective reward function is designed to capture necessary features of oscillations enabling timely damping of such oscillations, even under various kinds of uncertainties. A detailed analysis and a systematically designed numerical validation are presented to prove feasibility, scalability, interpretability, and comparative performance of the modelled low-frequency oscillation damping controller. The benefit of the technique is that stability is ensured even when uncertainties of load and generation are on the rise.