A Parallelized, Adam-Based Solver for Reserve and Security Constrained AC Unit Commitment

TL;DR

This paper introduces QuasiGrad, a parallelized Adam-based solver for complex power system optimization problems, demonstrating competitive performance and open-source availability, inspired by advances in machine learning optimization techniques.

Contribution

It develops a novel parallelized Adam-based solver for AC Unit Commitment problems, integrating ML optimization methods into power system optimization.

Findings

QuasiGrad achieved within 5% of top market surplus scores in competitions.

The solver is open-source and easily adaptable with alternative ML-inspired optimizers.

Large-scale experiments validate the solver's effectiveness.

Abstract

Power system optimization problems which include the nonlinear AC power flow equations require powerful and robust numerical solution algorithms. Within this sub-field of nonlinear optimization, interior point methods have come to dominate the solver landscape. Over the last decade, however, a number of efficient numerical optimizers have emerged from the field of Machine Learning (ML). One algorithm in particular, Adam, has become the optimizer-of-choice for a massive percentage of ML training problems (including, e.g., the training of GPT-3), solving some of the largest unconstrained optimization problems ever conceived of. Inspired by such progress, this paper designs a parallelized Adam-based numerical solver to overcome one of the most challenging power system optimization problems: security and reserve constrained AC Unit Commitment. The resulting solver, termed QuasiGrad, recently competed in the third ARPA-E Grid Optimization (GO3) competition. In the day-ahead market clearing category (with systems ranging from 3 to 23,643 buses over 48 time periods), QuasiGrad's aggregated market surplus scores were within 5% of the winningest market surplus scores. The QuasiGrad solver is now released as an open-source Julia package: QuasiGrad.jl. The internal gradient-based solver (Adam) can easily be substituted for other ML-inspired solvers (e.g., AdaGrad, AdaDelta, RMSProp, etc.). Test results from large experiments are provided.