LGAPOCMay 18, 2023

Actor-Critic Methods using Physics-Informed Neural Networks: Control of a 1D PDE Model for Fluid-Cooled Battery Packs

arXiv:2305.10952v12 citations
Originality Incremental advance
AI Analysis

This addresses temperature control in fluid-cooled battery packs, an incremental improvement in applying reinforcement learning to PDE-based systems.

The paper tackles controlling battery pack temperature via a cooling fluid modeled by a 1D PDE, proposing an actor-critic algorithm that uses a Physics-Informed Neural Network to solve the HJB equation, with a hybrid-policy method achieving the best results in experiments.

This paper proposes an actor-critic algorithm for controlling the temperature of a battery pack using a cooling fluid. This is modeled by a coupled 1D partial differential equation (PDE) with a controlled advection term that determines the speed of the cooling fluid. The Hamilton-Jacobi-Bellman (HJB) equation is a PDE that evaluates the optimality of the value function and determines an optimal controller. We propose an algorithm that treats the value network as a Physics-Informed Neural Network (PINN) to solve for the continuous-time HJB equation rather than a discrete-time Bellman optimality equation, and we derive an optimal controller for the environment that we exploit to achieve optimal control. Our experiments show that a hybrid-policy method that updates the value network using the HJB equation and updates the policy network identically to PPO achieves the best results in the control of this PDE system.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes