Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control

TL;DR

This paper develops a multi-objective reinforcement learning framework for energy-efficient control of an industrial testbed, balancing tracking accuracy and power consumption, and investigates the effects of reward weighting on control strategies.

Contribution

It introduces a novel MORL approach with a composite reward for industrial control, analyzing the impact of energy penalty weight on system performance and exploring optimizer effects.

Findings

Performance shifts observed for alpha between 0.0 and 0.25.

Non-Pareto solutions emerge at lower alpha values.

Optimizer artifacts may bias control strategies.

Abstract

Industrial automation increasingly demands energy-efficient control strategies to balance performance with environmental and cost constraints. In this work, we present a multi-objective reinforcement learning (MORL) framework for energy-efficient control of the Quanser Aero 2 testbed in its one-degree-of-freedom configuration. We design a composite reward function that simultaneously penalizes tracking error and electrical power consumption. Preliminary experiments explore the influence of varying the Energy penalty weight, alpha, on the trade-off between pitch tracking and energy savings. Our results reveal a marked performance shift for alpha values between 0.0 and 0.25, with non-Pareto optimal solutions emerging at lower alpha values, on both the simulation and the real system. We hypothesize that these effects may be attributed to artifacts introduced by the adaptive behavior of the Adam optimizer, which could bias the learning process and favor bang-bang control strategies. Future work will focus on automating alpha selection through Gaussian Process-based Pareto front modeling and transitioning the approach from simulation to real-world deployment.