Publications

Energy system digitization in the era of AI: A three-layered approach toward carbon neutrality

Published in Patterns, 2022

As one of the biggest game changers in addressing climate change, the transition to a carbon-neutral electric grid poses significant challenges to conventional paradigms of modern grid planning and operation. Artificial intelligence (AI) has the potential to address the challenges posed by large decision-making scale and increased uncertainty, as many key decision-making mechanisms of grid planning and operation can be formulated as representative AI problems. However, AI needs to be tailored for power system applications in three layers of technology, market, and policy to meet the needs of safety criticality, time sensitivity, and interpretability.

Recommended citation: Xie, Le, Tong Huang, Xiangtian Zheng, Yan Liu, Mengdi Wang, Vijay Vittal, P. R. Kumar, Srinivas Shakkottai, and Yi Cui. "Energy system digitization in the era of AI: A three-layered approach toward carbon neutrality." Patterns 3, no. 12 (2022): 100640. https://www.sciencedirect.com/science/article/pii/S2666389922002720

Analyzing Extreme Events in Power Systems: An Open, Cross-Domain Data-Driven Approach

Published in IEEE Power and Energy Magazine, 2022

Over the past several years the electric power sector has been challenged by a number of extreme events around the globe. Significant societal and economic shocks were due to the rapid spread of COVID-19 around the world. In addition to the pandemic, there have been several extreme weather and societal disruptions to the electricity sector, such as the February 2021 Texas power outage and the 9 pm nine-minute blackout event in India.

Recommended citation: Zheng, Xiangtian, Dongqi Wu, Liam Watts, Efstratios N. Pistikopoulos, and Le Xie. "Analyzing Extreme Events in Power Systems: An Open, Cross-Domain Data-Driven Approach." IEEE Power and Energy Magazine 20, no. 6 (2022): 47-55. https://ieeexplore.ieee.org/abstract/document/9920359

Eccentricity Severity Estimation of Induction Machines using a Sparsity-Driven Regression Model

Published in 2022 IEEE Energy Conversion Congress and Exposition (ECCE), 2022

In this paper, we develop a linear regression model incorporating multiple fault signature features to estimate the eccentricity severity level of induction machines under different operating conditions. In particular, the eccentricity severity level is modeled as a function of operating conditions and fault signature features including rotating speed, load torque, vibration, as well as current harmonics, etc, with corresponding weights to be determined.

Recommended citation: Zheng, Xiangtian, Hiroshi Inoue, Makoto Kanemaru, and Dehong Liu. "Eccentricity Severity Estimation of Induction Machines using a Sparsity-Driven Regression Model." In 2022 IEEE Energy Conversion Congress and Exposition (ECCE), pp. 1-6. IEEE, 2022. https://ieeexplore.ieee.org/abstract/document/9947498

How Much Demand Flexibility Could Have Spared Texas from the 2021 Outage?

Published in Advances in Applied Energy, 2022

In this paper, we study the scaling-up of demand flexibility as a means to avoid load shedding during such an extreme weather event. We identify portfolios of mixing mechanisms that exactly avoid outages, which a single mechanism may fail due to decaying marginal effects. We also reveal a complementary relationship between interruptible load and residential load rationing and find nonlinear impacts of incentive-based demand response on the efficacy of other mechanisms.

Recommended citation: Wu, Dongqi, Xiangtian Zheng, Ali Menati, Lane Smith, Bainan Xia, Yixing Xu, Chanan Singh, and Le Xie. "How Much Demand Flexibility Could Have Spared Texas from the 2021 Outage?." Advances in Applied Energy 7, (2022): 100106. https://www.sciencedirect.com/science/article/pii/S2666792422000245

Synthetic PMU Data Creation Based on Generative Adversarial Network under Time-Varying Load Conditions

Published in Journal of Modern Power Systems and Clean Energy, 2022

In this study, a machine learning based method is proposed for creating synthetic eventful phasor measurement unit (PMU) data under time-varying load conditions. The proposed method leverages generative adversarial networks to create quasi-steady states for the power system under slowly-varying load conditions and incorporates a framework of neural ordinary differential equations (ODEs) to capture the transient behaviors of the system during voltage oscillation events.

Recommended citation: Zheng, Xiangtian, Andrea Pinceti, Lalitha Sankar, and Le Xie. "Synthetic PMU Data Creation Based on Generative Adversarial Network under Time-Varying Load Conditions." Journal of Modern Power Systems and Clean Energy (2022). https://ieeexplore.ieee.org/abstract/document/9831104

A Multi-scale Time-series Dataset with Benchmark for Machine Learning in Decarbonized Energy Grids

Published in Scientific Data, 2022

This paper presents PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML) based approaches towards reliable operation of future electric grids. This paper provides state-of-the-art ML baselines on three challenging use cases of critical importance to achieve: (i) early detection, accurate classification and localization of dynamic disturbance events; (ii) robust hierarchical forecasting of load and renewable energy with the presence of uncertainties and extreme events; and (iii) realistic synthetic generation of physical-law-constrained measurement time series.

