# Data-Driven Distributionally Robust Optimal Power Flow for Distribution Systems

arXiv: https://arxiv.org/abs/1803.04912 · HTML: https://mlsanity.com/paper/1803.04912/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2018.

## Built on by (most cited first, 2 of 2)

- [Distributionally Robust Optimal Power Flow with Contextual Information](https://mlsanity.com/paper/2109.07896/) (2021)
- [AutoPQ: Automating Quantile estimation from Point forecasts in the context of sustainability](https://mlsanity.com/paper/2412.00419/) (2024)

## Abstract (arXiv)

Increasing penetration of distributed energy resources complicate operations of electric power distribution systems by amplifying volatility of nodal power injections. On the other hand, these resources can provide additional control means to the distribution system operator (DSO). This paper takes the DSO perspective and leverages a data-driven distributionally robust decision-making framework to overcome the uncertainty of these injections and its impact on the distribution system operations. We develop an AC OPF formulation for radial distribution systems based on the LinDistFlow AC power flow approximation and exploit distributionally robust optimization to immunize the optimized decisions against uncertainty in the probabilistic models of forecast errors obtained from the available observations. The model is reformulated to be computationally tractable and tested on multiple IEEE distribution test systems. We also release the code supplement that implements the proposed model in Julia and can be used to reproduce our numerical results.