An official website of the United States government
Deep reinforcement learning approaches are becoming appealing for the design of nonlinear controllers for voltage control problems, but the lack of stability guarantees hinders their real-world deployment. This letter constructs a decentralized RL-based controller for inverter-based real-time voltage control in distribution systems. It features two components: a transient control policy and a steady-state performance optimizer. The transient policy is parameterized as a neural network, and the steady-state optimizer represents the gradient of the long-term operating cost function. The two parts are synthesized through a safe gradient flow framework, which prevents the violation of reactive power capacity constraints. We prove that if the output of the transient controller is bounded and monotonically decreasing with respect to its input, then the closed-loop system is asymptotically stable and converges to the optimal steady-state solution. We demonstrate the effectiveness of our method by conducting experiments with IEEE 13-bus and 123-bus distribution system test feeders.
more »
« less
High-Speed Voltage Control in Active Distribution Systems with Smart Inverter Coordination and DRL
The increasing penetration of renewable energy resources in distribution systems necessitates high-speed monitoring and control of voltage for ensuring reliable system operation. However, existing voltage control algorithms often make simplifying assumptions in their formulation, such as real-time availability of smart meter measurements (for monitoring), or real-time knowledge of every power injection information (for control). This paper leverages the recent advances made in high-speed state estimation for real-time unobservable distribution systems to formulate a deep reinforcement learning (DRL)-based control algorithm that utilizes the state estimates alone to control the voltage of the entire system. The results obtained for a modified (renewable-rich) IEEE 34-node distribution feeder indicate that the proposed approach excels in monitoring and controlling voltage of active distribution systems.
more »
« less
- Award ID(s):
- 2145063
- PAR ID:
- 10565111
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3503-8183-2
- Page Range / eLocation ID:
- 1 to 5
- Format(s):
- Medium: X
- Location:
- Seattle, WA, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Distribution systems need significant voltage support with growing penetration of distributed generations especially intermittent renewable energy resources and smart loads. This paper introduces the application of the Multi-Port Solid State Transformer (MPSST) as an effective tool to support grid voltage at distribution level while integrating distributed energy resources. The solid state transformer replaces the conventional transformer between two voltage zones of distribution systems. Matlab/Simulink environment is used to simulate the IEEE 14 bus test system with an MPSST as a case study. The simulation results prove the effectiveness of the MPSST supporting the distribution system at local level in a fast and efficient manner in response to disturbances caused by load variations.more » « less
-
Electrical power systems are transitioning from fuel-based generation to renewable generation and transmission interfaced by power electronics. This transition challenges standard power system modeling, analysis, and control paradigms across timescales from milliseconds to seasons. This tutorial focuses on frequency stability on timescales of milliseconds to seconds. We first review basic results for grid-following (GFL) and grid-forming (GFM) control of voltage source converters (VSCs), typical renewable generation, and high voltage direct current (HVdc) transmission. In this context, it becomes apparent that GFL and GFM control functions are needed to operate emerging power systems. However, combining GFL resources, GFM resources, and legacy generation on the same system results in highly complex dynamics that are a significant obstacle to stability analysis. The remainder of the tutorial provides an overview of recent developments in universal GFM controls that bridge the gap between GFL and GFM control and provide a pathway to a coherent control and analysis framework accounting for power generation, power conversion, and power transmission.more » « less
-
The Phasor measurement unit (PMU) measurements are mandatory to monitor the power system’s voltage stability margin in an online manner. Monitoring is key to the secure operation of the grid. Traditionally, online monitoring of voltage stability using synchrophasors required a centralized communication architecture, which leads to the high investment cost and cyber-security concerns. The increasing importance of cyber-security and low investment costs have recently led to the development of distributed algorithms for online monitoring of the grid that are inherently less prone to malicious attacks. In this work, we proposed a novel distributed non-iterative voltage stability index (VSI) by recasting the power flow equations as circles. The processors embedded at each bus in the smart grid with the help of PMUs and communication of voltage phasors between neighboring buses perform simultaneous online computations of VSI. The distributed nature of the index enables the real-time identification of the critical bus of the system with minimal communication infrastructure. The effectiveness of the proposed distributed index is demonstrated on IEEE test systems and contrasted with existing methods to show the benefits of the proposed method in speed, interpretability, identification of outage location, and low sensitivity to noisy measurements.more » « less
-
The rapid expansion of distributed energy resources is heightening uncertainty and variability in distribution system operations, potentially leading to power quality challenges such as voltage magnitude violations and excessive voltage unbalance. Ensuring the dependable and secure operation of distribution grids requires system real-time assessment. However, constraints in sensing, measurement, and communication capabilities within distribution grids result in limited awareness of the system’s state. To achieve better real-time estimates of distribution system security, we propose a real-time security assessment based on data from smart meters, which are already prevalent in most distribution grids. Assuming that it is possible to obtain a limited number of voltage magnitude measurements in real time, we design an iterative algorithm to adaptively identify a subset of smart meters whose real-time measurements allow us to certify that all voltage magnitudes remain within bounds. This algorithm iterates between (i) solving optimization problems to determine the worst possible voltage magnitudes, given a limited set of voltage magnitude measurements, and (ii) leveraging the solutions and sensitivity information from these problems to update the measurement set. Numerical tests on the IEEE 123 bus distribution feeder demonstrate that the proposed algorithm consistently identifies and tracks the nodes with the highest and lowest voltage magnitude, even as the load changes over time.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/PESGM51994.2024.10688893
