Exploiting Convexity of Neural Networks in Dynamic Operating Envelope Optimization for Distributed Energy Resources

TL;DR

This paper introduces a convex neural network-based approach to optimize dynamic operating envelopes for distributed energy resources, improving solution speed and accuracy while ensuring network safety.

Contribution

It presents a novel convex neural network model and a linear relaxation technique to efficiently solve DOE optimization problems with theoretical guarantees.

Findings

Outperforms benchmark methods in solution quality

Reduces computation time significantly

Ensures network safety constraints are met

Abstract

The increasing penetration of distributed energy resources (DERs) brings opportunities and challenges to the operation of distribution systems. To ensure network integrity, dynamic operating envelopes (DOEs) are issued by utilities to DERs as their time-varying export/import power limits. Due to the non-convex nature of power flow equations, the optimization of DOEs faces a dilemma of solution accuracy and computation efficiency. To bridge this gap, in this paper, we facilitate DOE optimization by exploiting the convexity of input convex neural networks (ICNNs). A DOE optimization model is first presented, comprehensively considering multiple operational constraints. We propose a constraint embedding method that allows us to replace the non-convex power flow constraints with trained ICNN models and convexify the problem. To further speed up DOE optimization, we propose a linear relaxation of the ICNN-based DOE optimization problem, for which the tightness is theoretically proven. The effectiveness of the proposed method is validated with numerical case studies. Results show that the proposed ICNN-based method outperforms other benchmark methods in optimizing DOEs in terms of both solution quality and solution time.