Fast Block Linear System Solver Using Q-Learning Schduling for Unified Dynamic Power System Simulations

TL;DR

This paper introduces a novel Q-learning based task scheduling method for a fast block direct solver, significantly accelerating unified dynamic power system simulations by 2-6 times compared to existing solvers.

Contribution

It presents a learning-based task scheduling technique using Q-learning within a block solver for power system simulations, enhancing speed and efficiency.

Findings

Solver is 2-6 times faster than KLU.

Learning-based scheduling improves sparse solver performance.

Effective for large power system simulations.

Abstract

We present a fast block direct solver for the unified dynamic simulations of power systems. This solver uses a novel Q-learning based method for task scheduling. Unified dynamic simulations of power systems represent a method in which the electric-mechanical transient, medium-term and long-term dynamic phenomena are organically united. Due to the high rank and large numbers in solving, fast solution of these equations is the key to speeding up the simulation. The sparse systems of simulation contain complex nested block structure, which could be used by the solver to speed up. For the scheduling of blocks and frontals in the solver, we use a learning based task-tree scheduling technique in the framework of Markov Decision Process. That is, we could learn optimal scheduling strategies by offline training on many sample matrices. Then for any systems, the solver would get optimal task partition and scheduling on the learned model. Our learning-based algorithm could help improve the performance of sparse solver, which has been verified in some numerical experiments. The simulation on some large power systems shows that our solver is 2-6 times faster than KLU, which is the state-of-the-art sparse solver for circuit simulation problems.