Recommended citation: Zheng, Xiangtian, Nan Xu, Loc Trinh, Dongqi Wu, Tong Huang, S. Sivaranjani, Yan Liu, and Le Xie. "A multi-scale time-series dataset with benchmark for machine learning in decarbonized energy grids." Scientific Data 9, no. 1 (2022): 1-18. https://www.nature.com/articles/s41597-022-01455-7

Massively Digitized Power Grid: Opportunities and Challenges of Use-Inspired AI

Published in Proceedings of the IEEE, 2022

This article presents a use-inspired perspective of the opportunities and challenges in a massively digitized power grid. It argues that the intricate interplay of data availability, computing capability, and artificial intelligence (AI) algorithm development are the three key factors driving the adoption of digitized solutions in the power grid.

Recommended citation: L. Xie, X. Zheng, Y. Sun, T. Huang and T. Bruton, "Massively Digitized Power Grid: Opportunities and Challenges of Use-Inspired AI," in Proceedings of the IEEE, 2022, doi: 10.1109/JPROC.2022.3175070. https://ieeexplore.ieee.org/document/9803820

An Open-source Extendable Model and Corrective Measure Assessment of the 2021 Texas Power Outage

Published in Advances in Applied Energy, 2021

This paper releases an open-source extendable model that is synthetic but nevertheless provides a realistic representation of the actual energy grid, accompanied by open-source cross-domain data sets. This paper uncovers the regional disparity of load shedding and quantitatively assesses several corrective measures that could have mitigated the blackout under such extreme weather conditions.

Recommended citation: Wu, Dongqi, Xiangtian Zheng, Yixing Xu, Daniel Olsen, Bainan Xia, Chanan Singh, and Le Xie. "An open-source extendable model and corrective measure assessment of the 2021 texas power outage." Advances in Applied Energy 4 (2021): 100056. https://www.sciencedirect.com/science/article/pii/S2666792421000482

Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification

Published in IEEE Open Access Journal of Power and Energy, 2021

This paper proposes a two-stage machine learning-based approach for creating synthetic phasor measurement unit (PMU) data, leveraging generative adversarial networks (GAN) in data generation and incorporates neural ordinary differential equation (Neural ODE) to guarantee underlying physical meaning. This paper demonstrates the application of using synthetic PMU data for event classification by scaling up the real data set.

Recommended citation: Zheng, Xiangtian, Bin Wang, Dileep Kalathil, and Le Xie. "Generative Adversarial Networks-Based Synthetic PMU Data Creation for Improved Event Classification." IEEE Open Access Journal of Power and Energy 8 (2021): 68-76. https://ieeexplore.ieee.org/abstract/document/9361704

A Cross-domain Approach to Analyzing the Short-run Impact of COVID-19 on the US Electricity Sector

Published in Joule, 2020

This paper releases a first-of-its-kind cross-domain open-access data hub, integrating data from across all existing US wholesale electricity markets with other cross-domain data. This paper uncovers a significant reduction in electricity consumption that is strongly correlated with the number of COVID-19 cases, degree of social distancing, and level of commercial activity.

Recommended citation: Ruan, Guangchun, Dongqi Wu, Xiangtian Zheng, Haiwang Zhong, Chongqing Kang, Munther A. Dahleh, S. Sivaranjani, and Le Xie. "A cross-domain approach to analyzing the short-run impact of COVID-19 on the US electricity sector." Joule 4, no. 11 (2020): 2322-2337. https://www.sciencedirect.com/science/article/pii/S2542435120303986

Nested reinforcement learning based control for protective relays in power distribution systems

Published in 2019 IEEE 58th Conference on Decision and Control, 2019

This paper proposes a new nested deep reinforcement learning approach to take advantage of the structural property of distribution networks and develops a new set of training methods for tuning the protective relays.

Recommended citation: Wu, Dongqi, Xiangtian Zheng, Dileep Kalathil, and Le Xie. "Nested reinforcement learning based control for protective relays in power distribution systems." In 2019 IEEE 58th Conference on Decision and Control (CDC), pp. 1925-1930. IEEE, 2019. https://ieeexplore.ieee.org/abstract/document/9029268

Synthetic dynamic PMU data generation: A generative adversarial network approach

Published in 2019 International Conference on Smart Grid Synchronized Measurements and Analytics, 2019

This paper proposes a model-free approach to directly generate synthetic PMU data, by training the generative adversarial network (GAN) with real PMU data, which can be used to generate synthetic PMU data capturing the system dynamic behaviors.

Recommended citation: Zheng, Xiangtian, Bin Wang, and Le Xie. "Synthetic dynamic PMU data generation: A generative adversarial network approach." In 2019 International Conference on Smart Grid Synchronized Measurements and Analytics (SGSMA), pp. 1-6. IEEE, 2019. https://ieeexplore.ieee.org/abstract/document/8784681

A SVM-based setting of protection relays in distribution systems

Published in 2018 IEEE Texas Power and Energy Conference, 2018

This paper proposes a data-driven approach to design operating strategies of relays in distribution systems with high penetration of distributed energy resources (DERs).

Recommended citation: Zheng, Xiangtian, Xinbo Geng, Le Xie, Dongliang Duan, Liuqing Yang, and Shuguang Cui. "A SVM-based setting of protection relays in distribution systems." In 2018 IEEE Texas Power and Energy Conference (TPEC), pp. 1-6. IEEE, 2018. https://ieeexplore.ieee.org/abstract/document/8312071