Search for: All records

Optimal Power Flow (OPF) is a challenging problem in power systems, and recent research has explored the use of Deep Neural Networks (DNNs) to approximate OPF solutions with reduced computational times. While these approaches show promising accuracy and efficiency, there is a lack of analysis of their robustness. This paper addresses this gap by investigating the factors that lead to both successful and suboptimal predictions in DNN-based OPF solvers. It identifies power system features and DNN characteristics that contribute to higher prediction errors and offers insights on mitigating these challenges when designing deep learning models for OPF. 

Learning mappings between system loading and optimal dispatch solutions has been a recent topic of interest in the power systems and machine learning communities. However, previous works have ignored practical power system constraints such as generator ramp limits and other intertemporal requirements. Additionally, optimal power flow runs are not performed independently of previous timesteps - in most cases, an OPF solution representing the current state of the system is heavily related to the OPF solution from previous timesteps. In this paper, we train a recurrent neural network, which embeds natural relationships between timesteps, to predict the optimal solution of convex power systems optimization problems with intertemporal constraints. In contrast to traditional forecasting methods, the computational benefits from this technique can allow operators to rapidly simulate forecasts of system operation and corresponding optimal solutions to provide a more comprehensive view of future system states. 

Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently observed that DP learning systems may exacerbate bias and unfairness for different groups of individuals. This paper builds on these important observations and sheds light on the causes of the disparate impacts arising in the problem of differentially private empirical risk minimization. It focuses on the accuracy disparity arising among groups of individuals in two well-studied DP learning methods: output perturbation and differentially private stochastic gradient descent. The paper analyzes which data and model properties are responsible for the disproportionate impacts, why these aspects are affecting different groups disproportionately, and proposes guidelines to mitigate these effects. The proposed approach is evaluated on several datasets and settings. 

Optimal Power Flow (OPF) is a fundamental problem in power systems. It is computationally challenging and a recent line of research has proposed the use of Deep Neural Networks (DNNs) to find OPF approximations at vastly reduced runtimes when compared to those obtained by classical optimization methods. While these works show encouraging results in terms of accuracy and runtime, little is known on why these models can predict OPF solutions accurately, as well as about their robustness. This paper provides a step forward to address this knowledge gap. The paper connects the volatility of the outputs of the generators to the ability of a learning model to approximate them, it sheds light on the characteristics affecting the DNN models to learn good predictors, and it proposes a new model that exploits the observations made by this paper to produce accurate and robust OPF predictions.