24 March 2022 in IEEE Open Access Journal of Power and Energy
This paper introduces a new framework of deep reinforcement learning based protective relay design in power distribution systems with many distributed energy resources (DERs). With increasing penetration of power electronically-interfaced resources, conventional overcurrent relays’ performance is rendered less effective due to the two-way uncertainties in power flow patterns. In this paper, a machine learning-based protective relay that is designed for adaptively deciding the threshold for relay action is proposed. The particular algorithm used is an Long Short-Term Memory (LSTM) enhanced deep neural network that is highly accurate, communication-free and easy to implement. The proposed relay design is tested in OpenDSS simulation on the IEEE 34-node test feeder and a collection of large synthetic feeders in Austin, Texas area. By designing adaptability upfront, the proposed relay is shown to substantially improve the performance of relay in terms of failure rate, robustness, and response speed, in particular in scenarios with high level of distributed energy resources.
19 August 2022 in Advances in Applied Energy
5 April 2021 in Research Square
Unprecedented winter storms that hit across Texas in February 2021 have caused at least 4.5 million customers to experience load shedding due to the wide-ranging generation capacity outage and record-breaking electricity demand. While much remains to be investigated on what, how, and why such wide-spread power outages occurred across Texas, it is imperative for the broader research community to develop insights based on a coherent electric grid model and data set. In this paper, we collaboratively release an open-source large-scale baseline model that is synthetic but nevertheless provides a realistic representation of the actual energy grid, accompanied by open-source cross-domain data sets. Leveraging the synthetic grid model, we reproduce the blackout event and critically assess several corrective measures that could have mitigated the blackout under such extreme weather conditions. We uncover the regional disparity of load shedding. The analysis also quantifies the sensitivity of several corrective measures with respect to mitigating the power outage, as measured in energy not served (ENS). This approach and methodology are generalizable for other regions experiencing significant energy portfolio transitions.
10 October 2022 in IEEE Transactions on Smart Grid
This paper presents OpenGridGym, an open-source Python-based package that allows for seamless integration of distribution market simulation with state-of-the-art artificial intelligence (AI) decision-making algorithms. We present the architecture and design choice for the proposed framework, elaborate on how users interact with OpenGridGym, and highlight its value by providing multiple cases to demonstrate its use. Four modules are used in any simulation: (1) the physical grid, (2) market mechanisms, (3) a set of trainable agents which interact with the former two modules, and (4) environment module that connects and coordinates the above three. We provide templates for each of those four, but they are easily interchangeable with custom alternatives. Several case studies are presented to illustrate the capability and potential of this toolkit in helping researchers address key design and operational questions in distribution electricity markets.