Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods
This addresses the need for efficient and accurate solutions in power system optimization, exacerbated by renewable energy stochasticity, but is incremental as it builds on existing deep learning and optimization techniques.
The paper tackled the nonlinear and nonconvex Optimal Power Flow problem in electrical power systems by combining deep learning with Lagrangian dual methods, achieving highly accurate predictions with average errors as low as 0.2% and improving accuracy over linear approximations by at least two orders of magnitude.
The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often needed to be solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the prior states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of widely adopted OPF linear DC approximation by at least two orders of magnitude.