An Overview
Our lab’s core product is an optimization-based toolbox focused on the diagnosis and mitigation of high-impact threats (e.g. blackouts) in power systems, enhancing resilience across all stages of grid disturbance. Its key enabler, the SparseAct algorithm, identifies dominant sources of failure and recommends fast-acting, effective responses at a minimal set of targeted locations. Our work also synthesizes advanced power system modeling with artificial intelligence (AI) to improve the speed and accuracy of threat detection, analysis, and response.
The Exploiting of Sparsity
Sparsity is the special structure in vectors or matrices that only a small fraction of non-zero values exist – carrying essential information; whereas most other entries are zero – ignorable without losing significant accuracy. Our research is organized around exploiting the sparsity structures in system, data, and threats.
SparseAct: Make Power System Resilient to Collapses
|
1. Sparse Diagnosis: pinpoint dominant sources of blackout failure
Given a single scenario of overloading or contingency, power grid may result in system collapse (i.e., blackout). In this project, we investigate proactive defense using sparse optimization to pinpoint the dominant sources of blackout failure. Find out the basic idea here. And the sparse idea has been extended to distribution grid (see related works here, here, and here) |
Enforcing sparse diagnosis iteratively, and finally identify 1 key location responsible for the collapse of case2383wp
|
1.1 Sparse Diagnosis for multiple-scenario analysis
Given a set of extreme events or contingencies on a system, how do we locate the key system vulnerabilities responsible for all of them? Unlike analyzing one single scenario, we want the identified vulnerabilities to be shared or persistent across multiple scenarios.
Consider a sequence of extreme events with load demand growing incrementally
Sorting the scenarios in the order of increasing stress, we develop multi-period sparse optimization to identify a sequence of persistent vulnerability locations hidden behind the collapses. See arXiv preprint arXiv:2510.14045
Given a set of extreme events or contingencies on a system, how do we locate the key system vulnerabilities responsible for all of them? Unlike analyzing one single scenario, we want the identified vulnerabilities to be shared or persistent across multiple scenarios.
Consider a sequence of extreme events with load demand growing incrementally
Sorting the scenarios in the order of increasing stress, we develop multi-period sparse optimization to identify a sequence of persistent vulnerability locations hidden behind the collapses. See arXiv preprint arXiv:2510.14045
case2383wp: given a sequence of blackouts induced by load factor (LF) ranging from 1.35 to 1.44, we identify a growing set of vulnerability locations responsible for these failures.
1.2 Frequency-aware Sparse Diagnosis: a localized compensation can stablize the entire system!
When disturbance (like generator outage) occurs, droop response automatically adjusts power output to bring system to a new steady state. What might make a system unstable or collapse after droop response? Our work develops a frequency-aware sparse optimization to identify related system vulnerabilities. See our work arXiv:2511.07553
When disturbance (like generator outage) occurs, droop response automatically adjusts power output to bring system to a new steady state. What might make a system unstable or collapse after droop response? Our work develops a frequency-aware sparse optimization to identify related system vulnerabilities. See our work arXiv:2511.07553
The new steady state after a generator outage will have a dangerous frequency drop of >0.57Hz!
|
Compensate at node 13, then frequency will stay in the desirable 60±0.3Hz bound.
|
1.3 Voltage-regulated Sparse Diagnosis: make localized compensation to bring voltages back!
What makes a system unable to keep voltage within proper bound (e.g., 0.95pu ~ 1.05pu)? Our work develops a voltage-regulated spase optimization to identify related vulnerabilities. See our work arXiv:2511.06528
What makes a system unable to keep voltage within proper bound (e.g., 0.95pu ~ 1.05pu)? Our work develops a voltage-regulated spase optimization to identify related vulnerabilities. See our work arXiv:2511.06528
When demand increases by 40%, system remains feasible but voltage falls below min bound
|
Make compensation at node 8 to bring voltage back within bound!
|
|
|
2. Sparse Actions: suggesting fast-acting corrective actions at sparse targeted locations to mitigate failures (Ongoing)
3. AI Acceleration to boost computation speed
Our prior work developed a ML warm starter (here) offering 3x speed up in simulation of cyberattack-induced disturbances.
3. AI Acceleration to boost computation speed
Our prior work developed a ML warm starter (here) offering 3x speed up in simulation of cyberattack-induced disturbances.
Sparse inspection for cyber-resilient system monitoring
1. Time-series AI: sparse learning for dynamic time-series anomaly detection
Given sensors placed on dynamic graphs, how to detect anomalies? Our method, DynWatch, finds out a sparse set of relevant historical data via sparse temporal weighting. Find out more details here.
2. Accurately estimating system states and topology while identifying random bad data and topology errors
In real time when facing bad measurement devices and wrong switch statuses, the resulting anomalous data and topology errors prevents us from knowing the correct system conditions like voltage profile, line outages, etc. In this project, we investigate robust state estimator that can pinpoint these errors and retain accurate voltage and topology information. Find out more details here, here, and here.
3. Combinging state estimation + AI for further robustness against targeted interactive false data
See arXiv preprint arXiv:2510.14043
Given sensors placed on dynamic graphs, how to detect anomalies? Our method, DynWatch, finds out a sparse set of relevant historical data via sparse temporal weighting. Find out more details here.
2. Accurately estimating system states and topology while identifying random bad data and topology errors
In real time when facing bad measurement devices and wrong switch statuses, the resulting anomalous data and topology errors prevents us from knowing the correct system conditions like voltage profile, line outages, etc. In this project, we investigate robust state estimator that can pinpoint these errors and retain accurate voltage and topology information. Find out more details here, here, and here.
3. Combinging state estimation + AI for further robustness against targeted interactive false data
See arXiv preprint arXiv:2510.14043
More broadly exploiting sparsity
Sparse Weighting: Adapting Learning Models to Non-IID Data
Power system data distributions shift due to topology changes and operating conditions. We develop sparse temporal reweighting schemes to adapt learning models to these non-IID conditions.
Find an application in time-series anomaly detection here.
Sparse Probabilistic Graphical Models for Power Systems
The power grid’s sparse connectivity can be exploited to build more interpretable and efficient learning models. Our work explores probabilistic graphical models augmented with neural networks to incorporate grid topology and domain knowledge.
Find an application of ML-based simulation warm-starter here.
Power system data distributions shift due to topology changes and operating conditions. We develop sparse temporal reweighting schemes to adapt learning models to these non-IID conditions.
Find an application in time-series anomaly detection here.
Sparse Probabilistic Graphical Models for Power Systems
The power grid’s sparse connectivity can be exploited to build more interpretable and efficient learning models. Our work explores probabilistic graphical models augmented with neural networks to incorporate grid topology and domain knowledge.
Find an application of ML-based simulation warm-starter here.