# Risk-Aware Learning for Scalable Voltage Optimization in Distribution Grids

arXiv: https://arxiv.org/abs/2110.01490 · HTML: https://mlsanity.com/paper/2110.01490/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 4 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach](https://mlsanity.com/paper/1506.02188/) (2015)
- [Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization](https://mlsanity.com/paper/1308.6594/) (2013)
- [Optimizing the CVaR via Sampling](https://mlsanity.com/paper/1404.3862/) (2014)
- [Adaptive Sampling for Stochastic Risk-Averse Learning](https://mlsanity.com/paper/1910.12511/) (2019)
- [Learning Bounds for Risk-sensitive Learning](https://mlsanity.com/paper/2006.08138/) (2020)
- [Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks](https://mlsanity.com/paper/2006.11029/) (2020)
- [Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning](https://mlsanity.com/paper/1904.09374/) (2019)
- [Convex Relaxation of Optimal Power Flow, Part I: Formulations and Equivalence](https://mlsanity.com/paper/1405.0766/) (2014)
- [Risk-Averse Stochastic Convex Bandit](https://mlsanity.com/paper/1810.00737/) (2018)
- [Towards Distributed Energy Services: Decentralizing Optimal Power Flow with Machine Learning](https://mlsanity.com/paper/1806.06790/) (2018)
- [Designing reactive power control rules for smart inverters using support vector machines](https://mlsanity.com/paper/1903.01016/) (2019)
- [Noisy Linear Convergence of Stochastic Gradient Descent for CV@R Statistical Learning under Polyak-Lojasiewicz Conditions](https://mlsanity.com/paper/2012.07785/) (2020)
- [Fast Local Voltage Control under Limited Reactive Power: Optimality and Stability Analysis](https://mlsanity.com/paper/1510.07013/) (2015)
- [Load-Flow in Multiphase Distribution Networks: Existence, Uniqueness, Non-Singularity and Linear Models](https://mlsanity.com/paper/1702.03310/) (2017)
- [Controlling Smart Inverters using Proxies: A Chance-Constrained DNN-based Approach](https://mlsanity.com/paper/2105.00429/) (2021)
- [Graph Neural Networks for Learning Real-Time Prices in Electricity Market](https://mlsanity.com/paper/2106.10529/) (2021)
- [Matrix Completion for Low-Observability Voltage Estimation](https://mlsanity.com/paper/1801.09799/) (2018)
- [Data-driven Voltage Regulation in Radial Power Distribution Systems](https://mlsanity.com/paper/1901.03173/) (2019)
- [Dynamic Distribution State Estimation Using Synchrophasor Data](https://mlsanity.com/paper/1901.02554/) (2019)
- [On the Impact of Different Voltage Unbalance Metrics in Distribution System Optimization](https://mlsanity.com/paper/2004.10550/) (2020)

## Built on by (most cited first, 5 of 5)

- [Topology-aware Graph Neural Networks for Learning Feasible and Adaptive ac-OPF Solutions](https://mlsanity.com/paper/2205.10129/) (2022)
- [Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systems](https://mlsanity.com/paper/2203.07505/) (2022)
- [Scalable Learning for Optimal Load Shedding Under Power Grid Emergency Operations](https://mlsanity.com/paper/2111.11980/) (2021)
- [Minimizing Worst-Case Violations of Neural Networks](https://mlsanity.com/paper/2212.10930/) (2022)
- [Machine Learning for Scalable and Optimal Load Shedding Under Power System Contingency](https://mlsanity.com/paper/2405.05521/) (2024)

## Abstract (arXiv)

Real-time coordination of distributed energy resources (DERs) is crucial for regulating the voltage profile in distribution grids. By capitalizing on a scalable neural network (NN) architecture, one can attain decentralized DER decisions to address the lack of real-time communications. This paper develops an advanced learning-enabled DER coordination scheme by accounting for the potential risks associated with reactive power prediction and voltage deviation. Such risks are quantified by the conditional value-at-risk (CVaR) using the worst-case samples only, and we propose a mini-batch selection algorithm to address the training speed issue in minimizing the CVaR-regularized loss. Numerical tests using real-world data on the IEEE 123-bus test case have demonstrated the computation and safety improvements of the proposed risk-aware learning algorithm for decentralized DER decision making, especially in terms of reducing feeder voltage violations.